diff options
Diffstat (limited to 'arch/x86')
300 files changed, 8840 insertions, 14180 deletions
diff --git a/arch/x86/Kconfig b/arch/x86/Kconfig index 21f851179ff0..2792879d398e 100644 --- a/arch/x86/Kconfig +++ b/arch/x86/Kconfig @@ -32,6 +32,7 @@ config X86_64 select MODULES_USE_ELF_RELA select NEED_DMA_MAP_STATE select SWIOTLB + select ARCH_HAS_ELFCORE_COMPAT config FORCE_DYNAMIC_FTRACE def_bool y @@ -96,6 +97,8 @@ config X86 select ARCH_SUPPORTS_DEBUG_PAGEALLOC select ARCH_SUPPORTS_NUMA_BALANCING if X86_64 select ARCH_SUPPORTS_KMAP_LOCAL_FORCE_MAP if NR_CPUS <= 4096 + select ARCH_SUPPORTS_LTO_CLANG if X86_64 + select ARCH_SUPPORTS_LTO_CLANG_THIN if X86_64 select ARCH_USE_BUILTIN_BSWAP select ARCH_USE_QUEUED_RWLOCKS select ARCH_USE_QUEUED_SPINLOCKS @@ -148,6 +151,7 @@ config X86 select HAVE_ARCH_JUMP_LABEL_RELATIVE select HAVE_ARCH_KASAN if X86_64 select HAVE_ARCH_KASAN_VMALLOC if X86_64 + select HAVE_ARCH_KFENCE select HAVE_ARCH_KGDB select HAVE_ARCH_MMAP_RND_BITS if MMU select HAVE_ARCH_MMAP_RND_COMPAT_BITS if MMU && COMPAT @@ -168,6 +172,7 @@ config X86 select HAVE_CONTEXT_TRACKING if X86_64 select HAVE_CONTEXT_TRACKING_OFFSTACK if HAVE_CONTEXT_TRACKING select HAVE_C_RECORDMCOUNT + select HAVE_OBJTOOL_MCOUNT if STACK_VALIDATION select HAVE_DEBUG_KMEMLEAK select HAVE_DMA_CONTIGUOUS select HAVE_DYNAMIC_FTRACE @@ -187,6 +192,7 @@ config X86 select HAVE_HW_BREAKPOINT select HAVE_IDE select HAVE_IOREMAP_PROT + select HAVE_IRQ_EXIT_ON_IRQ_STACK if X86_64 select HAVE_IRQ_TIME_ACCOUNTING select HAVE_KERNEL_BZIP2 select HAVE_KERNEL_GZIP @@ -206,7 +212,6 @@ config X86 select HAVE_MOVE_PMD select HAVE_MOVE_PUD select HAVE_NMI - select HAVE_OPROFILE select HAVE_OPTPROBES select HAVE_PCSPKR_PLATFORM select HAVE_PERF_EVENTS @@ -220,10 +225,12 @@ config X86 select HAVE_REGS_AND_STACK_ACCESS_API select HAVE_RELIABLE_STACKTRACE if X86_64 && (UNWINDER_FRAME_POINTER || UNWINDER_ORC) && STACK_VALIDATION select HAVE_FUNCTION_ARG_ACCESS_API + select HAVE_SOFTIRQ_ON_OWN_STACK select HAVE_STACKPROTECTOR if CC_HAS_SANE_STACKPROTECTOR select HAVE_STACK_VALIDATION if X86_64 select HAVE_STATIC_CALL select HAVE_STATIC_CALL_INLINE if HAVE_STACK_VALIDATION + select HAVE_PREEMPT_DYNAMIC select HAVE_RSEQ select HAVE_SYSCALL_TRACEPOINTS select HAVE_UNSTABLE_SCHED_CLOCK @@ -444,7 +451,7 @@ config X86_X2APIC If you don't know what to do here, say N. config X86_MPPARSE - bool "Enable MPS table" if ACPI || SFI + bool "Enable MPS table" if ACPI default y depends on X86_LOCAL_APIC help @@ -603,7 +610,6 @@ config X86_INTEL_MID depends on PCI depends on X86_64 || (PCI_GOANY && X86_32) depends on X86_IO_APIC - select SFI select I2C select DW_APB_TIMER select APB_TIMER @@ -890,19 +896,7 @@ config HPET_TIMER config HPET_EMULATE_RTC def_bool y - depends on HPET_TIMER && (RTC=y || RTC=m || RTC_DRV_CMOS=m || RTC_DRV_CMOS=y) - -config APB_TIMER - 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 - systems, unlike the TSC, but it is more expensive to access, - as it is off-chip. APB timers are always running regardless of CPU - C states, they are used as per CPU clockevent device when possible. + depends on HPET_TIMER && (RTC_DRV_CMOS=m || RTC_DRV_CMOS=y) # Mark as expert because too many people got it wrong. # The code disables itself when not needed. @@ -1158,10 +1152,6 @@ config X86_MCE_INJECT If you don't know what a machine check is and you don't do kernel QA it is safe to say n. -config X86_THERMAL_VECTOR - def_bool y - depends on X86_MCE_INTEL - source "arch/x86/events/Kconfig" config X86_LEGACY_VM86 @@ -2469,8 +2459,6 @@ source "kernel/power/Kconfig" source "drivers/acpi/Kconfig" -source "drivers/sfi/Kconfig" - config X86_APM_BOOT def_bool y depends on APM @@ -2657,7 +2645,7 @@ config PCI_DIRECT config PCI_MMCONFIG bool "Support mmconfig PCI config space access" if X86_64 default y - depends on PCI && (ACPI || SFI || JAILHOUSE_GUEST) + depends on PCI && (ACPI || JAILHOUSE_GUEST) depends on X86_64 || (PCI_GOANY || PCI_GOMMCONFIG) config PCI_OLPC @@ -2864,7 +2852,6 @@ config IA32_EMULATION depends on X86_64 select ARCH_WANT_OLD_COMPAT_IPC select BINFMT_ELF - select COMPAT_BINFMT_ELF select COMPAT_OLD_SIGACTION help Include code to run legacy 32-bit programs under a diff --git a/arch/x86/Makefile b/arch/x86/Makefile index 30920d70b48b..2d6d5a28c3bf 100644 --- a/arch/x86/Makefile +++ b/arch/x86/Makefile @@ -169,6 +169,11 @@ ifeq ($(ACCUMULATE_OUTGOING_ARGS), 1) KBUILD_CFLAGS += $(call cc-option,-maccumulate-outgoing-args,) endif +ifdef CONFIG_LTO_CLANG +KBUILD_LDFLAGS += -plugin-opt=-code-model=kernel \ + -plugin-opt=-stack-alignment=$(if $(CONFIG_X86_32),4,8) +endif + # Workaround for a gcc prelease that unfortunately was shipped in a suse release KBUILD_CFLAGS += -Wno-sign-compare # @@ -232,9 +237,6 @@ core-y += arch/x86/ drivers-$(CONFIG_MATH_EMULATION) += arch/x86/math-emu/ drivers-$(CONFIG_PCI) += arch/x86/pci/ -# must be linked after kernel/ -drivers-$(CONFIG_OPROFILE) += arch/x86/oprofile/ - # suspend and hibernation support drivers-$(CONFIG_PM) += arch/x86/power/ @@ -295,16 +297,20 @@ archclean: $(Q)$(MAKE) $(clean)=arch/x86/tools define archhelp - echo '* bzImage - Compressed kernel image (arch/x86/boot/bzImage)' - echo ' install - Install kernel using' - echo ' (your) ~/bin/$(INSTALLKERNEL) or' - echo ' (distribution) /sbin/$(INSTALLKERNEL) or' - echo ' install to $$(INSTALL_PATH) and run lilo' - echo ' fdimage - Create 1.4MB boot floppy image (arch/x86/boot/fdimage)' - echo ' fdimage144 - Create 1.4MB boot floppy image (arch/x86/boot/fdimage)' - echo ' fdimage288 - Create 2.8MB boot floppy image (arch/x86/boot/fdimage)' - echo ' isoimage - Create a boot CD-ROM image (arch/x86/boot/image.iso)' - echo ' bzdisk/fdimage*/isoimage also accept:' - echo ' FDARGS="..." arguments for the booted kernel' - echo ' FDINITRD=file initrd for the booted kernel' + echo '* bzImage - Compressed kernel image (arch/x86/boot/bzImage)' + echo ' install - Install kernel using (your) ~/bin/$(INSTALLKERNEL) or' + echo ' (distribution) /sbin/$(INSTALLKERNEL) or install to ' + echo ' $$(INSTALL_PATH) and run lilo' + echo '' + echo ' fdimage - Create 1.4MB boot floppy image (arch/x86/boot/fdimage)' + echo ' fdimage144 - Create 1.4MB boot floppy image (arch/x86/boot/fdimage)' + echo ' fdimage288 - Create 2.8MB boot floppy image (arch/x86/boot/fdimage)' + echo ' isoimage - Create a boot CD-ROM image (arch/x86/boot/image.iso)' + echo ' bzdisk/fdimage*/isoimage also accept:' + echo ' FDARGS="..." arguments for the booted kernel' + echo ' FDINITRD=file initrd for the booted kernel' + echo '' + echo ' kvm_guest.config - Enable Kconfig items for running this kernel as a KVM guest' + echo ' xen.config - Enable Kconfig items for running this kernel as a Xen guest' + endef diff --git a/arch/x86/configs/i386_defconfig b/arch/x86/configs/i386_defconfig index 78210793d357..9c9c4a888b1d 100644 --- a/arch/x86/configs/i386_defconfig +++ b/arch/x86/configs/i386_defconfig @@ -50,7 +50,6 @@ CONFIG_JUMP_LABEL=y CONFIG_MODULES=y CONFIG_MODULE_UNLOAD=y CONFIG_MODULE_FORCE_UNLOAD=y -# CONFIG_UNUSED_SYMBOLS is not set CONFIG_BINFMT_MISC=y CONFIG_NET=y CONFIG_PACKET=y diff --git a/arch/x86/configs/x86_64_defconfig b/arch/x86/configs/x86_64_defconfig index 9936528e1939..b60bd2d86034 100644 --- a/arch/x86/configs/x86_64_defconfig +++ b/arch/x86/configs/x86_64_defconfig @@ -48,7 +48,6 @@ CONFIG_JUMP_LABEL=y CONFIG_MODULES=y CONFIG_MODULE_UNLOAD=y CONFIG_MODULE_FORCE_UNLOAD=y -# CONFIG_UNUSED_SYMBOLS is not set CONFIG_BINFMT_MISC=y CONFIG_NET=y CONFIG_PACKET=y diff --git a/arch/x86/crypto/Makefile b/arch/x86/crypto/Makefile index a31de0c6ccde..b28e36b7c96b 100644 --- a/arch/x86/crypto/Makefile +++ b/arch/x86/crypto/Makefile @@ -4,8 +4,6 @@ OBJECT_FILES_NON_STANDARD := y -obj-$(CONFIG_CRYPTO_GLUE_HELPER_X86) += glue_helper.o - obj-$(CONFIG_CRYPTO_TWOFISH_586) += twofish-i586.o twofish-i586-y := twofish-i586-asm_32.o twofish_glue.o obj-$(CONFIG_CRYPTO_TWOFISH_X86_64) += twofish-x86_64.o diff --git a/arch/x86/crypto/aesni-intel_asm.S b/arch/x86/crypto/aesni-intel_asm.S index d1436c37008b..4e3972570916 100644 --- a/arch/x86/crypto/aesni-intel_asm.S +++ b/arch/x86/crypto/aesni-intel_asm.S @@ -43,10 +43,6 @@ #ifdef __x86_64__ # constants in mergeable sections, linker can reorder and merge -.section .rodata.cst16.gf128mul_x_ble_mask, "aM", @progbits, 16 -.align 16 -.Lgf128mul_x_ble_mask: - .octa 0x00000000000000010000000000000087 .section .rodata.cst16.POLY, "aM", @progbits, 16 .align 16 POLY: .octa 0xC2000000000000000000000000000001 @@ -146,7 +142,7 @@ ALL_F: .octa 0xffffffffffffffffffffffffffffffff #define CTR %xmm11 #define INC %xmm12 -#define GF128MUL_MASK %xmm10 +#define GF128MUL_MASK %xmm7 #ifdef __x86_64__ #define AREG %rax @@ -2577,13 +2573,140 @@ SYM_FUNC_START(aesni_cbc_dec) ret SYM_FUNC_END(aesni_cbc_dec) -#ifdef __x86_64__ +/* + * void aesni_cts_cbc_enc(struct crypto_aes_ctx *ctx, const u8 *dst, u8 *src, + * size_t len, u8 *iv) + */ +SYM_FUNC_START(aesni_cts_cbc_enc) + FRAME_BEGIN +#ifndef __x86_64__ + pushl IVP + pushl LEN + pushl KEYP + pushl KLEN + movl (FRAME_OFFSET+20)(%esp), KEYP # ctx + movl (FRAME_OFFSET+24)(%esp), OUTP # dst + movl (FRAME_OFFSET+28)(%esp), INP # src + movl (FRAME_OFFSET+32)(%esp), LEN # len + movl (FRAME_OFFSET+36)(%esp), IVP # iv + lea .Lcts_permute_table, T1 +#else + lea .Lcts_permute_table(%rip), T1 +#endif + mov 480(KEYP), KLEN + movups (IVP), STATE + sub $16, LEN + mov T1, IVP + add $32, IVP + add LEN, T1 + sub LEN, IVP + movups (T1), %xmm4 + movups (IVP), %xmm5 + + movups (INP), IN1 + add LEN, INP + movups (INP), IN2 + + pxor IN1, STATE + call _aesni_enc1 + + pshufb %xmm5, IN2 + pxor STATE, IN2 + pshufb %xmm4, STATE + add OUTP, LEN + movups STATE, (LEN) + + movaps IN2, STATE + call _aesni_enc1 + movups STATE, (OUTP) + +#ifndef __x86_64__ + popl KLEN + popl KEYP + popl LEN + popl IVP +#endif + FRAME_END + ret +SYM_FUNC_END(aesni_cts_cbc_enc) + +/* + * void aesni_cts_cbc_dec(struct crypto_aes_ctx *ctx, const u8 *dst, u8 *src, + * size_t len, u8 *iv) + */ +SYM_FUNC_START(aesni_cts_cbc_dec) + FRAME_BEGIN +#ifndef __x86_64__ + pushl IVP + pushl LEN + pushl KEYP + pushl KLEN + movl (FRAME_OFFSET+20)(%esp), KEYP # ctx + movl (FRAME_OFFSET+24)(%esp), OUTP # dst + movl (FRAME_OFFSET+28)(%esp), INP # src + movl (FRAME_OFFSET+32)(%esp), LEN # len + movl (FRAME_OFFSET+36)(%esp), IVP # iv + lea .Lcts_permute_table, T1 +#else + lea .Lcts_permute_table(%rip), T1 +#endif + mov 480(KEYP), KLEN + add $240, KEYP + movups (IVP), IV + sub $16, LEN + mov T1, IVP + add $32, IVP + add LEN, T1 + sub LEN, IVP + movups (T1), %xmm4 + + movups (INP), STATE + add LEN, INP + movups (INP), IN1 + + call _aesni_dec1 + movaps STATE, IN2 + pshufb %xmm4, STATE + pxor IN1, STATE + + add OUTP, LEN + movups STATE, (LEN) + + movups (IVP), %xmm0 + pshufb %xmm0, IN1 + pblendvb IN2, IN1 + movaps IN1, STATE + call _aesni_dec1 + + pxor IV, STATE + movups STATE, (OUTP) + +#ifndef __x86_64__ + popl KLEN + popl KEYP + popl LEN + popl IVP +#endif + FRAME_END + ret +SYM_FUNC_END(aesni_cts_cbc_dec) + .pushsection .rodata .align 16 +.Lcts_permute_table: + .byte 0x80, 0x80, 0x80, 0x80, 0x80, 0x80, 0x80, 0x80 + .byte 0x80, 0x80, 0x80, 0x80, 0x80, 0x80, 0x80, 0x80 + .byte 0x00, 0x01, 0x02, 0x03, 0x04, 0x05, 0x06, 0x07 + .byte 0x08, 0x09, 0x0a, 0x0b, 0x0c, 0x0d, 0x0e, 0x0f + .byte 0x80, 0x80, 0x80, 0x80, 0x80, 0x80, 0x80, 0x80 + .byte 0x80, 0x80, 0x80, 0x80, 0x80, 0x80, 0x80, 0x80 +#ifdef __x86_64__ .Lbswap_mask: .byte 15, 14, 13, 12, 11, 10, 9, 8, 7, 6, 5, 4, 3, 2, 1, 0 +#endif .popsection +#ifdef __x86_64__ /* * _aesni_inc_init: internal ABI * setup registers used by _aesni_inc @@ -2696,6 +2819,14 @@ SYM_FUNC_START(aesni_ctr_enc) ret SYM_FUNC_END(aesni_ctr_enc) +#endif + +.section .rodata.cst16.gf128mul_x_ble_mask, "aM", @progbits, 16 +.align 16 +.Lgf128mul_x_ble_mask: + .octa 0x00000000000000010000000000000087 +.previous + /* * _aesni_gf128mul_x_ble: internal ABI * Multiply in GF(2^128) for XTS IVs @@ -2708,120 +2839,325 @@ SYM_FUNC_END(aesni_ctr_enc) * CTR: == temporary value */ #define _aesni_gf128mul_x_ble() \ - pshufd $0x13, IV, CTR; \ + pshufd $0x13, IV, KEY; \ paddq IV, IV; \ - psrad $31, CTR; \ - pand GF128MUL_MASK, CTR; \ - pxor CTR, IV; + psrad $31, KEY; \ + pand GF128MUL_MASK, KEY; \ + pxor KEY, IV; /* - * void aesni_xts_crypt8(const struct crypto_aes_ctx *ctx, u8 *dst, - * const u8 *src, bool enc, le128 *iv) + * void aesni_xts_encrypt(const struct crypto_aes_ctx *ctx, u8 *dst, + * const u8 *src, unsigned int len, le128 *iv) */ -SYM_FUNC_START(aesni_xts_crypt8) +SYM_FUNC_START(aesni_xts_encrypt) FRAME_BEGIN - testb %cl, %cl - movl $0, %ecx - movl $240, %r10d - leaq _aesni_enc4, %r11 - leaq _aesni_dec4, %rax - cmovel %r10d, %ecx - cmoveq %rax, %r11 - +#ifndef __x86_64__ + pushl IVP + pushl LEN + pushl KEYP + pushl KLEN + movl (FRAME_OFFSET+20)(%esp), KEYP # ctx + movl (FRAME_OFFSET+24)(%esp), OUTP # dst + movl (FRAME_OFFSET+28)(%esp), INP # src + movl (FRAME_OFFSET+32)(%esp), LEN # len + movl (FRAME_OFFSET+36)(%esp), IVP # iv movdqa .Lgf128mul_x_ble_mask, GF128MUL_MASK +#else + movdqa .Lgf128mul_x_ble_mask(%rip), GF128MUL_MASK +#endif movups (IVP), IV mov 480(KEYP), KLEN - addq %rcx, KEYP + +.Lxts_enc_loop4: + sub $64, LEN + jl .Lxts_enc_1x movdqa IV, STATE1 - movdqu 0x00(INP), INC - pxor INC, STATE1 + movdqu 0x00(INP), IN + pxor IN, STATE1 movdqu IV, 0x00(OUTP) _aesni_gf128mul_x_ble() movdqa IV, STATE2 - movdqu 0x10(INP), INC - pxor INC, STATE2 + movdqu 0x10(INP), IN + pxor IN, STATE2 movdqu IV, 0x10(OUTP) _aesni_gf128mul_x_ble() movdqa IV, STATE3 - movdqu 0x20(INP), INC - pxor INC, STATE3 + movdqu 0x20(INP), IN + pxor IN, STATE3 movdqu IV, 0x20(OUTP) _aesni_gf128mul_x_ble() movdqa IV, STATE4 - movdqu 0x30(INP), INC - pxor INC, STATE4 + movdqu 0x30(INP), IN + pxor IN, STATE4 movdqu IV, 0x30(OUTP) - CALL_NOSPEC r11 + call _aesni_enc4 - movdqu 0x00(OUTP), INC - pxor INC, STATE1 + movdqu 0x00(OUTP), IN + pxor IN, STATE1 movdqu STATE1, 0x00(OUTP) + movdqu 0x10(OUTP), IN + pxor IN, STATE2 + movdqu STATE2, 0x10(OUTP) + + movdqu 0x20(OUTP), IN + pxor IN, STATE3 + movdqu STATE3, 0x20(OUTP) + + movdqu 0x30(OUTP), IN + pxor IN, STATE4 + movdqu STATE4, 0x30(OUTP) + _aesni_gf128mul_x_ble() - movdqa IV, STATE1 - movdqu 0x40(INP), INC - pxor INC, STATE1 - movdqu IV, 0x40(OUTP) - movdqu 0x10(OUTP), INC - pxor INC, STATE2 - movdqu STATE2, 0x10(OUTP) + add $64, INP + add $64, OUTP + test LEN, LEN + jnz .Lxts_enc_loop4 +.Lxts_enc_ret_iv: + movups IV, (IVP) + +.Lxts_enc_ret: +#ifndef __x86_64__ + popl KLEN + popl KEYP + popl LEN + popl IVP +#endif + FRAME_END + ret + +.Lxts_enc_1x: + add $64, LEN + jz .Lxts_enc_ret_iv + sub $16, LEN + jl .Lxts_enc_cts4 + +.Lxts_enc_loop1: + movdqu (INP), STATE + pxor IV, STATE + call _aesni_enc1 + pxor IV, STATE _aesni_gf128mul_x_ble() - movdqa IV, STATE2 - movdqu 0x50(INP), INC - pxor INC, STATE2 - movdqu IV, 0x50(OUTP) - movdqu 0x20(OUTP), INC - pxor INC, STATE3 - movdqu STATE3, 0x20(OUTP) + test LEN, LEN + jz .Lxts_enc_out + + add $16, INP + sub $16, LEN + jl .Lxts_enc_cts1 + + movdqu STATE, (OUTP) + add $16, OUTP + jmp .Lxts_enc_loop1 + +.Lxts_enc_out: + movdqu STATE, (OUTP) + jmp .Lxts_enc_ret_iv + +.Lxts_enc_cts4: + movdqa STATE4, STATE + sub $16, OUTP + +.Lxts_enc_cts1: +#ifndef __x86_64__ + lea .Lcts_permute_table, T1 +#else + lea .Lcts_permute_table(%rip), T1 +#endif + add LEN, INP /* rewind input pointer */ + add $16, LEN /* # bytes in final block */ + movups (INP), IN1 + + mov T1, IVP + add $32, IVP + add LEN, T1 + sub LEN, IVP + add OUTP, LEN + + movups (T1), %xmm4 + movaps STATE, IN2 + pshufb %xmm4, STATE + movups STATE, (LEN) + + movups (IVP), %xmm0 + pshufb %xmm0, IN1 + pblendvb IN2, IN1 + movaps IN1, STATE + + pxor IV, STATE + call _aesni_enc1 + pxor IV, STATE + + movups STATE, (OUTP) + jmp .Lxts_enc_ret +SYM_FUNC_END(aesni_xts_encrypt) + +/* + * void aesni_xts_decrypt(const struct crypto_aes_ctx *ctx, u8 *dst, + * const u8 *src, unsigned int len, le128 *iv) + */ +SYM_FUNC_START(aesni_xts_decrypt) + FRAME_BEGIN +#ifndef __x86_64__ + pushl IVP + pushl LEN + pushl KEYP + pushl KLEN + movl (FRAME_OFFSET+20)(%esp), KEYP # ctx + movl (FRAME_OFFSET+24)(%esp), OUTP # dst + movl (FRAME_OFFSET+28)(%esp), INP # src + movl (FRAME_OFFSET+32)(%esp), LEN # len + movl (FRAME_OFFSET+36)(%esp), IVP # iv + movdqa .Lgf128mul_x_ble_mask, GF128MUL_MASK +#else + movdqa .Lgf128mul_x_ble_mask(%rip), GF128MUL_MASK +#endif + movups (IVP), IV + + mov 480(KEYP), KLEN + add $240, KEYP + + test $15, LEN + jz .Lxts_dec_loop4 + sub $16, LEN + +.Lxts_dec_loop4: + sub $64, LEN + jl .Lxts_dec_1x + + movdqa IV, STATE1 + movdqu 0x00(INP), IN + pxor IN, STATE1 + movdqu IV, 0x00(OUTP) _aesni_gf128mul_x_ble() - movdqa IV, STATE3 - movdqu 0x60(INP), INC - pxor INC, STATE3 - movdqu IV, 0x60(OUTP) + movdqa IV, STATE2 + movdqu 0x10(INP), IN + pxor IN, STATE2 + movdqu IV, 0x10(OUTP) - movdqu 0x30(OUTP), INC - pxor INC, STATE4 - movdqu STATE4, 0x30(OUTP) + _aesni_gf128mul_x_ble() + movdqa IV, STATE3 + movdqu 0x20(INP), IN + pxor IN, STATE3 + movdqu IV, 0x20(OUTP) _aesni_gf128mul_x_ble() movdqa IV, STATE4 - movdqu 0x70(INP), INC - pxor INC, STATE4 - movdqu IV, 0x70(OUTP) + movdqu 0x30(INP), IN + pxor IN, STATE4 + movdqu IV, 0x30(OUTP) - _aesni_gf128mul_x_ble() - movups IV, (IVP) + call _aesni_dec4 + + movdqu 0x00(OUTP), IN + pxor IN, STATE1 + movdqu STATE1, 0x00(OUTP) + + movdqu 0x10(OUTP), IN + pxor IN, STATE2 + movdqu STATE2, 0x10(OUTP) - CALL_NOSPEC r11 + movdqu 0x20(OUTP), IN + pxor IN, STATE3 + movdqu STATE3, 0x20(OUTP) - movdqu 0x40(OUTP), INC - pxor INC, STATE1 - movdqu STATE1, 0x40(OUTP) + movdqu 0x30(OUTP), IN + pxor IN, STATE4 + movdqu STATE4, 0x30(OUTP) - movdqu 0x50(OUTP), INC - pxor INC, STATE2 - movdqu STATE2, 0x50(OUTP) + _aesni_gf128mul_x_ble() - movdqu 0x60(OUTP), INC - pxor INC, STATE3 - movdqu STATE3, 0x60(OUTP) + add $64, INP + add $64, OUTP + test LEN, LEN + jnz .Lxts_dec_loop4 - movdqu 0x70(OUTP), INC - pxor INC, STATE4 - movdqu STATE4, 0x70(OUTP) +.Lxts_dec_ret_iv: + movups IV, (IVP) +.Lxts_dec_ret: +#ifndef __x86_64__ + popl KLEN + popl KEYP + popl LEN + popl IVP +#endif FRAME_END ret -SYM_FUNC_END(aesni_xts_crypt8) +.Lxts_dec_1x: + add $64, LEN + jz .Lxts_dec_ret_iv + +.Lxts_dec_loop1: + movdqu (INP), STATE + + add $16, INP + sub $16, LEN + jl .Lxts_dec_cts1 + + pxor IV, STATE + call _aesni_dec1 + pxor IV, STATE + _aesni_gf128mul_x_ble() + + test LEN, LEN + jz .Lxts_dec_out + + movdqu STATE, (OUTP) + add $16, OUTP + jmp .Lxts_dec_loop1 + +.Lxts_dec_out: + movdqu STATE, (OUTP) + jmp .Lxts_dec_ret_iv + +.Lxts_dec_cts1: + movdqa IV, STATE4 + _aesni_gf128mul_x_ble() + + pxor IV, STATE + call _aesni_dec1 + pxor IV, STATE + +#ifndef __x86_64__ + lea .Lcts_permute_table, T1 +#else + lea .Lcts_permute_table(%rip), T1 #endif + add LEN, INP /* rewind input pointer */ + add $16, LEN /* # bytes in final block */ + movups (INP), IN1 + + mov T1, IVP + add $32, IVP + add LEN, T1 + sub LEN, IVP + add OUTP, LEN + + movups (T1), %xmm4 + movaps STATE, IN2 + pshufb %xmm4, STATE + movups STATE, (LEN) + + movups (IVP), %xmm0 + pshufb %xmm0, IN1 + pblendvb IN2, IN1 + movaps IN1, STATE + + pxor STATE4, STATE + call _aesni_dec1 + pxor STATE4, STATE + + movups STATE, (OUTP) + jmp .Lxts_dec_ret +SYM_FUNC_END(aesni_xts_decrypt) diff --git a/arch/x86/crypto/aesni-intel_glue.c b/arch/x86/crypto/aesni-intel_glue.c index ad8a7188a2bf..2144e54a6c89 100644 --- a/arch/x86/crypto/aesni-intel_glue.c +++ b/arch/x86/crypto/aesni-intel_glue.c @@ -31,11 +31,10 @@ #include <crypto/internal/aead.h> #include <crypto/internal/simd.h> #include <crypto/internal/skcipher.h> +#include <linux/jump_label.h> #include <linux/workqueue.h> #include <linux/spinlock.h> -#ifdef CONFIG_X86_64 -#include <asm/crypto/glue_helper.h> -#endif +#include <linux/static_call.h> #define AESNI_ALIGN 16 @@ -93,62 +92,25 @@ asmlinkage void aesni_cbc_enc(struct crypto_aes_ctx *ctx, u8 *out, const u8 *in, unsigned int len, u8 *iv); asmlinkage void aesni_cbc_dec(struct crypto_aes_ctx *ctx, u8 *out, const u8 *in, unsigned int len, u8 *iv); +asmlinkage void aesni_cts_cbc_enc(struct crypto_aes_ctx *ctx, u8 *out, + const u8 *in, unsigned int len, u8 *iv); +asmlinkage void aesni_cts_cbc_dec(struct crypto_aes_ctx *ctx, u8 *out, + const u8 *in, unsigned int len, u8 *iv); #define AVX_GEN2_OPTSIZE 640 #define AVX_GEN4_OPTSIZE 4096 +asmlinkage void aesni_xts_encrypt(const struct crypto_aes_ctx *ctx, u8 *out, + const u8 *in, unsigned int len, u8 *iv); + +asmlinkage void aesni_xts_decrypt(const struct crypto_aes_ctx *ctx, u8 *out, + const u8 *in, unsigned int len, u8 *iv); + #ifdef CONFIG_X86_64 -static void (*aesni_ctr_enc_tfm)(struct crypto_aes_ctx *ctx, u8 *out, - const u8 *in, unsigned int len, u8 *iv); asmlinkage void aesni_ctr_enc(struct crypto_aes_ctx *ctx, u8 *out, const u8 *in, unsigned int len, u8 *iv); - -asmlinkage void aesni_xts_crypt8(const struct crypto_aes_ctx *ctx, u8 *out, - const u8 *in, bool enc, le128 *iv); - -/* asmlinkage void aesni_gcm_enc() - * void *ctx, AES Key schedule. Starts on a 16 byte boundary. - * struct gcm_context_data. May be uninitialized. - * u8 *out, Ciphertext output. Encrypt in-place is allowed. - * const u8 *in, Plaintext input - * unsigned long plaintext_len, Length of data in bytes for encryption. - * u8 *iv, Pre-counter block j0: 12 byte IV concatenated with 0x00000001. - * 16-byte aligned pointer. - * u8 *hash_subkey, the Hash sub key input. Data starts on a 16-byte boundary. - * const u8 *aad, Additional Authentication Data (AAD) - * unsigned long aad_len, Length of AAD in bytes. - * u8 *auth_tag, Authenticated Tag output. - * unsigned long auth_tag_len), Authenticated Tag Length in bytes. - * Valid values are 16 (most likely), 12 or 8. - */ -asmlinkage void aesni_gcm_enc(void *ctx, - struct gcm_context_data *gdata, u8 *out, - const u8 *in, unsigned long plaintext_len, u8 *iv, - u8 *hash_subkey, const u8 *aad, unsigned long aad_len, - u8 *auth_tag, unsigned long auth_tag_len); - -/* asmlinkage void aesni_gcm_dec() - * void *ctx, AES Key schedule. Starts on a 16 byte boundary. - * struct gcm_context_data. May be uninitialized. - * u8 *out, Plaintext output. Decrypt in-place is allowed. - * const u8 *in, Ciphertext input - * unsigned long ciphertext_len, Length of data in bytes for decryption. - * u8 *iv, Pre-counter block j0: 12 byte IV concatenated with 0x00000001. - * 16-byte aligned pointer. - * u8 *hash_subkey, the Hash sub key input. Data starts on a 16-byte boundary. - * const u8 *aad, Additional Authentication Data (AAD) - * unsigned long aad_len, Length of AAD in bytes. With RFC4106 this is going - * to be 8 or 12 bytes - * u8 *auth_tag, Authenticated Tag output. - * unsigned long auth_tag_len) Authenticated Tag Length in bytes. - * Valid values are 16 (most likely), 12 or 8. - */ -asmlinkage void aesni_gcm_dec(void *ctx, - struct gcm_context_data *gdata, u8 *out, - const u8 *in, unsigned long ciphertext_len, u8 *iv, - u8 *hash_subkey, const u8 *aad, unsigned long aad_len, - u8 *auth_tag, unsigned long auth_tag_len); +DEFINE_STATIC_CALL(aesni_ctr_enc_tfm, aesni_ctr_enc); /* Scatter / Gather routines, with args similar to above */ asmlinkage void aesni_gcm_init(void *ctx, @@ -167,24 +129,6 @@ asmlinkage void aesni_gcm_finalize(void *ctx, struct gcm_context_data *gdata, u8 *auth_tag, unsigned long auth_tag_len); -static const struct aesni_gcm_tfm_s { - void (*init)(void *ctx, struct gcm_context_data *gdata, u8 *iv, - u8 *hash_subkey, const u8 *aad, unsigned long aad_len); - void (*enc_update)(void *ctx, struct gcm_context_data *gdata, u8 *out, - const u8 *in, unsigned long plaintext_len); - void (*dec_update)(void *ctx, struct gcm_context_data *gdata, u8 *out, - const u8 *in, unsigned long ciphertext_len); - void (*finalize)(void *ctx, struct gcm_context_data *gdata, - u8 *auth_tag, unsigned long auth_tag_len); -} *aesni_gcm_tfm; - -static const struct aesni_gcm_tfm_s aesni_gcm_tfm_sse = { - .init = &aesni_gcm_init, - .enc_update = &aesni_gcm_enc_update, - .dec_update = &aesni_gcm_dec_update, - .finalize = &aesni_gcm_finalize, -}; - asmlinkage void aes_ctr_enc_128_avx_by8(const u8 *in, u8 *iv, void *keys, u8 *out, unsigned int num_bytes); asmlinkage void aes_ctr_enc_192_avx_by8(const u8 *in, u8 *iv, @@ -214,25 +158,6 @@ asmlinkage void aesni_gcm_finalize_avx_gen2(void *ctx, struct gcm_context_data *gdata, u8 *auth_tag, unsigned long auth_tag_len); -asmlinkage void aesni_gcm_enc_avx_gen2(void *ctx, - struct gcm_context_data *gdata, u8 *out, - const u8 *in, unsigned long plaintext_len, u8 *iv, - const u8 *aad, unsigned long aad_len, - u8 *auth_tag, unsigned long auth_tag_len); - -asmlinkage void aesni_gcm_dec_avx_gen2(void *ctx, - struct gcm_context_data *gdata, u8 *out, - const u8 *in, unsigned long ciphertext_len, u8 *iv, - const u8 *aad, unsigned long aad_len, - u8 *auth_tag, unsigned long auth_tag_len); - -static const struct aesni_gcm_tfm_s aesni_gcm_tfm_avx_gen2 = { - .init = &aesni_gcm_init_avx_gen2, - .enc_update = &aesni_gcm_enc_update_avx_gen2, - .dec_update = &aesni_gcm_dec_update_avx_gen2, - .finalize = &aesni_gcm_finalize_avx_gen2, -}; - /* * asmlinkage void aesni_gcm_init_avx_gen4() * gcm_data *my_ctx_data, context data @@ -256,24 +181,8 @@ asmlinkage void aesni_gcm_finalize_avx_gen4(void *ctx, struct gcm_context_data *gdata, u8 *auth_tag, unsigned long auth_tag_len); -asmlinkage void aesni_gcm_enc_avx_gen4(void *ctx, - struct gcm_context_data *gdata, u8 *out, - const u8 *in, unsigned long plaintext_len, u8 *iv, - const u8 *aad, unsigned long aad_len, - u8 *auth_tag, unsigned long auth_tag_len); - -asmlinkage void aesni_gcm_dec_avx_gen4(void *ctx, - struct gcm_context_data *gdata, u8 *out, - const u8 *in, unsigned long ciphertext_len, u8 *iv, - const u8 *aad, unsigned long aad_len, - u8 *auth_tag, unsigned long auth_tag_len); - -static const struct aesni_gcm_tfm_s aesni_gcm_tfm_avx_gen4 = { - .init = &aesni_gcm_init_avx_gen4, - .enc_update = &aesni_gcm_enc_update_avx_gen4, - .dec_update = &aesni_gcm_dec_update_avx_gen4, - .finalize = &aesni_gcm_finalize_avx_gen4, -}; +static __ro_after_init DEFINE_STATIC_KEY_FALSE(gcm_use_avx); +static __ro_after_init DEFINE_STATIC_KEY_FALSE(gcm_use_avx2); static inline struct aesni_rfc4106_gcm_ctx *aesni_rfc4106_gcm_ctx_get(struct crypto_aead *tfm) @@ -374,16 +283,16 @@ static int ecb_encrypt(struct skcipher_request *req) unsigned int nbytes; int err; - err = skcipher_walk_virt(&walk, req, true); + err = skcipher_walk_virt(&walk, req, false); - kernel_fpu_begin(); while ((nbytes = walk.nbytes)) { + kernel_fpu_begin(); aesni_ecb_enc(ctx, walk.dst.virt.addr, walk.src.virt.addr, nbytes & AES_BLOCK_MASK); + kernel_fpu_end(); nbytes &= AES_BLOCK_SIZE - 1; err = skcipher_walk_done(&walk, nbytes); } - kernel_fpu_end(); return err; } @@ -396,16 +305,16 @@ static int ecb_decrypt(struct skcipher_request *req) unsigned int nbytes; int err; - err = skcipher_walk_virt(&walk, req, true); + err = skcipher_walk_virt(&walk, req, false); - kernel_fpu_begin(); while ((nbytes = walk.nbytes)) { + kernel_fpu_begin(); aesni_ecb_dec(ctx, walk.dst.virt.addr, walk.src.virt.addr, nbytes & AES_BLOCK_MASK); + kernel_fpu_end(); nbytes &= AES_BLOCK_SIZE - 1; err = skcipher_walk_done(&walk, nbytes); } - kernel_fpu_end(); return err; } @@ -418,16 +327,16 @@ static int cbc_encrypt(struct skcipher_request *req) unsigned int nbytes; int err; - err = skcipher_walk_virt(&walk, req, true); + err = skcipher_walk_virt(&walk, req, false); - kernel_fpu_begin(); while ((nbytes = walk.nbytes)) { + kernel_fpu_begin(); aesni_cbc_enc(ctx, walk.dst.virt.addr, walk.src.virt.addr, nbytes & AES_BLOCK_MASK, walk.iv); + kernel_fpu_end(); nbytes &= AES_BLOCK_SIZE - 1; err = skcipher_walk_done(&walk, nbytes); } - kernel_fpu_end(); return err; } @@ -440,36 +349,133 @@ static int cbc_decrypt(struct skcipher_request *req) unsigned int nbytes; int err; - err = skcipher_walk_virt(&walk, req, true); + err = skcipher_walk_virt(&walk, req, false); - kernel_fpu_begin(); while ((nbytes = walk.nbytes)) { + kernel_fpu_begin(); aesni_cbc_dec(ctx, walk.dst.virt.addr, walk.src.virt.addr, nbytes & AES_BLOCK_MASK, walk.iv); + kernel_fpu_end(); nbytes &= AES_BLOCK_SIZE - 1; err = skcipher_walk_done(&walk, nbytes); } - kernel_fpu_end(); return err; } -#ifdef CONFIG_X86_64 -static void ctr_crypt_final(struct crypto_aes_ctx *ctx, - struct skcipher_walk *walk) +static int cts_cbc_encrypt(struct skcipher_request *req) { - u8 *ctrblk = walk->iv; - u8 keystream[AES_BLOCK_SIZE]; - u8 *src = walk->src.virt.addr; - u8 *dst = walk->dst.virt.addr; - unsigned int nbytes = walk->nbytes; + struct crypto_skcipher *tfm = crypto_skcipher_reqtfm(req); + struct crypto_aes_ctx *ctx = aes_ctx(crypto_skcipher_ctx(tfm)); + int cbc_blocks = DIV_ROUND_UP(req->cryptlen, AES_BLOCK_SIZE) - 2; + struct scatterlist *src = req->src, *dst = req->dst; + struct scatterlist sg_src[2], sg_dst[2]; + struct skcipher_request subreq; + struct skcipher_walk walk; + int err; + + skcipher_request_set_tfm(&subreq, tfm); + skcipher_request_set_callback(&subreq, skcipher_request_flags(req), + NULL, NULL); + + if (req->cryptlen <= AES_BLOCK_SIZE) { + if (req->cryptlen < AES_BLOCK_SIZE) + return -EINVAL; + cbc_blocks = 1; + } + + if (cbc_blocks > 0) { + skcipher_request_set_crypt(&subreq, req->src, req->dst, + cbc_blocks * AES_BLOCK_SIZE, + req->iv); + + err = cbc_encrypt(&subreq); + if (err) + return err; + + if (req->cryptlen == AES_BLOCK_SIZE) + return 0; + + dst = src = scatterwalk_ffwd(sg_src, req->src, subreq.cryptlen); + if (req->dst != req->src) + dst = scatterwalk_ffwd(sg_dst, req->dst, + subreq.cryptlen); + } + + /* handle ciphertext stealing */ + skcipher_request_set_crypt(&subreq, src, dst, + req->cryptlen - cbc_blocks * AES_BLOCK_SIZE, + req->iv); + + err = skcipher_walk_virt(&walk, &subreq, false); + if (err) + return err; + + kernel_fpu_begin(); + aesni_cts_cbc_enc(ctx, walk.dst.virt.addr, walk.src.virt.addr, + walk.nbytes, walk.iv); + kernel_fpu_end(); + + return skcipher_walk_done(&walk, 0); +} + +static int cts_cbc_decrypt(struct skcipher_request *req) +{ + struct crypto_skcipher *tfm = crypto_skcipher_reqtfm(req); + struct crypto_aes_ctx *ctx = aes_ctx(crypto_skcipher_ctx(tfm)); + int cbc_blocks = DIV_ROUND_UP(req->cryptlen, AES_BLOCK_SIZE) - 2; + struct scatterlist *src = req->src, *dst = req->dst; + struct scatterlist sg_src[2], sg_dst[2]; + struct skcipher_request subreq; + struct skcipher_walk walk; + int err; + + skcipher_request_set_tfm(&subreq, tfm); + skcipher_request_set_callback(&subreq, skcipher_request_flags(req), + NULL, NULL); + + if (req->cryptlen <= AES_BLOCK_SIZE) { + if (req->cryptlen < AES_BLOCK_SIZE) + return -EINVAL; + cbc_blocks = 1; + } + + if (cbc_blocks > 0) { + skcipher_request_set_crypt(&subreq, req->src, req->dst, + cbc_blocks * AES_BLOCK_SIZE, + req->iv); + + err = cbc_decrypt(&subreq); + if (err) + return err; + + if (req->cryptlen == AES_BLOCK_SIZE) + return 0; + + dst = src = scatterwalk_ffwd(sg_src, req->src, subreq.cryptlen); + if (req->dst != req->src) + dst = scatterwalk_ffwd(sg_dst, req->dst, + subreq.cryptlen); + } + + /* handle ciphertext stealing */ + skcipher_request_set_crypt(&subreq, src, dst, + req->cryptlen - cbc_blocks * AES_BLOCK_SIZE, + req->iv); - aesni_enc(ctx, keystream, ctrblk); - crypto_xor_cpy(dst, keystream, src, nbytes); + err = skcipher_walk_virt(&walk, &subreq, false); + if (err) + return err; + + kernel_fpu_begin(); + aesni_cts_cbc_dec(ctx, walk.dst.virt.addr, walk.src.virt.addr, + walk.nbytes, walk.iv); + kernel_fpu_end(); - crypto_inc(ctrblk, AES_BLOCK_SIZE); + return skcipher_walk_done(&walk, 0); } +#ifdef CONFIG_X86_64 static void aesni_ctr_enc_avx_tfm(struct crypto_aes_ctx *ctx, u8 *out, const u8 *in, unsigned int len, u8 *iv) { @@ -491,120 +497,36 @@ static int ctr_crypt(struct skcipher_request *req) { struct crypto_skcipher *tfm = crypto_skcipher_reqtfm(req); struct crypto_aes_ctx *ctx = aes_ctx(crypto_skcipher_ctx(tfm)); + u8 keystream[AES_BLOCK_SIZE]; struct skcipher_walk walk; unsigned int nbytes; int err; - err = skcipher_walk_virt(&walk, req, true); + err = skcipher_walk_virt(&walk, req, false); - kernel_fpu_begin(); - while ((nbytes = walk.nbytes) >= AES_BLOCK_SIZE) { - aesni_ctr_enc_tfm(ctx, walk.dst.virt.addr, walk.src.virt.addr, - nbytes & AES_BLOCK_MASK, walk.iv); - nbytes &= AES_BLOCK_SIZE - 1; + while ((nbytes = walk.nbytes) > 0) { + kernel_fpu_begin(); + if (nbytes & AES_BLOCK_MASK) + static_call(aesni_ctr_enc_tfm)(ctx, walk.dst.virt.addr, + walk.src.virt.addr, + nbytes & AES_BLOCK_MASK, + walk.iv); + nbytes &= ~AES_BLOCK_MASK; + + if (walk.nbytes == walk.total && nbytes > 0) { + aesni_enc(ctx, keystream, walk.iv); + crypto_xor_cpy(walk.dst.virt.addr + walk.nbytes - nbytes, + walk.src.virt.addr + walk.nbytes - nbytes, + keystream, nbytes); + crypto_inc(walk.iv, AES_BLOCK_SIZE); + nbytes = 0; + } + kernel_fpu_end(); err = skcipher_walk_done(&walk, nbytes); } - if (walk.nbytes) { - ctr_crypt_final(ctx, &walk); - err = skcipher_walk_done(&walk, 0); - } - kernel_fpu_end(); - return err; } -static int xts_aesni_setkey(struct crypto_skcipher *tfm, const u8 *key, - unsigned int keylen) -{ - struct aesni_xts_ctx *ctx = crypto_skcipher_ctx(tfm); - int err; - - err = xts_verify_key(tfm, key, keylen); - if (err) - return err; - - keylen /= 2; - - /* first half of xts-key is for crypt */ - err = aes_set_key_common(crypto_skcipher_tfm(tfm), ctx->raw_crypt_ctx, - key, keylen); - if (err) - return err; - - /* second half of xts-key is for tweak */ - return aes_set_key_common(crypto_skcipher_tfm(tfm), ctx->raw_tweak_ctx, - key + keylen, keylen); -} - - -static void aesni_xts_enc(const void *ctx, u8 *dst, const u8 *src, le128 *iv) -{ - glue_xts_crypt_128bit_one(ctx, dst, src, iv, aesni_enc); -} - -static void aesni_xts_dec(const void *ctx, u8 *dst, const u8 *src, le128 *iv) -{ - glue_xts_crypt_128bit_one(ctx, dst, src, iv, aesni_dec); -} - -static void aesni_xts_enc8(const void *ctx, u8 *dst, const u8 *src, le128 *iv) -{ - aesni_xts_crypt8(ctx, dst, src, true, iv); -} - -static void aesni_xts_dec8(const void *ctx, u8 *dst, const u8 *src, le128 *iv) -{ - aesni_xts_crypt8(ctx, dst, src, false, iv); -} - -static const struct common_glue_ctx aesni_enc_xts = { - .num_funcs = 2, - .fpu_blocks_limit = 1, - - .funcs = { { - .num_blocks = 8, - .fn_u = { .xts = aesni_xts_enc8 } - }, { - .num_blocks = 1, - .fn_u = { .xts = aesni_xts_enc } - } } -}; - -static const struct common_glue_ctx aesni_dec_xts = { - .num_funcs = 2, - .fpu_blocks_limit = 1, - - .funcs = { { - .num_blocks = 8, - .fn_u = { .xts = aesni_xts_dec8 } - }, { - .num_blocks = 1, - .fn_u = { .xts = aesni_xts_dec } - } } -}; - -static int xts_encrypt(struct skcipher_request *req) -{ - struct crypto_skcipher *tfm = crypto_skcipher_reqtfm(req); - struct aesni_xts_ctx *ctx = crypto_skcipher_ctx(tfm); - - return glue_xts_req_128bit(&aesni_enc_xts, req, aesni_enc, - aes_ctx(ctx->raw_tweak_ctx), - aes_ctx(ctx->raw_crypt_ctx), - false); -} - -static int xts_decrypt(struct skcipher_request *req) -{ - struct crypto_skcipher *tfm = crypto_skcipher_reqtfm(req); - struct aesni_xts_ctx *ctx = crypto_skcipher_ctx(tfm); - - return glue_xts_req_128bit(&aesni_dec_xts, req, aesni_enc, - aes_ctx(ctx->raw_tweak_ctx), - aes_ctx(ctx->raw_crypt_ctx), - true); -} - static int rfc4106_set_hash_subkey(u8 *hash_subkey, const u8 *key, unsigned int key_len) { @@ -681,42 +603,35 @@ static int generic_gcmaes_set_authsize(struct crypto_aead *tfm, static int gcmaes_crypt_by_sg(bool enc, struct aead_request *req, unsigned int assoclen, u8 *hash_subkey, - u8 *iv, void *aes_ctx) + u8 *iv, void *aes_ctx, u8 *auth_tag, + unsigned long auth_tag_len) { - struct crypto_aead *tfm = crypto_aead_reqtfm(req); - unsigned long auth_tag_len = crypto_aead_authsize(tfm); - const struct aesni_gcm_tfm_s *gcm_tfm = aesni_gcm_tfm; - struct gcm_context_data data AESNI_ALIGN_ATTR; - struct scatter_walk dst_sg_walk = {}; + u8 databuf[sizeof(struct gcm_context_data) + (AESNI_ALIGN - 8)] __aligned(8); + struct gcm_context_data *data = PTR_ALIGN((void *)databuf, AESNI_ALIGN); unsigned long left = req->cryptlen; - unsigned long len, srclen, dstlen; struct scatter_walk assoc_sg_walk; - struct scatter_walk src_sg_walk; - struct scatterlist src_start[2]; - struct scatterlist dst_start[2]; - struct scatterlist *src_sg; - struct scatterlist *dst_sg; - u8 *src, *dst, *assoc; + struct skcipher_walk walk; + bool do_avx, do_avx2; u8 *assocmem = NULL; - u8 authTag[16]; + u8 *assoc; + int err; if (!enc) left -= auth_tag_len; - if (left < AVX_GEN4_OPTSIZE && gcm_tfm == &aesni_gcm_tfm_avx_gen4) - gcm_tfm = &aesni_gcm_tfm_avx_gen2; - if (left < AVX_GEN2_OPTSIZE && gcm_tfm == &aesni_gcm_tfm_avx_gen2) - gcm_tfm = &aesni_gcm_tfm_sse; + do_avx = (left >= AVX_GEN2_OPTSIZE); + do_avx2 = (left >= AVX_GEN4_OPTSIZE); /* Linearize assoc, if not already linear */ - if (req->src->length >= assoclen && req->src->length && - (!PageHighMem(sg_page(req->src)) || - req->src->offset + req->src->length <= PAGE_SIZE)) { + if (req->src->length >= assoclen && req->src->length) { scatterwalk_start(&assoc_sg_walk, req->src); assoc = scatterwalk_map(&assoc_sg_walk); } else { + gfp_t flags = (req->base.flags & CRYPTO_TFM_REQ_MAY_SLEEP) ? + GFP_KERNEL : GFP_ATOMIC; + /* assoc can be any length, so must be on heap */ - assocmem = kmalloc(assoclen, GFP_ATOMIC); + assocmem = kmalloc(assoclen, flags); if (unlikely(!assocmem)) return -ENOMEM; assoc = assocmem; @@ -724,62 +639,15 @@ static int gcmaes_crypt_by_sg(bool enc, struct aead_request *req, scatterwalk_map_and_copy(assoc, req->src, 0, assoclen, 0); } - if (left) { - src_sg = scatterwalk_ffwd(src_start, req->src, req->assoclen); - scatterwalk_start(&src_sg_walk, src_sg); - if (req->src != req->dst) { - dst_sg = scatterwalk_ffwd(dst_start, req->dst, - req->assoclen); - scatterwalk_start(&dst_sg_walk, dst_sg); - } - } - kernel_fpu_begin(); - gcm_tfm->init(aes_ctx, &data, iv, - hash_subkey, assoc, assoclen); - if (req->src != req->dst) { - while (left) { - src = scatterwalk_map(&src_sg_walk); - dst = scatterwalk_map(&dst_sg_walk); - srclen = scatterwalk_clamp(&src_sg_walk, left); - dstlen = scatterwalk_clamp(&dst_sg_walk, left); - len = min(srclen, dstlen); - if (len) { - if (enc) - gcm_tfm->enc_update(aes_ctx, &data, - dst, src, len); - else - gcm_tfm->dec_update(aes_ctx, &data, - dst, src, len); - } - left -= len; - - scatterwalk_unmap(src); - scatterwalk_unmap(dst); - scatterwalk_advance(&src_sg_walk, len); - scatterwalk_advance(&dst_sg_walk, len); - scatterwalk_done(&src_sg_walk, 0, left); - scatterwalk_done(&dst_sg_walk, 1, left); - } - } else { - while (left) { - dst = src = scatterwalk_map(&src_sg_walk); - len = scatterwalk_clamp(&src_sg_walk, left); - if (len) { - if (enc) - gcm_tfm->enc_update(aes_ctx, &data, - src, src, len); - else - gcm_tfm->dec_update(aes_ctx, &data, - src, src, len); - } - left -= len; - scatterwalk_unmap(src); - scatterwalk_advance(&src_sg_walk, len); - scatterwalk_done(&src_sg_walk, 1, left); - } - } - gcm_tfm->finalize(aes_ctx, &data, authTag, auth_tag_len); + if (static_branch_likely(&gcm_use_avx2) && do_avx2) + aesni_gcm_init_avx_gen4(aes_ctx, data, iv, hash_subkey, assoc, + assoclen); + else if (static_branch_likely(&gcm_use_avx) && do_avx) + aesni_gcm_init_avx_gen2(aes_ctx, data, iv, hash_subkey, assoc, + assoclen); + else + aesni_gcm_init(aes_ctx, data, iv, hash_subkey, assoc, assoclen); kernel_fpu_end(); if (!assocmem) @@ -787,24 +655,58 @@ static int gcmaes_crypt_by_sg(bool enc, struct aead_request *req, else kfree(assocmem); - if (!enc) { - u8 authTagMsg[16]; + err = enc ? skcipher_walk_aead_encrypt(&walk, req, false) + : skcipher_walk_aead_decrypt(&walk, req, false); - /* Copy out original authTag */ - scatterwalk_map_and_copy(authTagMsg, req->src, - req->assoclen + req->cryptlen - - auth_tag_len, - auth_tag_len, 0); + while (walk.nbytes > 0) { + kernel_fpu_begin(); + if (static_branch_likely(&gcm_use_avx2) && do_avx2) { + if (enc) + aesni_gcm_enc_update_avx_gen4(aes_ctx, data, + walk.dst.virt.addr, + walk.src.virt.addr, + walk.nbytes); + else + aesni_gcm_dec_update_avx_gen4(aes_ctx, data, + walk.dst.virt.addr, + walk.src.virt.addr, + walk.nbytes); + } else if (static_branch_likely(&gcm_use_avx) && do_avx) { + if (enc) + aesni_gcm_enc_update_avx_gen2(aes_ctx, data, + walk.dst.virt.addr, + walk.src.virt.addr, + walk.nbytes); + else + aesni_gcm_dec_update_avx_gen2(aes_ctx, data, + walk.dst.virt.addr, + walk.src.virt.addr, + walk.nbytes); + } else if (enc) { + aesni_gcm_enc_update(aes_ctx, data, walk.dst.virt.addr, + walk.src.virt.addr, walk.nbytes); + } else { + aesni_gcm_dec_update(aes_ctx, data, walk.dst.virt.addr, + walk.src.virt.addr, walk.nbytes); + } + kernel_fpu_end(); - /* Compare generated tag with passed in tag. */ - return crypto_memneq(authTagMsg, authTag, auth_tag_len) ? - -EBADMSG : 0; + err = skcipher_walk_done(&walk, 0); } - /* Copy in the authTag */ - scatterwalk_map_and_copy(authTag, req->dst, - req->assoclen + req->cryptlen, - auth_tag_len, 1); + if (err) + return err; + + kernel_fpu_begin(); + if (static_branch_likely(&gcm_use_avx2) && do_avx2) + aesni_gcm_finalize_avx_gen4(aes_ctx, data, auth_tag, + auth_tag_len); + else if (static_branch_likely(&gcm_use_avx) && do_avx) + aesni_gcm_finalize_avx_gen2(aes_ctx, data, auth_tag, + auth_tag_len); + else + aesni_gcm_finalize(aes_ctx, data, auth_tag, auth_tag_len); + kernel_fpu_end(); return 0; } @@ -812,15 +714,47 @@ static int gcmaes_crypt_by_sg(bool enc, struct aead_request *req, static int gcmaes_encrypt(struct aead_request *req, unsigned int assoclen, u8 *hash_subkey, u8 *iv, void *aes_ctx) { - return gcmaes_crypt_by_sg(true, req, assoclen, hash_subkey, iv, - aes_ctx); + struct crypto_aead *tfm = crypto_aead_reqtfm(req); + unsigned long auth_tag_len = crypto_aead_authsize(tfm); + u8 auth_tag[16]; + int err; + + err = gcmaes_crypt_by_sg(true, req, assoclen, hash_subkey, iv, aes_ctx, + auth_tag, auth_tag_len); + if (err) + return err; + + scatterwalk_map_and_copy(auth_tag, req->dst, + req->assoclen + req->cryptlen, + auth_tag_len, 1); + return 0; } static int gcmaes_decrypt(struct aead_request *req, unsigned int assoclen, u8 *hash_subkey, u8 *iv, void *aes_ctx) { - return gcmaes_crypt_by_sg(false, req, assoclen, hash_subkey, iv, - aes_ctx); + struct crypto_aead *tfm = crypto_aead_reqtfm(req); + unsigned long auth_tag_len = crypto_aead_authsize(tfm); + u8 auth_tag_msg[16]; + u8 auth_tag[16]; + int err; + + err = gcmaes_crypt_by_sg(false, req, assoclen, hash_subkey, iv, aes_ctx, + auth_tag, auth_tag_len); + if (err) + return err; + + /* Copy out original auth_tag */ + scatterwalk_map_and_copy(auth_tag_msg, req->src, + req->assoclen + req->cryptlen - auth_tag_len, + auth_tag_len, 0); + + /* Compare generated tag with passed in tag. */ + if (crypto_memneq(auth_tag_msg, auth_tag, auth_tag_len)) { + memzero_explicit(auth_tag, sizeof(auth_tag)); + return -EBADMSG; + } + return 0; } static int helper_rfc4106_encrypt(struct aead_request *req) @@ -828,7 +762,8 @@ static int helper_rfc4106_encrypt(struct aead_request *req) struct crypto_aead *tfm = crypto_aead_reqtfm(req); struct aesni_rfc4106_gcm_ctx *ctx = aesni_rfc4106_gcm_ctx_get(tfm); void *aes_ctx = &(ctx->aes_key_expanded); - u8 iv[16] __attribute__ ((__aligned__(AESNI_ALIGN))); + u8 ivbuf[16 + (AESNI_ALIGN - 8)] __aligned(8); + u8 *iv = PTR_ALIGN(&ivbuf[0], AESNI_ALIGN); unsigned int i; __be32 counter = cpu_to_be32(1); @@ -855,7 +790,8 @@ static int helper_rfc4106_decrypt(struct aead_request *req) struct crypto_aead *tfm = crypto_aead_reqtfm(req); struct aesni_rfc4106_gcm_ctx *ctx = aesni_rfc4106_gcm_ctx_get(tfm); void *aes_ctx = &(ctx->aes_key_expanded); - u8 iv[16] __attribute__ ((__aligned__(AESNI_ALIGN))); + u8 ivbuf[16 + (AESNI_ALIGN - 8)] __aligned(8); + u8 *iv = PTR_ALIGN(&ivbuf[0], AESNI_ALIGN); unsigned int i; if (unlikely(req->assoclen != 16 && req->assoclen != 20)) @@ -877,6 +813,128 @@ static int helper_rfc4106_decrypt(struct aead_request *req) } #endif +static int xts_aesni_setkey(struct crypto_skcipher *tfm, const u8 *key, + unsigned int keylen) +{ + struct aesni_xts_ctx *ctx = crypto_skcipher_ctx(tfm); + int err; + + err = xts_verify_key(tfm, key, keylen); + if (err) + return err; + + keylen /= 2; + + /* first half of xts-key is for crypt */ + err = aes_set_key_common(crypto_skcipher_tfm(tfm), ctx->raw_crypt_ctx, + key, keylen); + if (err) + return err; + + /* second half of xts-key is for tweak */ + return aes_set_key_common(crypto_skcipher_tfm(tfm), ctx->raw_tweak_ctx, + key + keylen, keylen); +} + +static int xts_crypt(struct skcipher_request *req, bool encrypt) +{ + struct crypto_skcipher *tfm = crypto_skcipher_reqtfm(req); + struct aesni_xts_ctx *ctx = crypto_skcipher_ctx(tfm); + int tail = req->cryptlen % AES_BLOCK_SIZE; + struct skcipher_request subreq; + struct skcipher_walk walk; + int err; + + if (req->cryptlen < AES_BLOCK_SIZE) + return -EINVAL; + + err = skcipher_walk_virt(&walk, req, false); + + if (unlikely(tail > 0 && walk.nbytes < walk.total)) { + int blocks = DIV_ROUND_UP(req->cryptlen, AES_BLOCK_SIZE) - 2; + + skcipher_walk_abort(&walk); + + skcipher_request_set_tfm(&subreq, tfm); + skcipher_request_set_callback(&subreq, + skcipher_request_flags(req), + NULL, NULL); + skcipher_request_set_crypt(&subreq, req->src, req->dst, + blocks * AES_BLOCK_SIZE, req->iv); + req = &subreq; + err = skcipher_walk_virt(&walk, req, false); + } else { + tail = 0; + } + + kernel_fpu_begin(); + + /* calculate first value of T */ + aesni_enc(aes_ctx(ctx->raw_tweak_ctx), walk.iv, walk.iv); + + while (walk.nbytes > 0) { + int nbytes = walk.nbytes; + + if (nbytes < walk.total) + nbytes &= ~(AES_BLOCK_SIZE - 1); + + if (encrypt) + aesni_xts_encrypt(aes_ctx(ctx->raw_crypt_ctx), + walk.dst.virt.addr, walk.src.virt.addr, + nbytes, walk.iv); + else + aesni_xts_decrypt(aes_ctx(ctx->raw_crypt_ctx), + walk.dst.virt.addr, walk.src.virt.addr, + nbytes, walk.iv); + kernel_fpu_end(); + + err = skcipher_walk_done(&walk, walk.nbytes - nbytes); + + if (walk.nbytes > 0) + kernel_fpu_begin(); + } + + if (unlikely(tail > 0 && !err)) { + struct scatterlist sg_src[2], sg_dst[2]; + struct scatterlist *src, *dst; + + dst = src = scatterwalk_ffwd(sg_src, req->src, req->cryptlen); + if (req->dst != req->src) + dst = scatterwalk_ffwd(sg_dst, req->dst, req->cryptlen); + + skcipher_request_set_crypt(req, src, dst, AES_BLOCK_SIZE + tail, + req->iv); + + err = skcipher_walk_virt(&walk, &subreq, false); + if (err) + return err; + + kernel_fpu_begin(); + if (encrypt) + aesni_xts_encrypt(aes_ctx(ctx->raw_crypt_ctx), + walk.dst.virt.addr, walk.src.virt.addr, + walk.nbytes, walk.iv); + else + aesni_xts_decrypt(aes_ctx(ctx->raw_crypt_ctx), + walk.dst.virt.addr, walk.src.virt.addr, + walk.nbytes, walk.iv); + kernel_fpu_end(); + + err = skcipher_walk_done(&walk, 0); + } + return err; +} + +static int xts_encrypt(struct skcipher_request *req) +{ + return xts_crypt(req, true); +} + +static int xts_decrypt(struct skcipher_request *req) +{ + return xts_crypt(req, false); +} + static struct crypto_alg aesni_cipher_alg = { .cra_name = "aes", .cra_driver_name = "aes-aesni", @@ -928,6 +986,23 @@ static struct skcipher_alg aesni_skciphers[] = { .setkey = aesni_skcipher_setkey, .encrypt = cbc_encrypt, .decrypt = cbc_decrypt, + }, { + .base = { + .cra_name = "__cts(cbc(aes))", + .cra_driver_name = "__cts-cbc-aes-aesni", + .cra_priority = 400, + .cra_flags = CRYPTO_ALG_INTERNAL, + .cra_blocksize = AES_BLOCK_SIZE, + .cra_ctxsize = CRYPTO_AES_CTX_SIZE, + .cra_module = THIS_MODULE, + }, + .min_keysize = AES_MIN_KEY_SIZE, + .max_keysize = AES_MAX_KEY_SIZE, + .ivsize = AES_BLOCK_SIZE, + .walksize = 2 * AES_BLOCK_SIZE, + .setkey = aesni_skcipher_setkey, + .encrypt = cts_cbc_encrypt, + .decrypt = cts_cbc_decrypt, #ifdef CONFIG_X86_64 }, { .base = { @@ -946,6 +1021,7 @@ static struct skcipher_alg aesni_skciphers[] = { .setkey = aesni_skcipher_setkey, .encrypt = ctr_crypt, .decrypt = ctr_crypt, +#endif }, { .base = { .cra_name = "__xts(aes)", @@ -959,10 +1035,10 @@ static struct skcipher_alg aesni_skciphers[] = { .min_keysize = 2 * AES_MIN_KEY_SIZE, .max_keysize = 2 * AES_MAX_KEY_SIZE, .ivsize = AES_BLOCK_SIZE, + .walksize = 2 * AES_BLOCK_SIZE, .setkey = xts_aesni_setkey, .encrypt = xts_encrypt, .decrypt = xts_decrypt, -#endif } }; @@ -985,7 +1061,8 @@ static int generic_gcmaes_encrypt(struct aead_request *req) struct crypto_aead *tfm = crypto_aead_reqtfm(req); struct generic_gcmaes_ctx *ctx = generic_gcmaes_ctx_get(tfm); void *aes_ctx = &(ctx->aes_key_expanded); - u8 iv[16] __attribute__ ((__aligned__(AESNI_ALIGN))); + u8 ivbuf[16 + (AESNI_ALIGN - 8)] __aligned(8); + u8 *iv = PTR_ALIGN(&ivbuf[0], AESNI_ALIGN); __be32 counter = cpu_to_be32(1); memcpy(iv, req->iv, 12); @@ -1001,7 +1078,8 @@ static int generic_gcmaes_decrypt(struct aead_request *req) struct crypto_aead *tfm = crypto_aead_reqtfm(req); struct generic_gcmaes_ctx *ctx = generic_gcmaes_ctx_get(tfm); void *aes_ctx = &(ctx->aes_key_expanded); - u8 iv[16] __attribute__ ((__aligned__(AESNI_ALIGN))); + u8 ivbuf[16 + (AESNI_ALIGN - 8)] __aligned(8); + u8 *iv = PTR_ALIGN(&ivbuf[0], AESNI_ALIGN); memcpy(iv, req->iv, 12); *((__be32 *)(iv+12)) = counter; @@ -1066,19 +1144,18 @@ static int __init aesni_init(void) #ifdef CONFIG_X86_64 if (boot_cpu_has(X86_FEATURE_AVX2)) { pr_info("AVX2 version of gcm_enc/dec engaged.\n"); - aesni_gcm_tfm = &aesni_gcm_tfm_avx_gen4; + static_branch_enable(&gcm_use_avx); + static_branch_enable(&gcm_use_avx2); } else if (boot_cpu_has(X86_FEATURE_AVX)) { pr_info("AVX version of gcm_enc/dec engaged.\n"); - aesni_gcm_tfm = &aesni_gcm_tfm_avx_gen2; + static_branch_enable(&gcm_use_avx); } else { pr_info("SSE version of gcm_enc/dec engaged.\n"); - aesni_gcm_tfm = &aesni_gcm_tfm_sse; } - aesni_ctr_enc_tfm = aesni_ctr_enc; if (boot_cpu_has(X86_FEATURE_AVX)) { /* optimize performance of ctr mode encryption transform */ - aesni_ctr_enc_tfm = aesni_ctr_enc_avx_tfm; + static_call_update(aesni_ctr_enc_tfm, aesni_ctr_enc_avx_tfm); pr_info("AES CTR mode by8 optimization enabled\n"); } #endif diff --git a/arch/x86/crypto/blake2s-glue.c b/arch/x86/crypto/blake2s-glue.c index c025a01cf708..a40365ab301e 100644 --- a/arch/x86/crypto/blake2s-glue.c +++ b/arch/x86/crypto/blake2s-glue.c @@ -58,138 +58,40 @@ void blake2s_compress_arch(struct blake2s_state *state, } EXPORT_SYMBOL(blake2s_compress_arch); -static int crypto_blake2s_setkey(struct crypto_shash *tfm, const u8 *key, - unsigned int keylen) +static int crypto_blake2s_update_x86(struct shash_desc *desc, + const u8 *in, unsigned int inlen) { - struct blake2s_tfm_ctx *tctx = crypto_shash_ctx(tfm); - - if (keylen == 0 || keylen > BLAKE2S_KEY_SIZE) - return -EINVAL; - - memcpy(tctx->key, key, keylen); - tctx->keylen = keylen; - - return 0; + return crypto_blake2s_update(desc, in, inlen, blake2s_compress_arch); } -static int crypto_blake2s_init(struct shash_desc *desc) +static int crypto_blake2s_final_x86(struct shash_desc *desc, u8 *out) { - struct blake2s_tfm_ctx *tctx = crypto_shash_ctx(desc->tfm); - struct blake2s_state *state = shash_desc_ctx(desc); - const int outlen = crypto_shash_digestsize(desc->tfm); - - if (tctx->keylen) - blake2s_init_key(state, outlen, tctx->key, tctx->keylen); - else - blake2s_init(state, outlen); - - return 0; + return crypto_blake2s_final(desc, out, blake2s_compress_arch); } -static int crypto_blake2s_update(struct shash_desc *desc, const u8 *in, - unsigned int inlen) -{ - struct blake2s_state *state = shash_desc_ctx(desc); - const size_t fill = BLAKE2S_BLOCK_SIZE - state->buflen; - - if (unlikely(!inlen)) - return 0; - if (inlen > fill) { - memcpy(state->buf + state->buflen, in, fill); - blake2s_compress_arch(state, state->buf, 1, BLAKE2S_BLOCK_SIZE); - state->buflen = 0; - in += fill; - inlen -= fill; +#define BLAKE2S_ALG(name, driver_name, digest_size) \ + { \ + .base.cra_name = name, \ + .base.cra_driver_name = driver_name, \ + .base.cra_priority = 200, \ + .base.cra_flags = CRYPTO_ALG_OPTIONAL_KEY, \ + .base.cra_blocksize = BLAKE2S_BLOCK_SIZE, \ + .base.cra_ctxsize = sizeof(struct blake2s_tfm_ctx), \ + .base.cra_module = THIS_MODULE, \ + .digestsize = digest_size, \ + .setkey = crypto_blake2s_setkey, \ + .init = crypto_blake2s_init, \ + .update = crypto_blake2s_update_x86, \ + .final = crypto_blake2s_final_x86, \ + .descsize = sizeof(struct blake2s_state), \ } - if (inlen > BLAKE2S_BLOCK_SIZE) { - const size_t nblocks = DIV_ROUND_UP(inlen, BLAKE2S_BLOCK_SIZE); - /* Hash one less (full) block than strictly possible */ - blake2s_compress_arch(state, in, nblocks - 1, BLAKE2S_BLOCK_SIZE); - in += BLAKE2S_BLOCK_SIZE * (nblocks - 1); - inlen -= BLAKE2S_BLOCK_SIZE * (nblocks - 1); - } - memcpy(state->buf + state->buflen, in, inlen); - state->buflen += inlen; - - return 0; -} - -static int crypto_blake2s_final(struct shash_desc *desc, u8 *out) -{ - struct blake2s_state *state = shash_desc_ctx(desc); - - blake2s_set_lastblock(state); - memset(state->buf + state->buflen, 0, - BLAKE2S_BLOCK_SIZE - state->buflen); /* Padding */ - blake2s_compress_arch(state, state->buf, 1, state->buflen); - cpu_to_le32_array(state->h, ARRAY_SIZE(state->h)); - memcpy(out, state->h, state->outlen); - memzero_explicit(state, sizeof(*state)); - - return 0; -} -static struct shash_alg blake2s_algs[] = {{ - .base.cra_name = "blake2s-128", - .base.cra_driver_name = "blake2s-128-x86", - .base.cra_flags = CRYPTO_ALG_OPTIONAL_KEY, - .base.cra_ctxsize = sizeof(struct blake2s_tfm_ctx), - .base.cra_priority = 200, - .base.cra_blocksize = BLAKE2S_BLOCK_SIZE, - .base.cra_module = THIS_MODULE, - - .digestsize = BLAKE2S_128_HASH_SIZE, - .setkey = crypto_blake2s_setkey, - .init = crypto_blake2s_init, - .update = crypto_blake2s_update, - .final = crypto_blake2s_final, - .descsize = sizeof(struct blake2s_state), -}, { - .base.cra_name = "blake2s-160", - .base.cra_driver_name = "blake2s-160-x86", - .base.cra_flags = CRYPTO_ALG_OPTIONAL_KEY, - .base.cra_ctxsize = sizeof(struct blake2s_tfm_ctx), - .base.cra_priority = 200, - .base.cra_blocksize = BLAKE2S_BLOCK_SIZE, - .base.cra_module = THIS_MODULE, - - .digestsize = BLAKE2S_160_HASH_SIZE, - .setkey = crypto_blake2s_setkey, - .init = crypto_blake2s_init, - .update = crypto_blake2s_update, - .final = crypto_blake2s_final, - .descsize = sizeof(struct blake2s_state), -}, { - .base.cra_name = "blake2s-224", - .base.cra_driver_name = "blake2s-224-x86", - .base.cra_flags = CRYPTO_ALG_OPTIONAL_KEY, - .base.cra_ctxsize = sizeof(struct blake2s_tfm_ctx), - .base.cra_priority = 200, - .base.cra_blocksize = BLAKE2S_BLOCK_SIZE, - .base.cra_module = THIS_MODULE, - - .digestsize = BLAKE2S_224_HASH_SIZE, - .setkey = crypto_blake2s_setkey, - .init = crypto_blake2s_init, - .update = crypto_blake2s_update, - .final = crypto_blake2s_final, - .descsize = sizeof(struct blake2s_state), -}, { - .base.cra_name = "blake2s-256", - .base.cra_driver_name = "blake2s-256-x86", - .base.cra_flags = CRYPTO_ALG_OPTIONAL_KEY, - .base.cra_ctxsize = sizeof(struct blake2s_tfm_ctx), - .base.cra_priority = 200, - .base.cra_blocksize = BLAKE2S_BLOCK_SIZE, - .base.cra_module = THIS_MODULE, - - .digestsize = BLAKE2S_256_HASH_SIZE, - .setkey = crypto_blake2s_setkey, - .init = crypto_blake2s_init, - .update = crypto_blake2s_update, - .final = crypto_blake2s_final, - .descsize = sizeof(struct blake2s_state), -}}; +static struct shash_alg blake2s_algs[] = { + BLAKE2S_ALG("blake2s-128", "blake2s-128-x86", BLAKE2S_128_HASH_SIZE), + BLAKE2S_ALG("blake2s-160", "blake2s-160-x86", BLAKE2S_160_HASH_SIZE), + BLAKE2S_ALG("blake2s-224", "blake2s-224-x86", BLAKE2S_224_HASH_SIZE), + BLAKE2S_ALG("blake2s-256", "blake2s-256-x86", BLAKE2S_256_HASH_SIZE), +}; static int __init blake2s_mod_init(void) { diff --git a/arch/x86/crypto/blowfish_glue.c b/arch/x86/crypto/blowfish_glue.c index cedfdba69ce3..a880e0b1c255 100644 --- a/arch/x86/crypto/blowfish_glue.c +++ b/arch/x86/crypto/blowfish_glue.c @@ -6,8 +6,6 @@ * * 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> */ #include <crypto/algapi.h> @@ -247,97 +245,6 @@ static int cbc_decrypt(struct skcipher_request *req) return err; } -static void ctr_crypt_final(struct bf_ctx *ctx, struct skcipher_walk *walk) -{ - u8 *ctrblk = walk->iv; - u8 keystream[BF_BLOCK_SIZE]; - u8 *src = walk->src.virt.addr; - u8 *dst = walk->dst.virt.addr; - unsigned int nbytes = walk->nbytes; - - blowfish_enc_blk(ctx, keystream, ctrblk); - crypto_xor_cpy(dst, keystream, src, nbytes); - - crypto_inc(ctrblk, BF_BLOCK_SIZE); -} - -static unsigned int __ctr_crypt(struct bf_ctx *ctx, struct skcipher_walk *walk) -{ - unsigned int bsize = BF_BLOCK_SIZE; - unsigned int nbytes = walk->nbytes; - u64 *src = (u64 *)walk->src.virt.addr; - u64 *dst = (u64 *)walk->dst.virt.addr; - u64 ctrblk = be64_to_cpu(*(__be64 *)walk->iv); - __be64 ctrblocks[4]; - - /* Process four block batch */ - if (nbytes >= bsize * 4) { - do { - if (dst != src) { - dst[0] = src[0]; - dst[1] = src[1]; - dst[2] = src[2]; - dst[3] = src[3]; - } - - /* create ctrblks for parallel encrypt */ - ctrblocks[0] = cpu_to_be64(ctrblk++); - ctrblocks[1] = cpu_to_be64(ctrblk++); - ctrblocks[2] = cpu_to_be64(ctrblk++); - ctrblocks[3] = cpu_to_be64(ctrblk++); - - blowfish_enc_blk_xor_4way(ctx, (u8 *)dst, - (u8 *)ctrblocks); - - src += 4; - dst += 4; - } while ((nbytes -= bsize * 4) >= bsize * 4); - - if (nbytes < bsize) - goto done; - } - - /* Handle leftovers */ - do { - if (dst != src) - *dst = *src; - - ctrblocks[0] = cpu_to_be64(ctrblk++); - - blowfish_enc_blk_xor(ctx, (u8 *)dst, (u8 *)ctrblocks); - - src += 1; - dst += 1; - } while ((nbytes -= bsize) >= bsize); - -done: - *(__be64 *)walk->iv = cpu_to_be64(ctrblk); - return nbytes; -} - -static int ctr_crypt(struct skcipher_request *req) -{ - struct crypto_skcipher *tfm = crypto_skcipher_reqtfm(req); - struct bf_ctx *ctx = crypto_skcipher_ctx(tfm); - struct skcipher_walk walk; - unsigned int nbytes; - int err; - - err = skcipher_walk_virt(&walk, req, false); - - while ((nbytes = walk.nbytes) >= BF_BLOCK_SIZE) { - nbytes = __ctr_crypt(ctx, &walk); - err = skcipher_walk_done(&walk, nbytes); - } - - if (nbytes) { - ctr_crypt_final(ctx, &walk); - err = skcipher_walk_done(&walk, 0); - } - - return err; -} - static struct crypto_alg bf_cipher_alg = { .cra_name = "blowfish", .cra_driver_name = "blowfish-asm", @@ -384,20 +291,6 @@ static struct skcipher_alg bf_skcipher_algs[] = { .setkey = blowfish_setkey_skcipher, .encrypt = cbc_encrypt, .decrypt = cbc_decrypt, - }, { - .base.cra_name = "ctr(blowfish)", - .base.cra_driver_name = "ctr-blowfish-asm", - .base.cra_priority = 300, - .base.cra_blocksize = 1, - .base.cra_ctxsize = sizeof(struct bf_ctx), - .base.cra_module = THIS_MODULE, - .min_keysize = BF_MIN_KEY_SIZE, - .max_keysize = BF_MAX_KEY_SIZE, - .ivsize = BF_BLOCK_SIZE, - .chunksize = BF_BLOCK_SIZE, - .setkey = blowfish_setkey_skcipher, - .encrypt = ctr_crypt, - .decrypt = ctr_crypt, }, }; diff --git a/arch/x86/crypto/camellia-aesni-avx-asm_64.S b/arch/x86/crypto/camellia-aesni-avx-asm_64.S index ecc0a9a905c4..e2a0e0f4bf9d 100644 --- a/arch/x86/crypto/camellia-aesni-avx-asm_64.S +++ b/arch/x86/crypto/camellia-aesni-avx-asm_64.S @@ -17,7 +17,6 @@ #include <linux/linkage.h> #include <asm/frame.h> -#include <asm/nospec-branch.h> #define CAMELLIA_TABLE_BYTE_LEN 272 @@ -589,14 +588,6 @@ SYM_FUNC_END(roundsm16_x4_x5_x6_x7_x0_x1_x2_x3_y4_y5_y6_y7_y0_y1_y2_y3_ab) .long 0x80808080 .long 0x80808080 -/* For CTR-mode IV byteswap */ -.Lbswap128_mask: - .byte 15, 14, 13, 12, 11, 10, 9, 8, 7, 6, 5, 4, 3, 2, 1, 0 - -/* For XTS mode IV generation */ -.Lxts_gf128mul_and_shl1_mask: - .byte 0x87, 0, 0, 0, 0, 0, 0, 0, 1, 0, 0, 0, 0, 0, 0, 0 - /* * pre-SubByte transform * @@ -998,292 +989,3 @@ SYM_FUNC_START(camellia_cbc_dec_16way) FRAME_END ret; SYM_FUNC_END(camellia_cbc_dec_16way) - -#define inc_le128(x, minus_one, tmp) \ - vpcmpeqq minus_one, x, tmp; \ - vpsubq minus_one, x, x; \ - vpslldq $8, tmp, tmp; \ - vpsubq tmp, x, x; - -SYM_FUNC_START(camellia_ctr_16way) - /* input: - * %rdi: ctx, CTX - * %rsi: dst (16 blocks) - * %rdx: src (16 blocks) - * %rcx: iv (little endian, 128bit) - */ - FRAME_BEGIN - - subq $(16 * 16), %rsp; - movq %rsp, %rax; - - vmovdqa .Lbswap128_mask, %xmm14; - - /* load IV and byteswap */ - vmovdqu (%rcx), %xmm0; - vpshufb %xmm14, %xmm0, %xmm15; - vmovdqu %xmm15, 15 * 16(%rax); - - vpcmpeqd %xmm15, %xmm15, %xmm15; - vpsrldq $8, %xmm15, %xmm15; /* low: -1, high: 0 */ - - /* construct IVs */ - inc_le128(%xmm0, %xmm15, %xmm13); - vpshufb %xmm14, %xmm0, %xmm13; - vmovdqu %xmm13, 14 * 16(%rax); - inc_le128(%xmm0, %xmm15, %xmm13); - vpshufb %xmm14, %xmm0, %xmm13; - vmovdqu %xmm13, 13 * 16(%rax); - inc_le128(%xmm0, %xmm15, %xmm13); - vpshufb %xmm14, %xmm0, %xmm12; - inc_le128(%xmm0, %xmm15, %xmm13); - vpshufb %xmm14, %xmm0, %xmm11; - inc_le128(%xmm0, %xmm15, %xmm13); - vpshufb %xmm14, %xmm0, %xmm10; - inc_le128(%xmm0, %xmm15, %xmm13); - vpshufb %xmm14, %xmm0, %xmm9; - inc_le128(%xmm0, %xmm15, %xmm13); - vpshufb %xmm14, %xmm0, %xmm8; - inc_le128(%xmm0, %xmm15, %xmm13); - vpshufb %xmm14, %xmm0, %xmm7; - inc_le128(%xmm0, %xmm15, %xmm13); - vpshufb %xmm14, %xmm0, %xmm6; - inc_le128(%xmm0, %xmm15, %xmm13); - vpshufb %xmm14, %xmm0, %xmm5; - inc_le128(%xmm0, %xmm15, %xmm13); - vpshufb %xmm14, %xmm0, %xmm4; - inc_le128(%xmm0, %xmm15, %xmm13); - vpshufb %xmm14, %xmm0, %xmm3; - inc_le128(%xmm0, %xmm15, %xmm13); - vpshufb %xmm14, %xmm0, %xmm2; - inc_le128(%xmm0, %xmm15, %xmm13); - vpshufb %xmm14, %xmm0, %xmm1; - inc_le128(%xmm0, %xmm15, %xmm13); - vmovdqa %xmm0, %xmm13; - vpshufb %xmm14, %xmm0, %xmm0; - inc_le128(%xmm13, %xmm15, %xmm14); - vmovdqu %xmm13, (%rcx); - - /* inpack16_pre: */ - vmovq (key_table)(CTX), %xmm15; - vpshufb .Lpack_bswap, %xmm15, %xmm15; - vpxor %xmm0, %xmm15, %xmm0; - vpxor %xmm1, %xmm15, %xmm1; - vpxor %xmm2, %xmm15, %xmm2; - vpxor %xmm3, %xmm15, %xmm3; - vpxor %xmm4, %xmm15, %xmm4; - vpxor %xmm5, %xmm15, %xmm5; - vpxor %xmm6, %xmm15, %xmm6; - vpxor %xmm7, %xmm15, %xmm7; - vpxor %xmm8, %xmm15, %xmm8; - vpxor %xmm9, %xmm15, %xmm9; - vpxor %xmm10, %xmm15, %xmm10; - vpxor %xmm11, %xmm15, %xmm11; - vpxor %xmm12, %xmm15, %xmm12; - vpxor 13 * 16(%rax), %xmm15, %xmm13; - vpxor 14 * 16(%rax), %xmm15, %xmm14; - vpxor 15 * 16(%rax), %xmm15, %xmm15; - - call __camellia_enc_blk16; - - addq $(16 * 16), %rsp; - - vpxor 0 * 16(%rdx), %xmm7, %xmm7; - vpxor 1 * 16(%rdx), %xmm6, %xmm6; - vpxor 2 * 16(%rdx), %xmm5, %xmm5; - vpxor 3 * 16(%rdx), %xmm4, %xmm4; - vpxor 4 * 16(%rdx), %xmm3, %xmm3; - vpxor 5 * 16(%rdx), %xmm2, %xmm2; - vpxor 6 * 16(%rdx), %xmm1, %xmm1; - vpxor 7 * 16(%rdx), %xmm0, %xmm0; - vpxor 8 * 16(%rdx), %xmm15, %xmm15; - vpxor 9 * 16(%rdx), %xmm14, %xmm14; - vpxor 10 * 16(%rdx), %xmm13, %xmm13; - vpxor 11 * 16(%rdx), %xmm12, %xmm12; - vpxor 12 * 16(%rdx), %xmm11, %xmm11; - vpxor 13 * 16(%rdx), %xmm10, %xmm10; - vpxor 14 * 16(%rdx), %xmm9, %xmm9; - vpxor 15 * 16(%rdx), %xmm8, %xmm8; - write_output(%xmm7, %xmm6, %xmm5, %xmm4, %xmm3, %xmm2, %xmm1, %xmm0, - %xmm15, %xmm14, %xmm13, %xmm12, %xmm11, %xmm10, %xmm9, - %xmm8, %rsi); - - FRAME_END - ret; -SYM_FUNC_END(camellia_ctr_16way) - -#define gf128mul_x_ble(iv, mask, tmp) \ - vpsrad $31, iv, tmp; \ - vpaddq iv, iv, iv; \ - vpshufd $0x13, tmp, tmp; \ - vpand mask, tmp, tmp; \ - vpxor tmp, iv, iv; - -.align 8 -SYM_FUNC_START_LOCAL(camellia_xts_crypt_16way) - /* input: - * %rdi: ctx, CTX - * %rsi: dst (16 blocks) - * %rdx: src (16 blocks) - * %rcx: iv (t ⊕ αⁿ ∈ GF(2¹²⁸)) - * %r8: index for input whitening key - * %r9: pointer to __camellia_enc_blk16 or __camellia_dec_blk16 - */ - FRAME_BEGIN - - subq $(16 * 16), %rsp; - movq %rsp, %rax; - - vmovdqa .Lxts_gf128mul_and_shl1_mask, %xmm14; - - /* load IV */ - vmovdqu (%rcx), %xmm0; - vpxor 0 * 16(%rdx), %xmm0, %xmm15; - vmovdqu %xmm15, 15 * 16(%rax); - vmovdqu %xmm0, 0 * 16(%rsi); - - /* construct IVs */ - gf128mul_x_ble(%xmm0, %xmm14, %xmm15); - vpxor 1 * 16(%rdx), %xmm0, %xmm15; - vmovdqu %xmm15, 14 * 16(%rax); - vmovdqu %xmm0, 1 * 16(%rsi); - - gf128mul_x_ble(%xmm0, %xmm14, %xmm15); - vpxor 2 * 16(%rdx), %xmm0, %xmm13; - vmovdqu %xmm0, 2 * 16(%rsi); - - gf128mul_x_ble(%xmm0, %xmm14, %xmm15); - vpxor 3 * 16(%rdx), %xmm0, %xmm12; - vmovdqu %xmm0, 3 * 16(%rsi); - - gf128mul_x_ble(%xmm0, %xmm14, %xmm15); - vpxor 4 * 16(%rdx), %xmm0, %xmm11; - vmovdqu %xmm0, 4 * 16(%rsi); - - gf128mul_x_ble(%xmm0, %xmm14, %xmm15); - vpxor 5 * 16(%rdx), %xmm0, %xmm10; - vmovdqu %xmm0, 5 * 16(%rsi); - - gf128mul_x_ble(%xmm0, %xmm14, %xmm15); - vpxor 6 * 16(%rdx), %xmm0, %xmm9; - vmovdqu %xmm0, 6 * 16(%rsi); - - gf128mul_x_ble(%xmm0, %xmm14, %xmm15); - vpxor 7 * 16(%rdx), %xmm0, %xmm8; - vmovdqu %xmm0, 7 * 16(%rsi); - - gf128mul_x_ble(%xmm0, %xmm14, %xmm15); - vpxor 8 * 16(%rdx), %xmm0, %xmm7; - vmovdqu %xmm0, 8 * 16(%rsi); - - gf128mul_x_ble(%xmm0, %xmm14, %xmm15); - vpxor 9 * 16(%rdx), %xmm0, %xmm6; - vmovdqu %xmm0, 9 * 16(%rsi); - - gf128mul_x_ble(%xmm0, %xmm14, %xmm15); - vpxor 10 * 16(%rdx), %xmm0, %xmm5; - vmovdqu %xmm0, 10 * 16(%rsi); - - gf128mul_x_ble(%xmm0, %xmm14, %xmm15); - vpxor 11 * 16(%rdx), %xmm0, %xmm4; - vmovdqu %xmm0, 11 * 16(%rsi); - - gf128mul_x_ble(%xmm0, %xmm14, %xmm15); - vpxor 12 * 16(%rdx), %xmm0, %xmm3; - vmovdqu %xmm0, 12 * 16(%rsi); - - gf128mul_x_ble(%xmm0, %xmm14, %xmm15); - vpxor 13 * 16(%rdx), %xmm0, %xmm2; - vmovdqu %xmm0, 13 * 16(%rsi); - - gf128mul_x_ble(%xmm0, %xmm14, %xmm15); - vpxor 14 * 16(%rdx), %xmm0, %xmm1; - vmovdqu %xmm0, 14 * 16(%rsi); - - gf128mul_x_ble(%xmm0, %xmm14, %xmm15); - vpxor 15 * 16(%rdx), %xmm0, %xmm15; - vmovdqu %xmm15, 0 * 16(%rax); - vmovdqu %xmm0, 15 * 16(%rsi); - - gf128mul_x_ble(%xmm0, %xmm14, %xmm15); - vmovdqu %xmm0, (%rcx); - - /* inpack16_pre: */ - vmovq (key_table)(CTX, %r8, 8), %xmm15; - vpshufb .Lpack_bswap, %xmm15, %xmm15; - vpxor 0 * 16(%rax), %xmm15, %xmm0; - vpxor %xmm1, %xmm15, %xmm1; - vpxor %xmm2, %xmm15, %xmm2; - vpxor %xmm3, %xmm15, %xmm3; - vpxor %xmm4, %xmm15, %xmm4; - vpxor %xmm5, %xmm15, %xmm5; - vpxor %xmm6, %xmm15, %xmm6; - vpxor %xmm7, %xmm15, %xmm7; - vpxor %xmm8, %xmm15, %xmm8; - vpxor %xmm9, %xmm15, %xmm9; - vpxor %xmm10, %xmm15, %xmm10; - vpxor %xmm11, %xmm15, %xmm11; - vpxor %xmm12, %xmm15, %xmm12; - vpxor %xmm13, %xmm15, %xmm13; - vpxor 14 * 16(%rax), %xmm15, %xmm14; - vpxor 15 * 16(%rax), %xmm15, %xmm15; - - CALL_NOSPEC r9; - - addq $(16 * 16), %rsp; - - vpxor 0 * 16(%rsi), %xmm7, %xmm7; - vpxor 1 * 16(%rsi), %xmm6, %xmm6; - vpxor 2 * 16(%rsi), %xmm5, %xmm5; - vpxor 3 * 16(%rsi), %xmm4, %xmm4; - vpxor 4 * 16(%rsi), %xmm3, %xmm3; - vpxor 5 * 16(%rsi), %xmm2, %xmm2; - vpxor 6 * 16(%rsi), %xmm1, %xmm1; - vpxor 7 * 16(%rsi), %xmm0, %xmm0; - vpxor 8 * 16(%rsi), %xmm15, %xmm15; - vpxor 9 * 16(%rsi), %xmm14, %xmm14; - vpxor 10 * 16(%rsi), %xmm13, %xmm13; - vpxor 11 * 16(%rsi), %xmm12, %xmm12; - vpxor 12 * 16(%rsi), %xmm11, %xmm11; - vpxor 13 * 16(%rsi), %xmm10, %xmm10; - vpxor 14 * 16(%rsi), %xmm9, %xmm9; - vpxor 15 * 16(%rsi), %xmm8, %xmm8; - write_output(%xmm7, %xmm6, %xmm5, %xmm4, %xmm3, %xmm2, %xmm1, %xmm0, - %xmm15, %xmm14, %xmm13, %xmm12, %xmm11, %xmm10, %xmm9, - %xmm8, %rsi); - - FRAME_END - ret; -SYM_FUNC_END(camellia_xts_crypt_16way) - -SYM_FUNC_START(camellia_xts_enc_16way) - /* input: - * %rdi: ctx, CTX - * %rsi: dst (16 blocks) - * %rdx: src (16 blocks) - * %rcx: iv (t ⊕ αⁿ ∈ GF(2¹²⁸)) - */ - xorl %r8d, %r8d; /* input whitening key, 0 for enc */ - - leaq __camellia_enc_blk16, %r9; - - jmp camellia_xts_crypt_16way; -SYM_FUNC_END(camellia_xts_enc_16way) - -SYM_FUNC_START(camellia_xts_dec_16way) - /* input: - * %rdi: ctx, CTX - * %rsi: dst (16 blocks) - * %rdx: src (16 blocks) - * %rcx: iv (t ⊕ αⁿ ∈ GF(2¹²⁸)) - */ - - cmpl $16, key_length(CTX); - movl $32, %r8d; - movl $24, %eax; - cmovel %eax, %r8d; /* input whitening key, last for dec */ - - leaq __camellia_dec_blk16, %r9; - - jmp camellia_xts_crypt_16way; -SYM_FUNC_END(camellia_xts_dec_16way) diff --git a/arch/x86/crypto/camellia-aesni-avx2-asm_64.S b/arch/x86/crypto/camellia-aesni-avx2-asm_64.S index 0907243c501c..782e9712a1ec 100644 --- a/arch/x86/crypto/camellia-aesni-avx2-asm_64.S +++ b/arch/x86/crypto/camellia-aesni-avx2-asm_64.S @@ -7,7 +7,6 @@ #include <linux/linkage.h> #include <asm/frame.h> -#include <asm/nospec-branch.h> #define CAMELLIA_TABLE_BYTE_LEN 272 @@ -625,16 +624,6 @@ SYM_FUNC_END(roundsm32_x4_x5_x6_x7_x0_x1_x2_x3_y4_y5_y6_y7_y0_y1_y2_y3_ab) .section .rodata.cst16, "aM", @progbits, 16 .align 16 -/* For CTR-mode IV byteswap */ -.Lbswap128_mask: - .byte 15, 14, 13, 12, 11, 10, 9, 8, 7, 6, 5, 4, 3, 2, 1, 0 - -/* For XTS mode */ -.Lxts_gf128mul_and_shl1_mask_0: - .byte 0x87, 0, 0, 0, 0, 0, 0, 0, 1, 0, 0, 0, 0, 0, 0, 0 -.Lxts_gf128mul_and_shl1_mask_1: - .byte 0x0e, 1, 0, 0, 0, 0, 0, 0, 2, 0, 0, 0, 0, 0, 0, 0 - /* * pre-SubByte transform * @@ -1061,343 +1050,3 @@ SYM_FUNC_START(camellia_cbc_dec_32way) FRAME_END ret; SYM_FUNC_END(camellia_cbc_dec_32way) - -#define inc_le128(x, minus_one, tmp) \ - vpcmpeqq minus_one, x, tmp; \ - vpsubq minus_one, x, x; \ - vpslldq $8, tmp, tmp; \ - vpsubq tmp, x, x; - -#define add2_le128(x, minus_one, minus_two, tmp1, tmp2) \ - vpcmpeqq minus_one, x, tmp1; \ - vpcmpeqq minus_two, x, tmp2; \ - vpsubq minus_two, x, x; \ - vpor tmp2, tmp1, tmp1; \ - vpslldq $8, tmp1, tmp1; \ - vpsubq tmp1, x, x; - -SYM_FUNC_START(camellia_ctr_32way) - /* input: - * %rdi: ctx, CTX - * %rsi: dst (32 blocks) - * %rdx: src (32 blocks) - * %rcx: iv (little endian, 128bit) - */ - FRAME_BEGIN - - vzeroupper; - - movq %rsp, %r10; - cmpq %rsi, %rdx; - je .Lctr_use_stack; - - /* dst can be used as temporary storage, src is not overwritten. */ - movq %rsi, %rax; - jmp .Lctr_continue; - -.Lctr_use_stack: - subq $(16 * 32), %rsp; - movq %rsp, %rax; - -.Lctr_continue: - vpcmpeqd %ymm15, %ymm15, %ymm15; - vpsrldq $8, %ymm15, %ymm15; /* ab: -1:0 ; cd: -1:0 */ - vpaddq %ymm15, %ymm15, %ymm12; /* ab: -2:0 ; cd: -2:0 */ - - /* load IV and byteswap */ - vmovdqu (%rcx), %xmm0; - vmovdqa %xmm0, %xmm1; - inc_le128(%xmm0, %xmm15, %xmm14); - vbroadcasti128 .Lbswap128_mask, %ymm14; - vinserti128 $1, %xmm0, %ymm1, %ymm0; - vpshufb %ymm14, %ymm0, %ymm13; - vmovdqu %ymm13, 15 * 32(%rax); - - /* construct IVs */ - add2_le128(%ymm0, %ymm15, %ymm12, %ymm11, %ymm13); /* ab:le2 ; cd:le3 */ - vpshufb %ymm14, %ymm0, %ymm13; - vmovdqu %ymm13, 14 * 32(%rax); - add2_le128(%ymm0, %ymm15, %ymm12, %ymm11, %ymm13); - vpshufb %ymm14, %ymm0, %ymm13; - vmovdqu %ymm13, 13 * 32(%rax); - add2_le128(%ymm0, %ymm15, %ymm12, %ymm11, %ymm13); - vpshufb %ymm14, %ymm0, %ymm13; - vmovdqu %ymm13, 12 * 32(%rax); - add2_le128(%ymm0, %ymm15, %ymm12, %ymm11, %ymm13); - vpshufb %ymm14, %ymm0, %ymm13; - vmovdqu %ymm13, 11 * 32(%rax); - add2_le128(%ymm0, %ymm15, %ymm12, %ymm11, %ymm13); - vpshufb %ymm14, %ymm0, %ymm10; - add2_le128(%ymm0, %ymm15, %ymm12, %ymm11, %ymm13); - vpshufb %ymm14, %ymm0, %ymm9; - add2_le128(%ymm0, %ymm15, %ymm12, %ymm11, %ymm13); - vpshufb %ymm14, %ymm0, %ymm8; - add2_le128(%ymm0, %ymm15, %ymm12, %ymm11, %ymm13); - vpshufb %ymm14, %ymm0, %ymm7; - add2_le128(%ymm0, %ymm15, %ymm12, %ymm11, %ymm13); - vpshufb %ymm14, %ymm0, %ymm6; - add2_le128(%ymm0, %ymm15, %ymm12, %ymm11, %ymm13); - vpshufb %ymm14, %ymm0, %ymm5; - add2_le128(%ymm0, %ymm15, %ymm12, %ymm11, %ymm13); - vpshufb %ymm14, %ymm0, %ymm4; - add2_le128(%ymm0, %ymm15, %ymm12, %ymm11, %ymm13); - vpshufb %ymm14, %ymm0, %ymm3; - add2_le128(%ymm0, %ymm15, %ymm12, %ymm11, %ymm13); - vpshufb %ymm14, %ymm0, %ymm2; - add2_le128(%ymm0, %ymm15, %ymm12, %ymm11, %ymm13); - vpshufb %ymm14, %ymm0, %ymm1; - add2_le128(%ymm0, %ymm15, %ymm12, %ymm11, %ymm13); - vextracti128 $1, %ymm0, %xmm13; - vpshufb %ymm14, %ymm0, %ymm0; - inc_le128(%xmm13, %xmm15, %xmm14); - vmovdqu %xmm13, (%rcx); - - /* inpack32_pre: */ - vpbroadcastq (key_table)(CTX), %ymm15; - vpshufb .Lpack_bswap, %ymm15, %ymm15; - vpxor %ymm0, %ymm15, %ymm0; - vpxor %ymm1, %ymm15, %ymm1; - vpxor %ymm2, %ymm15, %ymm2; - vpxor %ymm3, %ymm15, %ymm3; - vpxor %ymm4, %ymm15, %ymm4; - vpxor %ymm5, %ymm15, %ymm5; - vpxor %ymm6, %ymm15, %ymm6; - vpxor %ymm7, %ymm15, %ymm7; - vpxor %ymm8, %ymm15, %ymm8; - vpxor %ymm9, %ymm15, %ymm9; - vpxor %ymm10, %ymm15, %ymm10; - vpxor 11 * 32(%rax), %ymm15, %ymm11; - vpxor 12 * 32(%rax), %ymm15, %ymm12; - vpxor 13 * 32(%rax), %ymm15, %ymm13; - vpxor 14 * 32(%rax), %ymm15, %ymm14; - vpxor 15 * 32(%rax), %ymm15, %ymm15; - - call __camellia_enc_blk32; - - movq %r10, %rsp; - - vpxor 0 * 32(%rdx), %ymm7, %ymm7; - vpxor 1 * 32(%rdx), %ymm6, %ymm6; - vpxor 2 * 32(%rdx), %ymm5, %ymm5; - vpxor 3 * 32(%rdx), %ymm4, %ymm4; - vpxor 4 * 32(%rdx), %ymm3, %ymm3; - vpxor 5 * 32(%rdx), %ymm2, %ymm2; - vpxor 6 * 32(%rdx), %ymm1, %ymm1; - vpxor 7 * 32(%rdx), %ymm0, %ymm0; - vpxor 8 * 32(%rdx), %ymm15, %ymm15; - vpxor 9 * 32(%rdx), %ymm14, %ymm14; - vpxor 10 * 32(%rdx), %ymm13, %ymm13; - vpxor 11 * 32(%rdx), %ymm12, %ymm12; - vpxor 12 * 32(%rdx), %ymm11, %ymm11; - vpxor 13 * 32(%rdx), %ymm10, %ymm10; - vpxor 14 * 32(%rdx), %ymm9, %ymm9; - vpxor 15 * 32(%rdx), %ymm8, %ymm8; - write_output(%ymm7, %ymm6, %ymm5, %ymm4, %ymm3, %ymm2, %ymm1, %ymm0, - %ymm15, %ymm14, %ymm13, %ymm12, %ymm11, %ymm10, %ymm9, - %ymm8, %rsi); - - vzeroupper; - - FRAME_END - ret; -SYM_FUNC_END(camellia_ctr_32way) - -#define gf128mul_x_ble(iv, mask, tmp) \ - vpsrad $31, iv, tmp; \ - vpaddq iv, iv, iv; \ - vpshufd $0x13, tmp, tmp; \ - vpand mask, tmp, tmp; \ - vpxor tmp, iv, iv; - -#define gf128mul_x2_ble(iv, mask1, mask2, tmp0, tmp1) \ - vpsrad $31, iv, tmp0; \ - vpaddq iv, iv, tmp1; \ - vpsllq $2, iv, iv; \ - vpshufd $0x13, tmp0, tmp0; \ - vpsrad $31, tmp1, tmp1; \ - vpand mask2, tmp0, tmp0; \ - vpshufd $0x13, tmp1, tmp1; \ - vpxor tmp0, iv, iv; \ - vpand mask1, tmp1, tmp1; \ - vpxor tmp1, iv, iv; - -.align 8 -SYM_FUNC_START_LOCAL(camellia_xts_crypt_32way) - /* input: - * %rdi: ctx, CTX - * %rsi: dst (32 blocks) - * %rdx: src (32 blocks) - * %rcx: iv (t ⊕ αⁿ ∈ GF(2¹²⁸)) - * %r8: index for input whitening key - * %r9: pointer to __camellia_enc_blk32 or __camellia_dec_blk32 - */ - FRAME_BEGIN - - vzeroupper; - - subq $(16 * 32), %rsp; - movq %rsp, %rax; - - vbroadcasti128 .Lxts_gf128mul_and_shl1_mask_0, %ymm12; - - /* load IV and construct second IV */ - vmovdqu (%rcx), %xmm0; - vmovdqa %xmm0, %xmm15; - gf128mul_x_ble(%xmm0, %xmm12, %xmm13); - vbroadcasti128 .Lxts_gf128mul_and_shl1_mask_1, %ymm13; - vinserti128 $1, %xmm0, %ymm15, %ymm0; - vpxor 0 * 32(%rdx), %ymm0, %ymm15; - vmovdqu %ymm15, 15 * 32(%rax); - vmovdqu %ymm0, 0 * 32(%rsi); - - /* construct IVs */ - gf128mul_x2_ble(%ymm0, %ymm12, %ymm13, %ymm14, %ymm15); - vpxor 1 * 32(%rdx), %ymm0, %ymm15; - vmovdqu %ymm15, 14 * 32(%rax); - vmovdqu %ymm0, 1 * 32(%rsi); - - gf128mul_x2_ble(%ymm0, %ymm12, %ymm13, %ymm14, %ymm15); - vpxor 2 * 32(%rdx), %ymm0, %ymm15; - vmovdqu %ymm15, 13 * 32(%rax); - vmovdqu %ymm0, 2 * 32(%rsi); - - gf128mul_x2_ble(%ymm0, %ymm12, %ymm13, %ymm14, %ymm15); - vpxor 3 * 32(%rdx), %ymm0, %ymm15; - vmovdqu %ymm15, 12 * 32(%rax); - vmovdqu %ymm0, 3 * 32(%rsi); - - gf128mul_x2_ble(%ymm0, %ymm12, %ymm13, %ymm14, %ymm15); - vpxor 4 * 32(%rdx), %ymm0, %ymm11; - vmovdqu %ymm0, 4 * 32(%rsi); - - gf128mul_x2_ble(%ymm0, %ymm12, %ymm13, %ymm14, %ymm15); - vpxor 5 * 32(%rdx), %ymm0, %ymm10; - vmovdqu %ymm0, 5 * 32(%rsi); - - gf128mul_x2_ble(%ymm0, %ymm12, %ymm13, %ymm14, %ymm15); - vpxor 6 * 32(%rdx), %ymm0, %ymm9; - vmovdqu %ymm0, 6 * 32(%rsi); - - gf128mul_x2_ble(%ymm0, %ymm12, %ymm13, %ymm14, %ymm15); - vpxor 7 * 32(%rdx), %ymm0, %ymm8; - vmovdqu %ymm0, 7 * 32(%rsi); - - gf128mul_x2_ble(%ymm0, %ymm12, %ymm13, %ymm14, %ymm15); - vpxor 8 * 32(%rdx), %ymm0, %ymm7; - vmovdqu %ymm0, 8 * 32(%rsi); - - gf128mul_x2_ble(%ymm0, %ymm12, %ymm13, %ymm14, %ymm15); - vpxor 9 * 32(%rdx), %ymm0, %ymm6; - vmovdqu %ymm0, 9 * 32(%rsi); - - gf128mul_x2_ble(%ymm0, %ymm12, %ymm13, %ymm14, %ymm15); - vpxor 10 * 32(%rdx), %ymm0, %ymm5; - vmovdqu %ymm0, 10 * 32(%rsi); - - gf128mul_x2_ble(%ymm0, %ymm12, %ymm13, %ymm14, %ymm15); - vpxor 11 * 32(%rdx), %ymm0, %ymm4; - vmovdqu %ymm0, 11 * 32(%rsi); - - gf128mul_x2_ble(%ymm0, %ymm12, %ymm13, %ymm14, %ymm15); - vpxor 12 * 32(%rdx), %ymm0, %ymm3; - vmovdqu %ymm0, 12 * 32(%rsi); - - gf128mul_x2_ble(%ymm0, %ymm12, %ymm13, %ymm14, %ymm15); - vpxor 13 * 32(%rdx), %ymm0, %ymm2; - vmovdqu %ymm0, 13 * 32(%rsi); - - gf128mul_x2_ble(%ymm0, %ymm12, %ymm13, %ymm14, %ymm15); - vpxor 14 * 32(%rdx), %ymm0, %ymm1; - vmovdqu %ymm0, 14 * 32(%rsi); - - gf128mul_x2_ble(%ymm0, %ymm12, %ymm13, %ymm14, %ymm15); - vpxor 15 * 32(%rdx), %ymm0, %ymm15; - vmovdqu %ymm15, 0 * 32(%rax); - vmovdqu %ymm0, 15 * 32(%rsi); - - vextracti128 $1, %ymm0, %xmm0; - gf128mul_x_ble(%xmm0, %xmm12, %xmm15); - vmovdqu %xmm0, (%rcx); - - /* inpack32_pre: */ - vpbroadcastq (key_table)(CTX, %r8, 8), %ymm15; - vpshufb .Lpack_bswap, %ymm15, %ymm15; - vpxor 0 * 32(%rax), %ymm15, %ymm0; - vpxor %ymm1, %ymm15, %ymm1; - vpxor %ymm2, %ymm15, %ymm2; - vpxor %ymm3, %ymm15, %ymm3; - vpxor %ymm4, %ymm15, %ymm4; - vpxor %ymm5, %ymm15, %ymm5; - vpxor %ymm6, %ymm15, %ymm6; - vpxor %ymm7, %ymm15, %ymm7; - vpxor %ymm8, %ymm15, %ymm8; - vpxor %ymm9, %ymm15, %ymm9; - vpxor %ymm10, %ymm15, %ymm10; - vpxor %ymm11, %ymm15, %ymm11; - vpxor 12 * 32(%rax), %ymm15, %ymm12; - vpxor 13 * 32(%rax), %ymm15, %ymm13; - vpxor 14 * 32(%rax), %ymm15, %ymm14; - vpxor 15 * 32(%rax), %ymm15, %ymm15; - - CALL_NOSPEC r9; - - addq $(16 * 32), %rsp; - - vpxor 0 * 32(%rsi), %ymm7, %ymm7; - vpxor 1 * 32(%rsi), %ymm6, %ymm6; - vpxor 2 * 32(%rsi), %ymm5, %ymm5; - vpxor 3 * 32(%rsi), %ymm4, %ymm4; - vpxor 4 * 32(%rsi), %ymm3, %ymm3; - vpxor 5 * 32(%rsi), %ymm2, %ymm2; - vpxor 6 * 32(%rsi), %ymm1, %ymm1; - vpxor 7 * 32(%rsi), %ymm0, %ymm0; - vpxor 8 * 32(%rsi), %ymm15, %ymm15; - vpxor 9 * 32(%rsi), %ymm14, %ymm14; - vpxor 10 * 32(%rsi), %ymm13, %ymm13; - vpxor 11 * 32(%rsi), %ymm12, %ymm12; - vpxor 12 * 32(%rsi), %ymm11, %ymm11; - vpxor 13 * 32(%rsi), %ymm10, %ymm10; - vpxor 14 * 32(%rsi), %ymm9, %ymm9; - vpxor 15 * 32(%rsi), %ymm8, %ymm8; - write_output(%ymm7, %ymm6, %ymm5, %ymm4, %ymm3, %ymm2, %ymm1, %ymm0, - %ymm15, %ymm14, %ymm13, %ymm12, %ymm11, %ymm10, %ymm9, - %ymm8, %rsi); - - vzeroupper; - - FRAME_END - ret; -SYM_FUNC_END(camellia_xts_crypt_32way) - -SYM_FUNC_START(camellia_xts_enc_32way) - /* input: - * %rdi: ctx, CTX - * %rsi: dst (32 blocks) - * %rdx: src (32 blocks) - * %rcx: iv (t ⊕ αⁿ ∈ GF(2¹²⁸)) - */ - - xorl %r8d, %r8d; /* input whitening key, 0 for enc */ - - leaq __camellia_enc_blk32, %r9; - - jmp camellia_xts_crypt_32way; -SYM_FUNC_END(camellia_xts_enc_32way) - -SYM_FUNC_START(camellia_xts_dec_32way) - /* input: - * %rdi: ctx, CTX - * %rsi: dst (32 blocks) - * %rdx: src (32 blocks) - * %rcx: iv (t ⊕ αⁿ ∈ GF(2¹²⁸)) - */ - - cmpl $16, key_length(CTX); - movl $32, %r8d; - movl $24, %eax; - cmovel %eax, %r8d; /* input whitening key, last for dec */ - - leaq __camellia_dec_blk32, %r9; - - jmp camellia_xts_crypt_32way; -SYM_FUNC_END(camellia_xts_dec_32way) diff --git a/arch/x86/include/asm/crypto/camellia.h b/arch/x86/crypto/camellia.h index f6d91861cb14..1dcea79e8f8e 100644 --- a/arch/x86/include/asm/crypto/camellia.h +++ b/arch/x86/crypto/camellia.h @@ -19,18 +19,10 @@ struct camellia_ctx { u32 key_length; }; -struct camellia_xts_ctx { - struct camellia_ctx tweak_ctx; - struct camellia_ctx crypt_ctx; -}; - extern int __camellia_setkey(struct camellia_ctx *cctx, const unsigned char *key, unsigned int key_len); -extern int xts_camellia_setkey(struct crypto_skcipher *tfm, const u8 *key, - unsigned int keylen); - /* regular block cipher functions */ asmlinkage void __camellia_enc_blk(const void *ctx, u8 *dst, const u8 *src, bool xor); @@ -46,13 +38,6 @@ asmlinkage void camellia_ecb_enc_16way(const void *ctx, u8 *dst, const u8 *src); asmlinkage void camellia_ecb_dec_16way(const void *ctx, u8 *dst, const u8 *src); asmlinkage void camellia_cbc_dec_16way(const void *ctx, u8 *dst, const u8 *src); -asmlinkage void camellia_ctr_16way(const void *ctx, u8 *dst, const u8 *src, - le128 *iv); - -asmlinkage void camellia_xts_enc_16way(const void *ctx, u8 *dst, const u8 *src, - le128 *iv); -asmlinkage void camellia_xts_dec_16way(const void *ctx, u8 *dst, const u8 *src, - le128 *iv); static inline void camellia_enc_blk(const void *ctx, u8 *dst, const u8 *src) { @@ -78,14 +63,5 @@ static inline void camellia_enc_blk_xor_2way(const void *ctx, u8 *dst, /* glue helpers */ extern void camellia_decrypt_cbc_2way(const void *ctx, u8 *dst, const u8 *src); -extern void camellia_crypt_ctr(const void *ctx, u8 *dst, const u8 *src, - le128 *iv); -extern void camellia_crypt_ctr_2way(const void *ctx, u8 *dst, const u8 *src, - le128 *iv); - -extern void camellia_xts_enc(const void *ctx, u8 *dst, const u8 *src, - le128 *iv); -extern void camellia_xts_dec(const void *ctx, u8 *dst, const u8 *src, - le128 *iv); #endif /* ASM_X86_CAMELLIA_H */ diff --git a/arch/x86/crypto/camellia_aesni_avx2_glue.c b/arch/x86/crypto/camellia_aesni_avx2_glue.c index ccda647422d6..e7e4d64e9577 100644 --- a/arch/x86/crypto/camellia_aesni_avx2_glue.c +++ b/arch/x86/crypto/camellia_aesni_avx2_glue.c @@ -5,16 +5,16 @@ * Copyright © 2013 Jussi Kivilinna <jussi.kivilinna@mbnet.fi> */ -#include <asm/crypto/camellia.h> -#include <asm/crypto/glue_helper.h> #include <crypto/algapi.h> #include <crypto/internal/simd.h> -#include <crypto/xts.h> #include <linux/crypto.h> #include <linux/err.h> #include <linux/module.h> #include <linux/types.h> +#include "camellia.h" +#include "ecb_cbc_helpers.h" + #define CAMELLIA_AESNI_PARALLEL_BLOCKS 16 #define CAMELLIA_AESNI_AVX2_PARALLEL_BLOCKS 32 @@ -23,121 +23,6 @@ asmlinkage void camellia_ecb_enc_32way(const void *ctx, u8 *dst, const u8 *src); asmlinkage void camellia_ecb_dec_32way(const void *ctx, u8 *dst, const u8 *src); asmlinkage void camellia_cbc_dec_32way(const void *ctx, u8 *dst, const u8 *src); -asmlinkage void camellia_ctr_32way(const void *ctx, u8 *dst, const u8 *src, - le128 *iv); - -asmlinkage void camellia_xts_enc_32way(const void *ctx, u8 *dst, const u8 *src, - le128 *iv); -asmlinkage void camellia_xts_dec_32way(const void *ctx, u8 *dst, const u8 *src, - le128 *iv); - -static const struct common_glue_ctx camellia_enc = { - .num_funcs = 4, - .fpu_blocks_limit = CAMELLIA_AESNI_PARALLEL_BLOCKS, - - .funcs = { { - .num_blocks = CAMELLIA_AESNI_AVX2_PARALLEL_BLOCKS, - .fn_u = { .ecb = camellia_ecb_enc_32way } - }, { - .num_blocks = CAMELLIA_AESNI_PARALLEL_BLOCKS, - .fn_u = { .ecb = camellia_ecb_enc_16way } - }, { - .num_blocks = 2, - .fn_u = { .ecb = camellia_enc_blk_2way } - }, { - .num_blocks = 1, - .fn_u = { .ecb = camellia_enc_blk } - } } -}; - -static const struct common_glue_ctx camellia_ctr = { - .num_funcs = 4, - .fpu_blocks_limit = CAMELLIA_AESNI_PARALLEL_BLOCKS, - - .funcs = { { - .num_blocks = CAMELLIA_AESNI_AVX2_PARALLEL_BLOCKS, - .fn_u = { .ctr = camellia_ctr_32way } - }, { - .num_blocks = CAMELLIA_AESNI_PARALLEL_BLOCKS, - .fn_u = { .ctr = camellia_ctr_16way } - }, { - .num_blocks = 2, - .fn_u = { .ctr = camellia_crypt_ctr_2way } - }, { - .num_blocks = 1, - .fn_u = { .ctr = camellia_crypt_ctr } - } } -}; - -static const struct common_glue_ctx camellia_enc_xts = { - .num_funcs = 3, - .fpu_blocks_limit = CAMELLIA_AESNI_PARALLEL_BLOCKS, - - .funcs = { { - .num_blocks = CAMELLIA_AESNI_AVX2_PARALLEL_BLOCKS, - .fn_u = { .xts = camellia_xts_enc_32way } - }, { - .num_blocks = CAMELLIA_AESNI_PARALLEL_BLOCKS, - .fn_u = { .xts = camellia_xts_enc_16way } - }, { - .num_blocks = 1, - .fn_u = { .xts = camellia_xts_enc } - } } -}; - -static const struct common_glue_ctx camellia_dec = { - .num_funcs = 4, - .fpu_blocks_limit = CAMELLIA_AESNI_PARALLEL_BLOCKS, - - .funcs = { { - .num_blocks = CAMELLIA_AESNI_AVX2_PARALLEL_BLOCKS, - .fn_u = { .ecb = camellia_ecb_dec_32way } - }, { - .num_blocks = CAMELLIA_AESNI_PARALLEL_BLOCKS, - .fn_u = { .ecb = camellia_ecb_dec_16way } - }, { - .num_blocks = 2, - .fn_u = { .ecb = camellia_dec_blk_2way } - }, { - .num_blocks = 1, - .fn_u = { .ecb = camellia_dec_blk } - } } -}; - -static const struct common_glue_ctx camellia_dec_cbc = { - .num_funcs = 4, - .fpu_blocks_limit = CAMELLIA_AESNI_PARALLEL_BLOCKS, - - .funcs = { { - .num_blocks = CAMELLIA_AESNI_AVX2_PARALLEL_BLOCKS, - .fn_u = { .cbc = camellia_cbc_dec_32way } - }, { - .num_blocks = CAMELLIA_AESNI_PARALLEL_BLOCKS, - .fn_u = { .cbc = camellia_cbc_dec_16way } - }, { - .num_blocks = 2, - .fn_u = { .cbc = camellia_decrypt_cbc_2way } - }, { - .num_blocks = 1, - .fn_u = { .cbc = camellia_dec_blk } - } } -}; - -static const struct common_glue_ctx camellia_dec_xts = { - .num_funcs = 3, - .fpu_blocks_limit = CAMELLIA_AESNI_PARALLEL_BLOCKS, - - .funcs = { { - .num_blocks = CAMELLIA_AESNI_AVX2_PARALLEL_BLOCKS, - .fn_u = { .xts = camellia_xts_dec_32way } - }, { - .num_blocks = CAMELLIA_AESNI_PARALLEL_BLOCKS, - .fn_u = { .xts = camellia_xts_dec_16way } - }, { - .num_blocks = 1, - .fn_u = { .xts = camellia_xts_dec } - } } -}; static int camellia_setkey(struct crypto_skcipher *tfm, const u8 *key, unsigned int keylen) @@ -147,45 +32,39 @@ static int camellia_setkey(struct crypto_skcipher *tfm, const u8 *key, static int ecb_encrypt(struct skcipher_request *req) { - return glue_ecb_req_128bit(&camellia_enc, req); + ECB_WALK_START(req, CAMELLIA_BLOCK_SIZE, CAMELLIA_AESNI_PARALLEL_BLOCKS); + ECB_BLOCK(CAMELLIA_AESNI_AVX2_PARALLEL_BLOCKS, camellia_ecb_enc_32way); + ECB_BLOCK(CAMELLIA_AESNI_PARALLEL_BLOCKS, camellia_ecb_enc_16way); + ECB_BLOCK(2, camellia_enc_blk_2way); + ECB_BLOCK(1, camellia_enc_blk); + ECB_WALK_END(); } static int ecb_decrypt(struct skcipher_request *req) { - return glue_ecb_req_128bit(&camellia_dec, req); + ECB_WALK_START(req, CAMELLIA_BLOCK_SIZE, CAMELLIA_AESNI_PARALLEL_BLOCKS); + ECB_BLOCK(CAMELLIA_AESNI_AVX2_PARALLEL_BLOCKS, camellia_ecb_dec_32way); + ECB_BLOCK(CAMELLIA_AESNI_PARALLEL_BLOCKS, camellia_ecb_dec_16way); + ECB_BLOCK(2, camellia_dec_blk_2way); + ECB_BLOCK(1, camellia_dec_blk); + ECB_WALK_END(); } static int cbc_encrypt(struct skcipher_request *req) { - return glue_cbc_encrypt_req_128bit(camellia_enc_blk, req); + CBC_WALK_START(req, CAMELLIA_BLOCK_SIZE, -1); + CBC_ENC_BLOCK(camellia_enc_blk); + CBC_WALK_END(); } static int cbc_decrypt(struct skcipher_request *req) { - return glue_cbc_decrypt_req_128bit(&camellia_dec_cbc, req); -} - -static int ctr_crypt(struct skcipher_request *req) -{ - return glue_ctr_req_128bit(&camellia_ctr, req); -} - -static int xts_encrypt(struct skcipher_request *req) -{ - struct crypto_skcipher *tfm = crypto_skcipher_reqtfm(req); - struct camellia_xts_ctx *ctx = crypto_skcipher_ctx(tfm); - - return glue_xts_req_128bit(&camellia_enc_xts, req, camellia_enc_blk, - &ctx->tweak_ctx, &ctx->crypt_ctx, false); -} - -static int xts_decrypt(struct skcipher_request *req) -{ - struct crypto_skcipher *tfm = crypto_skcipher_reqtfm(req); - struct camellia_xts_ctx *ctx = crypto_skcipher_ctx(tfm); - - return glue_xts_req_128bit(&camellia_dec_xts, req, camellia_enc_blk, - &ctx->tweak_ctx, &ctx->crypt_ctx, true); + CBC_WALK_START(req, CAMELLIA_BLOCK_SIZE, CAMELLIA_AESNI_PARALLEL_BLOCKS); + CBC_DEC_BLOCK(CAMELLIA_AESNI_AVX2_PARALLEL_BLOCKS, camellia_cbc_dec_32way); + CBC_DEC_BLOCK(CAMELLIA_AESNI_PARALLEL_BLOCKS, camellia_cbc_dec_16way); + CBC_DEC_BLOCK(2, camellia_decrypt_cbc_2way); + CBC_DEC_BLOCK(1, camellia_dec_blk); + CBC_WALK_END(); } static struct skcipher_alg camellia_algs[] = { @@ -216,35 +95,6 @@ static struct skcipher_alg camellia_algs[] = { .setkey = camellia_setkey, .encrypt = cbc_encrypt, .decrypt = cbc_decrypt, - }, { - .base.cra_name = "__ctr(camellia)", - .base.cra_driver_name = "__ctr-camellia-aesni-avx2", - .base.cra_priority = 500, - .base.cra_flags = CRYPTO_ALG_INTERNAL, - .base.cra_blocksize = 1, - .base.cra_ctxsize = sizeof(struct camellia_ctx), - .base.cra_module = THIS_MODULE, - .min_keysize = CAMELLIA_MIN_KEY_SIZE, - .max_keysize = CAMELLIA_MAX_KEY_SIZE, - .ivsize = CAMELLIA_BLOCK_SIZE, - .chunksize = CAMELLIA_BLOCK_SIZE, - .setkey = camellia_setkey, - .encrypt = ctr_crypt, - .decrypt = ctr_crypt, - }, { - .base.cra_name = "__xts(camellia)", - .base.cra_driver_name = "__xts-camellia-aesni-avx2", - .base.cra_priority = 500, - .base.cra_flags = CRYPTO_ALG_INTERNAL, - .base.cra_blocksize = CAMELLIA_BLOCK_SIZE, - .base.cra_ctxsize = sizeof(struct camellia_xts_ctx), - .base.cra_module = THIS_MODULE, - .min_keysize = 2 * CAMELLIA_MIN_KEY_SIZE, - .max_keysize = 2 * CAMELLIA_MAX_KEY_SIZE, - .ivsize = CAMELLIA_BLOCK_SIZE, - .setkey = xts_camellia_setkey, - .encrypt = xts_encrypt, - .decrypt = xts_decrypt, }, }; diff --git a/arch/x86/crypto/camellia_aesni_avx_glue.c b/arch/x86/crypto/camellia_aesni_avx_glue.c index 4e5de6ef206e..c7ccf63e741e 100644 --- a/arch/x86/crypto/camellia_aesni_avx_glue.c +++ b/arch/x86/crypto/camellia_aesni_avx_glue.c @@ -5,16 +5,16 @@ * Copyright © 2012-2013 Jussi Kivilinna <jussi.kivilinna@iki.fi> */ -#include <asm/crypto/camellia.h> -#include <asm/crypto/glue_helper.h> #include <crypto/algapi.h> #include <crypto/internal/simd.h> -#include <crypto/xts.h> #include <linux/crypto.h> #include <linux/err.h> #include <linux/module.h> #include <linux/types.h> +#include "camellia.h" +#include "ecb_cbc_helpers.h" + #define CAMELLIA_AESNI_PARALLEL_BLOCKS 16 /* 16-way parallel cipher functions (avx/aes-ni) */ @@ -27,120 +27,6 @@ EXPORT_SYMBOL_GPL(camellia_ecb_dec_16way); asmlinkage void camellia_cbc_dec_16way(const void *ctx, u8 *dst, const u8 *src); EXPORT_SYMBOL_GPL(camellia_cbc_dec_16way); -asmlinkage void camellia_ctr_16way(const void *ctx, u8 *dst, const u8 *src, - le128 *iv); -EXPORT_SYMBOL_GPL(camellia_ctr_16way); - -asmlinkage void camellia_xts_enc_16way(const void *ctx, u8 *dst, const u8 *src, - le128 *iv); -EXPORT_SYMBOL_GPL(camellia_xts_enc_16way); - -asmlinkage void camellia_xts_dec_16way(const void *ctx, u8 *dst, const u8 *src, - le128 *iv); -EXPORT_SYMBOL_GPL(camellia_xts_dec_16way); - -void camellia_xts_enc(const void *ctx, u8 *dst, const u8 *src, le128 *iv) -{ - glue_xts_crypt_128bit_one(ctx, dst, src, iv, camellia_enc_blk); -} -EXPORT_SYMBOL_GPL(camellia_xts_enc); - -void camellia_xts_dec(const void *ctx, u8 *dst, const u8 *src, le128 *iv) -{ - glue_xts_crypt_128bit_one(ctx, dst, src, iv, camellia_dec_blk); -} -EXPORT_SYMBOL_GPL(camellia_xts_dec); - -static const struct common_glue_ctx camellia_enc = { - .num_funcs = 3, - .fpu_blocks_limit = CAMELLIA_AESNI_PARALLEL_BLOCKS, - - .funcs = { { - .num_blocks = CAMELLIA_AESNI_PARALLEL_BLOCKS, - .fn_u = { .ecb = camellia_ecb_enc_16way } - }, { - .num_blocks = 2, - .fn_u = { .ecb = camellia_enc_blk_2way } - }, { - .num_blocks = 1, - .fn_u = { .ecb = camellia_enc_blk } - } } -}; - -static const struct common_glue_ctx camellia_ctr = { - .num_funcs = 3, - .fpu_blocks_limit = CAMELLIA_AESNI_PARALLEL_BLOCKS, - - .funcs = { { - .num_blocks = CAMELLIA_AESNI_PARALLEL_BLOCKS, - .fn_u = { .ctr = camellia_ctr_16way } - }, { - .num_blocks = 2, - .fn_u = { .ctr = camellia_crypt_ctr_2way } - }, { - .num_blocks = 1, - .fn_u = { .ctr = camellia_crypt_ctr } - } } -}; - -static const struct common_glue_ctx camellia_enc_xts = { - .num_funcs = 2, - .fpu_blocks_limit = CAMELLIA_AESNI_PARALLEL_BLOCKS, - - .funcs = { { - .num_blocks = CAMELLIA_AESNI_PARALLEL_BLOCKS, - .fn_u = { .xts = camellia_xts_enc_16way } - }, { - .num_blocks = 1, - .fn_u = { .xts = camellia_xts_enc } - } } -}; - -static const struct common_glue_ctx camellia_dec = { - .num_funcs = 3, - .fpu_blocks_limit = CAMELLIA_AESNI_PARALLEL_BLOCKS, - - .funcs = { { - .num_blocks = CAMELLIA_AESNI_PARALLEL_BLOCKS, - .fn_u = { .ecb = camellia_ecb_dec_16way } - }, { - .num_blocks = 2, - .fn_u = { .ecb = camellia_dec_blk_2way } - }, { - .num_blocks = 1, - .fn_u = { .ecb = camellia_dec_blk } - } } -}; - -static const struct common_glue_ctx camellia_dec_cbc = { - .num_funcs = 3, - .fpu_blocks_limit = CAMELLIA_AESNI_PARALLEL_BLOCKS, - - .funcs = { { - .num_blocks = CAMELLIA_AESNI_PARALLEL_BLOCKS, - .fn_u = { .cbc = camellia_cbc_dec_16way } - }, { - .num_blocks = 2, - .fn_u = { .cbc = camellia_decrypt_cbc_2way } - }, { - .num_blocks = 1, - .fn_u = { .cbc = camellia_dec_blk } - } } -}; - -static const struct common_glue_ctx camellia_dec_xts = { - .num_funcs = 2, - .fpu_blocks_limit = CAMELLIA_AESNI_PARALLEL_BLOCKS, - - .funcs = { { - .num_blocks = CAMELLIA_AESNI_PARALLEL_BLOCKS, - .fn_u = { .xts = camellia_xts_dec_16way } - }, { - .num_blocks = 1, - .fn_u = { .xts = camellia_xts_dec } - } } -}; - static int camellia_setkey(struct crypto_skcipher *tfm, const u8 *key, unsigned int keylen) { @@ -149,65 +35,36 @@ static int camellia_setkey(struct crypto_skcipher *tfm, const u8 *key, static int ecb_encrypt(struct skcipher_request *req) { - return glue_ecb_req_128bit(&camellia_enc, req); + ECB_WALK_START(req, CAMELLIA_BLOCK_SIZE, CAMELLIA_AESNI_PARALLEL_BLOCKS); + ECB_BLOCK(CAMELLIA_AESNI_PARALLEL_BLOCKS, camellia_ecb_enc_16way); + ECB_BLOCK(2, camellia_enc_blk_2way); + ECB_BLOCK(1, camellia_enc_blk); + ECB_WALK_END(); } static int ecb_decrypt(struct skcipher_request *req) { - return glue_ecb_req_128bit(&camellia_dec, req); + ECB_WALK_START(req, CAMELLIA_BLOCK_SIZE, CAMELLIA_AESNI_PARALLEL_BLOCKS); + ECB_BLOCK(CAMELLIA_AESNI_PARALLEL_BLOCKS, camellia_ecb_dec_16way); + ECB_BLOCK(2, camellia_dec_blk_2way); + ECB_BLOCK(1, camellia_dec_blk); + ECB_WALK_END(); } static int cbc_encrypt(struct skcipher_request *req) { - return glue_cbc_encrypt_req_128bit(camellia_enc_blk, req); + CBC_WALK_START(req, CAMELLIA_BLOCK_SIZE, -1); + CBC_ENC_BLOCK(camellia_enc_blk); + CBC_WALK_END(); } static int cbc_decrypt(struct skcipher_request *req) { - return glue_cbc_decrypt_req_128bit(&camellia_dec_cbc, req); -} - -static int ctr_crypt(struct skcipher_request *req) -{ - return glue_ctr_req_128bit(&camellia_ctr, req); -} - -int xts_camellia_setkey(struct crypto_skcipher *tfm, const u8 *key, - unsigned int keylen) -{ - struct camellia_xts_ctx *ctx = crypto_skcipher_ctx(tfm); - int err; - - err = xts_verify_key(tfm, key, keylen); - if (err) - return err; - - /* first half of xts-key is for crypt */ - err = __camellia_setkey(&ctx->crypt_ctx, key, keylen / 2); - if (err) - return err; - - /* second half of xts-key is for tweak */ - return __camellia_setkey(&ctx->tweak_ctx, key + keylen / 2, keylen / 2); -} -EXPORT_SYMBOL_GPL(xts_camellia_setkey); - -static int xts_encrypt(struct skcipher_request *req) -{ - struct crypto_skcipher *tfm = crypto_skcipher_reqtfm(req); - struct camellia_xts_ctx *ctx = crypto_skcipher_ctx(tfm); - - return glue_xts_req_128bit(&camellia_enc_xts, req, camellia_enc_blk, - &ctx->tweak_ctx, &ctx->crypt_ctx, false); -} - -static int xts_decrypt(struct skcipher_request *req) -{ - struct crypto_skcipher *tfm = crypto_skcipher_reqtfm(req); - struct camellia_xts_ctx *ctx = crypto_skcipher_ctx(tfm); - - return glue_xts_req_128bit(&camellia_dec_xts, req, camellia_enc_blk, - &ctx->tweak_ctx, &ctx->crypt_ctx, true); + CBC_WALK_START(req, CAMELLIA_BLOCK_SIZE, CAMELLIA_AESNI_PARALLEL_BLOCKS); + CBC_DEC_BLOCK(CAMELLIA_AESNI_PARALLEL_BLOCKS, camellia_cbc_dec_16way); + CBC_DEC_BLOCK(2, camellia_decrypt_cbc_2way); + CBC_DEC_BLOCK(1, camellia_dec_blk); + CBC_WALK_END(); } static struct skcipher_alg camellia_algs[] = { @@ -238,36 +95,7 @@ static struct skcipher_alg camellia_algs[] = { .setkey = camellia_setkey, .encrypt = cbc_encrypt, .decrypt = cbc_decrypt, - }, { - .base.cra_name = "__ctr(camellia)", - .base.cra_driver_name = "__ctr-camellia-aesni", - .base.cra_priority = 400, - .base.cra_flags = CRYPTO_ALG_INTERNAL, - .base.cra_blocksize = 1, - .base.cra_ctxsize = sizeof(struct camellia_ctx), - .base.cra_module = THIS_MODULE, - .min_keysize = CAMELLIA_MIN_KEY_SIZE, - .max_keysize = CAMELLIA_MAX_KEY_SIZE, - .ivsize = CAMELLIA_BLOCK_SIZE, - .chunksize = CAMELLIA_BLOCK_SIZE, - .setkey = camellia_setkey, - .encrypt = ctr_crypt, - .decrypt = ctr_crypt, - }, { - .base.cra_name = "__xts(camellia)", - .base.cra_driver_name = "__xts-camellia-aesni", - .base.cra_priority = 400, - .base.cra_flags = CRYPTO_ALG_INTERNAL, - .base.cra_blocksize = CAMELLIA_BLOCK_SIZE, - .base.cra_ctxsize = sizeof(struct camellia_xts_ctx), - .base.cra_module = THIS_MODULE, - .min_keysize = 2 * CAMELLIA_MIN_KEY_SIZE, - .max_keysize = 2 * CAMELLIA_MAX_KEY_SIZE, - .ivsize = CAMELLIA_BLOCK_SIZE, - .setkey = xts_camellia_setkey, - .encrypt = xts_encrypt, - .decrypt = xts_decrypt, - }, + } }; static struct simd_skcipher_alg *camellia_simd_algs[ARRAY_SIZE(camellia_algs)]; diff --git a/arch/x86/crypto/camellia_glue.c b/arch/x86/crypto/camellia_glue.c index 242c056e5fa8..66c435ba9d3d 100644 --- a/arch/x86/crypto/camellia_glue.c +++ b/arch/x86/crypto/camellia_glue.c @@ -14,8 +14,9 @@ #include <linux/module.h> #include <linux/types.h> #include <crypto/algapi.h> -#include <asm/crypto/camellia.h> -#include <asm/crypto/glue_helper.h> + +#include "camellia.h" +#include "ecb_cbc_helpers.h" /* regular block cipher functions */ asmlinkage void __camellia_enc_blk(const void *ctx, u8 *dst, const u8 *src, @@ -1262,129 +1263,47 @@ static int camellia_setkey_skcipher(struct crypto_skcipher *tfm, const u8 *key, return camellia_setkey(&tfm->base, key, key_len); } -void camellia_decrypt_cbc_2way(const void *ctx, u8 *d, const u8 *s) +void camellia_decrypt_cbc_2way(const void *ctx, u8 *dst, const u8 *src) { - u128 *dst = (u128 *)d; - const u128 *src = (const u128 *)s; - u128 iv = *src; - - camellia_dec_blk_2way(ctx, (u8 *)dst, (u8 *)src); + u8 buf[CAMELLIA_BLOCK_SIZE]; + const u8 *iv = src; - u128_xor(&dst[1], &dst[1], &iv); + if (dst == src) + iv = memcpy(buf, iv, sizeof(buf)); + camellia_dec_blk_2way(ctx, dst, src); + crypto_xor(dst + CAMELLIA_BLOCK_SIZE, iv, CAMELLIA_BLOCK_SIZE); } EXPORT_SYMBOL_GPL(camellia_decrypt_cbc_2way); -void camellia_crypt_ctr(const void *ctx, u8 *d, const u8 *s, le128 *iv) -{ - be128 ctrblk; - u128 *dst = (u128 *)d; - const u128 *src = (const u128 *)s; - - if (dst != src) - *dst = *src; - - le128_to_be128(&ctrblk, iv); - le128_inc(iv); - - camellia_enc_blk_xor(ctx, (u8 *)dst, (u8 *)&ctrblk); -} -EXPORT_SYMBOL_GPL(camellia_crypt_ctr); - -void camellia_crypt_ctr_2way(const void *ctx, u8 *d, const u8 *s, le128 *iv) -{ - be128 ctrblks[2]; - u128 *dst = (u128 *)d; - const u128 *src = (const u128 *)s; - - if (dst != src) { - dst[0] = src[0]; - dst[1] = src[1]; - } - - le128_to_be128(&ctrblks[0], iv); - le128_inc(iv); - le128_to_be128(&ctrblks[1], iv); - le128_inc(iv); - - camellia_enc_blk_xor_2way(ctx, (u8 *)dst, (u8 *)ctrblks); -} -EXPORT_SYMBOL_GPL(camellia_crypt_ctr_2way); - -static const struct common_glue_ctx camellia_enc = { - .num_funcs = 2, - .fpu_blocks_limit = -1, - - .funcs = { { - .num_blocks = 2, - .fn_u = { .ecb = camellia_enc_blk_2way } - }, { - .num_blocks = 1, - .fn_u = { .ecb = camellia_enc_blk } - } } -}; - -static const struct common_glue_ctx camellia_ctr = { - .num_funcs = 2, - .fpu_blocks_limit = -1, - - .funcs = { { - .num_blocks = 2, - .fn_u = { .ctr = camellia_crypt_ctr_2way } - }, { - .num_blocks = 1, - .fn_u = { .ctr = camellia_crypt_ctr } - } } -}; - -static const struct common_glue_ctx camellia_dec = { - .num_funcs = 2, - .fpu_blocks_limit = -1, - - .funcs = { { - .num_blocks = 2, - .fn_u = { .ecb = camellia_dec_blk_2way } - }, { - .num_blocks = 1, - .fn_u = { .ecb = camellia_dec_blk } - } } -}; - -static const struct common_glue_ctx camellia_dec_cbc = { - .num_funcs = 2, - .fpu_blocks_limit = -1, - - .funcs = { { - .num_blocks = 2, - .fn_u = { .cbc = camellia_decrypt_cbc_2way } - }, { - .num_blocks = 1, - .fn_u = { .cbc = camellia_dec_blk } - } } -}; - static int ecb_encrypt(struct skcipher_request *req) { - return glue_ecb_req_128bit(&camellia_enc, req); + ECB_WALK_START(req, CAMELLIA_BLOCK_SIZE, -1); + ECB_BLOCK(2, camellia_enc_blk_2way); + ECB_BLOCK(1, camellia_enc_blk); + ECB_WALK_END(); } static int ecb_decrypt(struct skcipher_request *req) { - return glue_ecb_req_128bit(&camellia_dec, req); + ECB_WALK_START(req, CAMELLIA_BLOCK_SIZE, -1); + ECB_BLOCK(2, camellia_dec_blk_2way); + ECB_BLOCK(1, camellia_dec_blk); + ECB_WALK_END(); } static int cbc_encrypt(struct skcipher_request *req) { - return glue_cbc_encrypt_req_128bit(camellia_enc_blk, req); + CBC_WALK_START(req, CAMELLIA_BLOCK_SIZE, -1); + CBC_ENC_BLOCK(camellia_enc_blk); + CBC_WALK_END(); } static int cbc_decrypt(struct skcipher_request *req) { - return glue_cbc_decrypt_req_128bit(&camellia_dec_cbc, req); -} - -static int ctr_crypt(struct skcipher_request *req) -{ - return glue_ctr_req_128bit(&camellia_ctr, req); + CBC_WALK_START(req, CAMELLIA_BLOCK_SIZE, -1); + CBC_DEC_BLOCK(2, camellia_decrypt_cbc_2way); + CBC_DEC_BLOCK(1, camellia_dec_blk); + CBC_WALK_END(); } static struct crypto_alg camellia_cipher_alg = { @@ -1433,20 +1352,6 @@ static struct skcipher_alg camellia_skcipher_algs[] = { .setkey = camellia_setkey_skcipher, .encrypt = cbc_encrypt, .decrypt = cbc_decrypt, - }, { - .base.cra_name = "ctr(camellia)", - .base.cra_driver_name = "ctr-camellia-asm", - .base.cra_priority = 300, - .base.cra_blocksize = 1, - .base.cra_ctxsize = sizeof(struct camellia_ctx), - .base.cra_module = THIS_MODULE, - .min_keysize = CAMELLIA_MIN_KEY_SIZE, - .max_keysize = CAMELLIA_MAX_KEY_SIZE, - .ivsize = CAMELLIA_BLOCK_SIZE, - .chunksize = CAMELLIA_BLOCK_SIZE, - .setkey = camellia_setkey_skcipher, - .encrypt = ctr_crypt, - .decrypt = ctr_crypt, } }; diff --git a/arch/x86/crypto/cast5_avx_glue.c b/arch/x86/crypto/cast5_avx_glue.c index 384ccb00f9e1..3976a87f92ad 100644 --- a/arch/x86/crypto/cast5_avx_glue.c +++ b/arch/x86/crypto/cast5_avx_glue.c @@ -6,7 +6,6 @@ * <Johannes.Goetzfried@informatik.stud.uni-erlangen.de> */ -#include <asm/crypto/glue_helper.h> #include <crypto/algapi.h> #include <crypto/cast5.h> #include <crypto/internal/simd.h> @@ -15,6 +14,8 @@ #include <linux/module.h> #include <linux/types.h> +#include "ecb_cbc_helpers.h" + #define CAST5_PARALLEL_BLOCKS 16 asmlinkage void cast5_ecb_enc_16way(struct cast5_ctx *ctx, u8 *dst, @@ -23,8 +24,6 @@ asmlinkage void cast5_ecb_dec_16way(struct cast5_ctx *ctx, u8 *dst, const u8 *src); asmlinkage void cast5_cbc_dec_16way(struct cast5_ctx *ctx, u8 *dst, const u8 *src); -asmlinkage void cast5_ctr_16way(struct cast5_ctx *ctx, u8 *dst, const u8 *src, - __be64 *iv); static int cast5_setkey_skcipher(struct crypto_skcipher *tfm, const u8 *key, unsigned int keylen) @@ -32,272 +31,35 @@ static int cast5_setkey_skcipher(struct crypto_skcipher *tfm, const u8 *key, return cast5_setkey(&tfm->base, key, keylen); } -static inline bool cast5_fpu_begin(bool fpu_enabled, struct skcipher_walk *walk, - unsigned int nbytes) -{ - return glue_fpu_begin(CAST5_BLOCK_SIZE, CAST5_PARALLEL_BLOCKS, - walk, fpu_enabled, nbytes); -} - -static inline void cast5_fpu_end(bool fpu_enabled) -{ - return glue_fpu_end(fpu_enabled); -} - -static int ecb_crypt(struct skcipher_request *req, bool enc) -{ - bool fpu_enabled = false; - struct crypto_skcipher *tfm = crypto_skcipher_reqtfm(req); - struct cast5_ctx *ctx = crypto_skcipher_ctx(tfm); - struct skcipher_walk walk; - const unsigned int bsize = CAST5_BLOCK_SIZE; - unsigned int nbytes; - void (*fn)(struct cast5_ctx *ctx, u8 *dst, const u8 *src); - int err; - - err = skcipher_walk_virt(&walk, req, false); - - while ((nbytes = walk.nbytes)) { - u8 *wsrc = walk.src.virt.addr; - u8 *wdst = walk.dst.virt.addr; - - fpu_enabled = cast5_fpu_begin(fpu_enabled, &walk, nbytes); - - /* Process multi-block batch */ - if (nbytes >= bsize * CAST5_PARALLEL_BLOCKS) { - fn = (enc) ? cast5_ecb_enc_16way : cast5_ecb_dec_16way; - do { - fn(ctx, wdst, wsrc); - - wsrc += bsize * CAST5_PARALLEL_BLOCKS; - wdst += bsize * CAST5_PARALLEL_BLOCKS; - nbytes -= bsize * CAST5_PARALLEL_BLOCKS; - } while (nbytes >= bsize * CAST5_PARALLEL_BLOCKS); - - if (nbytes < bsize) - goto done; - } - - fn = (enc) ? __cast5_encrypt : __cast5_decrypt; - - /* Handle leftovers */ - do { - fn(ctx, wdst, wsrc); - - wsrc += bsize; - wdst += bsize; - nbytes -= bsize; - } while (nbytes >= bsize); - -done: - err = skcipher_walk_done(&walk, nbytes); - } - - cast5_fpu_end(fpu_enabled); - return err; -} - static int ecb_encrypt(struct skcipher_request *req) { - return ecb_crypt(req, true); + ECB_WALK_START(req, CAST5_BLOCK_SIZE, CAST5_PARALLEL_BLOCKS); + ECB_BLOCK(CAST5_PARALLEL_BLOCKS, cast5_ecb_enc_16way); + ECB_BLOCK(1, __cast5_encrypt); + ECB_WALK_END(); } static int ecb_decrypt(struct skcipher_request *req) { - return ecb_crypt(req, false); + ECB_WALK_START(req, CAST5_BLOCK_SIZE, CAST5_PARALLEL_BLOCKS); + ECB_BLOCK(CAST5_PARALLEL_BLOCKS, cast5_ecb_dec_16way); + ECB_BLOCK(1, __cast5_decrypt); + ECB_WALK_END(); } static int cbc_encrypt(struct skcipher_request *req) { - const unsigned int bsize = CAST5_BLOCK_SIZE; - struct crypto_skcipher *tfm = crypto_skcipher_reqtfm(req); - struct cast5_ctx *ctx = crypto_skcipher_ctx(tfm); - struct skcipher_walk walk; - unsigned int nbytes; - int err; - - err = skcipher_walk_virt(&walk, req, false); - - while ((nbytes = walk.nbytes)) { - u64 *src = (u64 *)walk.src.virt.addr; - u64 *dst = (u64 *)walk.dst.virt.addr; - u64 *iv = (u64 *)walk.iv; - - do { - *dst = *src ^ *iv; - __cast5_encrypt(ctx, (u8 *)dst, (u8 *)dst); - iv = dst; - src++; - dst++; - nbytes -= bsize; - } while (nbytes >= bsize); - - *(u64 *)walk.iv = *iv; - err = skcipher_walk_done(&walk, nbytes); - } - - return err; -} - -static unsigned int __cbc_decrypt(struct cast5_ctx *ctx, - struct skcipher_walk *walk) -{ - const unsigned int bsize = CAST5_BLOCK_SIZE; - unsigned int nbytes = walk->nbytes; - u64 *src = (u64 *)walk->src.virt.addr; - u64 *dst = (u64 *)walk->dst.virt.addr; - u64 last_iv; - - /* Start of the last block. */ - src += nbytes / bsize - 1; - dst += nbytes / bsize - 1; - - last_iv = *src; - - /* Process multi-block batch */ - if (nbytes >= bsize * CAST5_PARALLEL_BLOCKS) { - do { - nbytes -= bsize * (CAST5_PARALLEL_BLOCKS - 1); - src -= CAST5_PARALLEL_BLOCKS - 1; - dst -= CAST5_PARALLEL_BLOCKS - 1; - - cast5_cbc_dec_16way(ctx, (u8 *)dst, (u8 *)src); - - nbytes -= bsize; - if (nbytes < bsize) - goto done; - - *dst ^= *(src - 1); - src -= 1; - dst -= 1; - } while (nbytes >= bsize * CAST5_PARALLEL_BLOCKS); - } - - /* Handle leftovers */ - for (;;) { - __cast5_decrypt(ctx, (u8 *)dst, (u8 *)src); - - nbytes -= bsize; - if (nbytes < bsize) - break; - - *dst ^= *(src - 1); - src -= 1; - dst -= 1; - } - -done: - *dst ^= *(u64 *)walk->iv; - *(u64 *)walk->iv = last_iv; - - return nbytes; + CBC_WALK_START(req, CAST5_BLOCK_SIZE, -1); + CBC_ENC_BLOCK(__cast5_encrypt); + CBC_WALK_END(); } static int cbc_decrypt(struct skcipher_request *req) { - struct crypto_skcipher *tfm = crypto_skcipher_reqtfm(req); - struct cast5_ctx *ctx = crypto_skcipher_ctx(tfm); - bool fpu_enabled = false; - struct skcipher_walk walk; - unsigned int nbytes; - int err; - - err = skcipher_walk_virt(&walk, req, false); - - while ((nbytes = walk.nbytes)) { - fpu_enabled = cast5_fpu_begin(fpu_enabled, &walk, nbytes); - nbytes = __cbc_decrypt(ctx, &walk); - err = skcipher_walk_done(&walk, nbytes); - } - - cast5_fpu_end(fpu_enabled); - return err; -} - -static void ctr_crypt_final(struct skcipher_walk *walk, struct cast5_ctx *ctx) -{ - u8 *ctrblk = walk->iv; - u8 keystream[CAST5_BLOCK_SIZE]; - u8 *src = walk->src.virt.addr; - u8 *dst = walk->dst.virt.addr; - unsigned int nbytes = walk->nbytes; - - __cast5_encrypt(ctx, keystream, ctrblk); - crypto_xor_cpy(dst, keystream, src, nbytes); - - crypto_inc(ctrblk, CAST5_BLOCK_SIZE); -} - -static unsigned int __ctr_crypt(struct skcipher_walk *walk, - struct cast5_ctx *ctx) -{ - const unsigned int bsize = CAST5_BLOCK_SIZE; - unsigned int nbytes = walk->nbytes; - u64 *src = (u64 *)walk->src.virt.addr; - u64 *dst = (u64 *)walk->dst.virt.addr; - - /* Process multi-block batch */ - if (nbytes >= bsize * CAST5_PARALLEL_BLOCKS) { - do { - cast5_ctr_16way(ctx, (u8 *)dst, (u8 *)src, - (__be64 *)walk->iv); - - src += CAST5_PARALLEL_BLOCKS; - dst += CAST5_PARALLEL_BLOCKS; - nbytes -= bsize * CAST5_PARALLEL_BLOCKS; - } while (nbytes >= bsize * CAST5_PARALLEL_BLOCKS); - - if (nbytes < bsize) - goto done; - } - - /* Handle leftovers */ - do { - u64 ctrblk; - - if (dst != src) - *dst = *src; - - ctrblk = *(u64 *)walk->iv; - be64_add_cpu((__be64 *)walk->iv, 1); - - __cast5_encrypt(ctx, (u8 *)&ctrblk, (u8 *)&ctrblk); - *dst ^= ctrblk; - - src += 1; - dst += 1; - nbytes -= bsize; - } while (nbytes >= bsize); - -done: - return nbytes; -} - -static int ctr_crypt(struct skcipher_request *req) -{ - struct crypto_skcipher *tfm = crypto_skcipher_reqtfm(req); - struct cast5_ctx *ctx = crypto_skcipher_ctx(tfm); - bool fpu_enabled = false; - struct skcipher_walk walk; - unsigned int nbytes; - int err; - - err = skcipher_walk_virt(&walk, req, false); - - while ((nbytes = walk.nbytes) >= CAST5_BLOCK_SIZE) { - fpu_enabled = cast5_fpu_begin(fpu_enabled, &walk, nbytes); - nbytes = __ctr_crypt(&walk, ctx); - err = skcipher_walk_done(&walk, nbytes); - } - - cast5_fpu_end(fpu_enabled); - - if (walk.nbytes) { - ctr_crypt_final(&walk, ctx); - err = skcipher_walk_done(&walk, 0); - } - - return err; + CBC_WALK_START(req, CAST5_BLOCK_SIZE, CAST5_PARALLEL_BLOCKS); + CBC_DEC_BLOCK(CAST5_PARALLEL_BLOCKS, cast5_cbc_dec_16way); + CBC_DEC_BLOCK(1, __cast5_decrypt); + CBC_WALK_END(); } static struct skcipher_alg cast5_algs[] = { @@ -328,21 +90,6 @@ static struct skcipher_alg cast5_algs[] = { .setkey = cast5_setkey_skcipher, .encrypt = cbc_encrypt, .decrypt = cbc_decrypt, - }, { - .base.cra_name = "__ctr(cast5)", - .base.cra_driver_name = "__ctr-cast5-avx", - .base.cra_priority = 200, - .base.cra_flags = CRYPTO_ALG_INTERNAL, - .base.cra_blocksize = 1, - .base.cra_ctxsize = sizeof(struct cast5_ctx), - .base.cra_module = THIS_MODULE, - .min_keysize = CAST5_MIN_KEY_SIZE, - .max_keysize = CAST5_MAX_KEY_SIZE, - .ivsize = CAST5_BLOCK_SIZE, - .chunksize = CAST5_BLOCK_SIZE, - .setkey = cast5_setkey_skcipher, - .encrypt = ctr_crypt, - .decrypt = ctr_crypt, } }; diff --git a/arch/x86/crypto/cast6-avx-x86_64-asm_64.S b/arch/x86/crypto/cast6-avx-x86_64-asm_64.S index 932a3ce32a88..fbddcecc3e3f 100644 --- a/arch/x86/crypto/cast6-avx-x86_64-asm_64.S +++ b/arch/x86/crypto/cast6-avx-x86_64-asm_64.S @@ -212,8 +212,6 @@ .section .rodata.cst16, "aM", @progbits, 16 .align 16 -.Lxts_gf128mul_and_shl1_mask: - .byte 0x87, 0, 0, 0, 0, 0, 0, 0, 1, 0, 0, 0, 0, 0, 0, 0 .Lbswap_mask: .byte 3, 2, 1, 0, 7, 6, 5, 4, 11, 10, 9, 8, 15, 14, 13, 12 .Lbswap128_mask: @@ -412,85 +410,3 @@ SYM_FUNC_START(cast6_cbc_dec_8way) FRAME_END ret; SYM_FUNC_END(cast6_cbc_dec_8way) - -SYM_FUNC_START(cast6_ctr_8way) - /* input: - * %rdi: ctx, CTX - * %rsi: dst - * %rdx: src - * %rcx: iv (little endian, 128bit) - */ - FRAME_BEGIN - pushq %r12; - pushq %r15 - - movq %rdi, CTX; - movq %rsi, %r11; - movq %rdx, %r12; - - load_ctr_8way(%rcx, .Lbswap128_mask, RA1, RB1, RC1, RD1, RA2, RB2, RC2, - RD2, RX, RKR, RKM); - - call __cast6_enc_blk8; - - store_ctr_8way(%r12, %r11, RA1, RB1, RC1, RD1, RA2, RB2, RC2, RD2); - - popq %r15; - popq %r12; - FRAME_END - ret; -SYM_FUNC_END(cast6_ctr_8way) - -SYM_FUNC_START(cast6_xts_enc_8way) - /* input: - * %rdi: ctx, CTX - * %rsi: dst - * %rdx: src - * %rcx: iv (t ⊕ αⁿ ∈ GF(2¹²⁸)) - */ - FRAME_BEGIN - pushq %r15; - - movq %rdi, CTX - movq %rsi, %r11; - - /* regs <= src, dst <= IVs, regs <= regs xor IVs */ - load_xts_8way(%rcx, %rdx, %rsi, RA1, RB1, RC1, RD1, RA2, RB2, RC2, RD2, - RX, RKR, RKM, .Lxts_gf128mul_and_shl1_mask); - - call __cast6_enc_blk8; - - /* dst <= regs xor IVs(in dst) */ - store_xts_8way(%r11, RA1, RB1, RC1, RD1, RA2, RB2, RC2, RD2); - - popq %r15; - FRAME_END - ret; -SYM_FUNC_END(cast6_xts_enc_8way) - -SYM_FUNC_START(cast6_xts_dec_8way) - /* input: - * %rdi: ctx, CTX - * %rsi: dst - * %rdx: src - * %rcx: iv (t ⊕ αⁿ ∈ GF(2¹²⁸)) - */ - FRAME_BEGIN - pushq %r15; - - movq %rdi, CTX - movq %rsi, %r11; - - /* regs <= src, dst <= IVs, regs <= regs xor IVs */ - load_xts_8way(%rcx, %rdx, %rsi, RA1, RB1, RC1, RD1, RA2, RB2, RC2, RD2, - RX, RKR, RKM, .Lxts_gf128mul_and_shl1_mask); - - call __cast6_dec_blk8; - - /* dst <= regs xor IVs(in dst) */ - store_xts_8way(%r11, RA1, RB1, RC1, RD1, RA2, RB2, RC2, RD2); - - popq %r15; - FRAME_END - ret; -SYM_FUNC_END(cast6_xts_dec_8way) diff --git a/arch/x86/crypto/cast6_avx_glue.c b/arch/x86/crypto/cast6_avx_glue.c index 48e0f37796fa..7e2aea372349 100644 --- a/arch/x86/crypto/cast6_avx_glue.c +++ b/arch/x86/crypto/cast6_avx_glue.c @@ -15,8 +15,8 @@ #include <crypto/algapi.h> #include <crypto/cast6.h> #include <crypto/internal/simd.h> -#include <crypto/xts.h> -#include <asm/crypto/glue_helper.h> + +#include "ecb_cbc_helpers.h" #define CAST6_PARALLEL_BLOCKS 8 @@ -24,13 +24,6 @@ asmlinkage void cast6_ecb_enc_8way(const void *ctx, u8 *dst, const u8 *src); asmlinkage void cast6_ecb_dec_8way(const void *ctx, u8 *dst, const u8 *src); asmlinkage void cast6_cbc_dec_8way(const void *ctx, u8 *dst, const u8 *src); -asmlinkage void cast6_ctr_8way(const void *ctx, u8 *dst, const u8 *src, - le128 *iv); - -asmlinkage void cast6_xts_enc_8way(const void *ctx, u8 *dst, const u8 *src, - le128 *iv); -asmlinkage void cast6_xts_dec_8way(const void *ctx, u8 *dst, const u8 *src, - le128 *iv); static int cast6_setkey_skcipher(struct crypto_skcipher *tfm, const u8 *key, unsigned int keylen) @@ -38,172 +31,35 @@ static int cast6_setkey_skcipher(struct crypto_skcipher *tfm, return cast6_setkey(&tfm->base, key, keylen); } -static void cast6_xts_enc(const void *ctx, u8 *dst, const u8 *src, le128 *iv) -{ - glue_xts_crypt_128bit_one(ctx, dst, src, iv, __cast6_encrypt); -} - -static void cast6_xts_dec(const void *ctx, u8 *dst, const u8 *src, le128 *iv) -{ - glue_xts_crypt_128bit_one(ctx, dst, src, iv, __cast6_decrypt); -} - -static void cast6_crypt_ctr(const void *ctx, u8 *d, const u8 *s, le128 *iv) -{ - be128 ctrblk; - u128 *dst = (u128 *)d; - const u128 *src = (const u128 *)s; - - le128_to_be128(&ctrblk, iv); - le128_inc(iv); - - __cast6_encrypt(ctx, (u8 *)&ctrblk, (u8 *)&ctrblk); - u128_xor(dst, src, (u128 *)&ctrblk); -} - -static const struct common_glue_ctx cast6_enc = { - .num_funcs = 2, - .fpu_blocks_limit = CAST6_PARALLEL_BLOCKS, - - .funcs = { { - .num_blocks = CAST6_PARALLEL_BLOCKS, - .fn_u = { .ecb = cast6_ecb_enc_8way } - }, { - .num_blocks = 1, - .fn_u = { .ecb = __cast6_encrypt } - } } -}; - -static const struct common_glue_ctx cast6_ctr = { - .num_funcs = 2, - .fpu_blocks_limit = CAST6_PARALLEL_BLOCKS, - - .funcs = { { - .num_blocks = CAST6_PARALLEL_BLOCKS, - .fn_u = { .ctr = cast6_ctr_8way } - }, { - .num_blocks = 1, - .fn_u = { .ctr = cast6_crypt_ctr } - } } -}; - -static const struct common_glue_ctx cast6_enc_xts = { - .num_funcs = 2, - .fpu_blocks_limit = CAST6_PARALLEL_BLOCKS, - - .funcs = { { - .num_blocks = CAST6_PARALLEL_BLOCKS, - .fn_u = { .xts = cast6_xts_enc_8way } - }, { - .num_blocks = 1, - .fn_u = { .xts = cast6_xts_enc } - } } -}; - -static const struct common_glue_ctx cast6_dec = { - .num_funcs = 2, - .fpu_blocks_limit = CAST6_PARALLEL_BLOCKS, - - .funcs = { { - .num_blocks = CAST6_PARALLEL_BLOCKS, - .fn_u = { .ecb = cast6_ecb_dec_8way } - }, { - .num_blocks = 1, - .fn_u = { .ecb = __cast6_decrypt } - } } -}; - -static const struct common_glue_ctx cast6_dec_cbc = { - .num_funcs = 2, - .fpu_blocks_limit = CAST6_PARALLEL_BLOCKS, - - .funcs = { { - .num_blocks = CAST6_PARALLEL_BLOCKS, - .fn_u = { .cbc = cast6_cbc_dec_8way } - }, { - .num_blocks = 1, - .fn_u = { .cbc = __cast6_decrypt } - } } -}; - -static const struct common_glue_ctx cast6_dec_xts = { - .num_funcs = 2, - .fpu_blocks_limit = CAST6_PARALLEL_BLOCKS, - - .funcs = { { - .num_blocks = CAST6_PARALLEL_BLOCKS, - .fn_u = { .xts = cast6_xts_dec_8way } - }, { - .num_blocks = 1, - .fn_u = { .xts = cast6_xts_dec } - } } -}; - static int ecb_encrypt(struct skcipher_request *req) { - return glue_ecb_req_128bit(&cast6_enc, req); + ECB_WALK_START(req, CAST6_BLOCK_SIZE, CAST6_PARALLEL_BLOCKS); + ECB_BLOCK(CAST6_PARALLEL_BLOCKS, cast6_ecb_enc_8way); + ECB_BLOCK(1, __cast6_encrypt); + ECB_WALK_END(); } static int ecb_decrypt(struct skcipher_request *req) { - return glue_ecb_req_128bit(&cast6_dec, req); + ECB_WALK_START(req, CAST6_BLOCK_SIZE, CAST6_PARALLEL_BLOCKS); + ECB_BLOCK(CAST6_PARALLEL_BLOCKS, cast6_ecb_dec_8way); + ECB_BLOCK(1, __cast6_decrypt); + ECB_WALK_END(); } static int cbc_encrypt(struct skcipher_request *req) { - return glue_cbc_encrypt_req_128bit(__cast6_encrypt, req); + CBC_WALK_START(req, CAST6_BLOCK_SIZE, -1); + CBC_ENC_BLOCK(__cast6_encrypt); + CBC_WALK_END(); } static int cbc_decrypt(struct skcipher_request *req) { - return glue_cbc_decrypt_req_128bit(&cast6_dec_cbc, req); -} - -static int ctr_crypt(struct skcipher_request *req) -{ - return glue_ctr_req_128bit(&cast6_ctr, req); -} - -struct cast6_xts_ctx { - struct cast6_ctx tweak_ctx; - struct cast6_ctx crypt_ctx; -}; - -static int xts_cast6_setkey(struct crypto_skcipher *tfm, const u8 *key, - unsigned int keylen) -{ - struct cast6_xts_ctx *ctx = crypto_skcipher_ctx(tfm); - int err; - - err = xts_verify_key(tfm, key, keylen); - if (err) - return err; - - /* first half of xts-key is for crypt */ - err = __cast6_setkey(&ctx->crypt_ctx, key, keylen / 2); - if (err) - return err; - - /* second half of xts-key is for tweak */ - return __cast6_setkey(&ctx->tweak_ctx, key + keylen / 2, keylen / 2); -} - -static int xts_encrypt(struct skcipher_request *req) -{ - struct crypto_skcipher *tfm = crypto_skcipher_reqtfm(req); - struct cast6_xts_ctx *ctx = crypto_skcipher_ctx(tfm); - - return glue_xts_req_128bit(&cast6_enc_xts, req, __cast6_encrypt, - &ctx->tweak_ctx, &ctx->crypt_ctx, false); -} - -static int xts_decrypt(struct skcipher_request *req) -{ - struct crypto_skcipher *tfm = crypto_skcipher_reqtfm(req); - struct cast6_xts_ctx *ctx = crypto_skcipher_ctx(tfm); - - return glue_xts_req_128bit(&cast6_dec_xts, req, __cast6_encrypt, - &ctx->tweak_ctx, &ctx->crypt_ctx, true); + CBC_WALK_START(req, CAST6_BLOCK_SIZE, CAST6_PARALLEL_BLOCKS); + CBC_DEC_BLOCK(CAST6_PARALLEL_BLOCKS, cast6_cbc_dec_8way); + CBC_DEC_BLOCK(1, __cast6_decrypt); + CBC_WALK_END(); } static struct skcipher_alg cast6_algs[] = { @@ -234,35 +90,6 @@ static struct skcipher_alg cast6_algs[] = { .setkey = cast6_setkey_skcipher, .encrypt = cbc_encrypt, .decrypt = cbc_decrypt, - }, { - .base.cra_name = "__ctr(cast6)", - .base.cra_driver_name = "__ctr-cast6-avx", - .base.cra_priority = 200, - .base.cra_flags = CRYPTO_ALG_INTERNAL, - .base.cra_blocksize = 1, - .base.cra_ctxsize = sizeof(struct cast6_ctx), - .base.cra_module = THIS_MODULE, - .min_keysize = CAST6_MIN_KEY_SIZE, - .max_keysize = CAST6_MAX_KEY_SIZE, - .ivsize = CAST6_BLOCK_SIZE, - .chunksize = CAST6_BLOCK_SIZE, - .setkey = cast6_setkey_skcipher, - .encrypt = ctr_crypt, - .decrypt = ctr_crypt, - }, { - .base.cra_name = "__xts(cast6)", - .base.cra_driver_name = "__xts-cast6-avx", - .base.cra_priority = 200, - .base.cra_flags = CRYPTO_ALG_INTERNAL, - .base.cra_blocksize = CAST6_BLOCK_SIZE, - .base.cra_ctxsize = sizeof(struct cast6_xts_ctx), - .base.cra_module = THIS_MODULE, - .min_keysize = 2 * CAST6_MIN_KEY_SIZE, - .max_keysize = 2 * CAST6_MAX_KEY_SIZE, - .ivsize = CAST6_BLOCK_SIZE, - .setkey = xts_cast6_setkey, - .encrypt = xts_encrypt, - .decrypt = xts_decrypt, }, }; diff --git a/arch/x86/crypto/des3_ede_glue.c b/arch/x86/crypto/des3_ede_glue.c index 89830e531350..e7cb68a3db3b 100644 --- a/arch/x86/crypto/des3_ede_glue.c +++ b/arch/x86/crypto/des3_ede_glue.c @@ -6,8 +6,6 @@ * * 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> */ #include <crypto/algapi.h> @@ -253,94 +251,6 @@ static int cbc_decrypt(struct skcipher_request *req) return err; } -static void ctr_crypt_final(struct des3_ede_x86_ctx *ctx, - struct skcipher_walk *walk) -{ - u8 *ctrblk = walk->iv; - u8 keystream[DES3_EDE_BLOCK_SIZE]; - u8 *src = walk->src.virt.addr; - u8 *dst = walk->dst.virt.addr; - unsigned int nbytes = walk->nbytes; - - des3_ede_enc_blk(ctx, keystream, ctrblk); - crypto_xor_cpy(dst, keystream, src, nbytes); - - crypto_inc(ctrblk, DES3_EDE_BLOCK_SIZE); -} - -static unsigned int __ctr_crypt(struct des3_ede_x86_ctx *ctx, - struct skcipher_walk *walk) -{ - unsigned int bsize = DES3_EDE_BLOCK_SIZE; - unsigned int nbytes = walk->nbytes; - __be64 *src = (__be64 *)walk->src.virt.addr; - __be64 *dst = (__be64 *)walk->dst.virt.addr; - u64 ctrblk = be64_to_cpu(*(__be64 *)walk->iv); - __be64 ctrblocks[3]; - - /* Process four block batch */ - if (nbytes >= bsize * 3) { - do { - /* create ctrblks for parallel encrypt */ - ctrblocks[0] = cpu_to_be64(ctrblk++); - ctrblocks[1] = cpu_to_be64(ctrblk++); - ctrblocks[2] = cpu_to_be64(ctrblk++); - - des3_ede_enc_blk_3way(ctx, (u8 *)ctrblocks, - (u8 *)ctrblocks); - - dst[0] = src[0] ^ ctrblocks[0]; - dst[1] = src[1] ^ ctrblocks[1]; - dst[2] = src[2] ^ ctrblocks[2]; - - src += 3; - dst += 3; - } while ((nbytes -= bsize * 3) >= bsize * 3); - - if (nbytes < bsize) - goto done; - } - - /* Handle leftovers */ - do { - ctrblocks[0] = cpu_to_be64(ctrblk++); - - des3_ede_enc_blk(ctx, (u8 *)ctrblocks, (u8 *)ctrblocks); - - dst[0] = src[0] ^ ctrblocks[0]; - - src += 1; - dst += 1; - } while ((nbytes -= bsize) >= bsize); - -done: - *(__be64 *)walk->iv = cpu_to_be64(ctrblk); - return nbytes; -} - -static int ctr_crypt(struct skcipher_request *req) -{ - struct crypto_skcipher *tfm = crypto_skcipher_reqtfm(req); - struct des3_ede_x86_ctx *ctx = crypto_skcipher_ctx(tfm); - struct skcipher_walk walk; - unsigned int nbytes; - int err; - - err = skcipher_walk_virt(&walk, req, false); - - while ((nbytes = walk.nbytes) >= DES3_EDE_BLOCK_SIZE) { - nbytes = __ctr_crypt(ctx, &walk); - err = skcipher_walk_done(&walk, nbytes); - } - - if (nbytes) { - ctr_crypt_final(ctx, &walk); - err = skcipher_walk_done(&walk, 0); - } - - return err; -} - static int des3_ede_x86_setkey(struct crypto_tfm *tfm, const u8 *key, unsigned int keylen) { @@ -428,20 +338,6 @@ static struct skcipher_alg des3_ede_skciphers[] = { .setkey = des3_ede_x86_setkey_skcipher, .encrypt = cbc_encrypt, .decrypt = cbc_decrypt, - }, { - .base.cra_name = "ctr(des3_ede)", - .base.cra_driver_name = "ctr-des3_ede-asm", - .base.cra_priority = 300, - .base.cra_blocksize = 1, - .base.cra_ctxsize = sizeof(struct des3_ede_x86_ctx), - .base.cra_module = THIS_MODULE, - .min_keysize = DES3_EDE_KEY_SIZE, - .max_keysize = DES3_EDE_KEY_SIZE, - .ivsize = DES3_EDE_BLOCK_SIZE, - .chunksize = DES3_EDE_BLOCK_SIZE, - .setkey = des3_ede_x86_setkey_skcipher, - .encrypt = ctr_crypt, - .decrypt = ctr_crypt, } }; diff --git a/arch/x86/crypto/ecb_cbc_helpers.h b/arch/x86/crypto/ecb_cbc_helpers.h new file mode 100644 index 000000000000..eaa15c7b29d6 --- /dev/null +++ b/arch/x86/crypto/ecb_cbc_helpers.h @@ -0,0 +1,76 @@ +/* SPDX-License-Identifier: GPL-2.0 */ + +#ifndef _CRYPTO_ECB_CBC_HELPER_H +#define _CRYPTO_ECB_CBC_HELPER_H + +#include <crypto/internal/skcipher.h> +#include <asm/fpu/api.h> + +/* + * Mode helpers to instantiate parameterized skcipher ECB/CBC modes without + * having to rely on indirect calls and retpolines. + */ + +#define ECB_WALK_START(req, bsize, fpu_blocks) do { \ + void *ctx = crypto_skcipher_ctx(crypto_skcipher_reqtfm(req)); \ + const int __bsize = (bsize); \ + struct skcipher_walk walk; \ + int err = skcipher_walk_virt(&walk, (req), false); \ + while (walk.nbytes > 0) { \ + unsigned int nbytes = walk.nbytes; \ + bool do_fpu = (fpu_blocks) != -1 && \ + nbytes >= (fpu_blocks) * __bsize; \ + const u8 *src = walk.src.virt.addr; \ + u8 *dst = walk.dst.virt.addr; \ + u8 __maybe_unused buf[(bsize)]; \ + if (do_fpu) kernel_fpu_begin() + +#define CBC_WALK_START(req, bsize, fpu_blocks) \ + ECB_WALK_START(req, bsize, fpu_blocks) + +#define ECB_WALK_ADVANCE(blocks) do { \ + dst += (blocks) * __bsize; \ + src += (blocks) * __bsize; \ + nbytes -= (blocks) * __bsize; \ +} while (0) + +#define ECB_BLOCK(blocks, func) do { \ + while (nbytes >= (blocks) * __bsize) { \ + (func)(ctx, dst, src); \ + ECB_WALK_ADVANCE(blocks); \ + } \ +} while (0) + +#define CBC_ENC_BLOCK(func) do { \ + const u8 *__iv = walk.iv; \ + while (nbytes >= __bsize) { \ + crypto_xor_cpy(dst, src, __iv, __bsize); \ + (func)(ctx, dst, dst); \ + __iv = dst; \ + ECB_WALK_ADVANCE(1); \ + } \ + memcpy(walk.iv, __iv, __bsize); \ +} while (0) + +#define CBC_DEC_BLOCK(blocks, func) do { \ + while (nbytes >= (blocks) * __bsize) { \ + const u8 *__iv = src + ((blocks) - 1) * __bsize; \ + if (dst == src) \ + __iv = memcpy(buf, __iv, __bsize); \ + (func)(ctx, dst, src); \ + crypto_xor(dst, walk.iv, __bsize); \ + memcpy(walk.iv, __iv, __bsize); \ + ECB_WALK_ADVANCE(blocks); \ + } \ +} while (0) + +#define ECB_WALK_END() \ + if (do_fpu) kernel_fpu_end(); \ + err = skcipher_walk_done(&walk, nbytes); \ + } \ + return err; \ +} while (0) + +#define CBC_WALK_END() ECB_WALK_END() + +#endif diff --git a/arch/x86/crypto/glue_helper-asm-avx.S b/arch/x86/crypto/glue_helper-asm-avx.S index d08fc575ef7f..3da385271227 100644 --- a/arch/x86/crypto/glue_helper-asm-avx.S +++ b/arch/x86/crypto/glue_helper-asm-avx.S @@ -34,107 +34,3 @@ vpxor (5*16)(src), x6, x6; \ vpxor (6*16)(src), x7, x7; \ store_8way(dst, x0, x1, x2, x3, x4, x5, x6, x7); - -#define inc_le128(x, minus_one, tmp) \ - vpcmpeqq minus_one, x, tmp; \ - vpsubq minus_one, x, x; \ - vpslldq $8, tmp, tmp; \ - vpsubq tmp, x, x; - -#define load_ctr_8way(iv, bswap, x0, x1, x2, x3, x4, x5, x6, x7, t0, t1, t2) \ - vpcmpeqd t0, t0, t0; \ - vpsrldq $8, t0, t0; /* low: -1, high: 0 */ \ - vmovdqa bswap, t1; \ - \ - /* load IV and byteswap */ \ - vmovdqu (iv), x7; \ - vpshufb t1, x7, x0; \ - \ - /* construct IVs */ \ - inc_le128(x7, t0, t2); \ - vpshufb t1, x7, x1; \ - inc_le128(x7, t0, t2); \ - vpshufb t1, x7, x2; \ - inc_le128(x7, t0, t2); \ - vpshufb t1, x7, x3; \ - inc_le128(x7, t0, t2); \ - vpshufb t1, x7, x4; \ - inc_le128(x7, t0, t2); \ - vpshufb t1, x7, x5; \ - inc_le128(x7, t0, t2); \ - vpshufb t1, x7, x6; \ - inc_le128(x7, t0, t2); \ - vmovdqa x7, t2; \ - vpshufb t1, x7, x7; \ - inc_le128(t2, t0, t1); \ - vmovdqu t2, (iv); - -#define store_ctr_8way(src, dst, x0, x1, x2, x3, x4, x5, x6, x7) \ - vpxor (0*16)(src), x0, x0; \ - vpxor (1*16)(src), x1, x1; \ - vpxor (2*16)(src), x2, x2; \ - vpxor (3*16)(src), x3, x3; \ - vpxor (4*16)(src), x4, x4; \ - vpxor (5*16)(src), x5, x5; \ - vpxor (6*16)(src), x6, x6; \ - vpxor (7*16)(src), x7, x7; \ - store_8way(dst, x0, x1, x2, x3, x4, x5, x6, x7); - -#define gf128mul_x_ble(iv, mask, tmp) \ - vpsrad $31, iv, tmp; \ - vpaddq iv, iv, iv; \ - vpshufd $0x13, tmp, tmp; \ - vpand mask, tmp, tmp; \ - vpxor tmp, iv, iv; - -#define load_xts_8way(iv, src, dst, x0, x1, x2, x3, x4, x5, x6, x7, tiv, t0, \ - t1, xts_gf128mul_and_shl1_mask) \ - vmovdqa xts_gf128mul_and_shl1_mask, t0; \ - \ - /* load IV */ \ - vmovdqu (iv), tiv; \ - vpxor (0*16)(src), tiv, x0; \ - vmovdqu tiv, (0*16)(dst); \ - \ - /* construct and store IVs, also xor with source */ \ - gf128mul_x_ble(tiv, t0, t1); \ - vpxor (1*16)(src), tiv, x1; \ - vmovdqu tiv, (1*16)(dst); \ - \ - gf128mul_x_ble(tiv, t0, t1); \ - vpxor (2*16)(src), tiv, x2; \ - vmovdqu tiv, (2*16)(dst); \ - \ - gf128mul_x_ble(tiv, t0, t1); \ - vpxor (3*16)(src), tiv, x3; \ - vmovdqu tiv, (3*16)(dst); \ - \ - gf128mul_x_ble(tiv, t0, t1); \ - vpxor (4*16)(src), tiv, x4; \ - vmovdqu tiv, (4*16)(dst); \ - \ - gf128mul_x_ble(tiv, t0, t1); \ - vpxor (5*16)(src), tiv, x5; \ - vmovdqu tiv, (5*16)(dst); \ - \ - gf128mul_x_ble(tiv, t0, t1); \ - vpxor (6*16)(src), tiv, x6; \ - vmovdqu tiv, (6*16)(dst); \ - \ - gf128mul_x_ble(tiv, t0, t1); \ - vpxor (7*16)(src), tiv, x7; \ - vmovdqu tiv, (7*16)(dst); \ - \ - gf128mul_x_ble(tiv, t0, t1); \ - vmovdqu tiv, (iv); - -#define store_xts_8way(dst, x0, x1, x2, x3, x4, x5, x6, x7) \ - vpxor (0*16)(dst), x0, x0; \ - vpxor (1*16)(dst), x1, x1; \ - vpxor (2*16)(dst), x2, x2; \ - vpxor (3*16)(dst), x3, x3; \ - vpxor (4*16)(dst), x4, x4; \ - vpxor (5*16)(dst), x5, x5; \ - vpxor (6*16)(dst), x6, x6; \ - vpxor (7*16)(dst), x7, x7; \ - store_8way(dst, x0, x1, x2, x3, x4, x5, x6, x7); diff --git a/arch/x86/crypto/glue_helper-asm-avx2.S b/arch/x86/crypto/glue_helper-asm-avx2.S index d84508c85c13..c77e9049431f 100644 --- a/arch/x86/crypto/glue_helper-asm-avx2.S +++ b/arch/x86/crypto/glue_helper-asm-avx2.S @@ -37,139 +37,3 @@ vpxor (5*32+16)(src), x6, x6; \ vpxor (6*32+16)(src), x7, x7; \ store_16way(dst, x0, x1, x2, x3, x4, x5, x6, x7); - -#define inc_le128(x, minus_one, tmp) \ - vpcmpeqq minus_one, x, tmp; \ - vpsubq minus_one, x, x; \ - vpslldq $8, tmp, tmp; \ - vpsubq tmp, x, x; - -#define add2_le128(x, minus_one, minus_two, tmp1, tmp2) \ - vpcmpeqq minus_one, x, tmp1; \ - vpcmpeqq minus_two, x, tmp2; \ - vpsubq minus_two, x, x; \ - vpor tmp2, tmp1, tmp1; \ - vpslldq $8, tmp1, tmp1; \ - vpsubq tmp1, x, x; - -#define load_ctr_16way(iv, bswap, x0, x1, x2, x3, x4, x5, x6, x7, t0, t0x, t1, \ - t1x, t2, t2x, t3, t3x, t4, t5) \ - vpcmpeqd t0, t0, t0; \ - vpsrldq $8, t0, t0; /* ab: -1:0 ; cd: -1:0 */ \ - vpaddq t0, t0, t4; /* ab: -2:0 ; cd: -2:0 */\ - \ - /* load IV and byteswap */ \ - vmovdqu (iv), t2x; \ - vmovdqa t2x, t3x; \ - inc_le128(t2x, t0x, t1x); \ - vbroadcasti128 bswap, t1; \ - vinserti128 $1, t2x, t3, t2; /* ab: le0 ; cd: le1 */ \ - vpshufb t1, t2, x0; \ - \ - /* construct IVs */ \ - add2_le128(t2, t0, t4, t3, t5); /* ab: le2 ; cd: le3 */ \ - vpshufb t1, t2, x1; \ - add2_le128(t2, t0, t4, t3, t5); \ - vpshufb t1, t2, x2; \ - add2_le128(t2, t0, t4, t3, t5); \ - vpshufb t1, t2, x3; \ - add2_le128(t2, t0, t4, t3, t5); \ - vpshufb t1, t2, x4; \ - add2_le128(t2, t0, t4, t3, t5); \ - vpshufb t1, t2, x5; \ - add2_le128(t2, t0, t4, t3, t5); \ - vpshufb t1, t2, x6; \ - add2_le128(t2, t0, t4, t3, t5); \ - vpshufb t1, t2, x7; \ - vextracti128 $1, t2, t2x; \ - inc_le128(t2x, t0x, t3x); \ - vmovdqu t2x, (iv); - -#define store_ctr_16way(src, dst, x0, x1, x2, x3, x4, x5, x6, x7) \ - vpxor (0*32)(src), x0, x0; \ - vpxor (1*32)(src), x1, x1; \ - vpxor (2*32)(src), x2, x2; \ - vpxor (3*32)(src), x3, x3; \ - vpxor (4*32)(src), x4, x4; \ - vpxor (5*32)(src), x5, x5; \ - vpxor (6*32)(src), x6, x6; \ - vpxor (7*32)(src), x7, x7; \ - store_16way(dst, x0, x1, x2, x3, x4, x5, x6, x7); - -#define gf128mul_x_ble(iv, mask, tmp) \ - vpsrad $31, iv, tmp; \ - vpaddq iv, iv, iv; \ - vpshufd $0x13, tmp, tmp; \ - vpand mask, tmp, tmp; \ - vpxor tmp, iv, iv; - -#define gf128mul_x2_ble(iv, mask1, mask2, tmp0, tmp1) \ - vpsrad $31, iv, tmp0; \ - vpaddq iv, iv, tmp1; \ - vpsllq $2, iv, iv; \ - vpshufd $0x13, tmp0, tmp0; \ - vpsrad $31, tmp1, tmp1; \ - vpand mask2, tmp0, tmp0; \ - vpshufd $0x13, tmp1, tmp1; \ - vpxor tmp0, iv, iv; \ - vpand mask1, tmp1, tmp1; \ - vpxor tmp1, iv, iv; - -#define load_xts_16way(iv, src, dst, x0, x1, x2, x3, x4, x5, x6, x7, tiv, \ - tivx, t0, t0x, t1, t1x, t2, t2x, t3, \ - xts_gf128mul_and_shl1_mask_0, \ - xts_gf128mul_and_shl1_mask_1) \ - vbroadcasti128 xts_gf128mul_and_shl1_mask_0, t1; \ - \ - /* load IV and construct second IV */ \ - vmovdqu (iv), tivx; \ - vmovdqa tivx, t0x; \ - gf128mul_x_ble(tivx, t1x, t2x); \ - vbroadcasti128 xts_gf128mul_and_shl1_mask_1, t2; \ - vinserti128 $1, tivx, t0, tiv; \ - vpxor (0*32)(src), tiv, x0; \ - vmovdqu tiv, (0*32)(dst); \ - \ - /* construct and store IVs, also xor with source */ \ - gf128mul_x2_ble(tiv, t1, t2, t0, t3); \ - vpxor (1*32)(src), tiv, x1; \ - vmovdqu tiv, (1*32)(dst); \ - \ - gf128mul_x2_ble(tiv, t1, t2, t0, t3); \ - vpxor (2*32)(src), tiv, x2; \ - vmovdqu tiv, (2*32)(dst); \ - \ - gf128mul_x2_ble(tiv, t1, t2, t0, t3); \ - vpxor (3*32)(src), tiv, x3; \ - vmovdqu tiv, (3*32)(dst); \ - \ - gf128mul_x2_ble(tiv, t1, t2, t0, t3); \ - vpxor (4*32)(src), tiv, x4; \ - vmovdqu tiv, (4*32)(dst); \ - \ - gf128mul_x2_ble(tiv, t1, t2, t0, t3); \ - vpxor (5*32)(src), tiv, x5; \ - vmovdqu tiv, (5*32)(dst); \ - \ - gf128mul_x2_ble(tiv, t1, t2, t0, t3); \ - vpxor (6*32)(src), tiv, x6; \ - vmovdqu tiv, (6*32)(dst); \ - \ - gf128mul_x2_ble(tiv, t1, t2, t0, t3); \ - vpxor (7*32)(src), tiv, x7; \ - vmovdqu tiv, (7*32)(dst); \ - \ - vextracti128 $1, tiv, tivx; \ - gf128mul_x_ble(tivx, t1x, t2x); \ - vmovdqu tivx, (iv); - -#define store_xts_16way(dst, x0, x1, x2, x3, x4, x5, x6, x7) \ - vpxor (0*32)(dst), x0, x0; \ - vpxor (1*32)(dst), x1, x1; \ - vpxor (2*32)(dst), x2, x2; \ - vpxor (3*32)(dst), x3, x3; \ - vpxor (4*32)(dst), x4, x4; \ - vpxor (5*32)(dst), x5, x5; \ - vpxor (6*32)(dst), x6, x6; \ - vpxor (7*32)(dst), x7, x7; \ - store_16way(dst, x0, x1, x2, x3, x4, x5, x6, x7); diff --git a/arch/x86/crypto/glue_helper.c b/arch/x86/crypto/glue_helper.c deleted file mode 100644 index d3d91a0abf88..000000000000 --- a/arch/x86/crypto/glue_helper.c +++ /dev/null @@ -1,381 +0,0 @@ -// SPDX-License-Identifier: GPL-2.0-or-later -/* - * Shared glue code for 128bit block ciphers - * - * Copyright © 2012-2013 Jussi Kivilinna <jussi.kivilinna@iki.fi> - * - * 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> - */ - -#include <linux/module.h> -#include <crypto/b128ops.h> -#include <crypto/gf128mul.h> -#include <crypto/internal/skcipher.h> -#include <crypto/scatterwalk.h> -#include <crypto/xts.h> -#include <asm/crypto/glue_helper.h> - -int glue_ecb_req_128bit(const struct common_glue_ctx *gctx, - struct skcipher_request *req) -{ - void *ctx = crypto_skcipher_ctx(crypto_skcipher_reqtfm(req)); - const unsigned int bsize = 128 / 8; - struct skcipher_walk walk; - bool fpu_enabled = false; - unsigned int nbytes; - int err; - - err = skcipher_walk_virt(&walk, req, false); - - while ((nbytes = walk.nbytes)) { - const u8 *src = walk.src.virt.addr; - u8 *dst = walk.dst.virt.addr; - unsigned int func_bytes; - unsigned int i; - - fpu_enabled = glue_fpu_begin(bsize, gctx->fpu_blocks_limit, - &walk, fpu_enabled, nbytes); - for (i = 0; i < gctx->num_funcs; i++) { - func_bytes = bsize * gctx->funcs[i].num_blocks; - - if (nbytes < func_bytes) - continue; - - /* Process multi-block batch */ - do { - gctx->funcs[i].fn_u.ecb(ctx, dst, src); - src += func_bytes; - dst += func_bytes; - nbytes -= func_bytes; - } while (nbytes >= func_bytes); - - if (nbytes < bsize) - break; - } - err = skcipher_walk_done(&walk, nbytes); - } - - glue_fpu_end(fpu_enabled); - return err; -} -EXPORT_SYMBOL_GPL(glue_ecb_req_128bit); - -int glue_cbc_encrypt_req_128bit(const common_glue_func_t fn, - struct skcipher_request *req) -{ - void *ctx = crypto_skcipher_ctx(crypto_skcipher_reqtfm(req)); - const unsigned int bsize = 128 / 8; - struct skcipher_walk walk; - unsigned int nbytes; - int err; - - err = skcipher_walk_virt(&walk, req, false); - - while ((nbytes = walk.nbytes)) { - const 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); - fn(ctx, (u8 *)dst, (u8 *)dst); - iv = dst; - src++; - dst++; - nbytes -= bsize; - } while (nbytes >= bsize); - - *(u128 *)walk.iv = *iv; - err = skcipher_walk_done(&walk, nbytes); - } - return err; -} -EXPORT_SYMBOL_GPL(glue_cbc_encrypt_req_128bit); - -int glue_cbc_decrypt_req_128bit(const struct common_glue_ctx *gctx, - struct skcipher_request *req) -{ - void *ctx = crypto_skcipher_ctx(crypto_skcipher_reqtfm(req)); - const unsigned int bsize = 128 / 8; - struct skcipher_walk walk; - bool fpu_enabled = false; - unsigned int nbytes; - int err; - - err = skcipher_walk_virt(&walk, req, false); - - while ((nbytes = walk.nbytes)) { - const u128 *src = walk.src.virt.addr; - u128 *dst = walk.dst.virt.addr; - unsigned int func_bytes, num_blocks; - unsigned int i; - u128 last_iv; - - fpu_enabled = glue_fpu_begin(bsize, gctx->fpu_blocks_limit, - &walk, fpu_enabled, nbytes); - /* Start of the last block. */ - src += nbytes / bsize - 1; - dst += nbytes / bsize - 1; - - last_iv = *src; - - for (i = 0; i < gctx->num_funcs; i++) { - num_blocks = gctx->funcs[i].num_blocks; - func_bytes = bsize * num_blocks; - - if (nbytes < func_bytes) - continue; - - /* Process multi-block batch */ - do { - src -= num_blocks - 1; - dst -= num_blocks - 1; - - gctx->funcs[i].fn_u.cbc(ctx, (u8 *)dst, - (const u8 *)src); - - nbytes -= func_bytes; - if (nbytes < bsize) - goto done; - - u128_xor(dst, dst, --src); - dst--; - } while (nbytes >= func_bytes); - } -done: - u128_xor(dst, dst, (u128 *)walk.iv); - *(u128 *)walk.iv = last_iv; - err = skcipher_walk_done(&walk, nbytes); - } - - glue_fpu_end(fpu_enabled); - return err; -} -EXPORT_SYMBOL_GPL(glue_cbc_decrypt_req_128bit); - -int glue_ctr_req_128bit(const struct common_glue_ctx *gctx, - struct skcipher_request *req) -{ - void *ctx = crypto_skcipher_ctx(crypto_skcipher_reqtfm(req)); - const unsigned int bsize = 128 / 8; - struct skcipher_walk walk; - bool fpu_enabled = false; - unsigned int nbytes; - int err; - - err = skcipher_walk_virt(&walk, req, false); - - while ((nbytes = walk.nbytes) >= bsize) { - const u128 *src = walk.src.virt.addr; - u128 *dst = walk.dst.virt.addr; - unsigned int func_bytes, num_blocks; - unsigned int i; - le128 ctrblk; - - fpu_enabled = glue_fpu_begin(bsize, gctx->fpu_blocks_limit, - &walk, fpu_enabled, nbytes); - - be128_to_le128(&ctrblk, (be128 *)walk.iv); - - for (i = 0; i < gctx->num_funcs; i++) { - num_blocks = gctx->funcs[i].num_blocks; - func_bytes = bsize * num_blocks; - - if (nbytes < func_bytes) - continue; - - /* Process multi-block batch */ - do { - gctx->funcs[i].fn_u.ctr(ctx, (u8 *)dst, - (const u8 *)src, - &ctrblk); - src += num_blocks; - dst += num_blocks; - nbytes -= func_bytes; - } while (nbytes >= func_bytes); - - if (nbytes < bsize) - break; - } - - le128_to_be128((be128 *)walk.iv, &ctrblk); - err = skcipher_walk_done(&walk, nbytes); - } - - glue_fpu_end(fpu_enabled); - - if (nbytes) { - le128 ctrblk; - u128 tmp; - - be128_to_le128(&ctrblk, (be128 *)walk.iv); - memcpy(&tmp, walk.src.virt.addr, nbytes); - gctx->funcs[gctx->num_funcs - 1].fn_u.ctr(ctx, (u8 *)&tmp, - (const u8 *)&tmp, - &ctrblk); - memcpy(walk.dst.virt.addr, &tmp, nbytes); - le128_to_be128((be128 *)walk.iv, &ctrblk); - - err = skcipher_walk_done(&walk, 0); - } - - return err; -} -EXPORT_SYMBOL_GPL(glue_ctr_req_128bit); - -static unsigned int __glue_xts_req_128bit(const struct common_glue_ctx *gctx, - void *ctx, - struct skcipher_walk *walk) -{ - const unsigned int bsize = 128 / 8; - unsigned int nbytes = walk->nbytes; - u128 *src = walk->src.virt.addr; - u128 *dst = walk->dst.virt.addr; - unsigned int num_blocks, func_bytes; - unsigned int i; - - /* Process multi-block batch */ - for (i = 0; i < gctx->num_funcs; i++) { - num_blocks = gctx->funcs[i].num_blocks; - func_bytes = bsize * num_blocks; - - if (nbytes >= func_bytes) { - do { - gctx->funcs[i].fn_u.xts(ctx, (u8 *)dst, - (const u8 *)src, - walk->iv); - - src += num_blocks; - dst += num_blocks; - nbytes -= func_bytes; - } while (nbytes >= func_bytes); - - if (nbytes < bsize) - goto done; - } - } - -done: - return nbytes; -} - -int glue_xts_req_128bit(const struct common_glue_ctx *gctx, - struct skcipher_request *req, - common_glue_func_t tweak_fn, void *tweak_ctx, - void *crypt_ctx, bool decrypt) -{ - const bool cts = (req->cryptlen % XTS_BLOCK_SIZE); - const unsigned int bsize = 128 / 8; - struct skcipher_request subreq; - struct skcipher_walk walk; - bool fpu_enabled = false; - unsigned int nbytes, tail; - int err; - - if (req->cryptlen < XTS_BLOCK_SIZE) - return -EINVAL; - - if (unlikely(cts)) { - struct crypto_skcipher *tfm = crypto_skcipher_reqtfm(req); - - tail = req->cryptlen % XTS_BLOCK_SIZE + XTS_BLOCK_SIZE; - - skcipher_request_set_tfm(&subreq, tfm); - skcipher_request_set_callback(&subreq, - crypto_skcipher_get_flags(tfm), - NULL, NULL); - skcipher_request_set_crypt(&subreq, req->src, req->dst, - req->cryptlen - tail, req->iv); - req = &subreq; - } - - err = skcipher_walk_virt(&walk, req, false); - nbytes = walk.nbytes; - if (err) - return err; - - /* set minimum length to bsize, for tweak_fn */ - fpu_enabled = glue_fpu_begin(bsize, gctx->fpu_blocks_limit, - &walk, fpu_enabled, - nbytes < bsize ? bsize : nbytes); - - /* calculate first value of T */ - tweak_fn(tweak_ctx, walk.iv, walk.iv); - - while (nbytes) { - nbytes = __glue_xts_req_128bit(gctx, crypt_ctx, &walk); - - err = skcipher_walk_done(&walk, nbytes); - nbytes = walk.nbytes; - } - - if (unlikely(cts)) { - u8 *next_tweak, *final_tweak = req->iv; - struct scatterlist *src, *dst; - struct scatterlist s[2], d[2]; - le128 b[2]; - - dst = src = scatterwalk_ffwd(s, req->src, req->cryptlen); - if (req->dst != req->src) - dst = scatterwalk_ffwd(d, req->dst, req->cryptlen); - - if (decrypt) { - next_tweak = memcpy(b, req->iv, XTS_BLOCK_SIZE); - gf128mul_x_ble(b, b); - } else { - next_tweak = req->iv; - } - - skcipher_request_set_crypt(&subreq, src, dst, XTS_BLOCK_SIZE, - next_tweak); - - err = skcipher_walk_virt(&walk, req, false) ?: - skcipher_walk_done(&walk, - __glue_xts_req_128bit(gctx, crypt_ctx, &walk)); - if (err) - goto out; - - scatterwalk_map_and_copy(b, dst, 0, XTS_BLOCK_SIZE, 0); - memcpy(b + 1, b, tail - XTS_BLOCK_SIZE); - scatterwalk_map_and_copy(b, src, XTS_BLOCK_SIZE, - tail - XTS_BLOCK_SIZE, 0); - scatterwalk_map_and_copy(b, dst, 0, tail, 1); - - skcipher_request_set_crypt(&subreq, dst, dst, XTS_BLOCK_SIZE, - final_tweak); - - err = skcipher_walk_virt(&walk, req, false) ?: - skcipher_walk_done(&walk, - __glue_xts_req_128bit(gctx, crypt_ctx, &walk)); - } - -out: - glue_fpu_end(fpu_enabled); - - return err; -} -EXPORT_SYMBOL_GPL(glue_xts_req_128bit); - -void glue_xts_crypt_128bit_one(const void *ctx, u8 *dst, const u8 *src, - le128 *iv, common_glue_func_t fn) -{ - le128 ivblk = *iv; - - /* generate next IV */ - gf128mul_x_ble(iv, &ivblk); - - /* CC <- T xor C */ - u128_xor((u128 *)dst, (const u128 *)src, (u128 *)&ivblk); - - /* PP <- D(Key2,CC) */ - fn(ctx, dst, dst); - - /* P <- T xor PP */ - u128_xor((u128 *)dst, (u128 *)dst, (u128 *)&ivblk); -} -EXPORT_SYMBOL_GPL(glue_xts_crypt_128bit_one); - -MODULE_LICENSE("GPL"); diff --git a/arch/x86/crypto/serpent-avx-x86_64-asm_64.S b/arch/x86/crypto/serpent-avx-x86_64-asm_64.S index ba9e4c1e7f5c..b7ee24df7fba 100644 --- a/arch/x86/crypto/serpent-avx-x86_64-asm_64.S +++ b/arch/x86/crypto/serpent-avx-x86_64-asm_64.S @@ -18,10 +18,6 @@ .align 16 .Lbswap128_mask: .byte 15, 14, 13, 12, 11, 10, 9, 8, 7, 6, 5, 4, 3, 2, 1, 0 -.section .rodata.cst16.xts_gf128mul_and_shl1_mask, "aM", @progbits, 16 -.align 16 -.Lxts_gf128mul_and_shl1_mask: - .byte 0x87, 0, 0, 0, 0, 0, 0, 0, 1, 0, 0, 0, 0, 0, 0, 0 .text @@ -715,67 +711,3 @@ SYM_FUNC_START(serpent_cbc_dec_8way_avx) FRAME_END ret; SYM_FUNC_END(serpent_cbc_dec_8way_avx) - -SYM_FUNC_START(serpent_ctr_8way_avx) - /* input: - * %rdi: ctx, CTX - * %rsi: dst - * %rdx: src - * %rcx: iv (little endian, 128bit) - */ - FRAME_BEGIN - - load_ctr_8way(%rcx, .Lbswap128_mask, RA1, RB1, RC1, RD1, RA2, RB2, RC2, - RD2, RK0, RK1, RK2); - - call __serpent_enc_blk8_avx; - - store_ctr_8way(%rdx, %rsi, RA1, RB1, RC1, RD1, RA2, RB2, RC2, RD2); - - FRAME_END - ret; -SYM_FUNC_END(serpent_ctr_8way_avx) - -SYM_FUNC_START(serpent_xts_enc_8way_avx) - /* input: - * %rdi: ctx, CTX - * %rsi: dst - * %rdx: src - * %rcx: iv (t ⊕ αⁿ ∈ GF(2¹²⁸)) - */ - FRAME_BEGIN - - /* regs <= src, dst <= IVs, regs <= regs xor IVs */ - load_xts_8way(%rcx, %rdx, %rsi, RA1, RB1, RC1, RD1, RA2, RB2, RC2, RD2, - RK0, RK1, RK2, .Lxts_gf128mul_and_shl1_mask); - - call __serpent_enc_blk8_avx; - - /* dst <= regs xor IVs(in dst) */ - store_xts_8way(%rsi, RA1, RB1, RC1, RD1, RA2, RB2, RC2, RD2); - - FRAME_END - ret; -SYM_FUNC_END(serpent_xts_enc_8way_avx) - -SYM_FUNC_START(serpent_xts_dec_8way_avx) - /* input: - * %rdi: ctx, CTX - * %rsi: dst - * %rdx: src - * %rcx: iv (t ⊕ αⁿ ∈ GF(2¹²⁸)) - */ - FRAME_BEGIN - - /* regs <= src, dst <= IVs, regs <= regs xor IVs */ - load_xts_8way(%rcx, %rdx, %rsi, RA1, RB1, RC1, RD1, RA2, RB2, RC2, RD2, - RK0, RK1, RK2, .Lxts_gf128mul_and_shl1_mask); - - call __serpent_dec_blk8_avx; - - /* dst <= regs xor IVs(in dst) */ - store_xts_8way(%rsi, RC1, RD1, RB1, RE1, RC2, RD2, RB2, RE2); - - FRAME_END - ret; -SYM_FUNC_END(serpent_xts_dec_8way_avx) diff --git a/arch/x86/crypto/serpent-avx.h b/arch/x86/crypto/serpent-avx.h new file mode 100644 index 000000000000..23f3361a0e72 --- /dev/null +++ b/arch/x86/crypto/serpent-avx.h @@ -0,0 +1,21 @@ +/* SPDX-License-Identifier: GPL-2.0 */ +#ifndef ASM_X86_SERPENT_AVX_H +#define ASM_X86_SERPENT_AVX_H + +#include <crypto/b128ops.h> +#include <crypto/serpent.h> +#include <linux/types.h> + +struct crypto_skcipher; + +#define SERPENT_PARALLEL_BLOCKS 8 + +asmlinkage void serpent_ecb_enc_8way_avx(const void *ctx, u8 *dst, + const u8 *src); +asmlinkage void serpent_ecb_dec_8way_avx(const void *ctx, u8 *dst, + const u8 *src); + +asmlinkage void serpent_cbc_dec_8way_avx(const void *ctx, u8 *dst, + const u8 *src); + +#endif diff --git a/arch/x86/crypto/serpent-avx2-asm_64.S b/arch/x86/crypto/serpent-avx2-asm_64.S index c9648aeae705..9161b6e441f3 100644 --- a/arch/x86/crypto/serpent-avx2-asm_64.S +++ b/arch/x86/crypto/serpent-avx2-asm_64.S @@ -20,16 +20,6 @@ .Lbswap128_mask: .byte 15, 14, 13, 12, 11, 10, 9, 8, 7, 6, 5, 4, 3, 2, 1, 0 -.section .rodata.cst16.xts_gf128mul_and_shl1_mask_0, "aM", @progbits, 16 -.align 16 -.Lxts_gf128mul_and_shl1_mask_0: - .byte 0x87, 0, 0, 0, 0, 0, 0, 0, 1, 0, 0, 0, 0, 0, 0, 0 - -.section .rodata.cst16.xts_gf128mul_and_shl1_mask_1, "aM", @progbits, 16 -.align 16 -.Lxts_gf128mul_and_shl1_mask_1: - .byte 0x0e, 1, 0, 0, 0, 0, 0, 0, 2, 0, 0, 0, 0, 0, 0, 0 - .text #define CTX %rdi @@ -734,80 +724,3 @@ SYM_FUNC_START(serpent_cbc_dec_16way) FRAME_END ret; SYM_FUNC_END(serpent_cbc_dec_16way) - -SYM_FUNC_START(serpent_ctr_16way) - /* input: - * %rdi: ctx, CTX - * %rsi: dst (16 blocks) - * %rdx: src (16 blocks) - * %rcx: iv (little endian, 128bit) - */ - FRAME_BEGIN - - vzeroupper; - - load_ctr_16way(%rcx, .Lbswap128_mask, RA1, RB1, RC1, RD1, RA2, RB2, RC2, - RD2, RK0, RK0x, RK1, RK1x, RK2, RK2x, RK3, RK3x, RNOT, - tp); - - call __serpent_enc_blk16; - - store_ctr_16way(%rdx, %rsi, RA1, RB1, RC1, RD1, RA2, RB2, RC2, RD2); - - vzeroupper; - - FRAME_END - ret; -SYM_FUNC_END(serpent_ctr_16way) - -SYM_FUNC_START(serpent_xts_enc_16way) - /* input: - * %rdi: ctx, CTX - * %rsi: dst (16 blocks) - * %rdx: src (16 blocks) - * %rcx: iv (t ⊕ αⁿ ∈ GF(2¹²⁸)) - */ - FRAME_BEGIN - - vzeroupper; - - load_xts_16way(%rcx, %rdx, %rsi, RA1, RB1, RC1, RD1, RA2, RB2, RC2, - RD2, RK0, RK0x, RK1, RK1x, RK2, RK2x, RK3, RK3x, RNOT, - .Lxts_gf128mul_and_shl1_mask_0, - .Lxts_gf128mul_and_shl1_mask_1); - - call __serpent_enc_blk16; - - store_xts_16way(%rsi, RA1, RB1, RC1, RD1, RA2, RB2, RC2, RD2); - - vzeroupper; - - FRAME_END - ret; -SYM_FUNC_END(serpent_xts_enc_16way) - -SYM_FUNC_START(serpent_xts_dec_16way) - /* input: - * %rdi: ctx, CTX - * %rsi: dst (16 blocks) - * %rdx: src (16 blocks) - * %rcx: iv (t ⊕ αⁿ ∈ GF(2¹²⁸)) - */ - FRAME_BEGIN - - vzeroupper; - - load_xts_16way(%rcx, %rdx, %rsi, RA1, RB1, RC1, RD1, RA2, RB2, RC2, - RD2, RK0, RK0x, RK1, RK1x, RK2, RK2x, RK3, RK3x, RNOT, - .Lxts_gf128mul_and_shl1_mask_0, - .Lxts_gf128mul_and_shl1_mask_1); - - call __serpent_dec_blk16; - - store_xts_16way(%rsi, RC1, RD1, RB1, RE1, RC2, RD2, RB2, RE2); - - vzeroupper; - - FRAME_END - ret; -SYM_FUNC_END(serpent_xts_dec_16way) diff --git a/arch/x86/include/asm/crypto/serpent-sse2.h b/arch/x86/crypto/serpent-sse2.h index 860ca248914b..860ca248914b 100644 --- a/arch/x86/include/asm/crypto/serpent-sse2.h +++ b/arch/x86/crypto/serpent-sse2.h diff --git a/arch/x86/crypto/serpent_avx2_glue.c b/arch/x86/crypto/serpent_avx2_glue.c index f973ace44ad3..ccf0b5fa4933 100644 --- a/arch/x86/crypto/serpent_avx2_glue.c +++ b/arch/x86/crypto/serpent_avx2_glue.c @@ -12,9 +12,9 @@ #include <crypto/algapi.h> #include <crypto/internal/simd.h> #include <crypto/serpent.h> -#include <crypto/xts.h> -#include <asm/crypto/glue_helper.h> -#include <asm/crypto/serpent-avx.h> + +#include "serpent-avx.h" +#include "ecb_cbc_helpers.h" #define SERPENT_AVX2_PARALLEL_BLOCKS 16 @@ -23,158 +23,44 @@ asmlinkage void serpent_ecb_enc_16way(const void *ctx, u8 *dst, const u8 *src); asmlinkage void serpent_ecb_dec_16way(const void *ctx, u8 *dst, const u8 *src); asmlinkage void serpent_cbc_dec_16way(const void *ctx, u8 *dst, const u8 *src); -asmlinkage void serpent_ctr_16way(const void *ctx, u8 *dst, const u8 *src, - le128 *iv); -asmlinkage void serpent_xts_enc_16way(const void *ctx, u8 *dst, const u8 *src, - le128 *iv); -asmlinkage void serpent_xts_dec_16way(const void *ctx, u8 *dst, const u8 *src, - le128 *iv); - static int serpent_setkey_skcipher(struct crypto_skcipher *tfm, const u8 *key, unsigned int keylen) { return __serpent_setkey(crypto_skcipher_ctx(tfm), key, keylen); } -static const struct common_glue_ctx serpent_enc = { - .num_funcs = 3, - .fpu_blocks_limit = 8, - - .funcs = { { - .num_blocks = 16, - .fn_u = { .ecb = serpent_ecb_enc_16way } - }, { - .num_blocks = 8, - .fn_u = { .ecb = serpent_ecb_enc_8way_avx } - }, { - .num_blocks = 1, - .fn_u = { .ecb = __serpent_encrypt } - } } -}; - -static const struct common_glue_ctx serpent_ctr = { - .num_funcs = 3, - .fpu_blocks_limit = 8, - - .funcs = { { - .num_blocks = 16, - .fn_u = { .ctr = serpent_ctr_16way } - }, { - .num_blocks = 8, - .fn_u = { .ctr = serpent_ctr_8way_avx } - }, { - .num_blocks = 1, - .fn_u = { .ctr = __serpent_crypt_ctr } - } } -}; - -static const struct common_glue_ctx serpent_enc_xts = { - .num_funcs = 3, - .fpu_blocks_limit = 8, - - .funcs = { { - .num_blocks = 16, - .fn_u = { .xts = serpent_xts_enc_16way } - }, { - .num_blocks = 8, - .fn_u = { .xts = serpent_xts_enc_8way_avx } - }, { - .num_blocks = 1, - .fn_u = { .xts = serpent_xts_enc } - } } -}; - -static const struct common_glue_ctx serpent_dec = { - .num_funcs = 3, - .fpu_blocks_limit = 8, - - .funcs = { { - .num_blocks = 16, - .fn_u = { .ecb = serpent_ecb_dec_16way } - }, { - .num_blocks = 8, - .fn_u = { .ecb = serpent_ecb_dec_8way_avx } - }, { - .num_blocks = 1, - .fn_u = { .ecb = __serpent_decrypt } - } } -}; - -static const struct common_glue_ctx serpent_dec_cbc = { - .num_funcs = 3, - .fpu_blocks_limit = 8, - - .funcs = { { - .num_blocks = 16, - .fn_u = { .cbc = serpent_cbc_dec_16way } - }, { - .num_blocks = 8, - .fn_u = { .cbc = serpent_cbc_dec_8way_avx } - }, { - .num_blocks = 1, - .fn_u = { .cbc = __serpent_decrypt } - } } -}; - -static const struct common_glue_ctx serpent_dec_xts = { - .num_funcs = 3, - .fpu_blocks_limit = 8, - - .funcs = { { - .num_blocks = 16, - .fn_u = { .xts = serpent_xts_dec_16way } - }, { - .num_blocks = 8, - .fn_u = { .xts = serpent_xts_dec_8way_avx } - }, { - .num_blocks = 1, - .fn_u = { .xts = serpent_xts_dec } - } } -}; - static int ecb_encrypt(struct skcipher_request *req) { - return glue_ecb_req_128bit(&serpent_enc, req); + ECB_WALK_START(req, SERPENT_BLOCK_SIZE, SERPENT_PARALLEL_BLOCKS); + ECB_BLOCK(SERPENT_AVX2_PARALLEL_BLOCKS, serpent_ecb_enc_16way); + ECB_BLOCK(SERPENT_PARALLEL_BLOCKS, serpent_ecb_enc_8way_avx); + ECB_BLOCK(1, __serpent_encrypt); + ECB_WALK_END(); } static int ecb_decrypt(struct skcipher_request *req) { - return glue_ecb_req_128bit(&serpent_dec, req); + ECB_WALK_START(req, SERPENT_BLOCK_SIZE, SERPENT_PARALLEL_BLOCKS); + ECB_BLOCK(SERPENT_AVX2_PARALLEL_BLOCKS, serpent_ecb_dec_16way); + ECB_BLOCK(SERPENT_PARALLEL_BLOCKS, serpent_ecb_dec_8way_avx); + ECB_BLOCK(1, __serpent_decrypt); + ECB_WALK_END(); } static int cbc_encrypt(struct skcipher_request *req) { - return glue_cbc_encrypt_req_128bit(__serpent_encrypt, req); + CBC_WALK_START(req, SERPENT_BLOCK_SIZE, -1); + CBC_ENC_BLOCK(__serpent_encrypt); + CBC_WALK_END(); } static int cbc_decrypt(struct skcipher_request *req) { - return glue_cbc_decrypt_req_128bit(&serpent_dec_cbc, req); -} - -static int ctr_crypt(struct skcipher_request *req) -{ - return glue_ctr_req_128bit(&serpent_ctr, req); -} - -static int xts_encrypt(struct skcipher_request *req) -{ - struct crypto_skcipher *tfm = crypto_skcipher_reqtfm(req); - struct serpent_xts_ctx *ctx = crypto_skcipher_ctx(tfm); - - return glue_xts_req_128bit(&serpent_enc_xts, req, - __serpent_encrypt, &ctx->tweak_ctx, - &ctx->crypt_ctx, false); -} - -static int xts_decrypt(struct skcipher_request *req) -{ - struct crypto_skcipher *tfm = crypto_skcipher_reqtfm(req); - struct serpent_xts_ctx *ctx = crypto_skcipher_ctx(tfm); - - return glue_xts_req_128bit(&serpent_dec_xts, req, - __serpent_encrypt, &ctx->tweak_ctx, - &ctx->crypt_ctx, true); + CBC_WALK_START(req, SERPENT_BLOCK_SIZE, SERPENT_PARALLEL_BLOCKS); + CBC_DEC_BLOCK(SERPENT_AVX2_PARALLEL_BLOCKS, serpent_cbc_dec_16way); + CBC_DEC_BLOCK(SERPENT_PARALLEL_BLOCKS, serpent_cbc_dec_8way_avx); + CBC_DEC_BLOCK(1, __serpent_decrypt); + CBC_WALK_END(); } static struct skcipher_alg serpent_algs[] = { @@ -205,35 +91,6 @@ static struct skcipher_alg serpent_algs[] = { .setkey = serpent_setkey_skcipher, .encrypt = cbc_encrypt, .decrypt = cbc_decrypt, - }, { - .base.cra_name = "__ctr(serpent)", - .base.cra_driver_name = "__ctr-serpent-avx2", - .base.cra_priority = 600, - .base.cra_flags = CRYPTO_ALG_INTERNAL, - .base.cra_blocksize = 1, - .base.cra_ctxsize = sizeof(struct serpent_ctx), - .base.cra_module = THIS_MODULE, - .min_keysize = SERPENT_MIN_KEY_SIZE, - .max_keysize = SERPENT_MAX_KEY_SIZE, - .ivsize = SERPENT_BLOCK_SIZE, - .chunksize = SERPENT_BLOCK_SIZE, - .setkey = serpent_setkey_skcipher, - .encrypt = ctr_crypt, - .decrypt = ctr_crypt, - }, { - .base.cra_name = "__xts(serpent)", - .base.cra_driver_name = "__xts-serpent-avx2", - .base.cra_priority = 600, - .base.cra_flags = CRYPTO_ALG_INTERNAL, - .base.cra_blocksize = SERPENT_BLOCK_SIZE, - .base.cra_ctxsize = sizeof(struct serpent_xts_ctx), - .base.cra_module = THIS_MODULE, - .min_keysize = 2 * SERPENT_MIN_KEY_SIZE, - .max_keysize = 2 * SERPENT_MAX_KEY_SIZE, - .ivsize = SERPENT_BLOCK_SIZE, - .setkey = xts_serpent_setkey, - .encrypt = xts_encrypt, - .decrypt = xts_decrypt, }, }; diff --git a/arch/x86/crypto/serpent_avx_glue.c b/arch/x86/crypto/serpent_avx_glue.c index 7806d1cbe854..6c248e1ea4ef 100644 --- a/arch/x86/crypto/serpent_avx_glue.c +++ b/arch/x86/crypto/serpent_avx_glue.c @@ -15,9 +15,9 @@ #include <crypto/algapi.h> #include <crypto/internal/simd.h> #include <crypto/serpent.h> -#include <crypto/xts.h> -#include <asm/crypto/glue_helper.h> -#include <asm/crypto/serpent-avx.h> + +#include "serpent-avx.h" +#include "ecb_cbc_helpers.h" /* 8-way parallel cipher functions */ asmlinkage void serpent_ecb_enc_8way_avx(const void *ctx, u8 *dst, @@ -32,191 +32,41 @@ asmlinkage void serpent_cbc_dec_8way_avx(const void *ctx, u8 *dst, const u8 *src); EXPORT_SYMBOL_GPL(serpent_cbc_dec_8way_avx); -asmlinkage void serpent_ctr_8way_avx(const void *ctx, u8 *dst, const u8 *src, - le128 *iv); -EXPORT_SYMBOL_GPL(serpent_ctr_8way_avx); - -asmlinkage void serpent_xts_enc_8way_avx(const void *ctx, u8 *dst, - const u8 *src, le128 *iv); -EXPORT_SYMBOL_GPL(serpent_xts_enc_8way_avx); - -asmlinkage void serpent_xts_dec_8way_avx(const void *ctx, u8 *dst, - const u8 *src, le128 *iv); -EXPORT_SYMBOL_GPL(serpent_xts_dec_8way_avx); - -void __serpent_crypt_ctr(const void *ctx, u8 *d, const u8 *s, le128 *iv) -{ - be128 ctrblk; - u128 *dst = (u128 *)d; - const u128 *src = (const u128 *)s; - - le128_to_be128(&ctrblk, iv); - le128_inc(iv); - - __serpent_encrypt(ctx, (u8 *)&ctrblk, (u8 *)&ctrblk); - u128_xor(dst, src, (u128 *)&ctrblk); -} -EXPORT_SYMBOL_GPL(__serpent_crypt_ctr); - -void serpent_xts_enc(const void *ctx, u8 *dst, const u8 *src, le128 *iv) -{ - glue_xts_crypt_128bit_one(ctx, dst, src, iv, __serpent_encrypt); -} -EXPORT_SYMBOL_GPL(serpent_xts_enc); - -void serpent_xts_dec(const void *ctx, u8 *dst, const u8 *src, le128 *iv) -{ - glue_xts_crypt_128bit_one(ctx, dst, src, iv, __serpent_decrypt); -} -EXPORT_SYMBOL_GPL(serpent_xts_dec); - static int serpent_setkey_skcipher(struct crypto_skcipher *tfm, const u8 *key, unsigned int keylen) { return __serpent_setkey(crypto_skcipher_ctx(tfm), key, keylen); } -int xts_serpent_setkey(struct crypto_skcipher *tfm, const u8 *key, - unsigned int keylen) -{ - struct serpent_xts_ctx *ctx = crypto_skcipher_ctx(tfm); - int err; - - err = xts_verify_key(tfm, key, keylen); - if (err) - return err; - - /* first half of xts-key is for crypt */ - err = __serpent_setkey(&ctx->crypt_ctx, key, keylen / 2); - if (err) - return err; - - /* second half of xts-key is for tweak */ - return __serpent_setkey(&ctx->tweak_ctx, key + keylen / 2, keylen / 2); -} -EXPORT_SYMBOL_GPL(xts_serpent_setkey); - -static const struct common_glue_ctx serpent_enc = { - .num_funcs = 2, - .fpu_blocks_limit = SERPENT_PARALLEL_BLOCKS, - - .funcs = { { - .num_blocks = SERPENT_PARALLEL_BLOCKS, - .fn_u = { .ecb = serpent_ecb_enc_8way_avx } - }, { - .num_blocks = 1, - .fn_u = { .ecb = __serpent_encrypt } - } } -}; - -static const struct common_glue_ctx serpent_ctr = { - .num_funcs = 2, - .fpu_blocks_limit = SERPENT_PARALLEL_BLOCKS, - - .funcs = { { - .num_blocks = SERPENT_PARALLEL_BLOCKS, - .fn_u = { .ctr = serpent_ctr_8way_avx } - }, { - .num_blocks = 1, - .fn_u = { .ctr = __serpent_crypt_ctr } - } } -}; - -static const struct common_glue_ctx serpent_enc_xts = { - .num_funcs = 2, - .fpu_blocks_limit = SERPENT_PARALLEL_BLOCKS, - - .funcs = { { - .num_blocks = SERPENT_PARALLEL_BLOCKS, - .fn_u = { .xts = serpent_xts_enc_8way_avx } - }, { - .num_blocks = 1, - .fn_u = { .xts = serpent_xts_enc } - } } -}; - -static const struct common_glue_ctx serpent_dec = { - .num_funcs = 2, - .fpu_blocks_limit = SERPENT_PARALLEL_BLOCKS, - - .funcs = { { - .num_blocks = SERPENT_PARALLEL_BLOCKS, - .fn_u = { .ecb = serpent_ecb_dec_8way_avx } - }, { - .num_blocks = 1, - .fn_u = { .ecb = __serpent_decrypt } - } } -}; - -static const struct common_glue_ctx serpent_dec_cbc = { - .num_funcs = 2, - .fpu_blocks_limit = SERPENT_PARALLEL_BLOCKS, - - .funcs = { { - .num_blocks = SERPENT_PARALLEL_BLOCKS, - .fn_u = { .cbc = serpent_cbc_dec_8way_avx } - }, { - .num_blocks = 1, - .fn_u = { .cbc = __serpent_decrypt } - } } -}; - -static const struct common_glue_ctx serpent_dec_xts = { - .num_funcs = 2, - .fpu_blocks_limit = SERPENT_PARALLEL_BLOCKS, - - .funcs = { { - .num_blocks = SERPENT_PARALLEL_BLOCKS, - .fn_u = { .xts = serpent_xts_dec_8way_avx } - }, { - .num_blocks = 1, - .fn_u = { .xts = serpent_xts_dec } - } } -}; - static int ecb_encrypt(struct skcipher_request *req) { - return glue_ecb_req_128bit(&serpent_enc, req); + ECB_WALK_START(req, SERPENT_BLOCK_SIZE, SERPENT_PARALLEL_BLOCKS); + ECB_BLOCK(SERPENT_PARALLEL_BLOCKS, serpent_ecb_enc_8way_avx); + ECB_BLOCK(1, __serpent_encrypt); + ECB_WALK_END(); } static int ecb_decrypt(struct skcipher_request *req) { - return glue_ecb_req_128bit(&serpent_dec, req); + ECB_WALK_START(req, SERPENT_BLOCK_SIZE, SERPENT_PARALLEL_BLOCKS); + ECB_BLOCK(SERPENT_PARALLEL_BLOCKS, serpent_ecb_dec_8way_avx); + ECB_BLOCK(1, __serpent_decrypt); + ECB_WALK_END(); } static int cbc_encrypt(struct skcipher_request *req) { - return glue_cbc_encrypt_req_128bit(__serpent_encrypt, req); + CBC_WALK_START(req, SERPENT_BLOCK_SIZE, -1); + CBC_ENC_BLOCK(__serpent_encrypt); + CBC_WALK_END(); } static int cbc_decrypt(struct skcipher_request *req) { - return glue_cbc_decrypt_req_128bit(&serpent_dec_cbc, req); -} - -static int ctr_crypt(struct skcipher_request *req) -{ - return glue_ctr_req_128bit(&serpent_ctr, req); -} - -static int xts_encrypt(struct skcipher_request *req) -{ - struct crypto_skcipher *tfm = crypto_skcipher_reqtfm(req); - struct serpent_xts_ctx *ctx = crypto_skcipher_ctx(tfm); - - return glue_xts_req_128bit(&serpent_enc_xts, req, - __serpent_encrypt, &ctx->tweak_ctx, - &ctx->crypt_ctx, false); -} - -static int xts_decrypt(struct skcipher_request *req) -{ - struct crypto_skcipher *tfm = crypto_skcipher_reqtfm(req); - struct serpent_xts_ctx *ctx = crypto_skcipher_ctx(tfm); - - return glue_xts_req_128bit(&serpent_dec_xts, req, - __serpent_encrypt, &ctx->tweak_ctx, - &ctx->crypt_ctx, true); + CBC_WALK_START(req, SERPENT_BLOCK_SIZE, SERPENT_PARALLEL_BLOCKS); + CBC_DEC_BLOCK(SERPENT_PARALLEL_BLOCKS, serpent_cbc_dec_8way_avx); + CBC_DEC_BLOCK(1, __serpent_decrypt); + CBC_WALK_END(); } static struct skcipher_alg serpent_algs[] = { @@ -247,35 +97,6 @@ static struct skcipher_alg serpent_algs[] = { .setkey = serpent_setkey_skcipher, .encrypt = cbc_encrypt, .decrypt = cbc_decrypt, - }, { - .base.cra_name = "__ctr(serpent)", - .base.cra_driver_name = "__ctr-serpent-avx", - .base.cra_priority = 500, - .base.cra_flags = CRYPTO_ALG_INTERNAL, - .base.cra_blocksize = 1, - .base.cra_ctxsize = sizeof(struct serpent_ctx), - .base.cra_module = THIS_MODULE, - .min_keysize = SERPENT_MIN_KEY_SIZE, - .max_keysize = SERPENT_MAX_KEY_SIZE, - .ivsize = SERPENT_BLOCK_SIZE, - .chunksize = SERPENT_BLOCK_SIZE, - .setkey = serpent_setkey_skcipher, - .encrypt = ctr_crypt, - .decrypt = ctr_crypt, - }, { - .base.cra_name = "__xts(serpent)", - .base.cra_driver_name = "__xts-serpent-avx", - .base.cra_priority = 500, - .base.cra_flags = CRYPTO_ALG_INTERNAL, - .base.cra_blocksize = SERPENT_BLOCK_SIZE, - .base.cra_ctxsize = sizeof(struct serpent_xts_ctx), - .base.cra_module = THIS_MODULE, - .min_keysize = 2 * SERPENT_MIN_KEY_SIZE, - .max_keysize = 2 * SERPENT_MAX_KEY_SIZE, - .ivsize = SERPENT_BLOCK_SIZE, - .setkey = xts_serpent_setkey, - .encrypt = xts_encrypt, - .decrypt = xts_decrypt, }, }; diff --git a/arch/x86/crypto/serpent_sse2_glue.c b/arch/x86/crypto/serpent_sse2_glue.c index 4fed8d26b91a..d78f37e9b2cf 100644 --- a/arch/x86/crypto/serpent_sse2_glue.c +++ b/arch/x86/crypto/serpent_sse2_glue.c @@ -10,8 +10,6 @@ * * 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> */ #include <linux/module.h> @@ -22,8 +20,9 @@ #include <crypto/b128ops.h> #include <crypto/internal/simd.h> #include <crypto/serpent.h> -#include <asm/crypto/serpent-sse2.h> -#include <asm/crypto/glue_helper.h> + +#include "serpent-sse2.h" +#include "ecb_cbc_helpers.h" static int serpent_setkey_skcipher(struct crypto_skcipher *tfm, const u8 *key, unsigned int keylen) @@ -31,130 +30,46 @@ static int serpent_setkey_skcipher(struct crypto_skcipher *tfm, return __serpent_setkey(crypto_skcipher_ctx(tfm), key, keylen); } -static void serpent_decrypt_cbc_xway(const void *ctx, u8 *d, const u8 *s) -{ - u128 ivs[SERPENT_PARALLEL_BLOCKS - 1]; - u128 *dst = (u128 *)d; - const u128 *src = (const u128 *)s; - unsigned int j; - - for (j = 0; j < SERPENT_PARALLEL_BLOCKS - 1; j++) - ivs[j] = src[j]; - - serpent_dec_blk_xway(ctx, (u8 *)dst, (u8 *)src); - - for (j = 0; j < SERPENT_PARALLEL_BLOCKS - 1; j++) - u128_xor(dst + (j + 1), dst + (j + 1), ivs + j); -} - -static void serpent_crypt_ctr(const void *ctx, u8 *d, const u8 *s, le128 *iv) -{ - be128 ctrblk; - u128 *dst = (u128 *)d; - const u128 *src = (const u128 *)s; - - le128_to_be128(&ctrblk, iv); - le128_inc(iv); - - __serpent_encrypt(ctx, (u8 *)&ctrblk, (u8 *)&ctrblk); - u128_xor(dst, src, (u128 *)&ctrblk); -} - -static void serpent_crypt_ctr_xway(const void *ctx, u8 *d, const u8 *s, - le128 *iv) +static void serpent_decrypt_cbc_xway(const void *ctx, u8 *dst, const u8 *src) { - be128 ctrblks[SERPENT_PARALLEL_BLOCKS]; - u128 *dst = (u128 *)d; - const u128 *src = (const u128 *)s; - unsigned int i; - - for (i = 0; i < SERPENT_PARALLEL_BLOCKS; i++) { - if (dst != src) - dst[i] = src[i]; - - le128_to_be128(&ctrblks[i], iv); - le128_inc(iv); - } + u8 buf[SERPENT_PARALLEL_BLOCKS - 1][SERPENT_BLOCK_SIZE]; + const u8 *s = src; - serpent_enc_blk_xway_xor(ctx, (u8 *)dst, (u8 *)ctrblks); + if (dst == src) + s = memcpy(buf, src, sizeof(buf)); + serpent_dec_blk_xway(ctx, dst, src); + crypto_xor(dst + SERPENT_BLOCK_SIZE, s, sizeof(buf)); } -static const struct common_glue_ctx serpent_enc = { - .num_funcs = 2, - .fpu_blocks_limit = SERPENT_PARALLEL_BLOCKS, - - .funcs = { { - .num_blocks = SERPENT_PARALLEL_BLOCKS, - .fn_u = { .ecb = serpent_enc_blk_xway } - }, { - .num_blocks = 1, - .fn_u = { .ecb = __serpent_encrypt } - } } -}; - -static const struct common_glue_ctx serpent_ctr = { - .num_funcs = 2, - .fpu_blocks_limit = SERPENT_PARALLEL_BLOCKS, - - .funcs = { { - .num_blocks = SERPENT_PARALLEL_BLOCKS, - .fn_u = { .ctr = serpent_crypt_ctr_xway } - }, { - .num_blocks = 1, - .fn_u = { .ctr = serpent_crypt_ctr } - } } -}; - -static const struct common_glue_ctx serpent_dec = { - .num_funcs = 2, - .fpu_blocks_limit = SERPENT_PARALLEL_BLOCKS, - - .funcs = { { - .num_blocks = SERPENT_PARALLEL_BLOCKS, - .fn_u = { .ecb = serpent_dec_blk_xway } - }, { - .num_blocks = 1, - .fn_u = { .ecb = __serpent_decrypt } - } } -}; - -static const struct common_glue_ctx serpent_dec_cbc = { - .num_funcs = 2, - .fpu_blocks_limit = SERPENT_PARALLEL_BLOCKS, - - .funcs = { { - .num_blocks = SERPENT_PARALLEL_BLOCKS, - .fn_u = { .cbc = serpent_decrypt_cbc_xway } - }, { - .num_blocks = 1, - .fn_u = { .cbc = __serpent_decrypt } - } } -}; - static int ecb_encrypt(struct skcipher_request *req) { - return glue_ecb_req_128bit(&serpent_enc, req); + ECB_WALK_START(req, SERPENT_BLOCK_SIZE, SERPENT_PARALLEL_BLOCKS); + ECB_BLOCK(SERPENT_PARALLEL_BLOCKS, serpent_enc_blk_xway); + ECB_BLOCK(1, __serpent_encrypt); + ECB_WALK_END(); } static int ecb_decrypt(struct skcipher_request *req) { - return glue_ecb_req_128bit(&serpent_dec, req); + ECB_WALK_START(req, SERPENT_BLOCK_SIZE, SERPENT_PARALLEL_BLOCKS); + ECB_BLOCK(SERPENT_PARALLEL_BLOCKS, serpent_dec_blk_xway); + ECB_BLOCK(1, __serpent_decrypt); + ECB_WALK_END(); } static int cbc_encrypt(struct skcipher_request *req) { - return glue_cbc_encrypt_req_128bit(__serpent_encrypt, - req); + CBC_WALK_START(req, SERPENT_BLOCK_SIZE, -1); + CBC_ENC_BLOCK(__serpent_encrypt); + CBC_WALK_END(); } static int cbc_decrypt(struct skcipher_request *req) { - return glue_cbc_decrypt_req_128bit(&serpent_dec_cbc, req); -} - -static int ctr_crypt(struct skcipher_request *req) -{ - return glue_ctr_req_128bit(&serpent_ctr, req); + CBC_WALK_START(req, SERPENT_BLOCK_SIZE, SERPENT_PARALLEL_BLOCKS); + CBC_DEC_BLOCK(SERPENT_PARALLEL_BLOCKS, serpent_decrypt_cbc_xway); + CBC_DEC_BLOCK(1, __serpent_decrypt); + CBC_WALK_END(); } static struct skcipher_alg serpent_algs[] = { @@ -185,21 +100,6 @@ static struct skcipher_alg serpent_algs[] = { .setkey = serpent_setkey_skcipher, .encrypt = cbc_encrypt, .decrypt = cbc_decrypt, - }, { - .base.cra_name = "__ctr(serpent)", - .base.cra_driver_name = "__ctr-serpent-sse2", - .base.cra_priority = 400, - .base.cra_flags = CRYPTO_ALG_INTERNAL, - .base.cra_blocksize = 1, - .base.cra_ctxsize = sizeof(struct serpent_ctx), - .base.cra_module = THIS_MODULE, - .min_keysize = SERPENT_MIN_KEY_SIZE, - .max_keysize = SERPENT_MAX_KEY_SIZE, - .ivsize = SERPENT_BLOCK_SIZE, - .chunksize = SERPENT_BLOCK_SIZE, - .setkey = serpent_setkey_skcipher, - .encrypt = ctr_crypt, - .decrypt = ctr_crypt, }, }; diff --git a/arch/x86/crypto/twofish-avx-x86_64-asm_64.S b/arch/x86/crypto/twofish-avx-x86_64-asm_64.S index a5151393bb2f..37e63b3c664e 100644 --- a/arch/x86/crypto/twofish-avx-x86_64-asm_64.S +++ b/arch/x86/crypto/twofish-avx-x86_64-asm_64.S @@ -19,11 +19,6 @@ .Lbswap128_mask: .byte 15, 14, 13, 12, 11, 10, 9, 8, 7, 6, 5, 4, 3, 2, 1, 0 -.section .rodata.cst16.xts_gf128mul_and_shl1_mask, "aM", @progbits, 16 -.align 16 -.Lxts_gf128mul_and_shl1_mask: - .byte 0x87, 0, 0, 0, 0, 0, 0, 0, 1, 0, 0, 0, 0, 0, 0, 0 - .text /* structure of crypto context */ @@ -379,78 +374,3 @@ SYM_FUNC_START(twofish_cbc_dec_8way) FRAME_END ret; SYM_FUNC_END(twofish_cbc_dec_8way) - -SYM_FUNC_START(twofish_ctr_8way) - /* input: - * %rdi: ctx, CTX - * %rsi: dst - * %rdx: src - * %rcx: iv (little endian, 128bit) - */ - FRAME_BEGIN - - pushq %r12; - - movq %rsi, %r11; - movq %rdx, %r12; - - load_ctr_8way(%rcx, .Lbswap128_mask, RA1, RB1, RC1, RD1, RA2, RB2, RC2, - RD2, RX0, RX1, RY0); - - call __twofish_enc_blk8; - - store_ctr_8way(%r12, %r11, RC1, RD1, RA1, RB1, RC2, RD2, RA2, RB2); - - popq %r12; - - FRAME_END - ret; -SYM_FUNC_END(twofish_ctr_8way) - -SYM_FUNC_START(twofish_xts_enc_8way) - /* input: - * %rdi: ctx, CTX - * %rsi: dst - * %rdx: src - * %rcx: iv (t ⊕ αⁿ ∈ GF(2¹²⁸)) - */ - FRAME_BEGIN - - movq %rsi, %r11; - - /* regs <= src, dst <= IVs, regs <= regs xor IVs */ - load_xts_8way(%rcx, %rdx, %rsi, RA1, RB1, RC1, RD1, RA2, RB2, RC2, RD2, - RX0, RX1, RY0, .Lxts_gf128mul_and_shl1_mask); - - call __twofish_enc_blk8; - - /* dst <= regs xor IVs(in dst) */ - store_xts_8way(%r11, RC1, RD1, RA1, RB1, RC2, RD2, RA2, RB2); - - FRAME_END - ret; -SYM_FUNC_END(twofish_xts_enc_8way) - -SYM_FUNC_START(twofish_xts_dec_8way) - /* input: - * %rdi: ctx, CTX - * %rsi: dst - * %rdx: src - * %rcx: iv (t ⊕ αⁿ ∈ GF(2¹²⁸)) - */ - FRAME_BEGIN - - movq %rsi, %r11; - - /* regs <= src, dst <= IVs, regs <= regs xor IVs */ - load_xts_8way(%rcx, %rdx, %rsi, RC1, RD1, RA1, RB1, RC2, RD2, RA2, RB2, - RX0, RX1, RY0, .Lxts_gf128mul_and_shl1_mask); - - call __twofish_dec_blk8; - - /* dst <= regs xor IVs(in dst) */ - store_xts_8way(%r11, RA1, RB1, RC1, RD1, RA2, RB2, RC2, RD2); - - FRAME_END - ret; -SYM_FUNC_END(twofish_xts_dec_8way) diff --git a/arch/x86/include/asm/crypto/twofish.h b/arch/x86/crypto/twofish.h index 2c377a8042e1..12df400e6d53 100644 --- a/arch/x86/include/asm/crypto/twofish.h +++ b/arch/x86/crypto/twofish.h @@ -17,9 +17,5 @@ asmlinkage void twofish_dec_blk_3way(const void *ctx, u8 *dst, const u8 *src); /* helpers from twofish_x86_64-3way module */ extern void twofish_dec_blk_cbc_3way(const void *ctx, u8 *dst, const u8 *src); -extern void twofish_enc_blk_ctr(const void *ctx, u8 *dst, const u8 *src, - le128 *iv); -extern void twofish_enc_blk_ctr_3way(const void *ctx, u8 *dst, const u8 *src, - le128 *iv); #endif /* ASM_X86_TWOFISH_H */ diff --git a/arch/x86/crypto/twofish_avx_glue.c b/arch/x86/crypto/twofish_avx_glue.c index 2dbc8ce3730e..3eb3440b477a 100644 --- a/arch/x86/crypto/twofish_avx_glue.c +++ b/arch/x86/crypto/twofish_avx_glue.c @@ -15,9 +15,9 @@ #include <crypto/algapi.h> #include <crypto/internal/simd.h> #include <crypto/twofish.h> -#include <crypto/xts.h> -#include <asm/crypto/glue_helper.h> -#include <asm/crypto/twofish.h> + +#include "twofish.h" +#include "ecb_cbc_helpers.h" #define TWOFISH_PARALLEL_BLOCKS 8 @@ -26,13 +26,6 @@ asmlinkage void twofish_ecb_enc_8way(const void *ctx, u8 *dst, const u8 *src); asmlinkage void twofish_ecb_dec_8way(const void *ctx, u8 *dst, const u8 *src); asmlinkage void twofish_cbc_dec_8way(const void *ctx, u8 *dst, const u8 *src); -asmlinkage void twofish_ctr_8way(const void *ctx, u8 *dst, const u8 *src, - le128 *iv); - -asmlinkage void twofish_xts_enc_8way(const void *ctx, u8 *dst, const u8 *src, - le128 *iv); -asmlinkage void twofish_xts_dec_8way(const void *ctx, u8 *dst, const u8 *src, - le128 *iv); static int twofish_setkey_skcipher(struct crypto_skcipher *tfm, const u8 *key, unsigned int keylen) @@ -45,171 +38,38 @@ static inline void twofish_enc_blk_3way(const void *ctx, u8 *dst, const u8 *src) __twofish_enc_blk_3way(ctx, dst, src, false); } -static void twofish_xts_enc(const void *ctx, u8 *dst, const u8 *src, le128 *iv) -{ - glue_xts_crypt_128bit_one(ctx, dst, src, iv, twofish_enc_blk); -} - -static void twofish_xts_dec(const void *ctx, u8 *dst, const u8 *src, le128 *iv) -{ - glue_xts_crypt_128bit_one(ctx, dst, src, iv, twofish_dec_blk); -} - -struct twofish_xts_ctx { - struct twofish_ctx tweak_ctx; - struct twofish_ctx crypt_ctx; -}; - -static int xts_twofish_setkey(struct crypto_skcipher *tfm, const u8 *key, - unsigned int keylen) -{ - struct twofish_xts_ctx *ctx = crypto_skcipher_ctx(tfm); - int err; - - err = xts_verify_key(tfm, key, keylen); - if (err) - return err; - - /* first half of xts-key is for crypt */ - err = __twofish_setkey(&ctx->crypt_ctx, key, keylen / 2); - if (err) - return err; - - /* second half of xts-key is for tweak */ - return __twofish_setkey(&ctx->tweak_ctx, key + keylen / 2, keylen / 2); -} - -static const struct common_glue_ctx twofish_enc = { - .num_funcs = 3, - .fpu_blocks_limit = TWOFISH_PARALLEL_BLOCKS, - - .funcs = { { - .num_blocks = TWOFISH_PARALLEL_BLOCKS, - .fn_u = { .ecb = twofish_ecb_enc_8way } - }, { - .num_blocks = 3, - .fn_u = { .ecb = twofish_enc_blk_3way } - }, { - .num_blocks = 1, - .fn_u = { .ecb = twofish_enc_blk } - } } -}; - -static const struct common_glue_ctx twofish_ctr = { - .num_funcs = 3, - .fpu_blocks_limit = TWOFISH_PARALLEL_BLOCKS, - - .funcs = { { - .num_blocks = TWOFISH_PARALLEL_BLOCKS, - .fn_u = { .ctr = twofish_ctr_8way } - }, { - .num_blocks = 3, - .fn_u = { .ctr = twofish_enc_blk_ctr_3way } - }, { - .num_blocks = 1, - .fn_u = { .ctr = twofish_enc_blk_ctr } - } } -}; - -static const struct common_glue_ctx twofish_enc_xts = { - .num_funcs = 2, - .fpu_blocks_limit = TWOFISH_PARALLEL_BLOCKS, - - .funcs = { { - .num_blocks = TWOFISH_PARALLEL_BLOCKS, - .fn_u = { .xts = twofish_xts_enc_8way } - }, { - .num_blocks = 1, - .fn_u = { .xts = twofish_xts_enc } - } } -}; - -static const struct common_glue_ctx twofish_dec = { - .num_funcs = 3, - .fpu_blocks_limit = TWOFISH_PARALLEL_BLOCKS, - - .funcs = { { - .num_blocks = TWOFISH_PARALLEL_BLOCKS, - .fn_u = { .ecb = twofish_ecb_dec_8way } - }, { - .num_blocks = 3, - .fn_u = { .ecb = twofish_dec_blk_3way } - }, { - .num_blocks = 1, - .fn_u = { .ecb = twofish_dec_blk } - } } -}; - -static const struct common_glue_ctx twofish_dec_cbc = { - .num_funcs = 3, - .fpu_blocks_limit = TWOFISH_PARALLEL_BLOCKS, - - .funcs = { { - .num_blocks = TWOFISH_PARALLEL_BLOCKS, - .fn_u = { .cbc = twofish_cbc_dec_8way } - }, { - .num_blocks = 3, - .fn_u = { .cbc = twofish_dec_blk_cbc_3way } - }, { - .num_blocks = 1, - .fn_u = { .cbc = twofish_dec_blk } - } } -}; - -static const struct common_glue_ctx twofish_dec_xts = { - .num_funcs = 2, - .fpu_blocks_limit = TWOFISH_PARALLEL_BLOCKS, - - .funcs = { { - .num_blocks = TWOFISH_PARALLEL_BLOCKS, - .fn_u = { .xts = twofish_xts_dec_8way } - }, { - .num_blocks = 1, - .fn_u = { .xts = twofish_xts_dec } - } } -}; - static int ecb_encrypt(struct skcipher_request *req) { - return glue_ecb_req_128bit(&twofish_enc, req); + ECB_WALK_START(req, TF_BLOCK_SIZE, TWOFISH_PARALLEL_BLOCKS); + ECB_BLOCK(TWOFISH_PARALLEL_BLOCKS, twofish_ecb_enc_8way); + ECB_BLOCK(3, twofish_enc_blk_3way); + ECB_BLOCK(1, twofish_enc_blk); + ECB_WALK_END(); } static int ecb_decrypt(struct skcipher_request *req) { - return glue_ecb_req_128bit(&twofish_dec, req); + ECB_WALK_START(req, TF_BLOCK_SIZE, TWOFISH_PARALLEL_BLOCKS); + ECB_BLOCK(TWOFISH_PARALLEL_BLOCKS, twofish_ecb_dec_8way); + ECB_BLOCK(3, twofish_dec_blk_3way); + ECB_BLOCK(1, twofish_dec_blk); + ECB_WALK_END(); } static int cbc_encrypt(struct skcipher_request *req) { - return glue_cbc_encrypt_req_128bit(twofish_enc_blk, req); + CBC_WALK_START(req, TF_BLOCK_SIZE, -1); + CBC_ENC_BLOCK(twofish_enc_blk); + CBC_WALK_END(); } static int cbc_decrypt(struct skcipher_request *req) { - return glue_cbc_decrypt_req_128bit(&twofish_dec_cbc, req); -} - -static int ctr_crypt(struct skcipher_request *req) -{ - return glue_ctr_req_128bit(&twofish_ctr, req); -} - -static int xts_encrypt(struct skcipher_request *req) -{ - struct crypto_skcipher *tfm = crypto_skcipher_reqtfm(req); - struct twofish_xts_ctx *ctx = crypto_skcipher_ctx(tfm); - - return glue_xts_req_128bit(&twofish_enc_xts, req, twofish_enc_blk, - &ctx->tweak_ctx, &ctx->crypt_ctx, false); -} - -static int xts_decrypt(struct skcipher_request *req) -{ - struct crypto_skcipher *tfm = crypto_skcipher_reqtfm(req); - struct twofish_xts_ctx *ctx = crypto_skcipher_ctx(tfm); - - return glue_xts_req_128bit(&twofish_dec_xts, req, twofish_enc_blk, - &ctx->tweak_ctx, &ctx->crypt_ctx, true); + CBC_WALK_START(req, TF_BLOCK_SIZE, TWOFISH_PARALLEL_BLOCKS); + CBC_DEC_BLOCK(TWOFISH_PARALLEL_BLOCKS, twofish_cbc_dec_8way); + CBC_DEC_BLOCK(3, twofish_dec_blk_cbc_3way); + CBC_DEC_BLOCK(1, twofish_dec_blk); + CBC_WALK_END(); } static struct skcipher_alg twofish_algs[] = { @@ -240,35 +100,6 @@ static struct skcipher_alg twofish_algs[] = { .setkey = twofish_setkey_skcipher, .encrypt = cbc_encrypt, .decrypt = cbc_decrypt, - }, { - .base.cra_name = "__ctr(twofish)", - .base.cra_driver_name = "__ctr-twofish-avx", - .base.cra_priority = 400, - .base.cra_flags = CRYPTO_ALG_INTERNAL, - .base.cra_blocksize = 1, - .base.cra_ctxsize = sizeof(struct twofish_ctx), - .base.cra_module = THIS_MODULE, - .min_keysize = TF_MIN_KEY_SIZE, - .max_keysize = TF_MAX_KEY_SIZE, - .ivsize = TF_BLOCK_SIZE, - .chunksize = TF_BLOCK_SIZE, - .setkey = twofish_setkey_skcipher, - .encrypt = ctr_crypt, - .decrypt = ctr_crypt, - }, { - .base.cra_name = "__xts(twofish)", - .base.cra_driver_name = "__xts-twofish-avx", - .base.cra_priority = 400, - .base.cra_flags = CRYPTO_ALG_INTERNAL, - .base.cra_blocksize = TF_BLOCK_SIZE, - .base.cra_ctxsize = sizeof(struct twofish_xts_ctx), - .base.cra_module = THIS_MODULE, - .min_keysize = 2 * TF_MIN_KEY_SIZE, - .max_keysize = 2 * TF_MAX_KEY_SIZE, - .ivsize = TF_BLOCK_SIZE, - .setkey = xts_twofish_setkey, - .encrypt = xts_encrypt, - .decrypt = xts_decrypt, }, }; diff --git a/arch/x86/crypto/twofish_glue_3way.c b/arch/x86/crypto/twofish_glue_3way.c index 768af6075479..03725696397c 100644 --- a/arch/x86/crypto/twofish_glue_3way.c +++ b/arch/x86/crypto/twofish_glue_3way.c @@ -5,17 +5,16 @@ * Copyright (c) 2011 Jussi Kivilinna <jussi.kivilinna@mbnet.fi> */ -#include <asm/crypto/glue_helper.h> -#include <asm/crypto/twofish.h> #include <crypto/algapi.h> -#include <crypto/b128ops.h> -#include <crypto/internal/skcipher.h> #include <crypto/twofish.h> #include <linux/crypto.h> #include <linux/init.h> #include <linux/module.h> #include <linux/types.h> +#include "twofish.h" +#include "ecb_cbc_helpers.h" + EXPORT_SYMBOL_GPL(__twofish_enc_blk_3way); EXPORT_SYMBOL_GPL(twofish_dec_blk_3way); @@ -30,143 +29,48 @@ static inline void twofish_enc_blk_3way(const void *ctx, u8 *dst, const u8 *src) __twofish_enc_blk_3way(ctx, dst, src, false); } -static inline void twofish_enc_blk_xor_3way(const void *ctx, u8 *dst, - const u8 *src) -{ - __twofish_enc_blk_3way(ctx, dst, src, true); -} - -void twofish_dec_blk_cbc_3way(const void *ctx, u8 *d, const u8 *s) +void twofish_dec_blk_cbc_3way(const void *ctx, u8 *dst, const u8 *src) { - u128 ivs[2]; - u128 *dst = (u128 *)d; - const u128 *src = (const u128 *)s; - - ivs[0] = src[0]; - ivs[1] = src[1]; + u8 buf[2][TF_BLOCK_SIZE]; + const u8 *s = src; - twofish_dec_blk_3way(ctx, (u8 *)dst, (u8 *)src); + if (dst == src) + s = memcpy(buf, src, sizeof(buf)); + twofish_dec_blk_3way(ctx, dst, src); + crypto_xor(dst + TF_BLOCK_SIZE, s, sizeof(buf)); - u128_xor(&dst[1], &dst[1], &ivs[0]); - u128_xor(&dst[2], &dst[2], &ivs[1]); } EXPORT_SYMBOL_GPL(twofish_dec_blk_cbc_3way); -void twofish_enc_blk_ctr(const void *ctx, u8 *d, const u8 *s, le128 *iv) -{ - be128 ctrblk; - u128 *dst = (u128 *)d; - const u128 *src = (const u128 *)s; - - if (dst != src) - *dst = *src; - - le128_to_be128(&ctrblk, iv); - le128_inc(iv); - - twofish_enc_blk(ctx, (u8 *)&ctrblk, (u8 *)&ctrblk); - u128_xor(dst, dst, (u128 *)&ctrblk); -} -EXPORT_SYMBOL_GPL(twofish_enc_blk_ctr); - -void twofish_enc_blk_ctr_3way(const void *ctx, u8 *d, const u8 *s, le128 *iv) -{ - be128 ctrblks[3]; - u128 *dst = (u128 *)d; - const u128 *src = (const u128 *)s; - - if (dst != src) { - dst[0] = src[0]; - dst[1] = src[1]; - dst[2] = src[2]; - } - - le128_to_be128(&ctrblks[0], iv); - le128_inc(iv); - le128_to_be128(&ctrblks[1], iv); - le128_inc(iv); - le128_to_be128(&ctrblks[2], iv); - le128_inc(iv); - - twofish_enc_blk_xor_3way(ctx, (u8 *)dst, (u8 *)ctrblks); -} -EXPORT_SYMBOL_GPL(twofish_enc_blk_ctr_3way); - -static const struct common_glue_ctx twofish_enc = { - .num_funcs = 2, - .fpu_blocks_limit = -1, - - .funcs = { { - .num_blocks = 3, - .fn_u = { .ecb = twofish_enc_blk_3way } - }, { - .num_blocks = 1, - .fn_u = { .ecb = twofish_enc_blk } - } } -}; - -static const struct common_glue_ctx twofish_ctr = { - .num_funcs = 2, - .fpu_blocks_limit = -1, - - .funcs = { { - .num_blocks = 3, - .fn_u = { .ctr = twofish_enc_blk_ctr_3way } - }, { - .num_blocks = 1, - .fn_u = { .ctr = twofish_enc_blk_ctr } - } } -}; - -static const struct common_glue_ctx twofish_dec = { - .num_funcs = 2, - .fpu_blocks_limit = -1, - - .funcs = { { - .num_blocks = 3, - .fn_u = { .ecb = twofish_dec_blk_3way } - }, { - .num_blocks = 1, - .fn_u = { .ecb = twofish_dec_blk } - } } -}; - -static const struct common_glue_ctx twofish_dec_cbc = { - .num_funcs = 2, - .fpu_blocks_limit = -1, - - .funcs = { { - .num_blocks = 3, - .fn_u = { .cbc = twofish_dec_blk_cbc_3way } - }, { - .num_blocks = 1, - .fn_u = { .cbc = twofish_dec_blk } - } } -}; - static int ecb_encrypt(struct skcipher_request *req) { - return glue_ecb_req_128bit(&twofish_enc, req); + ECB_WALK_START(req, TF_BLOCK_SIZE, -1); + ECB_BLOCK(3, twofish_enc_blk_3way); + ECB_BLOCK(1, twofish_enc_blk); + ECB_WALK_END(); } static int ecb_decrypt(struct skcipher_request *req) { - return glue_ecb_req_128bit(&twofish_dec, req); + ECB_WALK_START(req, TF_BLOCK_SIZE, -1); + ECB_BLOCK(3, twofish_dec_blk_3way); + ECB_BLOCK(1, twofish_dec_blk); + ECB_WALK_END(); } static int cbc_encrypt(struct skcipher_request *req) { - return glue_cbc_encrypt_req_128bit(twofish_enc_blk, req); + CBC_WALK_START(req, TF_BLOCK_SIZE, -1); + CBC_ENC_BLOCK(twofish_enc_blk); + CBC_WALK_END(); } static int cbc_decrypt(struct skcipher_request *req) { - return glue_cbc_decrypt_req_128bit(&twofish_dec_cbc, req); -} - -static int ctr_crypt(struct skcipher_request *req) -{ - return glue_ctr_req_128bit(&twofish_ctr, req); + CBC_WALK_START(req, TF_BLOCK_SIZE, -1); + CBC_DEC_BLOCK(3, twofish_dec_blk_cbc_3way); + CBC_DEC_BLOCK(1, twofish_dec_blk); + CBC_WALK_END(); } static struct skcipher_alg tf_skciphers[] = { @@ -195,20 +99,6 @@ static struct skcipher_alg tf_skciphers[] = { .setkey = twofish_setkey_skcipher, .encrypt = cbc_encrypt, .decrypt = cbc_decrypt, - }, { - .base.cra_name = "ctr(twofish)", - .base.cra_driver_name = "ctr-twofish-3way", - .base.cra_priority = 300, - .base.cra_blocksize = 1, - .base.cra_ctxsize = sizeof(struct twofish_ctx), - .base.cra_module = THIS_MODULE, - .min_keysize = TF_MIN_KEY_SIZE, - .max_keysize = TF_MAX_KEY_SIZE, - .ivsize = TF_BLOCK_SIZE, - .chunksize = TF_BLOCK_SIZE, - .setkey = twofish_setkey_skcipher, - .encrypt = ctr_crypt, - .decrypt = ctr_crypt, }, }; diff --git a/arch/x86/entry/common.c b/arch/x86/entry/common.c index 0904f5676e4d..4efd39aacb9f 100644 --- a/arch/x86/entry/common.c +++ b/arch/x86/entry/common.c @@ -128,7 +128,8 @@ static noinstr bool __do_fast_syscall_32(struct pt_regs *regs) regs->ax = -EFAULT; instrumentation_end(); - syscall_exit_to_user_mode(regs); + local_irq_disable(); + irqentry_exit_to_user_mode(regs); return false; } @@ -249,30 +250,23 @@ static __always_inline bool get_and_clear_inhcall(void) { return false; } static __always_inline void restore_inhcall(bool inhcall) { } #endif -static void __xen_pv_evtchn_do_upcall(void) +static void __xen_pv_evtchn_do_upcall(struct pt_regs *regs) { - irq_enter_rcu(); + struct pt_regs *old_regs = set_irq_regs(regs); + inc_irq_stat(irq_hv_callback_count); xen_hvm_evtchn_do_upcall(); - irq_exit_rcu(); + set_irq_regs(old_regs); } __visible noinstr void xen_pv_evtchn_do_upcall(struct pt_regs *regs) { - struct pt_regs *old_regs; + irqentry_state_t state = irqentry_enter(regs); bool inhcall; - irqentry_state_t state; - state = irqentry_enter(regs); - old_regs = set_irq_regs(regs); - - instrumentation_begin(); - run_on_irqstack_cond(__xen_pv_evtchn_do_upcall, regs); - instrumentation_begin(); - - set_irq_regs(old_regs); + run_sysvec_on_irqstack_cond(__xen_pv_evtchn_do_upcall, regs); inhcall = get_and_clear_inhcall(); if (inhcall && !WARN_ON_ONCE(state.exit_rcu)) { diff --git a/arch/x86/entry/entry_64.S b/arch/x86/entry/entry_64.S index cad08703c4ad..400908dff42e 100644 --- a/arch/x86/entry/entry_64.S +++ b/arch/x86/entry/entry_64.S @@ -46,14 +46,6 @@ .code64 .section .entry.text, "ax" -#ifdef CONFIG_PARAVIRT_XXL -SYM_CODE_START(native_usergs_sysret64) - UNWIND_HINT_EMPTY - swapgs - sysretq -SYM_CODE_END(native_usergs_sysret64) -#endif /* CONFIG_PARAVIRT_XXL */ - /* * 64-bit SYSCALL instruction entry. Up to 6 arguments in registers. * @@ -123,7 +115,12 @@ SYM_INNER_LABEL(entry_SYSCALL_64_after_hwframe, SYM_L_GLOBAL) * Try to use SYSRET instead of IRET if we're returning to * a completely clean 64-bit userspace context. If we're not, * go to the slow exit path. + * In the Xen PV case we must use iret anyway. */ + + ALTERNATIVE "", "jmp swapgs_restore_regs_and_return_to_usermode", \ + X86_FEATURE_XENPV + movq RCX(%rsp), %rcx movq RIP(%rsp), %r11 @@ -215,7 +212,8 @@ syscall_return_via_sysret: popq %rdi popq %rsp - USERGS_SYSRET64 + swapgs + sysretq SYM_CODE_END(entry_SYSCALL_64) /* @@ -669,7 +667,7 @@ native_irq_return_ldt: */ pushq %rdi /* Stash user RDI */ - SWAPGS /* to kernel GS */ + swapgs /* to kernel GS */ SWITCH_TO_KERNEL_CR3 scratch_reg=%rdi /* to kernel CR3 */ movq PER_CPU_VAR(espfix_waddr), %rdi @@ -699,7 +697,7 @@ native_irq_return_ldt: orq PER_CPU_VAR(espfix_stack), %rax SWITCH_TO_USER_CR3_STACK scratch_reg=%rdi - SWAPGS /* to user GS */ + swapgs /* to user GS */ popq %rdi /* Restore user RDI */ movq %rax, %rsp @@ -756,47 +754,6 @@ SYM_CODE_START_LOCAL_NOALIGN(.Lbad_gs) SYM_CODE_END(.Lbad_gs) .previous -/* - * rdi: New stack pointer points to the top word of the stack - * rsi: Function pointer - * rdx: Function argument (can be NULL if none) - */ -SYM_FUNC_START(asm_call_on_stack) -SYM_INNER_LABEL(asm_call_sysvec_on_stack, SYM_L_GLOBAL) -SYM_INNER_LABEL(asm_call_irq_on_stack, SYM_L_GLOBAL) - /* - * Save the frame pointer unconditionally. This allows the ORC - * unwinder to handle the stack switch. - */ - pushq %rbp - mov %rsp, %rbp - - /* - * The unwinder relies on the word at the top of the new stack - * page linking back to the previous RSP. - */ - mov %rsp, (%rdi) - mov %rdi, %rsp - /* Move the argument to the right place */ - mov %rdx, %rdi - -1: - .pushsection .discard.instr_begin - .long 1b - . - .popsection - - CALL_NOSPEC rsi - -2: - .pushsection .discard.instr_end - .long 2b - . - .popsection - - /* Restore the previous stack pointer from RBP. */ - leaveq - ret -SYM_FUNC_END(asm_call_on_stack) - #ifdef CONFIG_XEN_PV /* * A note on the "critical region" in our callback handler. @@ -943,7 +900,7 @@ SYM_CODE_START_LOCAL(paranoid_entry) ret .Lparanoid_entry_swapgs: - SWAPGS + swapgs /* * The above SAVE_AND_SWITCH_TO_KERNEL_CR3 macro doesn't do an @@ -1001,7 +958,7 @@ SYM_CODE_START_LOCAL(paranoid_exit) jnz restore_regs_and_return_to_kernel /* We are returning to a context with user GSBASE */ - SWAPGS_UNSAFE_STACK + swapgs jmp restore_regs_and_return_to_kernel SYM_CODE_END(paranoid_exit) @@ -1426,7 +1383,7 @@ nmi_no_fsgsbase: jnz nmi_restore nmi_swapgs: - SWAPGS_UNSAFE_STACK + swapgs nmi_restore: POP_REGS diff --git a/arch/x86/entry/entry_64_compat.S b/arch/x86/entry/entry_64_compat.S index 541fdaf64045..0051cf5c792d 100644 --- a/arch/x86/entry/entry_64_compat.S +++ b/arch/x86/entry/entry_64_compat.S @@ -210,6 +210,8 @@ SYM_CODE_START(entry_SYSCALL_compat) /* Switch to the kernel stack */ movq PER_CPU_VAR(cpu_current_top_of_stack), %rsp +SYM_INNER_LABEL(entry_SYSCALL_compat_safe_stack, SYM_L_GLOBAL) + /* Construct struct pt_regs on stack */ pushq $__USER32_DS /* pt_regs->ss */ pushq %r8 /* pt_regs->sp */ diff --git a/arch/x86/entry/syscalls/Makefile b/arch/x86/entry/syscalls/Makefile index 6fb9b57ed5ba..d8c4f6c9eadc 100644 --- a/arch/x86/entry/syscalls/Makefile +++ b/arch/x86/entry/syscalls/Makefile @@ -6,8 +6,8 @@ uapi := arch/$(SRCARCH)/include/generated/uapi/asm _dummy := $(shell [ -d '$(out)' ] || mkdir -p '$(out)') \ $(shell [ -d '$(uapi)' ] || mkdir -p '$(uapi)') -syscall32 := $(srctree)/$(src)/syscall_32.tbl -syscall64 := $(srctree)/$(src)/syscall_64.tbl +syscall32 := $(src)/syscall_32.tbl +syscall64 := $(src)/syscall_64.tbl syshdr := $(srctree)/$(src)/syscallhdr.sh systbl := $(srctree)/$(src)/syscalltbl.sh @@ -21,37 +21,37 @@ quiet_cmd_systbl = SYSTBL $@ cmd_systbl = $(CONFIG_SHELL) '$(systbl)' $< $@ quiet_cmd_hypercalls = HYPERCALLS $@ - cmd_hypercalls = $(CONFIG_SHELL) '$<' $@ $(filter-out $<,$^) + cmd_hypercalls = $(CONFIG_SHELL) '$<' $@ $(filter-out $<, $(real-prereqs)) syshdr_abi_unistd_32 := i386 -$(uapi)/unistd_32.h: $(syscall32) $(syshdr) +$(uapi)/unistd_32.h: $(syscall32) $(syshdr) FORCE $(call if_changed,syshdr) syshdr_abi_unistd_32_ia32 := i386 syshdr_pfx_unistd_32_ia32 := ia32_ -$(out)/unistd_32_ia32.h: $(syscall32) $(syshdr) +$(out)/unistd_32_ia32.h: $(syscall32) $(syshdr) FORCE $(call if_changed,syshdr) syshdr_abi_unistd_x32 := common,x32 syshdr_offset_unistd_x32 := __X32_SYSCALL_BIT -$(uapi)/unistd_x32.h: $(syscall64) $(syshdr) +$(uapi)/unistd_x32.h: $(syscall64) $(syshdr) FORCE $(call if_changed,syshdr) syshdr_abi_unistd_64 := common,64 -$(uapi)/unistd_64.h: $(syscall64) $(syshdr) +$(uapi)/unistd_64.h: $(syscall64) $(syshdr) FORCE $(call if_changed,syshdr) syshdr_abi_unistd_64_x32 := x32 syshdr_pfx_unistd_64_x32 := x32_ -$(out)/unistd_64_x32.h: $(syscall64) $(syshdr) +$(out)/unistd_64_x32.h: $(syscall64) $(syshdr) FORCE $(call if_changed,syshdr) -$(out)/syscalls_32.h: $(syscall32) $(systbl) +$(out)/syscalls_32.h: $(syscall32) $(systbl) FORCE $(call if_changed,systbl) -$(out)/syscalls_64.h: $(syscall64) $(systbl) +$(out)/syscalls_64.h: $(syscall64) $(systbl) FORCE $(call if_changed,systbl) -$(out)/xen-hypercalls.h: $(srctree)/scripts/xen-hypercalls.sh +$(out)/xen-hypercalls.h: $(srctree)/scripts/xen-hypercalls.sh FORCE $(call if_changed,hypercalls) $(out)/xen-hypercalls.h: $(srctree)/include/xen/interface/xen*.h @@ -62,9 +62,10 @@ syshdr-$(CONFIG_X86_64) += unistd_32_ia32.h unistd_64_x32.h syshdr-$(CONFIG_X86_64) += syscalls_64.h syshdr-$(CONFIG_XEN) += xen-hypercalls.h -targets += $(uapisyshdr-y) $(syshdr-y) +uapisyshdr-y := $(addprefix $(uapi)/, $(uapisyshdr-y)) +syshdr-y := $(addprefix $(out)/, $(syshdr-y)) +targets += $(addprefix ../../../../, $(uapisyshdr-y) $(syshdr-y)) PHONY += all -all: $(addprefix $(uapi)/,$(uapisyshdr-y)) -all: $(addprefix $(out)/,$(syshdr-y)) +all: $(uapisyshdr-y) $(syshdr-y) @: diff --git a/arch/x86/entry/syscalls/syscall_32.tbl b/arch/x86/entry/syscalls/syscall_32.tbl index 874aeacde2dd..a1c9f496fca6 100644 --- a/arch/x86/entry/syscalls/syscall_32.tbl +++ b/arch/x86/entry/syscalls/syscall_32.tbl @@ -446,3 +446,4 @@ 439 i386 faccessat2 sys_faccessat2 440 i386 process_madvise sys_process_madvise 441 i386 epoll_pwait2 sys_epoll_pwait2 compat_sys_epoll_pwait2 +442 i386 mount_setattr sys_mount_setattr diff --git a/arch/x86/entry/syscalls/syscall_64.tbl b/arch/x86/entry/syscalls/syscall_64.tbl index 78672124d28b..7bf01cbe582f 100644 --- a/arch/x86/entry/syscalls/syscall_64.tbl +++ b/arch/x86/entry/syscalls/syscall_64.tbl @@ -363,6 +363,7 @@ 439 common faccessat2 sys_faccessat2 440 common process_madvise sys_process_madvise 441 common epoll_pwait2 sys_epoll_pwait2 +442 common mount_setattr sys_mount_setattr # # Due to a historical design error, certain syscalls are numbered differently diff --git a/arch/x86/entry/vdso/Makefile b/arch/x86/entry/vdso/Makefile index 02e3e42f380b..05c4abc2fdfd 100644 --- a/arch/x86/entry/vdso/Makefile +++ b/arch/x86/entry/vdso/Makefile @@ -91,7 +91,7 @@ ifneq ($(RETPOLINE_VDSO_CFLAGS),) endif endif -$(vobjs): KBUILD_CFLAGS := $(filter-out $(GCC_PLUGINS_CFLAGS) $(RETPOLINE_CFLAGS),$(KBUILD_CFLAGS)) $(CFL) +$(vobjs): KBUILD_CFLAGS := $(filter-out $(CC_FLAGS_LTO) $(GCC_PLUGINS_CFLAGS) $(RETPOLINE_CFLAGS),$(KBUILD_CFLAGS)) $(CFL) # # vDSO code runs in userspace and -pg doesn't help with profiling anyway. @@ -150,6 +150,7 @@ KBUILD_CFLAGS_32 := $(filter-out -fno-pic,$(KBUILD_CFLAGS_32)) KBUILD_CFLAGS_32 := $(filter-out -mfentry,$(KBUILD_CFLAGS_32)) KBUILD_CFLAGS_32 := $(filter-out $(GCC_PLUGINS_CFLAGS),$(KBUILD_CFLAGS_32)) KBUILD_CFLAGS_32 := $(filter-out $(RETPOLINE_CFLAGS),$(KBUILD_CFLAGS_32)) +KBUILD_CFLAGS_32 := $(filter-out $(CC_FLAGS_LTO),$(KBUILD_CFLAGS_32)) KBUILD_CFLAGS_32 += -m32 -msoft-float -mregparm=0 -fpic KBUILD_CFLAGS_32 += -fno-stack-protector KBUILD_CFLAGS_32 += $(call cc-option, -foptimize-sibling-calls) diff --git a/arch/x86/events/core.c b/arch/x86/events/core.c index e37de298a495..18df17129695 100644 --- a/arch/x86/events/core.c +++ b/arch/x86/events/core.c @@ -81,6 +81,12 @@ DEFINE_STATIC_CALL_NULL(x86_pmu_swap_task_ctx, *x86_pmu.swap_task_ctx); DEFINE_STATIC_CALL_NULL(x86_pmu_drain_pebs, *x86_pmu.drain_pebs); DEFINE_STATIC_CALL_NULL(x86_pmu_pebs_aliases, *x86_pmu.pebs_aliases); +/* + * This one is magic, it will get called even when PMU init fails (because + * there is no PMU), in which case it should simply return NULL. + */ +DEFINE_STATIC_CALL_RET0(x86_pmu_guest_get_msrs, *x86_pmu.guest_get_msrs); + u64 __read_mostly hw_cache_event_ids [PERF_COUNT_HW_CACHE_MAX] [PERF_COUNT_HW_CACHE_OP_MAX] @@ -253,6 +259,8 @@ static bool check_hw_exists(void) if (ret) goto msr_fail; for (i = 0; i < x86_pmu.num_counters_fixed; i++) { + if (fixed_counter_disabled(i)) + continue; if (val & (0x03 << i*4)) { bios_fail = 1; val_fail = val; @@ -665,6 +673,12 @@ void x86_pmu_disable_all(void) } } +struct perf_guest_switch_msr *perf_guest_get_msrs(int *nr) +{ + return static_call(x86_pmu_guest_get_msrs)(nr); +} +EXPORT_SYMBOL_GPL(perf_guest_get_msrs); + /* * There may be PMI landing after enabled=0. The PMI hitting could be before or * after disable_all. @@ -1523,6 +1537,8 @@ void perf_event_print_debug(void) cpu, idx, prev_left); } for (idx = 0; idx < x86_pmu.num_counters_fixed; idx++) { + if (fixed_counter_disabled(idx)) + continue; rdmsrl(MSR_ARCH_PERFMON_FIXED_CTR0 + idx, pmc_count); pr_info("CPU#%d: fixed-PMC%d count: %016llx\n", @@ -1923,6 +1939,8 @@ static void x86_pmu_static_call_update(void) static_call_update(x86_pmu_drain_pebs, x86_pmu.drain_pebs); static_call_update(x86_pmu_pebs_aliases, x86_pmu.pebs_aliases); + + static_call_update(x86_pmu_guest_get_msrs, x86_pmu.guest_get_msrs); } static void _x86_pmu_read(struct perf_event *event) @@ -1995,12 +2013,17 @@ static int __init init_hw_perf_events(void) pr_info("... generic registers: %d\n", x86_pmu.num_counters); pr_info("... value mask: %016Lx\n", x86_pmu.cntval_mask); pr_info("... max period: %016Lx\n", x86_pmu.max_period); - pr_info("... fixed-purpose events: %d\n", x86_pmu.num_counters_fixed); + pr_info("... fixed-purpose events: %lu\n", + hweight64((((1ULL << x86_pmu.num_counters_fixed) - 1) + << INTEL_PMC_IDX_FIXED) & x86_pmu.intel_ctrl)); pr_info("... event mask: %016Lx\n", x86_pmu.intel_ctrl); if (!x86_pmu.read) x86_pmu.read = _x86_pmu_read; + if (!x86_pmu.guest_get_msrs) + x86_pmu.guest_get_msrs = (void *)&__static_call_return0; + x86_pmu_static_call_update(); /* diff --git a/arch/x86/events/intel/core.c b/arch/x86/events/intel/core.c index d4569bfa83e3..37ce38403cb8 100644 --- a/arch/x86/events/intel/core.c +++ b/arch/x86/events/intel/core.c @@ -275,6 +275,55 @@ static struct extra_reg intel_icl_extra_regs[] __read_mostly = { EVENT_EXTRA_END }; +static struct extra_reg intel_spr_extra_regs[] __read_mostly = { + INTEL_UEVENT_EXTRA_REG(0x012a, MSR_OFFCORE_RSP_0, 0x3fffffffffull, RSP_0), + INTEL_UEVENT_EXTRA_REG(0x012b, MSR_OFFCORE_RSP_1, 0x3fffffffffull, RSP_1), + INTEL_UEVENT_PEBS_LDLAT_EXTRA_REG(0x01cd), + INTEL_UEVENT_EXTRA_REG(0x01c6, MSR_PEBS_FRONTEND, 0x7fff17, FE), + EVENT_EXTRA_END +}; + +static struct event_constraint intel_spr_event_constraints[] = { + FIXED_EVENT_CONSTRAINT(0x00c0, 0), /* INST_RETIRED.ANY */ + FIXED_EVENT_CONSTRAINT(0x01c0, 0), /* INST_RETIRED.PREC_DIST */ + FIXED_EVENT_CONSTRAINT(0x003c, 1), /* CPU_CLK_UNHALTED.CORE */ + FIXED_EVENT_CONSTRAINT(0x0300, 2), /* CPU_CLK_UNHALTED.REF */ + FIXED_EVENT_CONSTRAINT(0x0400, 3), /* SLOTS */ + METRIC_EVENT_CONSTRAINT(INTEL_TD_METRIC_RETIRING, 0), + METRIC_EVENT_CONSTRAINT(INTEL_TD_METRIC_BAD_SPEC, 1), + METRIC_EVENT_CONSTRAINT(INTEL_TD_METRIC_FE_BOUND, 2), + METRIC_EVENT_CONSTRAINT(INTEL_TD_METRIC_BE_BOUND, 3), + METRIC_EVENT_CONSTRAINT(INTEL_TD_METRIC_HEAVY_OPS, 4), + METRIC_EVENT_CONSTRAINT(INTEL_TD_METRIC_BR_MISPREDICT, 5), + METRIC_EVENT_CONSTRAINT(INTEL_TD_METRIC_FETCH_LAT, 6), + METRIC_EVENT_CONSTRAINT(INTEL_TD_METRIC_MEM_BOUND, 7), + + INTEL_EVENT_CONSTRAINT(0x2e, 0xff), + INTEL_EVENT_CONSTRAINT(0x3c, 0xff), + /* + * Generally event codes < 0x90 are restricted to counters 0-3. + * The 0x2E and 0x3C are exception, which has no restriction. + */ + INTEL_EVENT_CONSTRAINT_RANGE(0x01, 0x8f, 0xf), + + INTEL_UEVENT_CONSTRAINT(0x01a3, 0xf), + INTEL_UEVENT_CONSTRAINT(0x02a3, 0xf), + INTEL_UEVENT_CONSTRAINT(0x08a3, 0xf), + INTEL_UEVENT_CONSTRAINT(0x04a4, 0x1), + INTEL_UEVENT_CONSTRAINT(0x08a4, 0x1), + INTEL_UEVENT_CONSTRAINT(0x02cd, 0x1), + INTEL_EVENT_CONSTRAINT(0xce, 0x1), + INTEL_EVENT_CONSTRAINT_RANGE(0xd0, 0xdf, 0xf), + /* + * Generally event codes >= 0x90 are likely to have no restrictions. + * The exception are defined as above. + */ + INTEL_EVENT_CONSTRAINT_RANGE(0x90, 0xfe, 0xff), + + EVENT_CONSTRAINT_END +}; + + EVENT_ATTR_STR(mem-loads, mem_ld_nhm, "event=0x0b,umask=0x10,ldlat=3"); EVENT_ATTR_STR(mem-loads, mem_ld_snb, "event=0xcd,umask=0x1,ldlat=3"); EVENT_ATTR_STR(mem-stores, mem_st_snb, "event=0xcd,umask=0x2"); @@ -314,11 +363,15 @@ EVENT_ATTR_STR_HT(topdown-recovery-bubbles, td_recovery_bubbles, EVENT_ATTR_STR_HT(topdown-recovery-bubbles.scale, td_recovery_bubbles_scale, "4", "2"); -EVENT_ATTR_STR(slots, slots, "event=0x00,umask=0x4"); -EVENT_ATTR_STR(topdown-retiring, td_retiring, "event=0x00,umask=0x80"); -EVENT_ATTR_STR(topdown-bad-spec, td_bad_spec, "event=0x00,umask=0x81"); -EVENT_ATTR_STR(topdown-fe-bound, td_fe_bound, "event=0x00,umask=0x82"); -EVENT_ATTR_STR(topdown-be-bound, td_be_bound, "event=0x00,umask=0x83"); +EVENT_ATTR_STR(slots, slots, "event=0x00,umask=0x4"); +EVENT_ATTR_STR(topdown-retiring, td_retiring, "event=0x00,umask=0x80"); +EVENT_ATTR_STR(topdown-bad-spec, td_bad_spec, "event=0x00,umask=0x81"); +EVENT_ATTR_STR(topdown-fe-bound, td_fe_bound, "event=0x00,umask=0x82"); +EVENT_ATTR_STR(topdown-be-bound, td_be_bound, "event=0x00,umask=0x83"); +EVENT_ATTR_STR(topdown-heavy-ops, td_heavy_ops, "event=0x00,umask=0x84"); +EVENT_ATTR_STR(topdown-br-mispredict, td_br_mispredict, "event=0x00,umask=0x85"); +EVENT_ATTR_STR(topdown-fetch-lat, td_fetch_lat, "event=0x00,umask=0x86"); +EVENT_ATTR_STR(topdown-mem-bound, td_mem_bound, "event=0x00,umask=0x87"); static struct attribute *snb_events_attrs[] = { EVENT_PTR(td_slots_issued), @@ -384,6 +437,108 @@ static u64 intel_pmu_event_map(int hw_event) return intel_perfmon_event_map[hw_event]; } +static __initconst const u64 spr_hw_cache_event_ids + [PERF_COUNT_HW_CACHE_MAX] + [PERF_COUNT_HW_CACHE_OP_MAX] + [PERF_COUNT_HW_CACHE_RESULT_MAX] = +{ + [ C(L1D ) ] = { + [ C(OP_READ) ] = { + [ C(RESULT_ACCESS) ] = 0x81d0, + [ C(RESULT_MISS) ] = 0xe124, + }, + [ C(OP_WRITE) ] = { + [ C(RESULT_ACCESS) ] = 0x82d0, + }, + }, + [ C(L1I ) ] = { + [ C(OP_READ) ] = { + [ C(RESULT_MISS) ] = 0xe424, + }, + [ C(OP_WRITE) ] = { + [ C(RESULT_ACCESS) ] = -1, + [ C(RESULT_MISS) ] = -1, + }, + }, + [ C(LL ) ] = { + [ C(OP_READ) ] = { + [ C(RESULT_ACCESS) ] = 0x12a, + [ C(RESULT_MISS) ] = 0x12a, + }, + [ C(OP_WRITE) ] = { + [ C(RESULT_ACCESS) ] = 0x12a, + [ C(RESULT_MISS) ] = 0x12a, + }, + }, + [ C(DTLB) ] = { + [ C(OP_READ) ] = { + [ C(RESULT_ACCESS) ] = 0x81d0, + [ C(RESULT_MISS) ] = 0xe12, + }, + [ C(OP_WRITE) ] = { + [ C(RESULT_ACCESS) ] = 0x82d0, + [ C(RESULT_MISS) ] = 0xe13, + }, + }, + [ C(ITLB) ] = { + [ C(OP_READ) ] = { + [ C(RESULT_ACCESS) ] = -1, + [ C(RESULT_MISS) ] = 0xe11, + }, + [ C(OP_WRITE) ] = { + [ C(RESULT_ACCESS) ] = -1, + [ C(RESULT_MISS) ] = -1, + }, + [ C(OP_PREFETCH) ] = { + [ C(RESULT_ACCESS) ] = -1, + [ C(RESULT_MISS) ] = -1, + }, + }, + [ C(BPU ) ] = { + [ C(OP_READ) ] = { + [ C(RESULT_ACCESS) ] = 0x4c4, + [ C(RESULT_MISS) ] = 0x4c5, + }, + [ C(OP_WRITE) ] = { + [ C(RESULT_ACCESS) ] = -1, + [ C(RESULT_MISS) ] = -1, + }, + [ C(OP_PREFETCH) ] = { + [ C(RESULT_ACCESS) ] = -1, + [ C(RESULT_MISS) ] = -1, + }, + }, + [ C(NODE) ] = { + [ C(OP_READ) ] = { + [ C(RESULT_ACCESS) ] = 0x12a, + [ C(RESULT_MISS) ] = 0x12a, + }, + }, +}; + +static __initconst const u64 spr_hw_cache_extra_regs + [PERF_COUNT_HW_CACHE_MAX] + [PERF_COUNT_HW_CACHE_OP_MAX] + [PERF_COUNT_HW_CACHE_RESULT_MAX] = +{ + [ C(LL ) ] = { + [ C(OP_READ) ] = { + [ C(RESULT_ACCESS) ] = 0x10001, + [ C(RESULT_MISS) ] = 0x3fbfc00001, + }, + [ C(OP_WRITE) ] = { + [ C(RESULT_ACCESS) ] = 0x3f3ffc0002, + [ C(RESULT_MISS) ] = 0x3f3fc00002, + }, + }, + [ C(NODE) ] = { + [ C(OP_READ) ] = { + [ C(RESULT_ACCESS) ] = 0x10c000001, + [ C(RESULT_MISS) ] = 0x3fb3000001, + }, + }, +}; + /* * Notes on the events: * - data reads do not include code reads (comparable to earlier tables) @@ -2134,18 +2289,6 @@ static void intel_tfa_pmu_enable_all(int added) intel_pmu_enable_all(added); } -static void enable_counter_freeze(void) -{ - update_debugctlmsr(get_debugctlmsr() | - DEBUGCTLMSR_FREEZE_PERFMON_ON_PMI); -} - -static void disable_counter_freeze(void) -{ - update_debugctlmsr(get_debugctlmsr() & - ~DEBUGCTLMSR_FREEZE_PERFMON_ON_PMI); -} - static inline u64 intel_pmu_get_status(void) { u64 status; @@ -2337,8 +2480,8 @@ static void __icl_update_topdown_event(struct perf_event *event, } } -static void update_saved_topdown_regs(struct perf_event *event, - u64 slots, u64 metrics) +static void update_saved_topdown_regs(struct perf_event *event, u64 slots, + u64 metrics, int metric_end) { struct cpu_hw_events *cpuc = this_cpu_ptr(&cpu_hw_events); struct perf_event *other; @@ -2347,7 +2490,7 @@ static void update_saved_topdown_regs(struct perf_event *event, event->hw.saved_slots = slots; event->hw.saved_metric = metrics; - for_each_set_bit(idx, cpuc->active_mask, INTEL_PMC_IDX_TD_BE_BOUND + 1) { + for_each_set_bit(idx, cpuc->active_mask, metric_end + 1) { if (!is_topdown_idx(idx)) continue; other = cpuc->events[idx]; @@ -2362,7 +2505,8 @@ static void update_saved_topdown_regs(struct perf_event *event, * The PERF_METRICS and Fixed counter 3 are read separately. The values may be * modify by a NMI. PMU has to be disabled before calling this function. */ -static u64 icl_update_topdown_event(struct perf_event *event) + +static u64 intel_update_topdown_event(struct perf_event *event, int metric_end) { struct cpu_hw_events *cpuc = this_cpu_ptr(&cpu_hw_events); struct perf_event *other; @@ -2378,7 +2522,7 @@ static u64 icl_update_topdown_event(struct perf_event *event) /* read PERF_METRICS */ rdpmcl(INTEL_PMC_FIXED_RDPMC_METRICS, metrics); - for_each_set_bit(idx, cpuc->active_mask, INTEL_PMC_IDX_TD_BE_BOUND + 1) { + for_each_set_bit(idx, cpuc->active_mask, metric_end + 1) { if (!is_topdown_idx(idx)) continue; other = cpuc->events[idx]; @@ -2404,7 +2548,7 @@ static u64 icl_update_topdown_event(struct perf_event *event) * Don't need to reset the PERF_METRICS and Fixed counter 3. * Because the values will be restored in next schedule in. */ - update_saved_topdown_regs(event, slots, metrics); + update_saved_topdown_regs(event, slots, metrics, metric_end); reset = false; } @@ -2413,12 +2557,18 @@ static u64 icl_update_topdown_event(struct perf_event *event) wrmsrl(MSR_CORE_PERF_FIXED_CTR3, 0); wrmsrl(MSR_PERF_METRICS, 0); if (event) - update_saved_topdown_regs(event, 0, 0); + update_saved_topdown_regs(event, 0, 0, metric_end); } return slots; } +static u64 icl_update_topdown_event(struct perf_event *event) +{ + return intel_update_topdown_event(event, INTEL_PMC_IDX_METRIC_BASE + + x86_pmu.num_topdown_events - 1); +} + static void intel_pmu_read_topdown_event(struct perf_event *event) { struct cpu_hw_events *cpuc = this_cpu_ptr(&cpu_hw_events); @@ -2573,8 +2723,11 @@ static void intel_pmu_reset(void) wrmsrl_safe(x86_pmu_config_addr(idx), 0ull); wrmsrl_safe(x86_pmu_event_addr(idx), 0ull); } - for (idx = 0; idx < x86_pmu.num_counters_fixed; idx++) + for (idx = 0; idx < x86_pmu.num_counters_fixed; idx++) { + if (fixed_counter_disabled(idx)) + continue; wrmsrl_safe(MSR_ARCH_PERFMON_FIXED_CTR0 + idx, 0ull); + } if (ds) ds->bts_index = ds->bts_buffer_base; @@ -2709,95 +2862,6 @@ static int handle_pmi_common(struct pt_regs *regs, u64 status) return handled; } -static bool disable_counter_freezing = true; -static int __init intel_perf_counter_freezing_setup(char *s) -{ - bool res; - - if (kstrtobool(s, &res)) - return -EINVAL; - - disable_counter_freezing = !res; - return 1; -} -__setup("perf_v4_pmi=", intel_perf_counter_freezing_setup); - -/* - * Simplified handler for Arch Perfmon v4: - * - We rely on counter freezing/unfreezing to enable/disable the PMU. - * This is done automatically on PMU ack. - * - Ack the PMU only after the APIC. - */ - -static int intel_pmu_handle_irq_v4(struct pt_regs *regs) -{ - struct cpu_hw_events *cpuc = this_cpu_ptr(&cpu_hw_events); - int handled = 0; - bool bts = false; - u64 status; - int pmu_enabled = cpuc->enabled; - int loops = 0; - - /* PMU has been disabled because of counter freezing */ - cpuc->enabled = 0; - if (test_bit(INTEL_PMC_IDX_FIXED_BTS, cpuc->active_mask)) { - bts = true; - intel_bts_disable_local(); - handled = intel_pmu_drain_bts_buffer(); - handled += intel_bts_interrupt(); - } - status = intel_pmu_get_status(); - if (!status) - goto done; -again: - intel_pmu_lbr_read(); - if (++loops > 100) { - static bool warned; - - if (!warned) { - WARN(1, "perfevents: irq loop stuck!\n"); - perf_event_print_debug(); - warned = true; - } - intel_pmu_reset(); - goto done; - } - - - handled += handle_pmi_common(regs, status); -done: - /* Ack the PMI in the APIC */ - apic_write(APIC_LVTPC, APIC_DM_NMI); - - /* - * The counters start counting immediately while ack the status. - * Make it as close as possible to IRET. This avoids bogus - * freezing on Skylake CPUs. - */ - if (status) { - intel_pmu_ack_status(status); - } else { - /* - * CPU may issues two PMIs very close to each other. - * When the PMI handler services the first one, the - * GLOBAL_STATUS is already updated to reflect both. - * When it IRETs, the second PMI is immediately - * handled and it sees clear status. At the meantime, - * there may be a third PMI, because the freezing bit - * isn't set since the ack in first PMI handlers. - * Double check if there is more work to be done. - */ - status = intel_pmu_get_status(); - if (status) - goto again; - } - - if (bts) - intel_bts_enable_local(); - cpuc->enabled = pmu_enabled; - return handled; -} - /* * This handler is triggered by the local APIC, so the APIC IRQ handling * rules apply: @@ -3563,6 +3627,26 @@ static int core_pmu_hw_config(struct perf_event *event) return intel_pmu_bts_config(event); } +#define INTEL_TD_METRIC_AVAILABLE_MAX (INTEL_TD_METRIC_RETIRING + \ + ((x86_pmu.num_topdown_events - 1) << 8)) + +static bool is_available_metric_event(struct perf_event *event) +{ + return is_metric_event(event) && + event->attr.config <= INTEL_TD_METRIC_AVAILABLE_MAX; +} + +static inline bool is_mem_loads_event(struct perf_event *event) +{ + return (event->attr.config & INTEL_ARCH_EVENT_MASK) == X86_CONFIG(.event=0xcd, .umask=0x01); +} + +static inline bool is_mem_loads_aux_event(struct perf_event *event) +{ + return (event->attr.config & INTEL_ARCH_EVENT_MASK) == X86_CONFIG(.event=0x03, .umask=0x82); +} + + static int intel_pmu_hw_config(struct perf_event *event) { int ret = x86_pmu_hw_config(event); @@ -3575,11 +3659,16 @@ static int intel_pmu_hw_config(struct perf_event *event) return ret; if (event->attr.precise_ip) { + if ((event->attr.config & INTEL_ARCH_EVENT_MASK) == INTEL_FIXED_VLBR_EVENT) + return -EINVAL; + if (!(event->attr.freq || (event->attr.wakeup_events && !event->attr.watermark))) { event->hw.flags |= PERF_X86_EVENT_AUTO_RELOAD; if (!(event->attr.sample_type & - ~intel_pmu_large_pebs_flags(event))) + ~intel_pmu_large_pebs_flags(event))) { event->hw.flags |= PERF_X86_EVENT_LARGE_PEBS; + event->attach_state |= PERF_ATTACH_SCHED_CB; + } } if (x86_pmu.pebs_aliases) x86_pmu.pebs_aliases(event); @@ -3592,6 +3681,7 @@ static int intel_pmu_hw_config(struct perf_event *event) ret = intel_pmu_setup_lbr_filter(event); if (ret) return ret; + event->attach_state |= PERF_ATTACH_SCHED_CB; /* * BTS is set up earlier in this path, so don't account twice @@ -3636,7 +3726,7 @@ static int intel_pmu_hw_config(struct perf_event *event) if (event->attr.config & X86_ALL_EVENT_FLAGS) return -EINVAL; - if (is_metric_event(event)) { + if (is_available_metric_event(event)) { struct perf_event *leader = event->group_leader; /* The metric events don't support sampling. */ @@ -3665,6 +3755,33 @@ static int intel_pmu_hw_config(struct perf_event *event) } } + /* + * The load latency event X86_CONFIG(.event=0xcd, .umask=0x01) on SPR + * doesn't function quite right. As a work-around it needs to always be + * co-scheduled with a auxiliary event X86_CONFIG(.event=0x03, .umask=0x82). + * The actual count of this second event is irrelevant it just needs + * to be active to make the first event function correctly. + * + * In a group, the auxiliary event must be in front of the load latency + * event. The rule is to simplify the implementation of the check. + * That's because perf cannot have a complete group at the moment. + */ + if (x86_pmu.flags & PMU_FL_MEM_LOADS_AUX && + (event->attr.sample_type & PERF_SAMPLE_DATA_SRC) && + is_mem_loads_event(event)) { + struct perf_event *leader = event->group_leader; + struct perf_event *sibling = NULL; + + if (!is_mem_loads_aux_event(leader)) { + for_each_sibling_event(sibling, leader) { + if (is_mem_loads_aux_event(sibling)) + break; + } + if (list_entry_is_head(sibling, &leader->sibling_list, sibling_list)) + return -ENODATA; + } + } + if (!(event->attr.config & ARCH_PERFMON_EVENTSEL_ANY)) return 0; @@ -3680,26 +3797,6 @@ static int intel_pmu_hw_config(struct perf_event *event) return 0; } -#ifdef CONFIG_RETPOLINE -static struct perf_guest_switch_msr *core_guest_get_msrs(int *nr); -static struct perf_guest_switch_msr *intel_guest_get_msrs(int *nr); -#endif - -struct perf_guest_switch_msr *perf_guest_get_msrs(int *nr) -{ -#ifdef CONFIG_RETPOLINE - if (x86_pmu.guest_get_msrs == intel_guest_get_msrs) - return intel_guest_get_msrs(nr); - else if (x86_pmu.guest_get_msrs == core_guest_get_msrs) - return core_guest_get_msrs(nr); -#endif - if (x86_pmu.guest_get_msrs) - return x86_pmu.guest_get_msrs(nr); - *nr = 0; - return NULL; -} -EXPORT_SYMBOL_GPL(perf_guest_get_msrs); - static struct perf_guest_switch_msr *intel_guest_get_msrs(int *nr) { struct cpu_hw_events *cpuc = this_cpu_ptr(&cpu_hw_events); @@ -3865,6 +3962,29 @@ icl_get_event_constraints(struct cpu_hw_events *cpuc, int idx, } static struct event_constraint * +spr_get_event_constraints(struct cpu_hw_events *cpuc, int idx, + struct perf_event *event) +{ + struct event_constraint *c; + + c = icl_get_event_constraints(cpuc, idx, event); + + /* + * The :ppp indicates the Precise Distribution (PDist) facility, which + * is only supported on the GP counter 0. If a :ppp event which is not + * available on the GP counter 0, error out. + */ + if (event->attr.precise_ip == 3) { + if (c->idxmsk64 & BIT_ULL(0)) + return &counter0_constraint; + + return &emptyconstraint; + } + + return c; +} + +static struct event_constraint * glp_get_event_constraints(struct cpu_hw_events *cpuc, int idx, struct perf_event *event) { @@ -3953,6 +4073,14 @@ static u64 nhm_limit_period(struct perf_event *event, u64 left) return max(left, 32ULL); } +static u64 spr_limit_period(struct perf_event *event, u64 left) +{ + if (event->attr.precise_ip == 3) + return max(left, 128ULL); + + return left; +} + PMU_FORMAT_ATTR(event, "config:0-7" ); PMU_FORMAT_ATTR(umask, "config:8-15" ); PMU_FORMAT_ATTR(edge, "config:18" ); @@ -4094,9 +4222,6 @@ static void intel_pmu_cpu_starting(int cpu) if (x86_pmu.version > 1) flip_smm_bit(&x86_pmu.attr_freeze_on_smi); - if (x86_pmu.counter_freezing) - enable_counter_freeze(); - /* Disable perf metrics if any added CPU doesn't support it. */ if (x86_pmu.intel_cap.perf_metrics) { union perf_capabilities perf_cap; @@ -4167,9 +4292,6 @@ static void free_excl_cntrs(struct cpu_hw_events *cpuc) static void intel_pmu_cpu_dying(int cpu) { fini_debug_store_on_cpu(cpu); - - if (x86_pmu.counter_freezing) - disable_counter_freeze(); } void intel_cpuc_finish(struct cpu_hw_events *cpuc) @@ -4397,6 +4519,9 @@ static const struct x86_cpu_desc isolation_ucodes[] = { INTEL_CPU_DESC(INTEL_FAM6_BROADWELL_X, 2, 0x0b000014), INTEL_CPU_DESC(INTEL_FAM6_SKYLAKE_X, 3, 0x00000021), INTEL_CPU_DESC(INTEL_FAM6_SKYLAKE_X, 4, 0x00000000), + INTEL_CPU_DESC(INTEL_FAM6_SKYLAKE_X, 5, 0x00000000), + INTEL_CPU_DESC(INTEL_FAM6_SKYLAKE_X, 6, 0x00000000), + INTEL_CPU_DESC(INTEL_FAM6_SKYLAKE_X, 7, 0x00000000), INTEL_CPU_DESC(INTEL_FAM6_SKYLAKE_L, 3, 0x0000007c), INTEL_CPU_DESC(INTEL_FAM6_SKYLAKE, 3, 0x0000007c), INTEL_CPU_DESC(INTEL_FAM6_KABYLAKE, 9, 0x0000004e), @@ -4561,39 +4686,6 @@ static __init void intel_nehalem_quirk(void) } } -static const struct x86_cpu_desc counter_freezing_ucodes[] = { - INTEL_CPU_DESC(INTEL_FAM6_ATOM_GOLDMONT, 2, 0x0000000e), - INTEL_CPU_DESC(INTEL_FAM6_ATOM_GOLDMONT, 9, 0x0000002e), - INTEL_CPU_DESC(INTEL_FAM6_ATOM_GOLDMONT, 10, 0x00000008), - INTEL_CPU_DESC(INTEL_FAM6_ATOM_GOLDMONT_D, 1, 0x00000028), - INTEL_CPU_DESC(INTEL_FAM6_ATOM_GOLDMONT_PLUS, 1, 0x00000028), - INTEL_CPU_DESC(INTEL_FAM6_ATOM_GOLDMONT_PLUS, 8, 0x00000006), - {} -}; - -static bool intel_counter_freezing_broken(void) -{ - return !x86_cpu_has_min_microcode_rev(counter_freezing_ucodes); -} - -static __init void intel_counter_freezing_quirk(void) -{ - /* Check if it's already disabled */ - if (disable_counter_freezing) - return; - - /* - * If the system starts with the wrong ucode, leave the - * counter-freezing feature permanently disabled. - */ - if (intel_counter_freezing_broken()) { - pr_info("PMU counter freezing disabled due to CPU errata," - "please upgrade microcode\n"); - x86_pmu.counter_freezing = false; - x86_pmu.handle_irq = intel_pmu_handle_irq; - } -} - /* * enable software workaround for errata: * SNB: BJ122 @@ -4703,6 +4795,42 @@ static struct attribute *icl_tsx_events_attrs[] = { NULL, }; + +EVENT_ATTR_STR(mem-stores, mem_st_spr, "event=0xcd,umask=0x2"); +EVENT_ATTR_STR(mem-loads-aux, mem_ld_aux, "event=0x03,umask=0x82"); + +static struct attribute *spr_events_attrs[] = { + EVENT_PTR(mem_ld_hsw), + EVENT_PTR(mem_st_spr), + EVENT_PTR(mem_ld_aux), + NULL, +}; + +static struct attribute *spr_td_events_attrs[] = { + EVENT_PTR(slots), + EVENT_PTR(td_retiring), + EVENT_PTR(td_bad_spec), + EVENT_PTR(td_fe_bound), + EVENT_PTR(td_be_bound), + EVENT_PTR(td_heavy_ops), + EVENT_PTR(td_br_mispredict), + EVENT_PTR(td_fetch_lat), + EVENT_PTR(td_mem_bound), + NULL, +}; + +static struct attribute *spr_tsx_events_attrs[] = { + EVENT_PTR(tx_start), + EVENT_PTR(tx_abort), + EVENT_PTR(tx_commit), + EVENT_PTR(tx_capacity_read), + EVENT_PTR(tx_capacity_write), + EVENT_PTR(tx_conflict), + EVENT_PTR(cycles_t), + EVENT_PTR(cycles_ct), + NULL, +}; + static ssize_t freeze_on_smi_show(struct device *cdev, struct device_attribute *attr, char *buf) @@ -4926,7 +5054,7 @@ __init int intel_pmu_init(void) union cpuid10_eax eax; union cpuid10_ebx ebx; struct event_constraint *c; - unsigned int unused; + unsigned int fixed_mask; struct extra_reg *er; bool pmem = false; int version, i; @@ -4948,7 +5076,7 @@ __init int intel_pmu_init(void) * Check whether the Architectural PerfMon supports * Branch Misses Retired hw_event or not. */ - cpuid(10, &eax.full, &ebx.full, &unused, &edx.full); + cpuid(10, &eax.full, &ebx.full, &fixed_mask, &edx.full); if (eax.split.mask_length < ARCH_PERFMON_EVENTS_COUNT) return -ENODEV; @@ -4972,15 +5100,15 @@ __init int intel_pmu_init(void) * Quirk: v2 perfmon does not report fixed-purpose events, so * assume at least 3 events, when not running in a hypervisor: */ - if (version > 1) { + if (version > 1 && version < 5) { int assume = 3 * !boot_cpu_has(X86_FEATURE_HYPERVISOR); x86_pmu.num_counters_fixed = max((int)edx.split.num_counters_fixed, assume); - } - if (version >= 4) - x86_pmu.counter_freezing = !disable_counter_freezing; + fixed_mask = (1L << x86_pmu.num_counters_fixed) - 1; + } else if (version >= 5) + x86_pmu.num_counters_fixed = fls(fixed_mask); if (boot_cpu_has(X86_FEATURE_PDCM)) { u64 capabilities; @@ -5109,7 +5237,6 @@ __init int intel_pmu_init(void) case INTEL_FAM6_ATOM_GOLDMONT: case INTEL_FAM6_ATOM_GOLDMONT_D: - x86_add_quirk(intel_counter_freezing_quirk); memcpy(hw_cache_event_ids, glm_hw_cache_event_ids, sizeof(hw_cache_event_ids)); memcpy(hw_cache_extra_regs, glm_hw_cache_extra_regs, @@ -5136,7 +5263,6 @@ __init int intel_pmu_init(void) break; case INTEL_FAM6_ATOM_GOLDMONT_PLUS: - x86_add_quirk(intel_counter_freezing_quirk); memcpy(hw_cache_event_ids, glp_hw_cache_event_ids, sizeof(hw_cache_event_ids)); memcpy(hw_cache_extra_regs, glp_hw_cache_extra_regs, @@ -5483,12 +5609,50 @@ __init int intel_pmu_init(void) x86_pmu.rtm_abort_event = X86_CONFIG(.event=0xc9, .umask=0x04); x86_pmu.lbr_pt_coexist = true; intel_pmu_pebs_data_source_skl(pmem); + x86_pmu.num_topdown_events = 4; x86_pmu.update_topdown_event = icl_update_topdown_event; x86_pmu.set_topdown_event_period = icl_set_topdown_event_period; pr_cont("Icelake events, "); name = "icelake"; break; + case INTEL_FAM6_SAPPHIRERAPIDS_X: + pmem = true; + x86_pmu.late_ack = true; + memcpy(hw_cache_event_ids, spr_hw_cache_event_ids, sizeof(hw_cache_event_ids)); + memcpy(hw_cache_extra_regs, spr_hw_cache_extra_regs, sizeof(hw_cache_extra_regs)); + + x86_pmu.event_constraints = intel_spr_event_constraints; + x86_pmu.pebs_constraints = intel_spr_pebs_event_constraints; + x86_pmu.extra_regs = intel_spr_extra_regs; + x86_pmu.limit_period = spr_limit_period; + x86_pmu.pebs_aliases = NULL; + x86_pmu.pebs_prec_dist = true; + x86_pmu.pebs_block = true; + x86_pmu.flags |= PMU_FL_HAS_RSP_1; + x86_pmu.flags |= PMU_FL_NO_HT_SHARING; + x86_pmu.flags |= PMU_FL_PEBS_ALL; + x86_pmu.flags |= PMU_FL_INSTR_LATENCY; + x86_pmu.flags |= PMU_FL_MEM_LOADS_AUX; + + x86_pmu.hw_config = hsw_hw_config; + x86_pmu.get_event_constraints = spr_get_event_constraints; + extra_attr = boot_cpu_has(X86_FEATURE_RTM) ? + hsw_format_attr : nhm_format_attr; + extra_skl_attr = skl_format_attr; + mem_attr = spr_events_attrs; + td_attr = spr_td_events_attrs; + tsx_attr = spr_tsx_events_attrs; + x86_pmu.rtm_abort_event = X86_CONFIG(.event=0xc9, .umask=0x04); + x86_pmu.lbr_pt_coexist = true; + intel_pmu_pebs_data_source_skl(pmem); + x86_pmu.num_topdown_events = 8; + x86_pmu.update_topdown_event = icl_update_topdown_event; + x86_pmu.set_topdown_event_period = icl_set_topdown_event_period; + pr_cont("Sapphire Rapids events, "); + name = "sapphire_rapids"; + break; + default: switch (x86_pmu.version) { case 1: @@ -5531,8 +5695,7 @@ __init int intel_pmu_init(void) x86_pmu.num_counters_fixed = INTEL_PMC_MAX_FIXED; } - x86_pmu.intel_ctrl |= - ((1LL << x86_pmu.num_counters_fixed)-1) << INTEL_PMC_IDX_FIXED; + x86_pmu.intel_ctrl |= (u64)fixed_mask << INTEL_PMC_IDX_FIXED; /* AnyThread may be deprecated on arch perfmon v5 or later */ if (x86_pmu.intel_cap.anythread_deprecated) @@ -5549,13 +5712,22 @@ __init int intel_pmu_init(void) * events to the generic counters. */ if (c->idxmsk64 & INTEL_PMC_MSK_TOPDOWN) { + /* + * Disable topdown slots and metrics events, + * if slots event is not in CPUID. + */ + if (!(INTEL_PMC_MSK_FIXED_SLOTS & x86_pmu.intel_ctrl)) + c->idxmsk64 = 0; c->weight = hweight64(c->idxmsk64); continue; } - if (c->cmask == FIXED_EVENT_FLAGS - && c->idxmsk64 != INTEL_PMC_MSK_FIXED_REF_CYCLES) { - c->idxmsk64 |= (1ULL << x86_pmu.num_counters) - 1; + if (c->cmask == FIXED_EVENT_FLAGS) { + /* Disabled fixed counters which are not in CPUID */ + c->idxmsk64 &= x86_pmu.intel_ctrl; + + if (c->idxmsk64 != INTEL_PMC_MSK_FIXED_REF_CYCLES) + c->idxmsk64 |= (1ULL << x86_pmu.num_counters) - 1; } c->idxmsk64 &= ~(~0ULL << (INTEL_PMC_IDX_FIXED + x86_pmu.num_counters_fixed)); @@ -5601,13 +5773,6 @@ __init int intel_pmu_init(void) pr_cont("full-width counters, "); } - /* - * For arch perfmon 4 use counter freezing to avoid - * several MSR accesses in the PMI. - */ - if (x86_pmu.counter_freezing) - x86_pmu.handle_irq = intel_pmu_handle_irq_v4; - if (x86_pmu.intel_cap.perf_metrics) x86_pmu.intel_ctrl |= 1ULL << GLOBAL_CTRL_EN_PERF_METRICS; diff --git a/arch/x86/events/intel/ds.c b/arch/x86/events/intel/ds.c index 67dbc91bccfe..d32b302719fe 100644 --- a/arch/x86/events/intel/ds.c +++ b/arch/x86/events/intel/ds.c @@ -36,7 +36,9 @@ union intel_x86_pebs_dse { unsigned int ld_dse:4; unsigned int ld_stlb_miss:1; unsigned int ld_locked:1; - unsigned int ld_reserved:26; + unsigned int ld_data_blk:1; + unsigned int ld_addr_blk:1; + unsigned int ld_reserved:24; }; struct { unsigned int st_l1d_hit:1; @@ -45,6 +47,12 @@ union intel_x86_pebs_dse { unsigned int st_locked:1; unsigned int st_reserved2:26; }; + struct { + unsigned int st_lat_dse:4; + unsigned int st_lat_stlb_miss:1; + unsigned int st_lat_locked:1; + unsigned int ld_reserved3:26; + }; }; @@ -198,6 +206,63 @@ static u64 load_latency_data(u64 status) if (dse.ld_locked) val |= P(LOCK, LOCKED); + /* + * Ice Lake and earlier models do not support block infos. + */ + if (!x86_pmu.pebs_block) { + val |= P(BLK, NA); + return val; + } + /* + * bit 6: load was blocked since its data could not be forwarded + * from a preceding store + */ + if (dse.ld_data_blk) + val |= P(BLK, DATA); + + /* + * bit 7: load was blocked due to potential address conflict with + * a preceding store + */ + if (dse.ld_addr_blk) + val |= P(BLK, ADDR); + + if (!dse.ld_data_blk && !dse.ld_addr_blk) + val |= P(BLK, NA); + + return val; +} + +static u64 store_latency_data(u64 status) +{ + union intel_x86_pebs_dse dse; + u64 val; + + dse.val = status; + + /* + * use the mapping table for bit 0-3 + */ + val = pebs_data_source[dse.st_lat_dse]; + + /* + * bit 4: TLB access + * 0 = did not miss 2nd level TLB + * 1 = missed 2nd level TLB + */ + if (dse.st_lat_stlb_miss) + val |= P(TLB, MISS) | P(TLB, L2); + else + val |= P(TLB, HIT) | P(TLB, L1) | P(TLB, L2); + + /* + * bit 5: locked prefix + */ + if (dse.st_lat_locked) + val |= P(LOCK, LOCKED); + + val |= P(BLK, NA); + return val; } @@ -870,6 +935,28 @@ struct event_constraint intel_icl_pebs_event_constraints[] = { EVENT_CONSTRAINT_END }; +struct event_constraint intel_spr_pebs_event_constraints[] = { + INTEL_FLAGS_UEVENT_CONSTRAINT(0x1c0, 0x100000000ULL), + INTEL_FLAGS_UEVENT_CONSTRAINT(0x0400, 0x800000000ULL), + + INTEL_FLAGS_EVENT_CONSTRAINT(0xc0, 0xfe), + INTEL_PLD_CONSTRAINT(0x1cd, 0xfe), + INTEL_PSD_CONSTRAINT(0x2cd, 0x1), + INTEL_FLAGS_UEVENT_CONSTRAINT_DATALA_LD(0x1d0, 0xf), + INTEL_FLAGS_UEVENT_CONSTRAINT_DATALA_ST(0x2d0, 0xf), + + INTEL_FLAGS_EVENT_CONSTRAINT_DATALA_LD_RANGE(0xd1, 0xd4, 0xf), + + INTEL_FLAGS_EVENT_CONSTRAINT(0xd0, 0xf), + + /* + * Everything else is handled by PMU_FL_PEBS_ALL, because we + * need the full constraints from the main table. + */ + + EVENT_CONSTRAINT_END +}; + struct event_constraint *intel_pebs_constraints(struct perf_event *event) { struct event_constraint *c; @@ -960,7 +1047,8 @@ static void adaptive_pebs_record_size_update(void) } #define PERF_PEBS_MEMINFO_TYPE (PERF_SAMPLE_ADDR | PERF_SAMPLE_DATA_SRC | \ - PERF_SAMPLE_PHYS_ADDR | PERF_SAMPLE_WEIGHT | \ + PERF_SAMPLE_PHYS_ADDR | \ + PERF_SAMPLE_WEIGHT_TYPE | \ PERF_SAMPLE_TRANSACTION | \ PERF_SAMPLE_DATA_PAGE_SIZE) @@ -987,7 +1075,7 @@ static u64 pebs_update_adaptive_cfg(struct perf_event *event) gprs = (sample_type & PERF_SAMPLE_REGS_INTR) && (attr->sample_regs_intr & PEBS_GP_REGS); - tsx_weight = (sample_type & PERF_SAMPLE_WEIGHT) && + tsx_weight = (sample_type & PERF_SAMPLE_WEIGHT_TYPE) && ((attr->config & INTEL_ARCH_EVENT_MASK) == x86_pmu.rtm_abort_event); @@ -1331,6 +1419,8 @@ static u64 get_data_src(struct perf_event *event, u64 aux) if (fl & PERF_X86_EVENT_PEBS_LDLAT) val = load_latency_data(aux); + else if (fl & PERF_X86_EVENT_PEBS_STLAT) + val = store_latency_data(aux); else if (fst && (fl & PERF_X86_EVENT_PEBS_HSW_PREC)) val = precise_datala_hsw(event, aux); else if (fst) @@ -1369,8 +1459,8 @@ static void setup_pebs_fixed_sample_data(struct perf_event *event, /* * Use latency for weight (only avail with PEBS-LL) */ - if (fll && (sample_type & PERF_SAMPLE_WEIGHT)) - data->weight = pebs->lat; + if (fll && (sample_type & PERF_SAMPLE_WEIGHT_TYPE)) + data->weight.full = pebs->lat; /* * data.data_src encodes the data source @@ -1462,8 +1552,8 @@ static void setup_pebs_fixed_sample_data(struct perf_event *event, if (x86_pmu.intel_cap.pebs_format >= 2) { /* Only set the TSX weight when no memory weight. */ - if ((sample_type & PERF_SAMPLE_WEIGHT) && !fll) - data->weight = intel_get_tsx_weight(pebs->tsx_tuning); + if ((sample_type & PERF_SAMPLE_WEIGHT_TYPE) && !fll) + data->weight.full = intel_get_tsx_weight(pebs->tsx_tuning); if (sample_type & PERF_SAMPLE_TRANSACTION) data->txn = intel_get_tsx_transaction(pebs->tsx_tuning, @@ -1507,6 +1597,9 @@ static void adaptive_pebs_save_regs(struct pt_regs *regs, #endif } +#define PEBS_LATENCY_MASK 0xffff +#define PEBS_CACHE_LATENCY_OFFSET 32 + /* * With adaptive PEBS the layout depends on what fields are configured. */ @@ -1577,9 +1670,27 @@ static void setup_pebs_adaptive_sample_data(struct perf_event *event, } if (format_size & PEBS_DATACFG_MEMINFO) { - if (sample_type & PERF_SAMPLE_WEIGHT) - data->weight = meminfo->latency ?: - intel_get_tsx_weight(meminfo->tsx_tuning); + if (sample_type & PERF_SAMPLE_WEIGHT_TYPE) { + u64 weight = meminfo->latency; + + if (x86_pmu.flags & PMU_FL_INSTR_LATENCY) { + data->weight.var2_w = weight & PEBS_LATENCY_MASK; + weight >>= PEBS_CACHE_LATENCY_OFFSET; + } + + /* + * Although meminfo::latency is defined as a u64, + * only the lower 32 bits include the valid data + * in practice on Ice Lake and earlier platforms. + */ + if (sample_type & PERF_SAMPLE_WEIGHT) { + data->weight.full = weight ?: + intel_get_tsx_weight(meminfo->tsx_tuning); + } else { + data->weight.var1_dw = (u32)(weight & PEBS_LATENCY_MASK) ?: + intel_get_tsx_weight(meminfo->tsx_tuning); + } + } if (sample_type & PERF_SAMPLE_DATA_SRC) data->data_src.val = get_data_src(event, meminfo->aux); @@ -1899,7 +2010,7 @@ static void intel_pmu_drain_pebs_nhm(struct pt_regs *iregs, struct perf_sample_d */ if (!pebs_status && cpuc->pebs_enabled && !(cpuc->pebs_enabled & (cpuc->pebs_enabled-1))) - pebs_status = cpuc->pebs_enabled; + pebs_status = p->status = cpuc->pebs_enabled; bit = find_first_bit((unsigned long *)&pebs_status, x86_pmu.max_pebs_events); diff --git a/arch/x86/events/intel/uncore.c b/arch/x86/events/intel/uncore.c index 357258f82dc8..33c8180d5a87 100644 --- a/arch/x86/events/intel/uncore.c +++ b/arch/x86/events/intel/uncore.c @@ -31,21 +31,21 @@ struct event_constraint uncore_constraint_empty = MODULE_LICENSE("GPL"); -int uncore_pcibus_to_physid(struct pci_bus *bus) +int uncore_pcibus_to_dieid(struct pci_bus *bus) { struct pci2phy_map *map; - int phys_id = -1; + int die_id = -1; raw_spin_lock(&pci2phy_map_lock); list_for_each_entry(map, &pci2phy_map_head, list) { if (map->segment == pci_domain_nr(bus)) { - phys_id = map->pbus_to_physid[bus->number]; + die_id = map->pbus_to_dieid[bus->number]; break; } } raw_spin_unlock(&pci2phy_map_lock); - return phys_id; + return die_id; } static void uncore_free_pcibus_map(void) @@ -86,7 +86,7 @@ lookup: alloc = NULL; map->segment = segment; for (i = 0; i < 256; i++) - map->pbus_to_physid[i] = -1; + map->pbus_to_dieid[i] = -1; list_add_tail(&map->list, &pci2phy_map_head); end: @@ -332,7 +332,6 @@ static struct intel_uncore_box *uncore_alloc_box(struct intel_uncore_type *type, uncore_pmu_init_hrtimer(box); box->cpu = -1; - box->pci_phys_id = -1; box->dieid = -1; /* set default hrtimer timeout */ @@ -993,18 +992,11 @@ uncore_types_init(struct intel_uncore_type **types, bool setid) /* * Get the die information of a PCI device. * @pdev: The PCI device. - * @phys_id: The physical socket id which the device maps to. * @die: The die id which the device maps to. */ -static int uncore_pci_get_dev_die_info(struct pci_dev *pdev, - int *phys_id, int *die) +static int uncore_pci_get_dev_die_info(struct pci_dev *pdev, int *die) { - *phys_id = uncore_pcibus_to_physid(pdev->bus); - if (*phys_id < 0) - return -ENODEV; - - *die = (topology_max_die_per_package() > 1) ? *phys_id : - topology_phys_to_logical_pkg(*phys_id); + *die = uncore_pcibus_to_dieid(pdev->bus); if (*die < 0) return -EINVAL; @@ -1046,13 +1038,12 @@ uncore_pci_find_dev_pmu(struct pci_dev *pdev, const struct pci_device_id *ids) * @pdev: The PCI device. * @type: The corresponding PMU type of the device. * @pmu: The corresponding PMU of the device. - * @phys_id: The physical socket id which the device maps to. * @die: The die id which the device maps to. */ static int uncore_pci_pmu_register(struct pci_dev *pdev, struct intel_uncore_type *type, struct intel_uncore_pmu *pmu, - int phys_id, int die) + int die) { struct intel_uncore_box *box; int ret; @@ -1070,7 +1061,6 @@ static int uncore_pci_pmu_register(struct pci_dev *pdev, WARN_ON_ONCE(pmu->func_id != pdev->devfn); atomic_inc(&box->refcnt); - box->pci_phys_id = phys_id; box->dieid = die; box->pci_dev = pdev; box->pmu = pmu; @@ -1097,9 +1087,9 @@ static int uncore_pci_probe(struct pci_dev *pdev, const struct pci_device_id *id { struct intel_uncore_type *type; struct intel_uncore_pmu *pmu = NULL; - int phys_id, die, ret; + int die, ret; - ret = uncore_pci_get_dev_die_info(pdev, &phys_id, &die); + ret = uncore_pci_get_dev_die_info(pdev, &die); if (ret) return ret; @@ -1132,7 +1122,7 @@ static int uncore_pci_probe(struct pci_dev *pdev, const struct pci_device_id *id pmu = &type->pmus[UNCORE_PCI_DEV_IDX(id->driver_data)]; } - ret = uncore_pci_pmu_register(pdev, type, pmu, phys_id, die); + ret = uncore_pci_pmu_register(pdev, type, pmu, die); pci_set_drvdata(pdev, pmu->boxes[die]); @@ -1142,17 +1132,12 @@ static int uncore_pci_probe(struct pci_dev *pdev, const struct pci_device_id *id /* * Unregister the PMU of a PCI device * @pmu: The corresponding PMU is unregistered. - * @phys_id: The physical socket id which the device maps to. * @die: The die id which the device maps to. */ -static void uncore_pci_pmu_unregister(struct intel_uncore_pmu *pmu, - int phys_id, int die) +static void uncore_pci_pmu_unregister(struct intel_uncore_pmu *pmu, int die) { struct intel_uncore_box *box = pmu->boxes[die]; - if (WARN_ON_ONCE(phys_id != box->pci_phys_id)) - return; - pmu->boxes[die] = NULL; if (atomic_dec_return(&pmu->activeboxes) == 0) uncore_pmu_unregister(pmu); @@ -1164,9 +1149,9 @@ static void uncore_pci_remove(struct pci_dev *pdev) { struct intel_uncore_box *box; struct intel_uncore_pmu *pmu; - int i, phys_id, die; + int i, die; - if (uncore_pci_get_dev_die_info(pdev, &phys_id, &die)) + if (uncore_pci_get_dev_die_info(pdev, &die)) return; box = pci_get_drvdata(pdev); @@ -1185,7 +1170,7 @@ static void uncore_pci_remove(struct pci_dev *pdev) pci_set_drvdata(pdev, NULL); - uncore_pci_pmu_unregister(pmu, phys_id, die); + uncore_pci_pmu_unregister(pmu, die); } static int uncore_bus_notify(struct notifier_block *nb, @@ -1194,7 +1179,7 @@ static int uncore_bus_notify(struct notifier_block *nb, struct device *dev = data; struct pci_dev *pdev = to_pci_dev(dev); struct intel_uncore_pmu *pmu; - int phys_id, die; + int die; /* Unregister the PMU when the device is going to be deleted. */ if (action != BUS_NOTIFY_DEL_DEVICE) @@ -1204,10 +1189,10 @@ static int uncore_bus_notify(struct notifier_block *nb, if (!pmu) return NOTIFY_DONE; - if (uncore_pci_get_dev_die_info(pdev, &phys_id, &die)) + if (uncore_pci_get_dev_die_info(pdev, &die)) return NOTIFY_DONE; - uncore_pci_pmu_unregister(pmu, phys_id, die); + uncore_pci_pmu_unregister(pmu, die); return NOTIFY_OK; } @@ -1224,7 +1209,7 @@ static void uncore_pci_sub_driver_init(void) struct pci_dev *pci_sub_dev; bool notify = false; unsigned int devfn; - int phys_id, die; + int die; while (ids && ids->vendor) { pci_sub_dev = NULL; @@ -1244,12 +1229,11 @@ static void uncore_pci_sub_driver_init(void) if (!pmu) continue; - if (uncore_pci_get_dev_die_info(pci_sub_dev, - &phys_id, &die)) + if (uncore_pci_get_dev_die_info(pci_sub_dev, &die)) continue; if (!uncore_pci_pmu_register(pci_sub_dev, type, pmu, - phys_id, die)) + die)) notify = true; } ids++; diff --git a/arch/x86/events/intel/uncore.h b/arch/x86/events/intel/uncore.h index 9efea154349d..a3c6e1643ad2 100644 --- a/arch/x86/events/intel/uncore.h +++ b/arch/x86/events/intel/uncore.h @@ -124,7 +124,6 @@ struct intel_uncore_extra_reg { }; struct intel_uncore_box { - int pci_phys_id; int dieid; /* Logical die ID */ int n_active; /* number of active events */ int n_events; @@ -173,11 +172,11 @@ struct freerunning_counters { struct pci2phy_map { struct list_head list; int segment; - int pbus_to_physid[256]; + int pbus_to_dieid[256]; }; struct pci2phy_map *__find_pci2phy_map(int segment); -int uncore_pcibus_to_physid(struct pci_bus *bus); +int uncore_pcibus_to_dieid(struct pci_bus *bus); ssize_t uncore_event_show(struct device *dev, struct device_attribute *attr, char *buf); diff --git a/arch/x86/events/intel/uncore_snb.c b/arch/x86/events/intel/uncore_snb.c index 098f893e2e22..51271288499e 100644 --- a/arch/x86/events/intel/uncore_snb.c +++ b/arch/x86/events/intel/uncore_snb.c @@ -657,7 +657,7 @@ int snb_pci2phy_map_init(int devid) pci_dev_put(dev); return -ENOMEM; } - map->pbus_to_physid[bus] = 0; + map->pbus_to_dieid[bus] = 0; raw_spin_unlock(&pci2phy_map_lock); pci_dev_put(dev); diff --git a/arch/x86/events/intel/uncore_snbep.c b/arch/x86/events/intel/uncore_snbep.c index 7bdb1821215d..b79951d0707c 100644 --- a/arch/x86/events/intel/uncore_snbep.c +++ b/arch/x86/events/intel/uncore_snbep.c @@ -1359,7 +1359,7 @@ static struct pci_driver snbep_uncore_pci_driver = { static int snbep_pci2phy_map_init(int devid, int nodeid_loc, int idmap_loc, bool reverse) { struct pci_dev *ubox_dev = NULL; - int i, bus, nodeid, segment; + int i, bus, nodeid, segment, die_id; struct pci2phy_map *map; int err = 0; u32 config = 0; @@ -1370,36 +1370,77 @@ static int snbep_pci2phy_map_init(int devid, int nodeid_loc, int idmap_loc, bool if (!ubox_dev) break; bus = ubox_dev->bus->number; - /* get the Node ID of the local register */ - err = pci_read_config_dword(ubox_dev, nodeid_loc, &config); - if (err) - break; - nodeid = config & NODE_ID_MASK; - /* get the Node ID mapping */ - err = pci_read_config_dword(ubox_dev, idmap_loc, &config); - if (err) - break; + /* + * The nodeid and idmap registers only contain enough + * information to handle 8 nodes. On systems with more + * than 8 nodes, we need to rely on NUMA information, + * filled in from BIOS supplied information, to determine + * the topology. + */ + if (nr_node_ids <= 8) { + /* get the Node ID of the local register */ + err = pci_read_config_dword(ubox_dev, nodeid_loc, &config); + if (err) + break; + nodeid = config & NODE_ID_MASK; + /* get the Node ID mapping */ + err = pci_read_config_dword(ubox_dev, idmap_loc, &config); + if (err) + break; - segment = pci_domain_nr(ubox_dev->bus); - raw_spin_lock(&pci2phy_map_lock); - map = __find_pci2phy_map(segment); - if (!map) { + segment = pci_domain_nr(ubox_dev->bus); + raw_spin_lock(&pci2phy_map_lock); + map = __find_pci2phy_map(segment); + if (!map) { + raw_spin_unlock(&pci2phy_map_lock); + err = -ENOMEM; + break; + } + + /* + * every three bits in the Node ID mapping register maps + * to a particular node. + */ + for (i = 0; i < 8; i++) { + if (nodeid == ((config >> (3 * i)) & 0x7)) { + if (topology_max_die_per_package() > 1) + die_id = i; + else + die_id = topology_phys_to_logical_pkg(i); + map->pbus_to_dieid[bus] = die_id; + break; + } + } raw_spin_unlock(&pci2phy_map_lock); - err = -ENOMEM; - break; - } + } else { + int node = pcibus_to_node(ubox_dev->bus); + int cpu; + + segment = pci_domain_nr(ubox_dev->bus); + raw_spin_lock(&pci2phy_map_lock); + map = __find_pci2phy_map(segment); + if (!map) { + raw_spin_unlock(&pci2phy_map_lock); + err = -ENOMEM; + break; + } - /* - * every three bits in the Node ID mapping register maps - * to a particular node. - */ - for (i = 0; i < 8; i++) { - if (nodeid == ((config >> (3 * i)) & 0x7)) { - map->pbus_to_physid[bus] = i; + die_id = -1; + for_each_cpu(cpu, cpumask_of_pcibus(ubox_dev->bus)) { + struct cpuinfo_x86 *c = &cpu_data(cpu); + + if (c->initialized && cpu_to_node(cpu) == node) { + map->pbus_to_dieid[bus] = die_id = c->logical_die_id; + break; + } + } + raw_spin_unlock(&pci2phy_map_lock); + + if (WARN_ON_ONCE(die_id == -1)) { + err = -EINVAL; break; } } - raw_spin_unlock(&pci2phy_map_lock); } if (!err) { @@ -1412,17 +1453,17 @@ static int snbep_pci2phy_map_init(int devid, int nodeid_loc, int idmap_loc, bool i = -1; if (reverse) { for (bus = 255; bus >= 0; bus--) { - if (map->pbus_to_physid[bus] >= 0) - i = map->pbus_to_physid[bus]; + if (map->pbus_to_dieid[bus] >= 0) + i = map->pbus_to_dieid[bus]; else - map->pbus_to_physid[bus] = i; + map->pbus_to_dieid[bus] = i; } } else { for (bus = 0; bus <= 255; bus++) { - if (map->pbus_to_physid[bus] >= 0) - i = map->pbus_to_physid[bus]; + if (map->pbus_to_dieid[bus] >= 0) + i = map->pbus_to_dieid[bus]; else - map->pbus_to_physid[bus] = i; + map->pbus_to_dieid[bus] = i; } } } @@ -4646,19 +4687,14 @@ int snr_uncore_pci_init(void) static struct pci_dev *snr_uncore_get_mc_dev(int id) { struct pci_dev *mc_dev = NULL; - int phys_id, pkg; + int pkg; while (1) { mc_dev = pci_get_device(PCI_VENDOR_ID_INTEL, 0x3451, mc_dev); if (!mc_dev) break; - phys_id = uncore_pcibus_to_physid(mc_dev->bus); - if (phys_id < 0) - continue; - pkg = topology_phys_to_logical_pkg(phys_id); - if (pkg < 0) - continue; - else if (pkg == id) + pkg = uncore_pcibus_to_dieid(mc_dev->bus); + if (pkg == id) break; } return mc_dev; diff --git a/arch/x86/events/perf_event.h b/arch/x86/events/perf_event.h index 7895cf4c59a7..53b2b5fc23bc 100644 --- a/arch/x86/events/perf_event.h +++ b/arch/x86/events/perf_event.h @@ -80,6 +80,7 @@ static inline bool constraint_match(struct event_constraint *c, u64 ecode) #define PERF_X86_EVENT_PAIR 0x1000 /* Large Increment per Cycle */ #define PERF_X86_EVENT_LBR_SELECT 0x2000 /* Save/Restore MSR_LBR_SELECT */ #define PERF_X86_EVENT_TOPDOWN 0x4000 /* Count Topdown slots/metrics events */ +#define PERF_X86_EVENT_PEBS_STLAT 0x8000 /* st+stlat data address sampling */ static inline bool is_topdown_count(struct perf_event *event) { @@ -443,6 +444,10 @@ struct cpu_hw_events { __EVENT_CONSTRAINT(c, n, INTEL_ARCH_EVENT_MASK|X86_ALL_EVENT_FLAGS, \ HWEIGHT(n), 0, PERF_X86_EVENT_PEBS_LDLAT) +#define INTEL_PSD_CONSTRAINT(c, n) \ + __EVENT_CONSTRAINT(c, n, INTEL_ARCH_EVENT_MASK|X86_ALL_EVENT_FLAGS, \ + HWEIGHT(n), 0, PERF_X86_EVENT_PEBS_STLAT) + #define INTEL_PST_CONSTRAINT(c, n) \ __EVENT_CONSTRAINT(c, n, INTEL_ARCH_EVENT_MASK|X86_ALL_EVENT_FLAGS, \ HWEIGHT(n), 0, PERF_X86_EVENT_PEBS_ST) @@ -682,8 +687,7 @@ struct x86_pmu { /* PMI handler bits */ unsigned int late_ack :1, - enabled_ack :1, - counter_freezing :1; + enabled_ack :1; /* * sysfs attrs */ @@ -724,7 +728,8 @@ struct x86_pmu { pebs_broken :1, pebs_prec_dist :1, pebs_no_tlb :1, - pebs_no_isolation :1; + pebs_no_isolation :1, + pebs_block :1; int pebs_record_size; int pebs_buffer_size; int max_pebs_events; @@ -776,6 +781,7 @@ struct x86_pmu { /* * Intel perf metrics */ + int num_topdown_events; u64 (*update_topdown_event)(struct perf_event *event); int (*set_topdown_event_period)(struct perf_event *event); @@ -871,6 +877,8 @@ do { \ #define PMU_FL_PEBS_ALL 0x10 /* all events are valid PEBS events */ #define PMU_FL_TFA 0x20 /* deal with TSX force abort */ #define PMU_FL_PAIR 0x40 /* merge counters for large incr. events */ +#define PMU_FL_INSTR_LATENCY 0x80 /* Support Instruction Latency in PEBS Memory Info Record */ +#define PMU_FL_MEM_LOADS_AUX 0x100 /* Require an auxiliary event for the complete memory info */ #define EVENT_VAR(_id) event_attr_##_id #define EVENT_PTR(_id) &event_attr_##_id.attr.attr @@ -1060,6 +1068,11 @@ ssize_t events_sysfs_show(struct device *dev, struct device_attribute *attr, ssize_t events_ht_sysfs_show(struct device *dev, struct device_attribute *attr, char *page); +static inline bool fixed_counter_disabled(int i) +{ + return !(x86_pmu.intel_ctrl >> (i + INTEL_PMC_IDX_FIXED)); +} + #ifdef CONFIG_CPU_SUP_AMD int amd_pmu_init(void); @@ -1157,6 +1170,8 @@ extern struct event_constraint intel_skl_pebs_event_constraints[]; extern struct event_constraint intel_icl_pebs_event_constraints[]; +extern struct event_constraint intel_spr_pebs_event_constraints[]; + struct event_constraint *intel_pebs_constraints(struct perf_event *event); void intel_pmu_pebs_add(struct perf_event *event); diff --git a/arch/x86/events/probe.c b/arch/x86/events/probe.c index 136a1e847254..600bf8d15c0c 100644 --- a/arch/x86/events/probe.c +++ b/arch/x86/events/probe.c @@ -28,6 +28,7 @@ perf_msr_probe(struct perf_msr *msr, int cnt, bool zero, void *data) for (bit = 0; bit < cnt; bit++) { if (!msr[bit].no_check) { struct attribute_group *grp = msr[bit].grp; + u64 mask; /* skip entry with no group */ if (!grp) @@ -44,8 +45,12 @@ perf_msr_probe(struct perf_msr *msr, int cnt, bool zero, void *data) /* Virt sucks; you cannot tell if a R/O MSR is present :/ */ if (rdmsrl_safe(msr[bit].msr, &val)) continue; + + mask = msr[bit].mask; + if (!mask) + mask = ~0ULL; /* Disable zero counters if requested. */ - if (!zero && !val) + if (!zero && !(val & mask)) continue; grp->is_visible = NULL; diff --git a/arch/x86/events/probe.h b/arch/x86/events/probe.h index 4c8e0afc5fb5..261b9bda24e3 100644 --- a/arch/x86/events/probe.h +++ b/arch/x86/events/probe.h @@ -4,10 +4,11 @@ #include <linux/sysfs.h> struct perf_msr { - u64 msr; - struct attribute_group *grp; + u64 msr; + struct attribute_group *grp; bool (*test)(int idx, void *data); - bool no_check; + bool no_check; + u64 mask; }; unsigned long diff --git a/arch/x86/events/rapl.c b/arch/x86/events/rapl.c index 7dbbeaacd995..f42a70496a24 100644 --- a/arch/x86/events/rapl.c +++ b/arch/x86/events/rapl.c @@ -454,16 +454,9 @@ static struct attribute *rapl_events_cores[] = { NULL, }; -static umode_t -rapl_not_visible(struct kobject *kobj, struct attribute *attr, int i) -{ - return 0; -} - static struct attribute_group rapl_events_cores_group = { .name = "events", .attrs = rapl_events_cores, - .is_visible = rapl_not_visible, }; static struct attribute *rapl_events_pkg[] = { @@ -476,7 +469,6 @@ static struct attribute *rapl_events_pkg[] = { static struct attribute_group rapl_events_pkg_group = { .name = "events", .attrs = rapl_events_pkg, - .is_visible = rapl_not_visible, }; static struct attribute *rapl_events_ram[] = { @@ -489,7 +481,6 @@ static struct attribute *rapl_events_ram[] = { static struct attribute_group rapl_events_ram_group = { .name = "events", .attrs = rapl_events_ram, - .is_visible = rapl_not_visible, }; static struct attribute *rapl_events_gpu[] = { @@ -502,7 +493,6 @@ static struct attribute *rapl_events_gpu[] = { static struct attribute_group rapl_events_gpu_group = { .name = "events", .attrs = rapl_events_gpu, - .is_visible = rapl_not_visible, }; static struct attribute *rapl_events_psys[] = { @@ -515,7 +505,6 @@ static struct attribute *rapl_events_psys[] = { static struct attribute_group rapl_events_psys_group = { .name = "events", .attrs = rapl_events_psys, - .is_visible = rapl_not_visible, }; static bool test_msr(int idx, void *data) @@ -523,12 +512,23 @@ static bool test_msr(int idx, void *data) return test_bit(idx, (unsigned long *) data); } +/* Only lower 32bits of the MSR represents the energy counter */ +#define RAPL_MSR_MASK 0xFFFFFFFF + static struct perf_msr intel_rapl_msrs[] = { - [PERF_RAPL_PP0] = { MSR_PP0_ENERGY_STATUS, &rapl_events_cores_group, test_msr }, - [PERF_RAPL_PKG] = { MSR_PKG_ENERGY_STATUS, &rapl_events_pkg_group, test_msr }, - [PERF_RAPL_RAM] = { MSR_DRAM_ENERGY_STATUS, &rapl_events_ram_group, test_msr }, - [PERF_RAPL_PP1] = { MSR_PP1_ENERGY_STATUS, &rapl_events_gpu_group, test_msr }, - [PERF_RAPL_PSYS] = { MSR_PLATFORM_ENERGY_STATUS, &rapl_events_psys_group, test_msr }, + [PERF_RAPL_PP0] = { MSR_PP0_ENERGY_STATUS, &rapl_events_cores_group, test_msr, false, RAPL_MSR_MASK }, + [PERF_RAPL_PKG] = { MSR_PKG_ENERGY_STATUS, &rapl_events_pkg_group, test_msr, false, RAPL_MSR_MASK }, + [PERF_RAPL_RAM] = { MSR_DRAM_ENERGY_STATUS, &rapl_events_ram_group, test_msr, false, RAPL_MSR_MASK }, + [PERF_RAPL_PP1] = { MSR_PP1_ENERGY_STATUS, &rapl_events_gpu_group, test_msr, false, RAPL_MSR_MASK }, + [PERF_RAPL_PSYS] = { MSR_PLATFORM_ENERGY_STATUS, &rapl_events_psys_group, test_msr, false, RAPL_MSR_MASK }, +}; + +static struct perf_msr intel_rapl_spr_msrs[] = { + [PERF_RAPL_PP0] = { MSR_PP0_ENERGY_STATUS, &rapl_events_cores_group, test_msr, false, RAPL_MSR_MASK }, + [PERF_RAPL_PKG] = { MSR_PKG_ENERGY_STATUS, &rapl_events_pkg_group, test_msr, false, RAPL_MSR_MASK }, + [PERF_RAPL_RAM] = { MSR_DRAM_ENERGY_STATUS, &rapl_events_ram_group, test_msr, false, RAPL_MSR_MASK }, + [PERF_RAPL_PP1] = { MSR_PP1_ENERGY_STATUS, &rapl_events_gpu_group, test_msr, false, RAPL_MSR_MASK }, + [PERF_RAPL_PSYS] = { MSR_PLATFORM_ENERGY_STATUS, &rapl_events_psys_group, test_msr, true, RAPL_MSR_MASK }, }; /* @@ -761,7 +761,7 @@ static struct rapl_model model_spr = { BIT(PERF_RAPL_PSYS), .unit_quirk = RAPL_UNIT_QUIRK_INTEL_SPR, .msr_power_unit = MSR_RAPL_POWER_UNIT, - .rapl_msrs = intel_rapl_msrs, + .rapl_msrs = intel_rapl_spr_msrs, }; static struct rapl_model model_amd_fam17h = { diff --git a/arch/x86/hyperv/Makefile b/arch/x86/hyperv/Makefile index 89b1f74d3225..48e2c51464e8 100644 --- a/arch/x86/hyperv/Makefile +++ b/arch/x86/hyperv/Makefile @@ -1,6 +1,6 @@ # SPDX-License-Identifier: GPL-2.0-only -obj-y := hv_init.o mmu.o nested.o -obj-$(CONFIG_X86_64) += hv_apic.o +obj-y := hv_init.o mmu.o nested.o irqdomain.o +obj-$(CONFIG_X86_64) += hv_apic.o hv_proc.o ifdef CONFIG_X86_64 obj-$(CONFIG_PARAVIRT_SPINLOCKS) += hv_spinlock.o diff --git a/arch/x86/hyperv/hv_init.c b/arch/x86/hyperv/hv_init.c index 6375967a8244..b81047dec1da 100644 --- a/arch/x86/hyperv/hv_init.c +++ b/arch/x86/hyperv/hv_init.c @@ -10,6 +10,7 @@ #include <linux/acpi.h> #include <linux/efi.h> #include <linux/types.h> +#include <linux/bitfield.h> #include <asm/apic.h> #include <asm/desc.h> #include <asm/hypervisor.h> @@ -26,8 +27,11 @@ #include <linux/cpuhotplug.h> #include <linux/syscore_ops.h> #include <clocksource/hyperv_timer.h> +#include <linux/highmem.h> int hyperv_init_cpuhp; +u64 hv_current_partition_id = ~0ull; +EXPORT_SYMBOL_GPL(hv_current_partition_id); void *hv_hypercall_pg; EXPORT_SYMBOL_GPL(hv_hypercall_pg); @@ -44,6 +48,9 @@ EXPORT_SYMBOL_GPL(hv_vp_assist_page); void __percpu **hyperv_pcpu_input_arg; EXPORT_SYMBOL_GPL(hyperv_pcpu_input_arg); +void __percpu **hyperv_pcpu_output_arg; +EXPORT_SYMBOL_GPL(hyperv_pcpu_output_arg); + u32 hv_max_vp_index; EXPORT_SYMBOL_GPL(hv_max_vp_index); @@ -76,12 +83,19 @@ static int hv_cpu_init(unsigned int cpu) void **input_arg; struct page *pg; - input_arg = (void **)this_cpu_ptr(hyperv_pcpu_input_arg); /* hv_cpu_init() can be called with IRQs disabled from hv_resume() */ - pg = alloc_page(irqs_disabled() ? GFP_ATOMIC : GFP_KERNEL); + pg = alloc_pages(irqs_disabled() ? GFP_ATOMIC : GFP_KERNEL, hv_root_partition ? 1 : 0); if (unlikely(!pg)) return -ENOMEM; + + input_arg = (void **)this_cpu_ptr(hyperv_pcpu_input_arg); *input_arg = page_address(pg); + if (hv_root_partition) { + void **output_arg; + + output_arg = (void **)this_cpu_ptr(hyperv_pcpu_output_arg); + *output_arg = page_address(pg + 1); + } hv_get_vp_index(msr_vp_index); @@ -208,14 +222,23 @@ static int hv_cpu_die(unsigned int cpu) unsigned int new_cpu; unsigned long flags; void **input_arg; - void *input_pg = NULL; + void *pg; local_irq_save(flags); input_arg = (void **)this_cpu_ptr(hyperv_pcpu_input_arg); - input_pg = *input_arg; + pg = *input_arg; *input_arg = NULL; + + if (hv_root_partition) { + void **output_arg; + + output_arg = (void **)this_cpu_ptr(hyperv_pcpu_output_arg); + *output_arg = NULL; + } + local_irq_restore(flags); - free_page((unsigned long)input_pg); + + free_pages((unsigned long)pg, hv_root_partition ? 1 : 0); if (hv_vp_assist_page && hv_vp_assist_page[cpu]) wrmsrl(HV_X64_MSR_VP_ASSIST_PAGE, 0); @@ -264,6 +287,9 @@ static int hv_suspend(void) union hv_x64_msr_hypercall_contents hypercall_msr; int ret; + if (hv_root_partition) + return -EPERM; + /* * Reset the hypercall page as it is going to be invalidated * accross hibernation. Setting hv_hypercall_pg to NULL ensures @@ -334,6 +360,24 @@ static void __init hv_stimer_setup_percpu_clockev(void) old_setup_percpu_clockev(); } +static void __init hv_get_partition_id(void) +{ + struct hv_get_partition_id *output_page; + u64 status; + unsigned long flags; + + local_irq_save(flags); + output_page = *this_cpu_ptr(hyperv_pcpu_output_arg); + status = hv_do_hypercall(HVCALL_GET_PARTITION_ID, NULL, output_page); + if ((status & HV_HYPERCALL_RESULT_MASK) != HV_STATUS_SUCCESS) { + /* No point in proceeding if this failed */ + pr_err("Failed to get partition ID: %lld\n", status); + BUG(); + } + hv_current_partition_id = output_page->partition_id; + local_irq_restore(flags); +} + /* * This function is to be invoked early in the boot sequence after the * hypervisor has been detected. @@ -368,6 +412,12 @@ void __init hyperv_init(void) BUG_ON(hyperv_pcpu_input_arg == NULL); + /* Allocate the per-CPU state for output arg for root */ + if (hv_root_partition) { + hyperv_pcpu_output_arg = alloc_percpu(void *); + BUG_ON(hyperv_pcpu_output_arg == NULL); + } + /* Allocate percpu VP index */ hv_vp_index = kmalloc_array(num_possible_cpus(), sizeof(*hv_vp_index), GFP_KERNEL); @@ -408,8 +458,35 @@ void __init hyperv_init(void) rdmsrl(HV_X64_MSR_HYPERCALL, hypercall_msr.as_uint64); hypercall_msr.enable = 1; - hypercall_msr.guest_physical_address = vmalloc_to_pfn(hv_hypercall_pg); - wrmsrl(HV_X64_MSR_HYPERCALL, hypercall_msr.as_uint64); + + if (hv_root_partition) { + struct page *pg; + void *src, *dst; + + /* + * For the root partition, the hypervisor will set up its + * hypercall page. The hypervisor guarantees it will not show + * up in the root's address space. The root can't change the + * location of the hypercall page. + * + * Order is important here. We must enable the hypercall page + * so it is populated with code, then copy the code to an + * executable page. + */ + wrmsrl(HV_X64_MSR_HYPERCALL, hypercall_msr.as_uint64); + + pg = vmalloc_to_page(hv_hypercall_pg); + dst = kmap(pg); + src = memremap(hypercall_msr.guest_physical_address << PAGE_SHIFT, PAGE_SIZE, + MEMREMAP_WB); + BUG_ON(!(src && dst)); + memcpy(dst, src, HV_HYP_PAGE_SIZE); + memunmap(src); + kunmap(pg); + } else { + hypercall_msr.guest_physical_address = vmalloc_to_pfn(hv_hypercall_pg); + wrmsrl(HV_X64_MSR_HYPERCALL, hypercall_msr.as_uint64); + } /* * hyperv_init() is called before LAPIC is initialized: see @@ -428,6 +505,21 @@ void __init hyperv_init(void) register_syscore_ops(&hv_syscore_ops); hyperv_init_cpuhp = cpuhp; + + if (cpuid_ebx(HYPERV_CPUID_FEATURES) & HV_ACCESS_PARTITION_ID) + hv_get_partition_id(); + + BUG_ON(hv_root_partition && hv_current_partition_id == ~0ull); + +#ifdef CONFIG_PCI_MSI + /* + * If we're running as root, we want to create our own PCI MSI domain. + * We can't set this in hv_pci_init because that would be too late. + */ + if (hv_root_partition) + x86_init.irqs.create_pci_msi_domain = hv_create_pci_msi_domain; +#endif + return; remove_cpuhp_state: @@ -552,6 +644,20 @@ EXPORT_SYMBOL_GPL(hv_is_hyperv_initialized); bool hv_is_hibernation_supported(void) { - return acpi_sleep_state_supported(ACPI_STATE_S4); + return !hv_root_partition && acpi_sleep_state_supported(ACPI_STATE_S4); } EXPORT_SYMBOL_GPL(hv_is_hibernation_supported); + +enum hv_isolation_type hv_get_isolation_type(void) +{ + if (!(ms_hyperv.features_b & HV_ISOLATION)) + return HV_ISOLATION_TYPE_NONE; + return FIELD_GET(HV_ISOLATION_TYPE, ms_hyperv.isolation_config_b); +} +EXPORT_SYMBOL_GPL(hv_get_isolation_type); + +bool hv_is_isolation_supported(void) +{ + return hv_get_isolation_type() != HV_ISOLATION_TYPE_NONE; +} +EXPORT_SYMBOL_GPL(hv_is_isolation_supported); diff --git a/arch/x86/hyperv/hv_proc.c b/arch/x86/hyperv/hv_proc.c new file mode 100644 index 000000000000..60461e598239 --- /dev/null +++ b/arch/x86/hyperv/hv_proc.c @@ -0,0 +1,219 @@ +// SPDX-License-Identifier: GPL-2.0 +#include <linux/types.h> +#include <linux/version.h> +#include <linux/vmalloc.h> +#include <linux/mm.h> +#include <linux/clockchips.h> +#include <linux/acpi.h> +#include <linux/hyperv.h> +#include <linux/slab.h> +#include <linux/cpuhotplug.h> +#include <linux/minmax.h> +#include <asm/hypervisor.h> +#include <asm/mshyperv.h> +#include <asm/apic.h> + +#include <asm/trace/hyperv.h> + +/* + * See struct hv_deposit_memory. The first u64 is partition ID, the rest + * are GPAs. + */ +#define HV_DEPOSIT_MAX (HV_HYP_PAGE_SIZE / sizeof(u64) - 1) + +/* Deposits exact number of pages. Must be called with interrupts enabled. */ +int hv_call_deposit_pages(int node, u64 partition_id, u32 num_pages) +{ + struct page **pages, *page; + int *counts; + int num_allocations; + int i, j, page_count; + int order; + u64 status; + int ret; + u64 base_pfn; + struct hv_deposit_memory *input_page; + unsigned long flags; + + if (num_pages > HV_DEPOSIT_MAX) + return -E2BIG; + if (!num_pages) + return 0; + + /* One buffer for page pointers and counts */ + page = alloc_page(GFP_KERNEL); + if (!page) + return -ENOMEM; + pages = page_address(page); + + counts = kcalloc(HV_DEPOSIT_MAX, sizeof(int), GFP_KERNEL); + if (!counts) { + free_page((unsigned long)pages); + return -ENOMEM; + } + + /* Allocate all the pages before disabling interrupts */ + i = 0; + + while (num_pages) { + /* Find highest order we can actually allocate */ + order = 31 - __builtin_clz(num_pages); + + while (1) { + pages[i] = alloc_pages_node(node, GFP_KERNEL, order); + if (pages[i]) + break; + if (!order) { + ret = -ENOMEM; + num_allocations = i; + goto err_free_allocations; + } + --order; + } + + split_page(pages[i], order); + counts[i] = 1 << order; + num_pages -= counts[i]; + i++; + } + num_allocations = i; + + local_irq_save(flags); + + input_page = *this_cpu_ptr(hyperv_pcpu_input_arg); + + input_page->partition_id = partition_id; + + /* Populate gpa_page_list - these will fit on the input page */ + for (i = 0, page_count = 0; i < num_allocations; ++i) { + base_pfn = page_to_pfn(pages[i]); + for (j = 0; j < counts[i]; ++j, ++page_count) + input_page->gpa_page_list[page_count] = base_pfn + j; + } + status = hv_do_rep_hypercall(HVCALL_DEPOSIT_MEMORY, + page_count, 0, input_page, NULL); + local_irq_restore(flags); + + if ((status & HV_HYPERCALL_RESULT_MASK) != HV_STATUS_SUCCESS) { + pr_err("Failed to deposit pages: %lld\n", status); + ret = status; + goto err_free_allocations; + } + + ret = 0; + goto free_buf; + +err_free_allocations: + for (i = 0; i < num_allocations; ++i) { + base_pfn = page_to_pfn(pages[i]); + for (j = 0; j < counts[i]; ++j) + __free_page(pfn_to_page(base_pfn + j)); + } + +free_buf: + free_page((unsigned long)pages); + kfree(counts); + return ret; +} + +int hv_call_add_logical_proc(int node, u32 lp_index, u32 apic_id) +{ + struct hv_add_logical_processor_in *input; + struct hv_add_logical_processor_out *output; + u64 status; + unsigned long flags; + int ret = 0; + int pxm = node_to_pxm(node); + + /* + * When adding a logical processor, the hypervisor may return + * HV_STATUS_INSUFFICIENT_MEMORY. When that happens, we deposit more + * pages and retry. + */ + do { + local_irq_save(flags); + + input = *this_cpu_ptr(hyperv_pcpu_input_arg); + /* We don't do anything with the output right now */ + output = *this_cpu_ptr(hyperv_pcpu_output_arg); + + input->lp_index = lp_index; + input->apic_id = apic_id; + input->flags = 0; + input->proximity_domain_info.domain_id = pxm; + input->proximity_domain_info.flags.reserved = 0; + input->proximity_domain_info.flags.proximity_info_valid = 1; + input->proximity_domain_info.flags.proximity_preferred = 1; + status = hv_do_hypercall(HVCALL_ADD_LOGICAL_PROCESSOR, + input, output); + local_irq_restore(flags); + + status &= HV_HYPERCALL_RESULT_MASK; + + if (status != HV_STATUS_INSUFFICIENT_MEMORY) { + if (status != HV_STATUS_SUCCESS) { + pr_err("%s: cpu %u apic ID %u, %lld\n", __func__, + lp_index, apic_id, status); + ret = status; + } + break; + } + ret = hv_call_deposit_pages(node, hv_current_partition_id, 1); + } while (!ret); + + return ret; +} + +int hv_call_create_vp(int node, u64 partition_id, u32 vp_index, u32 flags) +{ + struct hv_create_vp *input; + u64 status; + unsigned long irq_flags; + int ret = 0; + int pxm = node_to_pxm(node); + + /* Root VPs don't seem to need pages deposited */ + if (partition_id != hv_current_partition_id) { + /* The value 90 is empirically determined. It may change. */ + ret = hv_call_deposit_pages(node, partition_id, 90); + if (ret) + return ret; + } + + do { + local_irq_save(irq_flags); + + input = *this_cpu_ptr(hyperv_pcpu_input_arg); + + input->partition_id = partition_id; + input->vp_index = vp_index; + input->flags = flags; + input->subnode_type = HvSubnodeAny; + if (node != NUMA_NO_NODE) { + input->proximity_domain_info.domain_id = pxm; + input->proximity_domain_info.flags.reserved = 0; + input->proximity_domain_info.flags.proximity_info_valid = 1; + input->proximity_domain_info.flags.proximity_preferred = 1; + } else { + input->proximity_domain_info.as_uint64 = 0; + } + status = hv_do_hypercall(HVCALL_CREATE_VP, input, NULL); + local_irq_restore(irq_flags); + + status &= HV_HYPERCALL_RESULT_MASK; + + if (status != HV_STATUS_INSUFFICIENT_MEMORY) { + if (status != HV_STATUS_SUCCESS) { + pr_err("%s: vcpu %u, lp %u, %lld\n", __func__, + vp_index, flags, status); + ret = status; + } + break; + } + ret = hv_call_deposit_pages(node, partition_id, 1); + + } while (!ret); + + return ret; +} + diff --git a/arch/x86/hyperv/irqdomain.c b/arch/x86/hyperv/irqdomain.c new file mode 100644 index 000000000000..4421a8d92e23 --- /dev/null +++ b/arch/x86/hyperv/irqdomain.c @@ -0,0 +1,385 @@ +// SPDX-License-Identifier: GPL-2.0 + +/* + * Irqdomain for Linux to run as the root partition on Microsoft Hypervisor. + * + * Authors: + * Sunil Muthuswamy <sunilmut@microsoft.com> + * Wei Liu <wei.liu@kernel.org> + */ + +#include <linux/pci.h> +#include <linux/irq.h> +#include <asm/mshyperv.h> + +static int hv_map_interrupt(union hv_device_id device_id, bool level, + int cpu, int vector, struct hv_interrupt_entry *entry) +{ + struct hv_input_map_device_interrupt *input; + struct hv_output_map_device_interrupt *output; + struct hv_device_interrupt_descriptor *intr_desc; + unsigned long flags; + u64 status; + int nr_bank, var_size; + + local_irq_save(flags); + + input = *this_cpu_ptr(hyperv_pcpu_input_arg); + output = *this_cpu_ptr(hyperv_pcpu_output_arg); + + intr_desc = &input->interrupt_descriptor; + memset(input, 0, sizeof(*input)); + input->partition_id = hv_current_partition_id; + input->device_id = device_id.as_uint64; + intr_desc->interrupt_type = HV_X64_INTERRUPT_TYPE_FIXED; + intr_desc->vector_count = 1; + intr_desc->target.vector = vector; + + if (level) + intr_desc->trigger_mode = HV_INTERRUPT_TRIGGER_MODE_LEVEL; + else + intr_desc->trigger_mode = HV_INTERRUPT_TRIGGER_MODE_EDGE; + + intr_desc->target.vp_set.valid_bank_mask = 0; + intr_desc->target.vp_set.format = HV_GENERIC_SET_SPARSE_4K; + nr_bank = cpumask_to_vpset(&(intr_desc->target.vp_set), cpumask_of(cpu)); + if (nr_bank < 0) { + local_irq_restore(flags); + pr_err("%s: unable to generate VP set\n", __func__); + return EINVAL; + } + intr_desc->target.flags = HV_DEVICE_INTERRUPT_TARGET_PROCESSOR_SET; + + /* + * var-sized hypercall, var-size starts after vp_mask (thus + * vp_set.format does not count, but vp_set.valid_bank_mask + * does). + */ + var_size = nr_bank + 1; + + status = hv_do_rep_hypercall(HVCALL_MAP_DEVICE_INTERRUPT, 0, var_size, + input, output); + *entry = output->interrupt_entry; + + local_irq_restore(flags); + + if ((status & HV_HYPERCALL_RESULT_MASK) != HV_STATUS_SUCCESS) + pr_err("%s: hypercall failed, status %lld\n", __func__, status); + + return status & HV_HYPERCALL_RESULT_MASK; +} + +static int hv_unmap_interrupt(u64 id, struct hv_interrupt_entry *old_entry) +{ + unsigned long flags; + struct hv_input_unmap_device_interrupt *input; + struct hv_interrupt_entry *intr_entry; + u64 status; + + local_irq_save(flags); + input = *this_cpu_ptr(hyperv_pcpu_input_arg); + + memset(input, 0, sizeof(*input)); + intr_entry = &input->interrupt_entry; + input->partition_id = hv_current_partition_id; + input->device_id = id; + *intr_entry = *old_entry; + + status = hv_do_hypercall(HVCALL_UNMAP_DEVICE_INTERRUPT, input, NULL); + local_irq_restore(flags); + + return status & HV_HYPERCALL_RESULT_MASK; +} + +#ifdef CONFIG_PCI_MSI +struct rid_data { + struct pci_dev *bridge; + u32 rid; +}; + +static int get_rid_cb(struct pci_dev *pdev, u16 alias, void *data) +{ + struct rid_data *rd = data; + u8 bus = PCI_BUS_NUM(rd->rid); + + if (pdev->bus->number != bus || PCI_BUS_NUM(alias) != bus) { + rd->bridge = pdev; + rd->rid = alias; + } + + return 0; +} + +static union hv_device_id hv_build_pci_dev_id(struct pci_dev *dev) +{ + union hv_device_id dev_id; + struct rid_data data = { + .bridge = NULL, + .rid = PCI_DEVID(dev->bus->number, dev->devfn) + }; + + pci_for_each_dma_alias(dev, get_rid_cb, &data); + + dev_id.as_uint64 = 0; + dev_id.device_type = HV_DEVICE_TYPE_PCI; + dev_id.pci.segment = pci_domain_nr(dev->bus); + + dev_id.pci.bdf.bus = PCI_BUS_NUM(data.rid); + dev_id.pci.bdf.device = PCI_SLOT(data.rid); + dev_id.pci.bdf.function = PCI_FUNC(data.rid); + dev_id.pci.source_shadow = HV_SOURCE_SHADOW_NONE; + + if (data.bridge) { + int pos; + + /* + * Microsoft Hypervisor requires a bus range when the bridge is + * running in PCI-X mode. + * + * To distinguish conventional vs PCI-X bridge, we can check + * the bridge's PCI-X Secondary Status Register, Secondary Bus + * Mode and Frequency bits. See PCI Express to PCI/PCI-X Bridge + * Specification Revision 1.0 5.2.2.1.3. + * + * Value zero means it is in conventional mode, otherwise it is + * in PCI-X mode. + */ + + pos = pci_find_capability(data.bridge, PCI_CAP_ID_PCIX); + if (pos) { + u16 status; + + pci_read_config_word(data.bridge, pos + + PCI_X_BRIDGE_SSTATUS, &status); + + if (status & PCI_X_SSTATUS_FREQ) { + /* Non-zero, PCI-X mode */ + u8 sec_bus, sub_bus; + + dev_id.pci.source_shadow = HV_SOURCE_SHADOW_BRIDGE_BUS_RANGE; + + pci_read_config_byte(data.bridge, PCI_SECONDARY_BUS, &sec_bus); + dev_id.pci.shadow_bus_range.secondary_bus = sec_bus; + pci_read_config_byte(data.bridge, PCI_SUBORDINATE_BUS, &sub_bus); + dev_id.pci.shadow_bus_range.subordinate_bus = sub_bus; + } + } + } + + return dev_id; +} + +static int hv_map_msi_interrupt(struct pci_dev *dev, int cpu, int vector, + struct hv_interrupt_entry *entry) +{ + union hv_device_id device_id = hv_build_pci_dev_id(dev); + + return hv_map_interrupt(device_id, false, cpu, vector, entry); +} + +static inline void entry_to_msi_msg(struct hv_interrupt_entry *entry, struct msi_msg *msg) +{ + /* High address is always 0 */ + msg->address_hi = 0; + msg->address_lo = entry->msi_entry.address.as_uint32; + msg->data = entry->msi_entry.data.as_uint32; +} + +static int hv_unmap_msi_interrupt(struct pci_dev *dev, struct hv_interrupt_entry *old_entry); +static void hv_irq_compose_msi_msg(struct irq_data *data, struct msi_msg *msg) +{ + struct msi_desc *msidesc; + struct pci_dev *dev; + struct hv_interrupt_entry out_entry, *stored_entry; + struct irq_cfg *cfg = irqd_cfg(data); + cpumask_t *affinity; + int cpu; + u64 status; + + msidesc = irq_data_get_msi_desc(data); + dev = msi_desc_to_pci_dev(msidesc); + + if (!cfg) { + pr_debug("%s: cfg is NULL", __func__); + return; + } + + affinity = irq_data_get_effective_affinity_mask(data); + cpu = cpumask_first_and(affinity, cpu_online_mask); + + if (data->chip_data) { + /* + * This interrupt is already mapped. Let's unmap first. + * + * We don't use retarget interrupt hypercalls here because + * Microsoft Hypervisor doens't allow root to change the vector + * or specify VPs outside of the set that is initially used + * during mapping. + */ + stored_entry = data->chip_data; + data->chip_data = NULL; + + status = hv_unmap_msi_interrupt(dev, stored_entry); + + kfree(stored_entry); + + if (status != HV_STATUS_SUCCESS) { + pr_debug("%s: failed to unmap, status %lld", __func__, status); + return; + } + } + + stored_entry = kzalloc(sizeof(*stored_entry), GFP_ATOMIC); + if (!stored_entry) { + pr_debug("%s: failed to allocate chip data\n", __func__); + return; + } + + status = hv_map_msi_interrupt(dev, cpu, cfg->vector, &out_entry); + if (status != HV_STATUS_SUCCESS) { + kfree(stored_entry); + return; + } + + *stored_entry = out_entry; + data->chip_data = stored_entry; + entry_to_msi_msg(&out_entry, msg); + + return; +} + +static int hv_unmap_msi_interrupt(struct pci_dev *dev, struct hv_interrupt_entry *old_entry) +{ + return hv_unmap_interrupt(hv_build_pci_dev_id(dev).as_uint64, old_entry); +} + +static void hv_teardown_msi_irq_common(struct pci_dev *dev, struct msi_desc *msidesc, int irq) +{ + u64 status; + struct hv_interrupt_entry old_entry; + struct irq_desc *desc; + struct irq_data *data; + struct msi_msg msg; + + desc = irq_to_desc(irq); + if (!desc) { + pr_debug("%s: no irq desc\n", __func__); + return; + } + + data = &desc->irq_data; + if (!data) { + pr_debug("%s: no irq data\n", __func__); + return; + } + + if (!data->chip_data) { + pr_debug("%s: no chip data\n!", __func__); + return; + } + + old_entry = *(struct hv_interrupt_entry *)data->chip_data; + entry_to_msi_msg(&old_entry, &msg); + + kfree(data->chip_data); + data->chip_data = NULL; + + status = hv_unmap_msi_interrupt(dev, &old_entry); + + if (status != HV_STATUS_SUCCESS) { + pr_err("%s: hypercall failed, status %lld\n", __func__, status); + return; + } +} + +static void hv_msi_domain_free_irqs(struct irq_domain *domain, struct device *dev) +{ + int i; + struct msi_desc *entry; + struct pci_dev *pdev; + + if (WARN_ON_ONCE(!dev_is_pci(dev))) + return; + + pdev = to_pci_dev(dev); + + for_each_pci_msi_entry(entry, pdev) { + if (entry->irq) { + for (i = 0; i < entry->nvec_used; i++) { + hv_teardown_msi_irq_common(pdev, entry, entry->irq + i); + irq_domain_free_irqs(entry->irq + i, 1); + } + } + } +} + +/* + * IRQ Chip for MSI PCI/PCI-X/PCI-Express Devices, + * which implement the MSI or MSI-X Capability Structure. + */ +static struct irq_chip hv_pci_msi_controller = { + .name = "HV-PCI-MSI", + .irq_unmask = pci_msi_unmask_irq, + .irq_mask = pci_msi_mask_irq, + .irq_ack = irq_chip_ack_parent, + .irq_retrigger = irq_chip_retrigger_hierarchy, + .irq_compose_msi_msg = hv_irq_compose_msi_msg, + .irq_set_affinity = msi_domain_set_affinity, + .flags = IRQCHIP_SKIP_SET_WAKE, +}; + +static struct msi_domain_ops pci_msi_domain_ops = { + .domain_free_irqs = hv_msi_domain_free_irqs, + .msi_prepare = pci_msi_prepare, +}; + +static struct msi_domain_info hv_pci_msi_domain_info = { + .flags = MSI_FLAG_USE_DEF_DOM_OPS | MSI_FLAG_USE_DEF_CHIP_OPS | + MSI_FLAG_PCI_MSIX, + .ops = &pci_msi_domain_ops, + .chip = &hv_pci_msi_controller, + .handler = handle_edge_irq, + .handler_name = "edge", +}; + +struct irq_domain * __init hv_create_pci_msi_domain(void) +{ + struct irq_domain *d = NULL; + struct fwnode_handle *fn; + + fn = irq_domain_alloc_named_fwnode("HV-PCI-MSI"); + if (fn) + d = pci_msi_create_irq_domain(fn, &hv_pci_msi_domain_info, x86_vector_domain); + + /* No point in going further if we can't get an irq domain */ + BUG_ON(!d); + + return d; +} + +#endif /* CONFIG_PCI_MSI */ + +int hv_unmap_ioapic_interrupt(int ioapic_id, struct hv_interrupt_entry *entry) +{ + union hv_device_id device_id; + + device_id.as_uint64 = 0; + device_id.device_type = HV_DEVICE_TYPE_IOAPIC; + device_id.ioapic.ioapic_id = (u8)ioapic_id; + + return hv_unmap_interrupt(device_id.as_uint64, entry); +} +EXPORT_SYMBOL_GPL(hv_unmap_ioapic_interrupt); + +int hv_map_ioapic_interrupt(int ioapic_id, bool level, int cpu, int vector, + struct hv_interrupt_entry *entry) +{ + union hv_device_id device_id; + + device_id.as_uint64 = 0; + device_id.device_type = HV_DEVICE_TYPE_IOAPIC; + device_id.ioapic.ioapic_id = (u8)ioapic_id; + + return hv_map_interrupt(device_id, level, cpu, vector, entry); +} +EXPORT_SYMBOL_GPL(hv_map_ioapic_interrupt); diff --git a/arch/x86/include/asm/acrn.h b/arch/x86/include/asm/acrn.h new file mode 100644 index 000000000000..e003a01b7c67 --- /dev/null +++ b/arch/x86/include/asm/acrn.h @@ -0,0 +1,78 @@ +/* SPDX-License-Identifier: GPL-2.0 */ +#ifndef _ASM_X86_ACRN_H +#define _ASM_X86_ACRN_H + +/* + * This CPUID returns feature bitmaps in EAX. + * Guest VM uses this to detect the appropriate feature bit. + */ +#define ACRN_CPUID_FEATURES 0x40000001 +/* Bit 0 indicates whether guest VM is privileged */ +#define ACRN_FEATURE_PRIVILEGED_VM BIT(0) + +void acrn_setup_intr_handler(void (*handler)(void)); +void acrn_remove_intr_handler(void); + +static inline u32 acrn_cpuid_base(void) +{ + if (boot_cpu_has(X86_FEATURE_HYPERVISOR)) + return hypervisor_cpuid_base("ACRNACRNACRN", 0); + + return 0; +} + +/* + * Hypercalls for ACRN + * + * - VMCALL instruction is used to implement ACRN hypercalls. + * - ACRN hypercall ABI: + * - Hypercall number is passed in R8 register. + * - Up to 2 arguments are passed in RDI, RSI. + * - Return value will be placed in RAX. + * + * Because GCC doesn't support R8 register as direct register constraints, use + * supported constraint as input with a explicit MOV to R8 in beginning of asm. + */ +static inline long acrn_hypercall0(unsigned long hcall_id) +{ + long result; + + asm volatile("movl %1, %%r8d\n\t" + "vmcall\n\t" + : "=a" (result) + : "g" (hcall_id) + : "r8", "memory"); + + return result; +} + +static inline long acrn_hypercall1(unsigned long hcall_id, + unsigned long param1) +{ + long result; + + asm volatile("movl %1, %%r8d\n\t" + "vmcall\n\t" + : "=a" (result) + : "g" (hcall_id), "D" (param1) + : "r8", "memory"); + + return result; +} + +static inline long acrn_hypercall2(unsigned long hcall_id, + unsigned long param1, + unsigned long param2) +{ + long result; + + asm volatile("movl %1, %%r8d\n\t" + "vmcall\n\t" + : "=a" (result) + : "g" (hcall_id), "D" (param1), "S" (param2) + : "r8", "memory"); + + return result; +} + +#endif /* _ASM_X86_ACRN_H */ diff --git a/arch/x86/include/asm/apb_timer.h b/arch/x86/include/asm/apb_timer.h deleted file mode 100644 index 87ce8e963215..000000000000 --- a/arch/x86/include/asm/apb_timer.h +++ /dev/null @@ -1,40 +0,0 @@ -/* SPDX-License-Identifier: GPL-2.0-only */ -/* - * apb_timer.h: Driver for Langwell APB timer based on Synopsis DesignWare - * - * (C) Copyright 2009 Intel Corporation - * Author: Jacob Pan (jacob.jun.pan@intel.com) - * - * Note: - */ - -#ifndef ASM_X86_APBT_H -#define ASM_X86_APBT_H -#include <linux/sfi.h> - -#ifdef CONFIG_APB_TIMER - -/* default memory mapped register base */ -#define LNW_SCU_ADDR 0xFF100000 -#define LNW_EXT_TIMER_OFFSET 0x1B800 -#define APBT_DEFAULT_BASE (LNW_SCU_ADDR+LNW_EXT_TIMER_OFFSET) -#define LNW_EXT_TIMER_PGOFFSET 0x800 - -/* APBT clock speed range from PCLK to fabric base, 25-100MHz */ -#define APBT_MAX_FREQ 50000000 -#define APBT_MIN_FREQ 1000000 -#define APBT_MMAP_SIZE 1024 - -extern void apbt_time_init(void); -extern void apbt_setup_secondary_clock(void); - -extern struct sfi_timer_table_entry *sfi_get_mtmr(int hint); -extern void sfi_free_mtmr(struct sfi_timer_table_entry *mtmr); -extern int sfi_mtimer_num; - -#else /* CONFIG_APB_TIMER */ - -static inline void apbt_time_init(void) { } - -#endif -#endif /* ASM_X86_APBT_H */ diff --git a/arch/x86/include/asm/compat.h b/arch/x86/include/asm/compat.h index f145e3326c6d..be09c7eac89f 100644 --- a/arch/x86/include/asm/compat.h +++ b/arch/x86/include/asm/compat.h @@ -159,17 +159,6 @@ struct compat_shmid64_ds { compat_ulong_t __unused5; }; -/* - * The type of struct elf_prstatus.pr_reg in compatible core dumps. - */ -typedef struct user_regs_struct compat_elf_gregset_t; - -/* Full regset -- prstatus on x32, otherwise on ia32 */ -#define PRSTATUS_SIZE(S, R) (R != sizeof(S.pr_reg) ? 144 : 296) -#define SET_PR_FPVALID(S, V, R) \ - do { *(int *) (((void *) &((S)->pr_reg)) + R) = (V); } \ - while (0) - #ifdef CONFIG_X86_X32_ABI #define COMPAT_USE_64BIT_TIME \ (!!(task_pt_regs(current)->orig_ax & __X32_SYSCALL_BIT)) diff --git a/arch/x86/include/asm/cpufeature.h b/arch/x86/include/asm/cpufeature.h index 59bf91c57aa8..1728d4ce5730 100644 --- a/arch/x86/include/asm/cpufeature.h +++ b/arch/x86/include/asm/cpufeature.h @@ -30,6 +30,7 @@ enum cpuid_leafs CPUID_7_ECX, CPUID_8000_0007_EBX, CPUID_7_EDX, + CPUID_8000_001F_EAX, }; #ifdef CONFIG_X86_FEATURE_NAMES @@ -88,8 +89,9 @@ extern const char * const x86_bug_flags[NBUGINTS*32]; CHECK_BIT_IN_MASK_WORD(REQUIRED_MASK, 16, feature_bit) || \ CHECK_BIT_IN_MASK_WORD(REQUIRED_MASK, 17, feature_bit) || \ CHECK_BIT_IN_MASK_WORD(REQUIRED_MASK, 18, feature_bit) || \ + CHECK_BIT_IN_MASK_WORD(REQUIRED_MASK, 19, feature_bit) || \ REQUIRED_MASK_CHECK || \ - BUILD_BUG_ON_ZERO(NCAPINTS != 19)) + BUILD_BUG_ON_ZERO(NCAPINTS != 20)) #define DISABLED_MASK_BIT_SET(feature_bit) \ ( CHECK_BIT_IN_MASK_WORD(DISABLED_MASK, 0, feature_bit) || \ @@ -111,8 +113,9 @@ extern const char * const x86_bug_flags[NBUGINTS*32]; CHECK_BIT_IN_MASK_WORD(DISABLED_MASK, 16, feature_bit) || \ CHECK_BIT_IN_MASK_WORD(DISABLED_MASK, 17, feature_bit) || \ CHECK_BIT_IN_MASK_WORD(DISABLED_MASK, 18, feature_bit) || \ + CHECK_BIT_IN_MASK_WORD(DISABLED_MASK, 19, feature_bit) || \ DISABLED_MASK_CHECK || \ - BUILD_BUG_ON_ZERO(NCAPINTS != 19)) + BUILD_BUG_ON_ZERO(NCAPINTS != 20)) #define cpu_has(c, bit) \ (__builtin_constant_p(bit) && REQUIRED_MASK_BIT_SET(bit) ? 1 : \ diff --git a/arch/x86/include/asm/cpufeatures.h b/arch/x86/include/asm/cpufeatures.h index 84b887825f12..cc96e26d69f7 100644 --- a/arch/x86/include/asm/cpufeatures.h +++ b/arch/x86/include/asm/cpufeatures.h @@ -13,7 +13,7 @@ /* * Defines x86 CPU feature bits */ -#define NCAPINTS 19 /* N 32-bit words worth of info */ +#define NCAPINTS 20 /* N 32-bit words worth of info */ #define NBUGINTS 1 /* N 32-bit bug flags */ /* @@ -96,7 +96,7 @@ #define X86_FEATURE_SYSCALL32 ( 3*32+14) /* "" syscall in IA32 userspace */ #define X86_FEATURE_SYSENTER32 ( 3*32+15) /* "" sysenter in IA32 userspace */ #define X86_FEATURE_REP_GOOD ( 3*32+16) /* REP microcode works well */ -#define X86_FEATURE_SME_COHERENT ( 3*32+17) /* "" AMD hardware-enforced cache coherency */ +/* FREE! ( 3*32+17) */ #define X86_FEATURE_LFENCE_RDTSC ( 3*32+18) /* "" LFENCE synchronizes RDTSC */ #define X86_FEATURE_ACC_POWER ( 3*32+19) /* AMD Accumulated Power Mechanism */ #define X86_FEATURE_NOPL ( 3*32+20) /* The NOPL (0F 1F) instructions */ @@ -201,7 +201,7 @@ #define X86_FEATURE_INVPCID_SINGLE ( 7*32+ 7) /* Effectively INVPCID && CR4.PCIDE=1 */ #define X86_FEATURE_HW_PSTATE ( 7*32+ 8) /* AMD HW-PState */ #define X86_FEATURE_PROC_FEEDBACK ( 7*32+ 9) /* AMD ProcFeedbackInterface */ -#define X86_FEATURE_SME ( 7*32+10) /* AMD Secure Memory Encryption */ +/* FREE! ( 7*32+10) */ #define X86_FEATURE_PTI ( 7*32+11) /* Kernel Page Table Isolation enabled */ #define X86_FEATURE_RETPOLINE ( 7*32+12) /* "" Generic Retpoline mitigation for Spectre variant 2 */ #define X86_FEATURE_RETPOLINE_AMD ( 7*32+13) /* "" AMD Retpoline mitigation for Spectre variant 2 */ @@ -211,7 +211,7 @@ #define X86_FEATURE_SSBD ( 7*32+17) /* Speculative Store Bypass Disable */ #define X86_FEATURE_MBA ( 7*32+18) /* Memory Bandwidth Allocation */ #define X86_FEATURE_RSB_CTXSW ( 7*32+19) /* "" Fill RSB on context switches */ -#define X86_FEATURE_SEV ( 7*32+20) /* AMD Secure Encrypted Virtualization */ +/* FREE! ( 7*32+20) */ #define X86_FEATURE_USE_IBPB ( 7*32+21) /* "" Indirect Branch Prediction Barrier enabled */ #define X86_FEATURE_USE_IBRS_FW ( 7*32+22) /* "" Use IBRS during runtime firmware calls */ #define X86_FEATURE_SPEC_STORE_BYPASS_DISABLE ( 7*32+23) /* "" Disable Speculative Store Bypass. */ @@ -236,8 +236,6 @@ #define X86_FEATURE_EPT_AD ( 8*32+17) /* Intel Extended Page Table access-dirty bit */ #define X86_FEATURE_VMCALL ( 8*32+18) /* "" Hypervisor supports the VMCALL instruction */ #define X86_FEATURE_VMW_VMMCALL ( 8*32+19) /* "" VMware prefers VMMCALL hypercall instruction */ -#define X86_FEATURE_SEV_ES ( 8*32+20) /* AMD Secure Encrypted Virtualization - Encrypted State */ -#define X86_FEATURE_VM_PAGE_FLUSH ( 8*32+21) /* "" VM Page Flush MSR is supported */ /* Intel-defined CPU features, CPUID level 0x00000007:0 (EBX), word 9 */ #define X86_FEATURE_FSGSBASE ( 9*32+ 0) /* RDFSBASE, WRFSBASE, RDGSBASE, WRGSBASE instructions*/ @@ -294,6 +292,7 @@ #define X86_FEATURE_PER_THREAD_MBA (11*32+ 7) /* "" Per-thread Memory Bandwidth Allocation */ /* Intel-defined CPU features, CPUID level 0x00000007:1 (EAX), word 12 */ +#define X86_FEATURE_AVX_VNNI (12*32+ 4) /* AVX VNNI instructions */ #define X86_FEATURE_AVX512_BF16 (12*32+ 5) /* AVX512 BFLOAT16 instructions */ /* AMD-defined CPU features, CPUID level 0x80000008 (EBX), word 13 */ @@ -337,6 +336,7 @@ #define X86_FEATURE_AVIC (15*32+13) /* Virtual Interrupt Controller */ #define X86_FEATURE_V_VMSAVE_VMLOAD (15*32+15) /* Virtual VMSAVE VMLOAD */ #define X86_FEATURE_VGIF (15*32+16) /* Virtual GIF */ +#define X86_FEATURE_SVME_ADDR_CHK (15*32+28) /* "" SVME addr check */ /* Intel-defined CPU features, CPUID level 0x00000007:0 (ECX), word 16 */ #define X86_FEATURE_AVX512VBMI (16*32+ 1) /* AVX512 Vector Bit Manipulation instructions*/ @@ -385,6 +385,13 @@ #define X86_FEATURE_CORE_CAPABILITIES (18*32+30) /* "" IA32_CORE_CAPABILITIES MSR */ #define X86_FEATURE_SPEC_CTRL_SSBD (18*32+31) /* "" Speculative Store Bypass Disable */ +/* AMD-defined memory encryption features, CPUID level 0x8000001f (EAX), word 19 */ +#define X86_FEATURE_SME (19*32+ 0) /* AMD Secure Memory Encryption */ +#define X86_FEATURE_SEV (19*32+ 1) /* AMD Secure Encrypted Virtualization */ +#define X86_FEATURE_VM_PAGE_FLUSH (19*32+ 2) /* "" VM Page Flush MSR is supported */ +#define X86_FEATURE_SEV_ES (19*32+ 3) /* AMD Secure Encrypted Virtualization - Encrypted State */ +#define X86_FEATURE_SME_COHERENT (19*32+10) /* "" AMD hardware-enforced cache coherency */ + /* * BUG word(s) */ diff --git a/arch/x86/include/asm/crypto/glue_helper.h b/arch/x86/include/asm/crypto/glue_helper.h deleted file mode 100644 index 777c0f63418c..000000000000 --- a/arch/x86/include/asm/crypto/glue_helper.h +++ /dev/null @@ -1,118 +0,0 @@ -/* SPDX-License-Identifier: GPL-2.0 */ -/* - * Shared glue code for 128bit block ciphers - */ - -#ifndef _CRYPTO_GLUE_HELPER_H -#define _CRYPTO_GLUE_HELPER_H - -#include <crypto/internal/skcipher.h> -#include <linux/kernel.h> -#include <asm/fpu/api.h> -#include <crypto/b128ops.h> - -typedef void (*common_glue_func_t)(const void *ctx, u8 *dst, const u8 *src); -typedef void (*common_glue_cbc_func_t)(const void *ctx, u8 *dst, const u8 *src); -typedef void (*common_glue_ctr_func_t)(const void *ctx, u8 *dst, const u8 *src, - le128 *iv); -typedef void (*common_glue_xts_func_t)(const void *ctx, u8 *dst, const u8 *src, - le128 *iv); - -struct common_glue_func_entry { - unsigned int num_blocks; /* number of blocks that @fn will process */ - union { - common_glue_func_t ecb; - common_glue_cbc_func_t cbc; - common_glue_ctr_func_t ctr; - common_glue_xts_func_t xts; - } fn_u; -}; - -struct common_glue_ctx { - unsigned int num_funcs; - int fpu_blocks_limit; /* -1 means fpu not needed at all */ - - /* - * First funcs entry must have largest num_blocks and last funcs entry - * must have num_blocks == 1! - */ - struct common_glue_func_entry funcs[]; -}; - -static inline bool glue_fpu_begin(unsigned int bsize, int fpu_blocks_limit, - struct skcipher_walk *walk, - bool fpu_enabled, unsigned int nbytes) -{ - if (likely(fpu_blocks_limit < 0)) - return false; - - if (fpu_enabled) - return true; - - /* - * Vector-registers are only used when chunk to be processed is large - * enough, so do not enable FPU until it is necessary. - */ - if (nbytes < bsize * (unsigned int)fpu_blocks_limit) - return false; - - /* prevent sleeping if FPU is in use */ - skcipher_walk_atomise(walk); - - kernel_fpu_begin(); - return true; -} - -static inline void glue_fpu_end(bool fpu_enabled) -{ - if (fpu_enabled) - kernel_fpu_end(); -} - -static inline void le128_to_be128(be128 *dst, const le128 *src) -{ - dst->a = cpu_to_be64(le64_to_cpu(src->a)); - dst->b = cpu_to_be64(le64_to_cpu(src->b)); -} - -static inline void be128_to_le128(le128 *dst, const be128 *src) -{ - dst->a = cpu_to_le64(be64_to_cpu(src->a)); - dst->b = cpu_to_le64(be64_to_cpu(src->b)); -} - -static inline void le128_inc(le128 *i) -{ - u64 a = le64_to_cpu(i->a); - u64 b = le64_to_cpu(i->b); - - b++; - if (!b) - a++; - - i->a = cpu_to_le64(a); - i->b = cpu_to_le64(b); -} - -extern int glue_ecb_req_128bit(const struct common_glue_ctx *gctx, - struct skcipher_request *req); - -extern int glue_cbc_encrypt_req_128bit(const common_glue_func_t fn, - struct skcipher_request *req); - -extern int glue_cbc_decrypt_req_128bit(const struct common_glue_ctx *gctx, - struct skcipher_request *req); - -extern int glue_ctr_req_128bit(const struct common_glue_ctx *gctx, - struct skcipher_request *req); - -extern int glue_xts_req_128bit(const struct common_glue_ctx *gctx, - struct skcipher_request *req, - common_glue_func_t tweak_fn, void *tweak_ctx, - void *crypt_ctx, bool decrypt); - -extern void glue_xts_crypt_128bit_one(const void *ctx, u8 *dst, - const u8 *src, le128 *iv, - common_glue_func_t fn); - -#endif /* _CRYPTO_GLUE_HELPER_H */ diff --git a/arch/x86/include/asm/crypto/serpent-avx.h b/arch/x86/include/asm/crypto/serpent-avx.h deleted file mode 100644 index 251c2c89d7cf..000000000000 --- a/arch/x86/include/asm/crypto/serpent-avx.h +++ /dev/null @@ -1,42 +0,0 @@ -/* SPDX-License-Identifier: GPL-2.0 */ -#ifndef ASM_X86_SERPENT_AVX_H -#define ASM_X86_SERPENT_AVX_H - -#include <crypto/b128ops.h> -#include <crypto/serpent.h> -#include <linux/types.h> - -struct crypto_skcipher; - -#define SERPENT_PARALLEL_BLOCKS 8 - -struct serpent_xts_ctx { - struct serpent_ctx tweak_ctx; - struct serpent_ctx crypt_ctx; -}; - -asmlinkage void serpent_ecb_enc_8way_avx(const void *ctx, u8 *dst, - const u8 *src); -asmlinkage void serpent_ecb_dec_8way_avx(const void *ctx, u8 *dst, - const u8 *src); - -asmlinkage void serpent_cbc_dec_8way_avx(const void *ctx, u8 *dst, - const u8 *src); -asmlinkage void serpent_ctr_8way_avx(const void *ctx, u8 *dst, const u8 *src, - le128 *iv); - -asmlinkage void serpent_xts_enc_8way_avx(const void *ctx, u8 *dst, - const u8 *src, le128 *iv); -asmlinkage void serpent_xts_dec_8way_avx(const void *ctx, u8 *dst, - const u8 *src, le128 *iv); - -extern void __serpent_crypt_ctr(const void *ctx, u8 *dst, const u8 *src, - le128 *iv); - -extern void serpent_xts_enc(const void *ctx, u8 *dst, const u8 *src, le128 *iv); -extern void serpent_xts_dec(const void *ctx, u8 *dst, const u8 *src, le128 *iv); - -extern int xts_serpent_setkey(struct crypto_skcipher *tfm, const u8 *key, - unsigned int keylen); - -#endif diff --git a/arch/x86/include/asm/disabled-features.h b/arch/x86/include/asm/disabled-features.h index 7947cb1782da..b7dd944dc867 100644 --- a/arch/x86/include/asm/disabled-features.h +++ b/arch/x86/include/asm/disabled-features.h @@ -91,6 +91,7 @@ DISABLE_ENQCMD) #define DISABLED_MASK17 0 #define DISABLED_MASK18 0 -#define DISABLED_MASK_CHECK BUILD_BUG_ON_ZERO(NCAPINTS != 19) +#define DISABLED_MASK19 0 +#define DISABLED_MASK_CHECK BUILD_BUG_ON_ZERO(NCAPINTS != 20) #endif /* _ASM_X86_DISABLED_FEATURES_H */ diff --git a/arch/x86/include/asm/efi.h b/arch/x86/include/asm/efi.h index c98f78330b09..4d0b126835b8 100644 --- a/arch/x86/include/asm/efi.h +++ b/arch/x86/include/asm/efi.h @@ -12,6 +12,7 @@ #include <linux/pgtable.h> extern unsigned long efi_fw_vendor, efi_config_table; +extern unsigned long efi_mixed_mode_stack_pa; /* * We map the EFI regions needed for runtime services non-contiguously, @@ -68,17 +69,33 @@ extern unsigned long efi_fw_vendor, efi_config_table; #f " called with too many arguments (" #p ">" #n ")"); \ }) +static inline void efi_fpu_begin(void) +{ + /* + * The UEFI calling convention (UEFI spec 2.3.2 and 2.3.4) requires + * that FCW and MXCSR (64-bit) must be initialized prior to calling + * UEFI code. (Oddly the spec does not require that the FPU stack + * be empty.) + */ + kernel_fpu_begin_mask(KFPU_387 | KFPU_MXCSR); +} + +static inline void efi_fpu_end(void) +{ + kernel_fpu_end(); +} + #ifdef CONFIG_X86_32 #define arch_efi_call_virt_setup() \ ({ \ - kernel_fpu_begin(); \ + efi_fpu_begin(); \ firmware_restrict_branch_speculation_start(); \ }) #define arch_efi_call_virt_teardown() \ ({ \ firmware_restrict_branch_speculation_end(); \ - kernel_fpu_end(); \ + efi_fpu_end(); \ }) #define arch_efi_call_virt(p, f, args...) p->f(args) @@ -94,22 +111,12 @@ extern asmlinkage u64 __efi_call(void *fp, ...); __efi_call(__VA_ARGS__); \ }) -/* - * struct efi_scratch - Scratch space used while switching to/from efi_mm - * @phys_stack: stack used during EFI Mixed Mode - * @prev_mm: store/restore stolen mm_struct while switching to/from efi_mm - */ -struct efi_scratch { - u64 phys_stack; - struct mm_struct *prev_mm; -} __packed; - #define arch_efi_call_virt_setup() \ ({ \ efi_sync_low_kernel_mappings(); \ - kernel_fpu_begin(); \ + efi_fpu_begin(); \ firmware_restrict_branch_speculation_start(); \ - efi_switch_mm(&efi_mm); \ + efi_enter_mm(); \ }) #define arch_efi_call_virt(p, f, args...) \ @@ -117,9 +124,9 @@ struct efi_scratch { #define arch_efi_call_virt_teardown() \ ({ \ - efi_switch_mm(efi_scratch.prev_mm); \ + efi_leave_mm(); \ firmware_restrict_branch_speculation_end(); \ - kernel_fpu_end(); \ + efi_fpu_end(); \ }) #ifdef CONFIG_KASAN @@ -136,7 +143,6 @@ struct efi_scratch { #endif /* CONFIG_X86_32 */ -extern struct efi_scratch efi_scratch; extern int __init efi_memblock_x86_reserve_range(void); extern void __init efi_print_memmap(void); extern void __init efi_map_region(efi_memory_desc_t *md); @@ -149,10 +155,12 @@ extern void __init efi_dump_pagetable(void); extern void __init efi_apply_memmap_quirks(void); extern int __init efi_reuse_config(u64 tables, int nr_tables); extern void efi_delete_dummy_variable(void); -extern void efi_switch_mm(struct mm_struct *mm); -extern void efi_recover_from_page_fault(unsigned long phys_addr); +extern void efi_crash_gracefully_on_page_fault(unsigned long phys_addr); extern void efi_free_boot_services(void); +void efi_enter_mm(void); +void efi_leave_mm(void); + /* kexec external ABI */ struct efi_setup_data { u64 fw_vendor; diff --git a/arch/x86/include/asm/elf.h b/arch/x86/include/asm/elf.h index 66bdfe838d61..9224d40cdefe 100644 --- a/arch/x86/include/asm/elf.h +++ b/arch/x86/include/asm/elf.h @@ -364,7 +364,7 @@ do { \ #define COMPAT_ARCH_DLINFO \ if (exec->e_machine == EM_X86_64) \ ARCH_DLINFO_X32; \ -else \ +else if (IS_ENABLED(CONFIG_IA32_EMULATION)) \ ARCH_DLINFO_IA32 #define COMPAT_ELF_ET_DYN_BASE (TASK_UNMAPPED_BASE + 0x1000000) diff --git a/arch/x86/include/asm/elfcore-compat.h b/arch/x86/include/asm/elfcore-compat.h new file mode 100644 index 000000000000..f1b6c7a8d8fc --- /dev/null +++ b/arch/x86/include/asm/elfcore-compat.h @@ -0,0 +1,31 @@ +#ifndef _ASM_X86_ELFCORE_COMPAT_H +#define _ASM_X86_ELFCORE_COMPAT_H + +#include <asm/user32.h> + +/* + * On amd64 we have two 32bit ABIs - i386 and x32. The latter + * has bigger registers, so we use it for compat_elf_regset_t. + * The former uses i386_elf_prstatus and PRSTATUS_SIZE/SET_PR_FPVALID + * are used to choose the size and location of ->pr_fpvalid of + * the layout actually used. + */ +typedef struct user_regs_struct compat_elf_gregset_t; + +struct i386_elf_prstatus +{ + struct compat_elf_prstatus_common common; + struct user_regs_struct32 pr_reg; + compat_int_t pr_fpvalid; +}; + +#define PRSTATUS_SIZE \ + (user_64bit_mode(task_pt_regs(current)) \ + ? sizeof(struct compat_elf_prstatus) \ + : sizeof(struct i386_elf_prstatus)) +#define SET_PR_FPVALID(S) \ + (*(user_64bit_mode(task_pt_regs(current)) \ + ? &(S)->pr_fpvalid \ + : &((struct i386_elf_prstatus *)(S))->pr_fpvalid) = 1) + +#endif diff --git a/arch/x86/include/asm/fixmap.h b/arch/x86/include/asm/fixmap.h index 9f1a0a987e5e..d0dcefb5cc59 100644 --- a/arch/x86/include/asm/fixmap.h +++ b/arch/x86/include/asm/fixmap.h @@ -108,9 +108,6 @@ enum fixed_addresses { #ifdef CONFIG_PARAVIRT_XXL FIX_PARAVIRT_BOOTMAP, #endif -#ifdef CONFIG_X86_INTEL_MID - FIX_LNW_VRTC, -#endif #ifdef CONFIG_ACPI_APEI_GHES /* Used for GHES mapping from assorted contexts */ diff --git a/arch/x86/include/asm/fpu/api.h b/arch/x86/include/asm/fpu/api.h index 67a4f1cb2aac..ed33a14188f6 100644 --- a/arch/x86/include/asm/fpu/api.h +++ b/arch/x86/include/asm/fpu/api.h @@ -32,7 +32,19 @@ extern void fpregs_mark_activate(void); /* Code that is unaware of kernel_fpu_begin_mask() can use this */ static inline void kernel_fpu_begin(void) { +#ifdef CONFIG_X86_64 + /* + * Any 64-bit code that uses 387 instructions must explicitly request + * KFPU_387. + */ + kernel_fpu_begin_mask(KFPU_MXCSR); +#else + /* + * 32-bit kernel code may use 387 operations as well as SSE2, etc, + * as long as it checks that the CPU has the required capability. + */ kernel_fpu_begin_mask(KFPU_387 | KFPU_MXCSR); +#endif } /* diff --git a/arch/x86/include/asm/hyperv-tlfs.h b/arch/x86/include/asm/hyperv-tlfs.h index 6bf42aed387e..e6cd3fee562b 100644 --- a/arch/x86/include/asm/hyperv-tlfs.h +++ b/arch/x86/include/asm/hyperv-tlfs.h @@ -21,7 +21,9 @@ #define HYPERV_CPUID_FEATURES 0x40000003 #define HYPERV_CPUID_ENLIGHTMENT_INFO 0x40000004 #define HYPERV_CPUID_IMPLEMENT_LIMITS 0x40000005 +#define HYPERV_CPUID_CPU_MANAGEMENT_FEATURES 0x40000007 #define HYPERV_CPUID_NESTED_FEATURES 0x4000000A +#define HYPERV_CPUID_ISOLATION_CONFIG 0x4000000C #define HYPERV_CPUID_VIRT_STACK_INTERFACE 0x40000081 #define HYPERV_VS_INTERFACE_EAX_SIGNATURE 0x31235356 /* "VS#1" */ @@ -111,6 +113,15 @@ #define HV_X64_ENLIGHTENED_VMCS_RECOMMENDED BIT(14) /* + * CPU management features identification. + * These are HYPERV_CPUID_CPU_MANAGEMENT_FEATURES.EAX bits. + */ +#define HV_X64_START_LOGICAL_PROCESSOR BIT(0) +#define HV_X64_CREATE_ROOT_VIRTUAL_PROCESSOR BIT(1) +#define HV_X64_PERFORMANCE_COUNTER_SYNC BIT(2) +#define HV_X64_RESERVED_IDENTITY_BIT BIT(31) + +/* * Virtual processor will never share a physical core with another virtual * processor, except for virtual processors that are reported as sibling SMT * threads. @@ -122,6 +133,20 @@ #define HV_X64_NESTED_GUEST_MAPPING_FLUSH BIT(18) #define HV_X64_NESTED_MSR_BITMAP BIT(19) +/* HYPERV_CPUID_ISOLATION_CONFIG.EAX bits. */ +#define HV_PARAVISOR_PRESENT BIT(0) + +/* HYPERV_CPUID_ISOLATION_CONFIG.EBX bits. */ +#define HV_ISOLATION_TYPE GENMASK(3, 0) +#define HV_SHARED_GPA_BOUNDARY_ACTIVE BIT(5) +#define HV_SHARED_GPA_BOUNDARY_BITS GENMASK(11, 6) + +enum hv_isolation_type { + HV_ISOLATION_TYPE_NONE = 0, + HV_ISOLATION_TYPE_VBS = 1, + HV_ISOLATION_TYPE_SNP = 2 +}; + /* Hyper-V specific model specific registers (MSRs) */ /* MSR used to identify the guest OS. */ @@ -523,6 +548,19 @@ struct hv_partition_assist_pg { u32 tlb_lock_count; }; +enum hv_interrupt_type { + HV_X64_INTERRUPT_TYPE_FIXED = 0x0000, + HV_X64_INTERRUPT_TYPE_LOWESTPRIORITY = 0x0001, + HV_X64_INTERRUPT_TYPE_SMI = 0x0002, + HV_X64_INTERRUPT_TYPE_REMOTEREAD = 0x0003, + HV_X64_INTERRUPT_TYPE_NMI = 0x0004, + HV_X64_INTERRUPT_TYPE_INIT = 0x0005, + HV_X64_INTERRUPT_TYPE_SIPI = 0x0006, + HV_X64_INTERRUPT_TYPE_EXTINT = 0x0007, + HV_X64_INTERRUPT_TYPE_LOCALINT0 = 0x0008, + HV_X64_INTERRUPT_TYPE_LOCALINT1 = 0x0009, + HV_X64_INTERRUPT_TYPE_MAXIMUM = 0x000A, +}; #include <asm-generic/hyperv-tlfs.h> diff --git a/arch/x86/include/asm/idtentry.h b/arch/x86/include/asm/idtentry.h index f656aabd1545..5eb3bdf36a41 100644 --- a/arch/x86/include/asm/idtentry.h +++ b/arch/x86/include/asm/idtentry.h @@ -187,23 +187,22 @@ __visible noinstr void func(struct pt_regs *regs, unsigned long error_code) * has to be done in the function body if necessary. */ #define DEFINE_IDTENTRY_IRQ(func) \ -static __always_inline void __##func(struct pt_regs *regs, u8 vector); \ +static void __##func(struct pt_regs *regs, u32 vector); \ \ __visible noinstr void func(struct pt_regs *regs, \ unsigned long error_code) \ { \ irqentry_state_t state = irqentry_enter(regs); \ + u32 vector = (u32)(u8)error_code; \ \ instrumentation_begin(); \ - irq_enter_rcu(); \ kvm_set_cpu_l1tf_flush_l1d(); \ - __##func (regs, (u8)error_code); \ - irq_exit_rcu(); \ + run_irq_on_irqstack_cond(__##func, regs, vector); \ instrumentation_end(); \ irqentry_exit(regs, state); \ } \ \ -static __always_inline void __##func(struct pt_regs *regs, u8 vector) +static noinline void __##func(struct pt_regs *regs, u32 vector) /** * DECLARE_IDTENTRY_SYSVEC - Declare functions for system vector entry points @@ -237,10 +236,8 @@ __visible noinstr void func(struct pt_regs *regs) \ irqentry_state_t state = irqentry_enter(regs); \ \ instrumentation_begin(); \ - irq_enter_rcu(); \ kvm_set_cpu_l1tf_flush_l1d(); \ run_sysvec_on_irqstack_cond(__##func, regs); \ - irq_exit_rcu(); \ instrumentation_end(); \ irqentry_exit(regs, state); \ } \ @@ -585,6 +582,9 @@ DECLARE_IDTENTRY_MCE(X86_TRAP_MC, exc_machine_check); #else DECLARE_IDTENTRY_RAW(X86_TRAP_MC, exc_machine_check); #endif +#ifdef CONFIG_XEN_PV +DECLARE_IDTENTRY_RAW(X86_TRAP_MC, xenpv_exc_machine_check); +#endif #endif /* NMI */ @@ -605,6 +605,9 @@ DECLARE_IDTENTRY_RAW(X86_TRAP_DB, xenpv_exc_debug); /* #DF */ DECLARE_IDTENTRY_DF(X86_TRAP_DF, exc_double_fault); +#ifdef CONFIG_XEN_PV +DECLARE_IDTENTRY_RAW_ERRORCODE(X86_TRAP_DF, xenpv_exc_double_fault); +#endif /* #VC */ #ifdef CONFIG_AMD_MEM_ENCRYPT diff --git a/arch/x86/include/asm/insn-eval.h b/arch/x86/include/asm/insn-eval.h index a0f839aa144d..98b4dae5e8bc 100644 --- a/arch/x86/include/asm/insn-eval.h +++ b/arch/x86/include/asm/insn-eval.h @@ -23,6 +23,8 @@ unsigned long insn_get_seg_base(struct pt_regs *regs, int seg_reg_idx); int insn_get_code_seg_params(struct pt_regs *regs); int insn_fetch_from_user(struct pt_regs *regs, unsigned char buf[MAX_INSN_SIZE]); +int insn_fetch_from_user_inatomic(struct pt_regs *regs, + unsigned char buf[MAX_INSN_SIZE]); bool insn_decode(struct insn *insn, struct pt_regs *regs, unsigned char buf[MAX_INSN_SIZE], int buf_size); diff --git a/arch/x86/include/asm/insn.h b/arch/x86/include/asm/insn.h index a8c3d284fa46..95a448fbb44c 100644 --- a/arch/x86/include/asm/insn.h +++ b/arch/x86/include/asm/insn.h @@ -7,9 +7,12 @@ * Copyright (C) IBM Corporation, 2009 */ +#include <asm/byteorder.h> /* insn_attr_t is defined in inat.h */ #include <asm/inat.h> +#if defined(__BYTE_ORDER) ? __BYTE_ORDER == __LITTLE_ENDIAN : defined(__LITTLE_ENDIAN) + struct insn_field { union { insn_value_t value; @@ -20,6 +23,48 @@ struct insn_field { unsigned char nbytes; }; +static inline void insn_field_set(struct insn_field *p, insn_value_t v, + unsigned char n) +{ + p->value = v; + p->nbytes = n; +} + +static inline void insn_set_byte(struct insn_field *p, unsigned char n, + insn_byte_t v) +{ + p->bytes[n] = v; +} + +#else + +struct insn_field { + insn_value_t value; + union { + insn_value_t little; + insn_byte_t bytes[4]; + }; + /* !0 if we've run insn_get_xxx() for this field */ + unsigned char got; + unsigned char nbytes; +}; + +static inline void insn_field_set(struct insn_field *p, insn_value_t v, + unsigned char n) +{ + p->value = v; + p->little = __cpu_to_le32(v); + p->nbytes = n; +} + +static inline void insn_set_byte(struct insn_field *p, unsigned char n, + insn_byte_t v) +{ + p->bytes[n] = v; + p->value = __le32_to_cpu(p->little); +} +#endif + struct insn { struct insn_field prefixes; /* * Prefixes diff --git a/arch/x86/include/asm/intel-mid.h b/arch/x86/include/asm/intel-mid.h index cf0e25f45422..c201083b34f6 100644 --- a/arch/x86/include/asm/intel-mid.h +++ b/arch/x86/include/asm/intel-mid.h @@ -1,15 +1,13 @@ /* SPDX-License-Identifier: GPL-2.0-only */ /* - * intel-mid.h: Intel MID specific setup code + * Intel MID specific setup code * - * (C) Copyright 2009 Intel Corporation + * (C) Copyright 2009, 2021 Intel Corporation */ #ifndef _ASM_X86_INTEL_MID_H #define _ASM_X86_INTEL_MID_H -#include <linux/sfi.h> #include <linux/pci.h> -#include <linux/platform_device.h> extern int intel_mid_pci_init(void); extern int intel_mid_pci_set_power_state(struct pci_dev *pdev, pci_power_t state); @@ -22,93 +20,18 @@ extern void intel_mid_pwr_power_off(void); extern int intel_mid_pwr_get_lss_id(struct pci_dev *pdev); -extern int get_gpio_by_name(const char *name); -extern int __init sfi_parse_mrtc(struct sfi_table_header *table); -extern int __init sfi_parse_mtmr(struct sfi_table_header *table); -extern int sfi_mrtc_num; -extern struct sfi_rtc_table_entry sfi_mrtc_array[]; - -/* - * Here defines the array of devices platform data that IAFW would export - * through SFI "DEVS" table, we use name and type to match the device and - * its platform data. - */ -struct devs_id { - char name[SFI_NAME_LEN + 1]; - u8 type; - u8 delay; - u8 msic; - void *(*get_platform_data)(void *info); -}; - -#define sfi_device(i) \ - static const struct devs_id *const __intel_mid_sfi_##i##_dev __used \ - __section(".x86_intel_mid_dev.init") = &i - -/** -* struct mid_sd_board_info - template for SD device creation -* @name: identifies the driver -* @bus_num: board-specific identifier for a given SD controller -* @max_clk: the maximum frequency device supports -* @platform_data: the particular data stored there is driver-specific -*/ -struct mid_sd_board_info { - char name[SFI_NAME_LEN]; - int bus_num; - unsigned short addr; - u32 max_clk; - void *platform_data; -}; - -/* - * Medfield is the follow-up of Moorestown, it combines two chip solution into - * one. Other than that it also added always-on and constant tsc and lapic - * timers. Medfield is the platform name, and the chip name is called Penwell - * we treat Medfield/Penwell as a variant of Moorestown. Penwell can be - * identified via MSRs. - */ -enum intel_mid_cpu_type { - /* 1 was Moorestown */ - INTEL_MID_CPU_CHIP_PENWELL = 2, - INTEL_MID_CPU_CHIP_CLOVERVIEW, - INTEL_MID_CPU_CHIP_TANGIER, -}; - -extern enum intel_mid_cpu_type __intel_mid_cpu_chip; - #ifdef CONFIG_X86_INTEL_MID -static inline enum intel_mid_cpu_type intel_mid_identify_cpu(void) -{ - return __intel_mid_cpu_chip; -} - -static inline bool intel_mid_has_msic(void) -{ - return (intel_mid_identify_cpu() == INTEL_MID_CPU_CHIP_PENWELL); -} - extern void intel_scu_devices_create(void); extern void intel_scu_devices_destroy(void); #else /* !CONFIG_X86_INTEL_MID */ -#define intel_mid_identify_cpu() 0 -#define intel_mid_has_msic() 0 - static inline void intel_scu_devices_create(void) { } static inline void intel_scu_devices_destroy(void) { } #endif /* !CONFIG_X86_INTEL_MID */ -enum intel_mid_timer_options { - INTEL_MID_TIMER_DEFAULT, - INTEL_MID_TIMER_APBT_ONLY, - INTEL_MID_TIMER_LAPIC_APBT, -}; - -extern enum intel_mid_timer_options intel_mid_timer_options; - /* Bus Select SoC Fuse value */ #define BSEL_SOC_FUSE_MASK 0x7 /* FSB 133MHz */ @@ -118,16 +41,4 @@ extern enum intel_mid_timer_options intel_mid_timer_options; /* FSB 83MHz */ #define BSEL_SOC_FUSE_111 0x7 -#define SFI_MTMR_MAX_NUM 8 -#define SFI_MRTC_MAX 8 - -/* VRTC timer */ -#define MRST_VRTC_MAP_SZ 1024 -/* #define MRST_VRTC_PGOFFSET 0xc00 */ - -extern void intel_mid_rtc_init(void); - -/* The offset for the mapping of global gpio pin to irq */ -#define INTEL_MID_IRQ_OFFSET 0x100 - #endif /* _ASM_X86_INTEL_MID_H */ diff --git a/arch/x86/include/asm/intel_mid_vrtc.h b/arch/x86/include/asm/intel_mid_vrtc.h deleted file mode 100644 index 0b44b1abe4d9..000000000000 --- a/arch/x86/include/asm/intel_mid_vrtc.h +++ /dev/null @@ -1,10 +0,0 @@ -/* SPDX-License-Identifier: GPL-2.0 */ -#ifndef _INTEL_MID_VRTC_H -#define _INTEL_MID_VRTC_H - -extern unsigned char vrtc_cmos_read(unsigned char reg); -extern void vrtc_cmos_write(unsigned char val, unsigned char reg); -extern void vrtc_get_time(struct timespec64 *now); -extern int vrtc_set_mmss(const struct timespec64 *now); - -#endif diff --git a/arch/x86/include/asm/intel_scu_ipc.h b/arch/x86/include/asm/intel_scu_ipc.h index 11d457af68c5..8537f597d20a 100644 --- a/arch/x86/include/asm/intel_scu_ipc.h +++ b/arch/x86/include/asm/intel_scu_ipc.h @@ -65,6 +65,4 @@ static inline int intel_scu_ipc_dev_command(struct intel_scu_ipc_dev *scu, int c inlen, out, outlen); } -#include <asm/intel_scu_ipc_legacy.h> - #endif diff --git a/arch/x86/include/asm/intel_scu_ipc_legacy.h b/arch/x86/include/asm/intel_scu_ipc_legacy.h deleted file mode 100644 index 4cf13fecb673..000000000000 --- a/arch/x86/include/asm/intel_scu_ipc_legacy.h +++ /dev/null @@ -1,91 +0,0 @@ -/* SPDX-License-Identifier: GPL-2.0 */ -#ifndef _ASM_X86_INTEL_SCU_IPC_LEGACY_H_ -#define _ASM_X86_INTEL_SCU_IPC_LEGACY_H_ - -#include <linux/notifier.h> - -#define IPCMSG_INDIRECT_READ 0x02 -#define IPCMSG_INDIRECT_WRITE 0x05 - -#define IPCMSG_COLD_OFF 0x80 /* Only for Tangier */ - -#define IPCMSG_WARM_RESET 0xF0 -#define IPCMSG_COLD_RESET 0xF1 -#define IPCMSG_SOFT_RESET 0xF2 -#define IPCMSG_COLD_BOOT 0xF3 - -#define IPCMSG_VRTC 0xFA /* Set vRTC device */ -/* Command id associated with message IPCMSG_VRTC */ -#define IPC_CMD_VRTC_SETTIME 1 /* Set time */ -#define IPC_CMD_VRTC_SETALARM 2 /* Set alarm */ - -/* Don't call these in new code - they will be removed eventually */ - -/* Read single register */ -static inline int intel_scu_ipc_ioread8(u16 addr, u8 *data) -{ - return intel_scu_ipc_dev_ioread8(NULL, addr, data); -} - -/* Read a vector */ -static inline int intel_scu_ipc_readv(u16 *addr, u8 *data, int len) -{ - return intel_scu_ipc_dev_readv(NULL, addr, data, len); -} - -/* Write single register */ -static inline int intel_scu_ipc_iowrite8(u16 addr, u8 data) -{ - return intel_scu_ipc_dev_iowrite8(NULL, addr, data); -} - -/* Write a vector */ -static inline int intel_scu_ipc_writev(u16 *addr, u8 *data, int len) -{ - return intel_scu_ipc_dev_writev(NULL, addr, data, len); -} - -/* Update single register based on the mask */ -static inline int intel_scu_ipc_update_register(u16 addr, u8 data, u8 mask) -{ - return intel_scu_ipc_dev_update(NULL, addr, data, mask); -} - -/* Issue commands to the SCU with or without data */ -static inline int intel_scu_ipc_simple_command(int cmd, int sub) -{ - return intel_scu_ipc_dev_simple_command(NULL, cmd, sub); -} - -static inline int intel_scu_ipc_command(int cmd, int sub, u32 *in, int inlen, - u32 *out, int outlen) -{ - /* New API takes both inlen and outlen as bytes so convert here */ - size_t inbytes = inlen * sizeof(u32); - size_t outbytes = outlen * sizeof(u32); - - return intel_scu_ipc_dev_command_with_size(NULL, cmd, sub, in, inbytes, - inlen, out, outbytes); -} - -extern struct blocking_notifier_head intel_scu_notifier; - -static inline void intel_scu_notifier_add(struct notifier_block *nb) -{ - blocking_notifier_chain_register(&intel_scu_notifier, nb); -} - -static inline void intel_scu_notifier_remove(struct notifier_block *nb) -{ - blocking_notifier_chain_unregister(&intel_scu_notifier, nb); -} - -static inline int intel_scu_notifier_post(unsigned long v, void *p) -{ - return blocking_notifier_call_chain(&intel_scu_notifier, v, p); -} - -#define SCU_AVAILABLE 1 -#define SCU_DOWN 2 - -#endif diff --git a/arch/x86/include/asm/irq.h b/arch/x86/include/asm/irq.h index 528c8a71fe7f..768aa234cbb4 100644 --- a/arch/x86/include/asm/irq.h +++ b/arch/x86/include/asm/irq.h @@ -25,8 +25,6 @@ static inline int irq_canonicalize(int irq) extern int irq_init_percpu_irqstack(unsigned int cpu); -#define __ARCH_HAS_DO_SOFTIRQ - struct irq_desc; extern void fixup_irqs(void); @@ -40,8 +38,6 @@ extern void native_init_IRQ(void); extern void __handle_irq(struct irq_desc *desc, struct pt_regs *regs); -extern __visible void do_IRQ(struct pt_regs *regs, unsigned long vector); - extern void init_ISA_irqs(void); extern void __init init_IRQ(void); diff --git a/arch/x86/include/asm/irq_stack.h b/arch/x86/include/asm/irq_stack.h index 775816965c6a..9b2a0ff76c73 100644 --- a/arch/x86/include/asm/irq_stack.h +++ b/arch/x86/include/asm/irq_stack.h @@ -7,100 +7,217 @@ #include <asm/processor.h> #ifdef CONFIG_X86_64 -static __always_inline bool irqstack_active(void) -{ - return __this_cpu_read(irq_count) != -1; -} - -void asm_call_on_stack(void *sp, void (*func)(void), void *arg); -void asm_call_sysvec_on_stack(void *sp, void (*func)(struct pt_regs *regs), - struct pt_regs *regs); -void asm_call_irq_on_stack(void *sp, void (*func)(struct irq_desc *desc), - struct irq_desc *desc); -static __always_inline void __run_on_irqstack(void (*func)(void)) -{ - void *tos = __this_cpu_read(hardirq_stack_ptr); - - __this_cpu_add(irq_count, 1); - asm_call_on_stack(tos - 8, func, NULL); - __this_cpu_sub(irq_count, 1); +/* + * Macro to inline switching to an interrupt stack and invoking function + * calls from there. The following rules apply: + * + * - Ordering: + * + * 1. Write the stack pointer into the top most place of the irq + * stack. This ensures that the various unwinders can link back to the + * original stack. + * + * 2. Switch the stack pointer to the top of the irq stack. + * + * 3. Invoke whatever needs to be done (@asm_call argument) + * + * 4. Pop the original stack pointer from the top of the irq stack + * which brings it back to the original stack where it left off. + * + * - Function invocation: + * + * To allow flexible usage of the macro, the actual function code including + * the store of the arguments in the call ABI registers is handed in via + * the @asm_call argument. + * + * - Local variables: + * + * @tos: + * The @tos variable holds a pointer to the top of the irq stack and + * _must_ be allocated in a non-callee saved register as this is a + * restriction coming from objtool. + * + * Note, that (tos) is both in input and output constraints to ensure + * that the compiler does not assume that R11 is left untouched in + * case this macro is used in some place where the per cpu interrupt + * stack pointer is used again afterwards + * + * - Function arguments: + * The function argument(s), if any, have to be defined in register + * variables at the place where this is invoked. Storing the + * argument(s) in the proper register(s) is part of the @asm_call + * + * - Constraints: + * + * The constraints have to be done very carefully because the compiler + * does not know about the assembly call. + * + * output: + * As documented already above the @tos variable is required to be in + * the output constraints to make the compiler aware that R11 cannot be + * reused after the asm() statement. + * + * For builds with CONFIG_UNWIND_FRAME_POINTER ASM_CALL_CONSTRAINT is + * required as well as this prevents certain creative GCC variants from + * misplacing the ASM code. + * + * input: + * - func: + * Immediate, which tells the compiler that the function is referenced. + * + * - tos: + * Register. The actual register is defined by the variable declaration. + * + * - function arguments: + * The constraints are handed in via the 'argconstr' argument list. They + * describe the register arguments which are used in @asm_call. + * + * clobbers: + * Function calls can clobber anything except the callee-saved + * registers. Tell the compiler. + */ +#define call_on_irqstack(func, asm_call, argconstr...) \ +{ \ + register void *tos asm("r11"); \ + \ + tos = ((void *)__this_cpu_read(hardirq_stack_ptr)); \ + \ + asm_inline volatile( \ + "movq %%rsp, (%[tos]) \n" \ + "movq %[tos], %%rsp \n" \ + \ + asm_call \ + \ + "popq %%rsp \n" \ + \ + : "+r" (tos), ASM_CALL_CONSTRAINT \ + : [__func] "i" (func), [tos] "r" (tos) argconstr \ + : "cc", "rax", "rcx", "rdx", "rsi", "rdi", "r8", "r9", "r10", \ + "memory" \ + ); \ } -static __always_inline void -__run_sysvec_on_irqstack(void (*func)(struct pt_regs *regs), - struct pt_regs *regs) -{ - void *tos = __this_cpu_read(hardirq_stack_ptr); - - __this_cpu_add(irq_count, 1); - asm_call_sysvec_on_stack(tos - 8, func, regs); - __this_cpu_sub(irq_count, 1); +/* Macros to assert type correctness for run_*_on_irqstack macros */ +#define assert_function_type(func, proto) \ + static_assert(__builtin_types_compatible_p(typeof(&func), proto)) + +#define assert_arg_type(arg, proto) \ + static_assert(__builtin_types_compatible_p(typeof(arg), proto)) + +/* + * Macro to invoke system vector and device interrupt C handlers. + */ +#define call_on_irqstack_cond(func, regs, asm_call, constr, c_args...) \ +{ \ + /* \ + * User mode entry and interrupt on the irq stack do not \ + * switch stacks. If from user mode the task stack is empty. \ + */ \ + if (user_mode(regs) || __this_cpu_read(hardirq_stack_inuse)) { \ + irq_enter_rcu(); \ + func(c_args); \ + irq_exit_rcu(); \ + } else { \ + /* \ + * Mark the irq stack inuse _before_ and unmark _after_ \ + * switching stacks. Interrupts are disabled in both \ + * places. Invoke the stack switch macro with the call \ + * sequence which matches the above direct invocation. \ + */ \ + __this_cpu_write(hardirq_stack_inuse, true); \ + call_on_irqstack(func, asm_call, constr); \ + __this_cpu_write(hardirq_stack_inuse, false); \ + } \ } -static __always_inline void -__run_irq_on_irqstack(void (*func)(struct irq_desc *desc), - struct irq_desc *desc) -{ - void *tos = __this_cpu_read(hardirq_stack_ptr); - - __this_cpu_add(irq_count, 1); - asm_call_irq_on_stack(tos - 8, func, desc); - __this_cpu_sub(irq_count, 1); +/* + * Function call sequence for __call_on_irqstack() for system vectors. + * + * Note that irq_enter_rcu() and irq_exit_rcu() do not use the input + * mechanism because these functions are global and cannot be optimized out + * when compiling a particular source file which uses one of these macros. + * + * The argument (regs) does not need to be pushed or stashed in a callee + * saved register to be safe vs. the irq_enter_rcu() call because the + * clobbers already prevent the compiler from storing it in a callee + * clobbered register. As the compiler has to preserve @regs for the final + * call to idtentry_exit() anyway, it's likely that it does not cause extra + * effort for this asm magic. + */ +#define ASM_CALL_SYSVEC \ + "call irq_enter_rcu \n" \ + "movq %[arg1], %%rdi \n" \ + "call %P[__func] \n" \ + "call irq_exit_rcu \n" + +#define SYSVEC_CONSTRAINTS , [arg1] "r" (regs) + +#define run_sysvec_on_irqstack_cond(func, regs) \ +{ \ + assert_function_type(func, void (*)(struct pt_regs *)); \ + assert_arg_type(regs, struct pt_regs *); \ + \ + call_on_irqstack_cond(func, regs, ASM_CALL_SYSVEC, \ + SYSVEC_CONSTRAINTS, regs); \ } -#else /* CONFIG_X86_64 */ -static inline bool irqstack_active(void) { return false; } -static inline void __run_on_irqstack(void (*func)(void)) { } -static inline void __run_sysvec_on_irqstack(void (*func)(struct pt_regs *regs), - struct pt_regs *regs) { } -static inline void __run_irq_on_irqstack(void (*func)(struct irq_desc *desc), - struct irq_desc *desc) { } -#endif /* !CONFIG_X86_64 */ - -static __always_inline bool irq_needs_irq_stack(struct pt_regs *regs) -{ - if (IS_ENABLED(CONFIG_X86_32)) - return false; - if (!regs) - return !irqstack_active(); - return !user_mode(regs) && !irqstack_active(); +/* + * As in ASM_CALL_SYSVEC above the clobbers force the compiler to store + * @regs and @vector in callee saved registers. + */ +#define ASM_CALL_IRQ \ + "call irq_enter_rcu \n" \ + "movq %[arg1], %%rdi \n" \ + "movl %[arg2], %%esi \n" \ + "call %P[__func] \n" \ + "call irq_exit_rcu \n" + +#define IRQ_CONSTRAINTS , [arg1] "r" (regs), [arg2] "r" (vector) + +#define run_irq_on_irqstack_cond(func, regs, vector) \ +{ \ + assert_function_type(func, void (*)(struct pt_regs *, u32)); \ + assert_arg_type(regs, struct pt_regs *); \ + assert_arg_type(vector, u32); \ + \ + call_on_irqstack_cond(func, regs, ASM_CALL_IRQ, \ + IRQ_CONSTRAINTS, regs, vector); \ } - -static __always_inline void run_on_irqstack_cond(void (*func)(void), - struct pt_regs *regs) -{ - lockdep_assert_irqs_disabled(); - - if (irq_needs_irq_stack(regs)) - __run_on_irqstack(func); - else - func(); +#define ASM_CALL_SOFTIRQ \ + "call %P[__func] \n" + +/* + * Macro to invoke __do_softirq on the irq stack. This is only called from + * task context when bottom halfs are about to be reenabled and soft + * interrupts are pending to be processed. The interrupt stack cannot be in + * use here. + */ +#define do_softirq_own_stack() \ +{ \ + __this_cpu_write(hardirq_stack_inuse, true); \ + call_on_irqstack(__do_softirq, ASM_CALL_SOFTIRQ); \ + __this_cpu_write(hardirq_stack_inuse, false); \ } -static __always_inline void -run_sysvec_on_irqstack_cond(void (*func)(struct pt_regs *regs), - struct pt_regs *regs) -{ - lockdep_assert_irqs_disabled(); - - if (irq_needs_irq_stack(regs)) - __run_sysvec_on_irqstack(func, regs); - else - func(regs); +#else /* CONFIG_X86_64 */ +/* System vector handlers always run on the stack they interrupted. */ +#define run_sysvec_on_irqstack_cond(func, regs) \ +{ \ + irq_enter_rcu(); \ + func(regs); \ + irq_exit_rcu(); \ } -static __always_inline void -run_irq_on_irqstack_cond(void (*func)(struct irq_desc *desc), struct irq_desc *desc, - struct pt_regs *regs) -{ - lockdep_assert_irqs_disabled(); - - if (irq_needs_irq_stack(regs)) - __run_irq_on_irqstack(func, desc); - else - func(desc); +/* Switches to the irq stack within func() */ +#define run_irq_on_irqstack_cond(func, regs, vector) \ +{ \ + irq_enter_rcu(); \ + func(regs, vector); \ + irq_exit_rcu(); \ } +#endif /* !CONFIG_X86_64 */ + #endif diff --git a/arch/x86/include/asm/irqflags.h b/arch/x86/include/asm/irqflags.h index 2dfc8d380dab..144d70ea4393 100644 --- a/arch/x86/include/asm/irqflags.h +++ b/arch/x86/include/asm/irqflags.h @@ -35,15 +35,6 @@ extern __always_inline unsigned long native_save_fl(void) return flags; } -extern inline void native_restore_fl(unsigned long flags); -extern inline void native_restore_fl(unsigned long flags) -{ - asm volatile("push %0 ; popf" - : /* no output */ - :"g" (flags) - :"memory", "cc"); -} - static __always_inline void native_irq_disable(void) { asm volatile("cli": : :"memory"); @@ -79,11 +70,6 @@ static __always_inline unsigned long arch_local_save_flags(void) return native_save_fl(); } -static __always_inline void arch_local_irq_restore(unsigned long flags) -{ - native_restore_fl(flags); -} - static __always_inline void arch_local_irq_disable(void) { native_irq_disable(); @@ -131,25 +117,7 @@ static __always_inline unsigned long arch_local_irq_save(void) #define SAVE_FLAGS(x) pushfq; popq %rax #endif -#define SWAPGS swapgs -/* - * Currently paravirt can't handle swapgs nicely when we - * don't have a stack we can rely on (such as a user space - * stack). So we either find a way around these or just fault - * and emulate if a guest tries to call swapgs directly. - * - * Either way, this is a good way to document that we don't - * have a reliable stack. x86_64 only. - */ -#define SWAPGS_UNSAFE_STACK swapgs - #define INTERRUPT_RETURN jmp native_iret -#define USERGS_SYSRET64 \ - swapgs; \ - sysretq; -#define USERGS_SYSRET32 \ - swapgs; \ - sysretl #else #define INTERRUPT_RETURN iret @@ -170,6 +138,20 @@ static __always_inline int arch_irqs_disabled(void) return arch_irqs_disabled_flags(flags); } + +static __always_inline void arch_local_irq_restore(unsigned long flags) +{ + if (!arch_irqs_disabled_flags(flags)) + arch_local_irq_enable(); +} +#else +#ifdef CONFIG_X86_64 +#ifdef CONFIG_XEN_PV +#define SWAPGS ALTERNATIVE "swapgs", "", X86_FEATURE_XENPV +#else +#define SWAPGS swapgs +#endif +#endif #endif /* !__ASSEMBLY__ */ #endif diff --git a/arch/x86/include/asm/kfence.h b/arch/x86/include/asm/kfence.h new file mode 100644 index 000000000000..97bbb4a9083a --- /dev/null +++ b/arch/x86/include/asm/kfence.h @@ -0,0 +1,64 @@ +/* SPDX-License-Identifier: GPL-2.0 */ +/* + * x86 KFENCE support. + * + * Copyright (C) 2020, Google LLC. + */ + +#ifndef _ASM_X86_KFENCE_H +#define _ASM_X86_KFENCE_H + +#include <linux/bug.h> +#include <linux/kfence.h> + +#include <asm/pgalloc.h> +#include <asm/pgtable.h> +#include <asm/set_memory.h> +#include <asm/tlbflush.h> + +/* Force 4K pages for __kfence_pool. */ +static inline bool arch_kfence_init_pool(void) +{ + unsigned long addr; + + for (addr = (unsigned long)__kfence_pool; is_kfence_address((void *)addr); + addr += PAGE_SIZE) { + unsigned int level; + + if (!lookup_address(addr, &level)) + return false; + + if (level != PG_LEVEL_4K) + set_memory_4k(addr, 1); + } + + return true; +} + +/* Protect the given page and flush TLB. */ +static inline bool kfence_protect_page(unsigned long addr, bool protect) +{ + unsigned int level; + pte_t *pte = lookup_address(addr, &level); + + if (WARN_ON(!pte || level != PG_LEVEL_4K)) + return false; + + /* + * We need to avoid IPIs, as we may get KFENCE allocations or faults + * with interrupts disabled. Therefore, the below is best-effort, and + * does not flush TLBs on all CPUs. We can tolerate some inaccuracy; + * lazy fault handling takes care of faults after the page is PRESENT. + */ + + if (protect) + set_pte(pte, __pte(pte_val(*pte) & ~_PAGE_PRESENT)); + else + set_pte(pte, __pte(pte_val(*pte) | _PAGE_PRESENT)); + + /* Flush this CPU's TLB. */ + flush_tlb_one_kernel(addr); + return true; +} + +#endif /* _ASM_X86_KFENCE_H */ diff --git a/arch/x86/include/asm/kprobes.h b/arch/x86/include/asm/kprobes.h index 991a7ad540c7..d20a3d6be36e 100644 --- a/arch/x86/include/asm/kprobes.h +++ b/arch/x86/include/asm/kprobes.h @@ -58,14 +58,17 @@ struct arch_specific_insn { /* copy of the original instruction */ kprobe_opcode_t *insn; /* - * boostable = false: This instruction type is not boostable. - * boostable = true: This instruction has been boosted: we have + * boostable = 0: This instruction type is not boostable. + * boostable = 1: This instruction has been boosted: we have * added a relative jump after the instruction copy in insn, * so no single-step and fixup are needed (unless there's * a post_handler). */ - bool boostable; - bool if_modifier; + unsigned boostable:1; + unsigned if_modifier:1; + unsigned is_call:1; + unsigned is_pushf:1; + unsigned is_abs_ip:1; /* Number of bytes of text poked */ int tp_len; }; diff --git a/arch/x86/include/asm/kvm-x86-ops.h b/arch/x86/include/asm/kvm-x86-ops.h new file mode 100644 index 000000000000..323641097f63 --- /dev/null +++ b/arch/x86/include/asm/kvm-x86-ops.h @@ -0,0 +1,123 @@ +/* SPDX-License-Identifier: GPL-2.0 */ +#if !defined(KVM_X86_OP) || !defined(KVM_X86_OP_NULL) +BUILD_BUG_ON(1) +#endif + +/* + * KVM_X86_OP() and KVM_X86_OP_NULL() are used to help generate + * "static_call()"s. They are also intended for use when defining + * the vmx/svm kvm_x86_ops. KVM_X86_OP() can be used for those + * functions that follow the [svm|vmx]_func_name convention. + * KVM_X86_OP_NULL() can leave a NULL definition for the + * case where there is no definition or a function name that + * doesn't match the typical naming convention is supplied. + */ +KVM_X86_OP_NULL(hardware_enable) +KVM_X86_OP_NULL(hardware_disable) +KVM_X86_OP_NULL(hardware_unsetup) +KVM_X86_OP_NULL(cpu_has_accelerated_tpr) +KVM_X86_OP(has_emulated_msr) +KVM_X86_OP(vcpu_after_set_cpuid) +KVM_X86_OP(vm_init) +KVM_X86_OP_NULL(vm_destroy) +KVM_X86_OP(vcpu_create) +KVM_X86_OP(vcpu_free) +KVM_X86_OP(vcpu_reset) +KVM_X86_OP(prepare_guest_switch) +KVM_X86_OP(vcpu_load) +KVM_X86_OP(vcpu_put) +KVM_X86_OP(update_exception_bitmap) +KVM_X86_OP(get_msr) +KVM_X86_OP(set_msr) +KVM_X86_OP(get_segment_base) +KVM_X86_OP(get_segment) +KVM_X86_OP(get_cpl) +KVM_X86_OP(set_segment) +KVM_X86_OP_NULL(get_cs_db_l_bits) +KVM_X86_OP(set_cr0) +KVM_X86_OP(is_valid_cr4) +KVM_X86_OP(set_cr4) +KVM_X86_OP(set_efer) +KVM_X86_OP(get_idt) +KVM_X86_OP(set_idt) +KVM_X86_OP(get_gdt) +KVM_X86_OP(set_gdt) +KVM_X86_OP(sync_dirty_debug_regs) +KVM_X86_OP(set_dr7) +KVM_X86_OP(cache_reg) +KVM_X86_OP(get_rflags) +KVM_X86_OP(set_rflags) +KVM_X86_OP(tlb_flush_all) +KVM_X86_OP(tlb_flush_current) +KVM_X86_OP_NULL(tlb_remote_flush) +KVM_X86_OP_NULL(tlb_remote_flush_with_range) +KVM_X86_OP(tlb_flush_gva) +KVM_X86_OP(tlb_flush_guest) +KVM_X86_OP(run) +KVM_X86_OP_NULL(handle_exit) +KVM_X86_OP_NULL(skip_emulated_instruction) +KVM_X86_OP_NULL(update_emulated_instruction) +KVM_X86_OP(set_interrupt_shadow) +KVM_X86_OP(get_interrupt_shadow) +KVM_X86_OP(patch_hypercall) +KVM_X86_OP(set_irq) +KVM_X86_OP(set_nmi) +KVM_X86_OP(queue_exception) +KVM_X86_OP(cancel_injection) +KVM_X86_OP(interrupt_allowed) +KVM_X86_OP(nmi_allowed) +KVM_X86_OP(get_nmi_mask) +KVM_X86_OP(set_nmi_mask) +KVM_X86_OP(enable_nmi_window) +KVM_X86_OP(enable_irq_window) +KVM_X86_OP(update_cr8_intercept) +KVM_X86_OP(check_apicv_inhibit_reasons) +KVM_X86_OP_NULL(pre_update_apicv_exec_ctrl) +KVM_X86_OP(refresh_apicv_exec_ctrl) +KVM_X86_OP(hwapic_irr_update) +KVM_X86_OP(hwapic_isr_update) +KVM_X86_OP_NULL(guest_apic_has_interrupt) +KVM_X86_OP(load_eoi_exitmap) +KVM_X86_OP(set_virtual_apic_mode) +KVM_X86_OP_NULL(set_apic_access_page_addr) +KVM_X86_OP(deliver_posted_interrupt) +KVM_X86_OP_NULL(sync_pir_to_irr) +KVM_X86_OP(set_tss_addr) +KVM_X86_OP(set_identity_map_addr) +KVM_X86_OP(get_mt_mask) +KVM_X86_OP(load_mmu_pgd) +KVM_X86_OP_NULL(has_wbinvd_exit) +KVM_X86_OP(write_l1_tsc_offset) +KVM_X86_OP(get_exit_info) +KVM_X86_OP(check_intercept) +KVM_X86_OP(handle_exit_irqoff) +KVM_X86_OP_NULL(request_immediate_exit) +KVM_X86_OP(sched_in) +KVM_X86_OP_NULL(update_cpu_dirty_logging) +KVM_X86_OP_NULL(pre_block) +KVM_X86_OP_NULL(post_block) +KVM_X86_OP_NULL(vcpu_blocking) +KVM_X86_OP_NULL(vcpu_unblocking) +KVM_X86_OP_NULL(update_pi_irte) +KVM_X86_OP_NULL(apicv_post_state_restore) +KVM_X86_OP_NULL(dy_apicv_has_pending_interrupt) +KVM_X86_OP_NULL(set_hv_timer) +KVM_X86_OP_NULL(cancel_hv_timer) +KVM_X86_OP(setup_mce) +KVM_X86_OP(smi_allowed) +KVM_X86_OP(pre_enter_smm) +KVM_X86_OP(pre_leave_smm) +KVM_X86_OP(enable_smi_window) +KVM_X86_OP_NULL(mem_enc_op) +KVM_X86_OP_NULL(mem_enc_reg_region) +KVM_X86_OP_NULL(mem_enc_unreg_region) +KVM_X86_OP(get_msr_feature) +KVM_X86_OP(can_emulate_instruction) +KVM_X86_OP(apic_init_signal_blocked) +KVM_X86_OP_NULL(enable_direct_tlbflush) +KVM_X86_OP_NULL(migrate_timers) +KVM_X86_OP(msr_filter_changed) +KVM_X86_OP_NULL(complete_emulated_msr) + +#undef KVM_X86_OP +#undef KVM_X86_OP_NULL diff --git a/arch/x86/include/asm/kvm_host.h b/arch/x86/include/asm/kvm_host.h index 3d6616f6f6ef..3768819693e5 100644 --- a/arch/x86/include/asm/kvm_host.h +++ b/arch/x86/include/asm/kvm_host.h @@ -40,10 +40,8 @@ #define KVM_MAX_VCPUS 288 #define KVM_SOFT_MAX_VCPUS 240 #define KVM_MAX_VCPU_ID 1023 -#define KVM_USER_MEM_SLOTS 509 /* memory slots that are not exposed to userspace */ #define KVM_PRIVATE_MEM_SLOTS 3 -#define KVM_MEM_SLOTS_NUM (KVM_USER_MEM_SLOTS + KVM_PRIVATE_MEM_SLOTS) #define KVM_HALT_POLL_NS_DEFAULT 200000 @@ -52,6 +50,9 @@ #define KVM_DIRTY_LOG_MANUAL_CAPS (KVM_DIRTY_LOG_MANUAL_PROTECT_ENABLE | \ KVM_DIRTY_LOG_INITIALLY_SET) +#define KVM_BUS_LOCK_DETECTION_VALID_MODE (KVM_BUS_LOCK_DETECTION_OFF | \ + KVM_BUS_LOCK_DETECTION_EXIT) + /* x86-specific vcpu->requests bit members */ #define KVM_REQ_MIGRATE_TIMER KVM_ARCH_REQ(0) #define KVM_REQ_REPORT_TPR_ACCESS KVM_ARCH_REQ(1) @@ -88,6 +89,8 @@ KVM_ARCH_REQ_FLAGS(27, KVM_REQUEST_NO_WAKEUP) #define KVM_REQ_APF_READY KVM_ARCH_REQ(28) #define KVM_REQ_MSR_FILTER_CHANGED KVM_ARCH_REQ(29) +#define KVM_REQ_UPDATE_CPU_DIRTY_LOGGING \ + KVM_ARCH_REQ_FLAGS(30, KVM_REQUEST_WAIT | KVM_REQUEST_NO_WAKEUP) #define CR0_RESERVED_BITS \ (~(unsigned long)(X86_CR0_PE | X86_CR0_MP | X86_CR0_EM | X86_CR0_TS \ @@ -200,9 +203,17 @@ enum x86_intercept_stage; #define DR6_BS (1 << 14) #define DR6_BT (1 << 15) #define DR6_RTM (1 << 16) -#define DR6_FIXED_1 0xfffe0ff0 -#define DR6_INIT 0xffff0ff0 +/* + * DR6_ACTIVE_LOW combines fixed-1 and active-low bits. + * We can regard all the bits in DR6_FIXED_1 as active_low bits; + * they will never be 0 for now, but when they are defined + * in the future it will require no code change. + * + * DR6_ACTIVE_LOW is also used as the init/reset value for DR6. + */ +#define DR6_ACTIVE_LOW 0xffff0ff0 #define DR6_VOLATILE 0x0001e00f +#define DR6_FIXED_1 (DR6_ACTIVE_LOW & ~DR6_VOLATILE) #define DR7_BP_EN_MASK 0x000000ff #define DR7_GE (1 << 9) @@ -337,6 +348,8 @@ struct kvm_mmu_root_info { #define KVM_MMU_NUM_PREV_ROOTS 3 +#define KVM_HAVE_MMU_RWLOCK + struct kvm_mmu_page; /* @@ -358,8 +371,6 @@ struct kvm_mmu { int (*sync_page)(struct kvm_vcpu *vcpu, struct kvm_mmu_page *sp); void (*invlpg)(struct kvm_vcpu *vcpu, gva_t gva, hpa_t root_hpa); - void (*update_pte)(struct kvm_vcpu *vcpu, struct kvm_mmu_page *sp, - u64 *spte, const void *pte); hpa_t root_hpa; gpa_t root_pgd; union kvm_mmu_role mmu_role; @@ -510,6 +521,7 @@ struct kvm_vcpu_hv_synic { /* Hyper-V per vcpu emulation context */ struct kvm_vcpu_hv { + struct kvm_vcpu *vcpu; u32 vp_index; u64 hv_vapic; s64 runtime_offset; @@ -520,6 +532,21 @@ struct kvm_vcpu_hv { cpumask_t tlb_flush; }; +/* Xen HVM per vcpu emulation context */ +struct kvm_vcpu_xen { + u64 hypercall_rip; + u32 current_runstate; + bool vcpu_info_set; + bool vcpu_time_info_set; + bool runstate_set; + struct gfn_to_hva_cache vcpu_info_cache; + struct gfn_to_hva_cache vcpu_time_info_cache; + struct gfn_to_hva_cache runstate_cache; + u64 last_steal; + u64 runstate_entry_time; + u64 runstate_times[4]; +}; + struct kvm_vcpu_arch { /* * rip and regs accesses must go through @@ -640,7 +667,7 @@ struct kvm_vcpu_arch { int cpuid_nent; struct kvm_cpuid_entry2 *cpuid_entries; - unsigned long cr3_lm_rsvd_bits; + u64 reserved_gpa_bits; int maxphyaddr; int max_tdp_level; @@ -717,7 +744,9 @@ struct kvm_vcpu_arch { /* used for guest single stepping over the given code position */ unsigned long singlestep_rip; - struct kvm_vcpu_hv hyperv; + bool hyperv_enabled; + struct kvm_vcpu_hv *hyperv; + struct kvm_vcpu_xen xen; cpumask_var_t wbinvd_dirty_mask; @@ -855,12 +884,29 @@ struct kvm_hv_syndbg { u64 options; }; +/* Current state of Hyper-V TSC page clocksource */ +enum hv_tsc_page_status { + /* TSC page was not set up or disabled */ + HV_TSC_PAGE_UNSET = 0, + /* TSC page MSR was written by the guest, update pending */ + HV_TSC_PAGE_GUEST_CHANGED, + /* TSC page MSR was written by KVM userspace, update pending */ + HV_TSC_PAGE_HOST_CHANGED, + /* TSC page was properly set up and is currently active */ + HV_TSC_PAGE_SET, + /* TSC page is currently being updated and therefore is inactive */ + HV_TSC_PAGE_UPDATING, + /* TSC page was set up with an inaccessible GPA */ + HV_TSC_PAGE_BROKEN, +}; + /* Hyper-V emulation context */ struct kvm_hv { struct mutex hv_lock; u64 hv_guest_os_id; u64 hv_hypercall; u64 hv_tsc_page; + enum hv_tsc_page_status hv_tsc_page_status; /* Hyper-v based guest crash (NT kernel bugcheck) parameters */ u64 hv_crash_param[HV_X64_MSR_CRASH_PARAMS]; @@ -888,12 +934,26 @@ struct msr_bitmap_range { unsigned long *bitmap; }; +/* Xen emulation context */ +struct kvm_xen { + bool long_mode; + bool shinfo_set; + u8 upcall_vector; + struct gfn_to_hva_cache shinfo_cache; +}; + enum kvm_irqchip_mode { KVM_IRQCHIP_NONE, KVM_IRQCHIP_KERNEL, /* created with KVM_CREATE_IRQCHIP */ KVM_IRQCHIP_SPLIT, /* created with KVM_CAP_SPLIT_IRQCHIP */ }; +struct kvm_x86_msr_filter { + u8 count; + bool default_allow:1; + struct msr_bitmap_range ranges[16]; +}; + #define APICV_INHIBIT_REASON_DISABLE 0 #define APICV_INHIBIT_REASON_HYPERV 1 #define APICV_INHIBIT_REASON_NESTED 2 @@ -908,9 +968,6 @@ struct kvm_arch { unsigned int indirect_shadow_pages; u8 mmu_valid_gen; struct hlist_head mmu_page_hash[KVM_NUM_MMU_PAGES]; - /* - * Hash table of struct kvm_mmu_page. - */ struct list_head active_mmu_pages; struct list_head zapped_obsolete_pages; struct list_head lpage_disallowed_mmu_pages; @@ -929,7 +986,7 @@ struct kvm_arch { struct kvm_pit *vpit; atomic_t vapics_in_nmi_mode; struct mutex apic_map_lock; - struct kvm_apic_map *apic_map; + struct kvm_apic_map __rcu *apic_map; atomic_t apic_map_dirty; bool apic_access_page_done; @@ -967,6 +1024,7 @@ struct kvm_arch { struct hlist_head mask_notifier_list; struct kvm_hv hyperv; + struct kvm_xen xen; #ifdef CONFIG_KVM_MMU_AUDIT int audit_point; @@ -977,6 +1035,7 @@ struct kvm_arch { u32 bsp_vcpu_id; u64 disabled_quirks; + int cpu_dirty_logging_count; enum kvm_irqchip_mode irqchip_mode; u8 nr_reserved_ioapic_pins; @@ -989,18 +1048,16 @@ struct kvm_arch { bool guest_can_read_msr_platform_info; bool exception_payload_enabled; + bool bus_lock_detection_enabled; + /* Deflect RDMSR and WRMSR to user space when they trigger a #GP */ u32 user_space_msr_mask; + struct kvm_x86_msr_filter __rcu *msr_filter; - struct { - u8 count; - bool default_allow:1; - struct msr_bitmap_range ranges[16]; - } msr_filter; - - struct kvm_pmu_event_filter *pmu_event_filter; + struct kvm_pmu_event_filter __rcu *pmu_event_filter; struct task_struct *nx_lpage_recovery_thread; +#ifdef CONFIG_X86_64 /* * Whether the TDP MMU is enabled for this VM. This contains a * snapshot of the TDP MMU module parameter from when the VM was @@ -1026,12 +1083,25 @@ struct kvm_arch { * tdp_mmu_page set and a root_count of 0. */ struct list_head tdp_mmu_pages; + + /* + * Protects accesses to the following fields when the MMU lock + * is held in read mode: + * - tdp_mmu_pages (above) + * - the link field of struct kvm_mmu_pages used by the TDP MMU + * - lpage_disallowed_mmu_pages + * - the lpage_disallowed_link field of struct kvm_mmu_pages used + * by the TDP MMU + * It is acceptable, but not necessary, to acquire this lock when + * the thread holds the MMU lock in write mode. + */ + spinlock_t tdp_mmu_pages_lock; +#endif /* CONFIG_X86_64 */ }; struct kvm_vm_stat { ulong mmu_shadow_zapped; ulong mmu_pte_write; - ulong mmu_pte_updated; ulong mmu_pde_zapped; ulong mmu_flooded; ulong mmu_recycled; @@ -1225,30 +1295,11 @@ struct kvm_x86_ops { void (*sched_in)(struct kvm_vcpu *kvm, int cpu); /* - * Arch-specific dirty logging hooks. These hooks are only supposed to - * be valid if the specific arch has hardware-accelerated dirty logging - * mechanism. Currently only for PML on VMX. - * - * - slot_enable_log_dirty: - * called when enabling log dirty mode for the slot. - * - slot_disable_log_dirty: - * called when disabling log dirty mode for the slot. - * also called when slot is created with log dirty disabled. - * - flush_log_dirty: - * called before reporting dirty_bitmap to userspace. - * - enable_log_dirty_pt_masked: - * called when reenabling log dirty for the GFNs in the mask after - * corresponding bits are cleared in slot->dirty_bitmap. + * Size of the CPU's dirty log buffer, i.e. VMX's PML buffer. A zero + * value indicates CPU dirty logging is unsupported or disabled. */ - void (*slot_enable_log_dirty)(struct kvm *kvm, - struct kvm_memory_slot *slot); - void (*slot_disable_log_dirty)(struct kvm *kvm, - struct kvm_memory_slot *slot); - void (*flush_log_dirty)(struct kvm *kvm); - void (*enable_log_dirty_pt_masked)(struct kvm *kvm, - struct kvm_memory_slot *slot, - gfn_t offset, unsigned long mask); - int (*cpu_dirty_log_size)(void); + int cpu_dirty_log_size; + void (*update_cpu_dirty_logging)(struct kvm_vcpu *vcpu); /* pmu operations of sub-arch */ const struct kvm_pmu_ops *pmu_ops; @@ -1340,6 +1391,19 @@ extern u64 __read_mostly host_efer; extern bool __read_mostly allow_smaller_maxphyaddr; extern struct kvm_x86_ops kvm_x86_ops; +#define KVM_X86_OP(func) \ + DECLARE_STATIC_CALL(kvm_x86_##func, *(((struct kvm_x86_ops *)0)->func)); +#define KVM_X86_OP_NULL KVM_X86_OP +#include <asm/kvm-x86-ops.h> + +static inline void kvm_ops_static_call_update(void) +{ +#define KVM_X86_OP(func) \ + static_call_update(kvm_x86_##func, kvm_x86_ops.func); +#define KVM_X86_OP_NULL KVM_X86_OP +#include <asm/kvm-x86-ops.h> +} + #define __KVM_HAVE_ARCH_VM_ALLOC static inline struct kvm *kvm_arch_alloc_vm(void) { @@ -1351,7 +1415,7 @@ void kvm_arch_free_vm(struct kvm *kvm); static inline int kvm_arch_flush_remote_tlb(struct kvm *kvm) { if (kvm_x86_ops.tlb_remote_flush && - !kvm_x86_ops.tlb_remote_flush(kvm)) + !static_call(kvm_x86_tlb_remote_flush)(kvm)) return 0; else return -ENOTSUPP; @@ -1378,11 +1442,6 @@ void kvm_mmu_slot_leaf_clear_dirty(struct kvm *kvm, struct kvm_memory_slot *memslot); void kvm_mmu_slot_largepage_remove_write_access(struct kvm *kvm, struct kvm_memory_slot *memslot); -void kvm_mmu_slot_set_dirty(struct kvm *kvm, - struct kvm_memory_slot *memslot); -void kvm_mmu_clear_dirty_pt_masked(struct kvm *kvm, - struct kvm_memory_slot *slot, - gfn_t gfn_offset, unsigned long mask); void kvm_mmu_zap_all(struct kvm *kvm); void kvm_mmu_invalidate_mmio_sptes(struct kvm *kvm, u64 gen); unsigned long kvm_mmu_calculate_default_mmu_pages(struct kvm *kvm); @@ -1421,6 +1480,8 @@ extern u8 kvm_tsc_scaling_ratio_frac_bits; extern u64 kvm_max_tsc_scaling_ratio; /* 1ull << kvm_tsc_scaling_ratio_frac_bits */ extern u64 kvm_default_tsc_scaling_ratio; +/* bus lock detection supported? */ +extern bool kvm_has_bus_lock_exit; extern u64 kvm_mce_cap_supported; @@ -1501,7 +1562,7 @@ int kvm_set_cr3(struct kvm_vcpu *vcpu, unsigned long cr3); int kvm_set_cr4(struct kvm_vcpu *vcpu, unsigned long cr4); int kvm_set_cr8(struct kvm_vcpu *vcpu, unsigned long cr8); int kvm_set_dr(struct kvm_vcpu *vcpu, int dr, unsigned long val); -int kvm_get_dr(struct kvm_vcpu *vcpu, int dr, unsigned long *val); +void kvm_get_dr(struct kvm_vcpu *vcpu, int dr, unsigned long *val); unsigned long kvm_get_cr8(struct kvm_vcpu *vcpu); void kvm_lmsw(struct kvm_vcpu *vcpu, unsigned long msw); void kvm_get_cs_db_l_bits(struct kvm_vcpu *vcpu, int *db, int *l); @@ -1552,7 +1613,6 @@ void kvm_inject_nmi(struct kvm_vcpu *vcpu); void kvm_update_dr7(struct kvm_vcpu *vcpu); int kvm_mmu_unprotect_page(struct kvm *kvm, gfn_t gfn); -int kvm_mmu_unprotect_page_virt(struct kvm_vcpu *vcpu, gva_t gva); void __kvm_mmu_free_some_pages(struct kvm_vcpu *vcpu); int kvm_mmu_load(struct kvm_vcpu *vcpu); void kvm_mmu_unload(struct kvm_vcpu *vcpu); @@ -1742,14 +1802,12 @@ static inline bool kvm_irq_is_postable(struct kvm_lapic_irq *irq) static inline void kvm_arch_vcpu_blocking(struct kvm_vcpu *vcpu) { - if (kvm_x86_ops.vcpu_blocking) - kvm_x86_ops.vcpu_blocking(vcpu); + static_call_cond(kvm_x86_vcpu_blocking)(vcpu); } static inline void kvm_arch_vcpu_unblocking(struct kvm_vcpu *vcpu) { - if (kvm_x86_ops.vcpu_unblocking) - kvm_x86_ops.vcpu_unblocking(vcpu); + static_call_cond(kvm_x86_vcpu_unblocking)(vcpu); } static inline void kvm_arch_vcpu_block_finish(struct kvm_vcpu *vcpu) {} diff --git a/arch/x86/include/asm/mce.h b/arch/x86/include/asm/mce.h index 56cdeaac76a0..ddfb3cad8dff 100644 --- a/arch/x86/include/asm/mce.h +++ b/arch/x86/include/asm/mce.h @@ -289,28 +289,6 @@ extern void (*mce_threshold_vector)(void); extern void (*deferred_error_int_vector)(void); /* - * Thermal handler - */ - -void intel_init_thermal(struct cpuinfo_x86 *c); - -/* Interrupt Handler for core thermal thresholds */ -extern int (*platform_thermal_notify)(__u64 msr_val); - -/* Interrupt Handler for package thermal thresholds */ -extern int (*platform_thermal_package_notify)(__u64 msr_val); - -/* Callback support of rate control, return true, if - * callback has rate control */ -extern bool (*platform_thermal_package_rate_control)(void); - -#ifdef CONFIG_X86_THERMAL_VECTOR -extern void mcheck_intel_therm_init(void); -#else -static inline void mcheck_intel_therm_init(void) { } -#endif - -/* * Used by APEI to report memory error via /dev/mcelog */ diff --git a/arch/x86/include/asm/microcode.h b/arch/x86/include/asm/microcode.h index 2b7cc5397f80..ab45a220fac4 100644 --- a/arch/x86/include/asm/microcode.h +++ b/arch/x86/include/asm/microcode.h @@ -127,14 +127,12 @@ static inline unsigned int x86_cpuid_family(void) } #ifdef CONFIG_MICROCODE -int __init microcode_init(void); extern void __init load_ucode_bsp(void); extern void load_ucode_ap(void); void reload_early_microcode(void); extern bool get_builtin_firmware(struct cpio_data *cd, const char *name); extern bool initrd_gone; #else -static inline int __init microcode_init(void) { return 0; }; static inline void __init load_ucode_bsp(void) { } static inline void load_ucode_ap(void) { } static inline void reload_early_microcode(void) { } diff --git a/arch/x86/include/asm/mshyperv.h b/arch/x86/include/asm/mshyperv.h index 30f76b966857..ccf60a809a17 100644 --- a/arch/x86/include/asm/mshyperv.h +++ b/arch/x86/include/asm/mshyperv.h @@ -78,6 +78,13 @@ extern int hyperv_init_cpuhp; extern void *hv_hypercall_pg; extern void __percpu **hyperv_pcpu_input_arg; +extern void __percpu **hyperv_pcpu_output_arg; + +extern u64 hv_current_partition_id; + +int hv_call_deposit_pages(int node, u64 partition_id, u32 num_pages); +int hv_call_add_logical_proc(int node, u32 lp_index, u32 acpi_id); +int hv_call_create_vp(int node, u64 partition_id, u32 vp_index, u32 flags); static inline u64 hv_do_hypercall(u64 control, void *input, void *output) { @@ -239,6 +246,8 @@ int hyperv_fill_flush_guest_mapping_list( struct hv_guest_mapping_flush_list *flush, u64 start_gfn, u64 end_gfn); +extern bool hv_root_partition; + #ifdef CONFIG_X86_64 void hv_apic_init(void); void __init hv_init_spinlocks(void); @@ -250,10 +259,16 @@ static inline void hv_apic_init(void) {} static inline void hv_set_msi_entry_from_desc(union hv_msi_entry *msi_entry, struct msi_desc *msi_desc) { - msi_entry->address = msi_desc->msg.address_lo; - msi_entry->data = msi_desc->msg.data; + msi_entry->address.as_uint32 = msi_desc->msg.address_lo; + msi_entry->data.as_uint32 = msi_desc->msg.data; } +struct irq_domain *hv_create_pci_msi_domain(void); + +int hv_map_ioapic_interrupt(int ioapic_id, bool level, int vcpu, int vector, + struct hv_interrupt_entry *entry); +int hv_unmap_ioapic_interrupt(int ioapic_id, struct hv_interrupt_entry *entry); + #else /* CONFIG_HYPERV */ static inline void hyperv_init(void) {} static inline void hyperv_setup_mmu_ops(void) {} diff --git a/arch/x86/include/asm/nmi.h b/arch/x86/include/asm/nmi.h index 9d5d949e662e..1cb9c17a4cb4 100644 --- a/arch/x86/include/asm/nmi.h +++ b/arch/x86/include/asm/nmi.h @@ -9,7 +9,6 @@ #ifdef CONFIG_X86_LOCAL_APIC -extern int avail_to_resrv_perfctr_nmi_bit(unsigned int); extern int reserve_perfctr_nmi(unsigned int); extern void release_perfctr_nmi(unsigned int); extern int reserve_evntsel_nmi(unsigned int); diff --git a/arch/x86/include/asm/orc_types.h b/arch/x86/include/asm/orc_types.h index fdbffec4cfde..5a2baf28a1dc 100644 --- a/arch/x86/include/asm/orc_types.h +++ b/arch/x86/include/asm/orc_types.h @@ -40,6 +40,8 @@ #define ORC_REG_MAX 15 #ifndef __ASSEMBLY__ +#include <asm/byteorder.h> + /* * This struct is more or less a vastly simplified version of the DWARF Call * Frame Information standard. It contains only the necessary parts of DWARF @@ -51,10 +53,18 @@ struct orc_entry { s16 sp_offset; s16 bp_offset; +#if defined(__LITTLE_ENDIAN_BITFIELD) unsigned sp_reg:4; unsigned bp_reg:4; unsigned type:2; unsigned end:1; +#elif defined(__BIG_ENDIAN_BITFIELD) + unsigned bp_reg:4; + unsigned sp_reg:4; + unsigned unused:5; + unsigned end:1; + unsigned type:2; +#endif } __packed; #endif /* __ASSEMBLY__ */ diff --git a/arch/x86/include/asm/page_64_types.h b/arch/x86/include/asm/page_64_types.h index 645bd1d0ee07..64297eabad63 100644 --- a/arch/x86/include/asm/page_64_types.h +++ b/arch/x86/include/asm/page_64_types.h @@ -66,7 +66,7 @@ * On Intel CPUs, if a SYSCALL instruction is at the highest canonical * address, then that syscall will enter the kernel with a * non-canonical return address, and SYSRET will explode dangerously. - * We avoid this particular problem by preventing anything executable + * We avoid this particular problem by preventing anything * from being mapped at the maximum canonical address. * * On AMD CPUs in the Ryzen family, there's a nasty bug in which the diff --git a/arch/x86/include/asm/paravirt.h b/arch/x86/include/asm/paravirt.h index f8dce11d2bc1..4abf110e2243 100644 --- a/arch/x86/include/asm/paravirt.h +++ b/arch/x86/include/asm/paravirt.h @@ -648,11 +648,6 @@ static inline notrace unsigned long arch_local_save_flags(void) return PVOP_CALLEE0(unsigned long, irq.save_fl); } -static inline notrace void arch_local_irq_restore(unsigned long f) -{ - PVOP_VCALLEE1(irq.restore_fl, f); -} - static inline notrace void arch_local_irq_disable(void) { PVOP_VCALLEE0(irq.irq_disable); @@ -776,31 +771,6 @@ extern void default_banner(void); #ifdef CONFIG_X86_64 #ifdef CONFIG_PARAVIRT_XXL -/* - * If swapgs is used while the userspace stack is still current, - * there's no way to call a pvop. The PV replacement *must* be - * inlined, or the swapgs instruction must be trapped and emulated. - */ -#define SWAPGS_UNSAFE_STACK \ - PARA_SITE(PARA_PATCH(PV_CPU_swapgs), swapgs) - -/* - * Note: swapgs is very special, and in practise is either going to be - * implemented with a single "swapgs" instruction or something very - * special. Either way, we don't need to save any registers for - * it. - */ -#define SWAPGS \ - PARA_SITE(PARA_PATCH(PV_CPU_swapgs), \ - ANNOTATE_RETPOLINE_SAFE; \ - call PARA_INDIRECT(pv_ops+PV_CPU_swapgs); \ - ) - -#define USERGS_SYSRET64 \ - PARA_SITE(PARA_PATCH(PV_CPU_usergs_sysret64), \ - ANNOTATE_RETPOLINE_SAFE; \ - jmp PARA_INDIRECT(pv_ops+PV_CPU_usergs_sysret64);) - #ifdef CONFIG_DEBUG_ENTRY #define SAVE_FLAGS(clobbers) \ PARA_SITE(PARA_PATCH(PV_IRQ_save_fl), \ diff --git a/arch/x86/include/asm/paravirt_types.h b/arch/x86/include/asm/paravirt_types.h index b6b02b7c19cc..de87087d3bde 100644 --- a/arch/x86/include/asm/paravirt_types.h +++ b/arch/x86/include/asm/paravirt_types.h @@ -156,20 +156,10 @@ struct pv_cpu_ops { u64 (*read_pmc)(int counter); - /* - * Switch to usermode gs and return to 64-bit usermode using - * sysret. Only used in 64-bit kernels to return to 64-bit - * processes. Usermode register state, including %rsp, must - * already be restored. - */ - void (*usergs_sysret64)(void); - /* Normal iret. Jump to this with the standard iret stack frame set up. */ void (*iret)(void); - void (*swapgs)(void); - void (*start_context_switch)(struct task_struct *prev); void (*end_context_switch)(struct task_struct *next); #endif @@ -178,16 +168,13 @@ struct pv_cpu_ops { struct pv_irq_ops { #ifdef CONFIG_PARAVIRT_XXL /* - * Get/set interrupt state. save_fl and restore_fl are only - * expected to use X86_EFLAGS_IF; all other bits - * returned from save_fl are undefined, and may be ignored by - * restore_fl. + * Get/set interrupt state. save_fl is expected to use X86_EFLAGS_IF; + * all other bits returned from save_fl are undefined. * * NOTE: These functions callers expect the callee to preserve * more registers than the standard C calling convention. */ struct paravirt_callee_save save_fl; - struct paravirt_callee_save restore_fl; struct paravirt_callee_save irq_disable; struct paravirt_callee_save irq_enable; diff --git a/arch/x86/include/asm/perf_event.h b/arch/x86/include/asm/perf_event.h index b9a7fd0a27e2..544f41a179fb 100644 --- a/arch/x86/include/asm/perf_event.h +++ b/arch/x86/include/asm/perf_event.h @@ -261,8 +261,12 @@ struct x86_pmu_capability { #define INTEL_PMC_IDX_TD_BAD_SPEC (INTEL_PMC_IDX_METRIC_BASE + 1) #define INTEL_PMC_IDX_TD_FE_BOUND (INTEL_PMC_IDX_METRIC_BASE + 2) #define INTEL_PMC_IDX_TD_BE_BOUND (INTEL_PMC_IDX_METRIC_BASE + 3) -#define INTEL_PMC_IDX_METRIC_END INTEL_PMC_IDX_TD_BE_BOUND -#define INTEL_PMC_MSK_TOPDOWN ((0xfull << INTEL_PMC_IDX_METRIC_BASE) | \ +#define INTEL_PMC_IDX_TD_HEAVY_OPS (INTEL_PMC_IDX_METRIC_BASE + 4) +#define INTEL_PMC_IDX_TD_BR_MISPREDICT (INTEL_PMC_IDX_METRIC_BASE + 5) +#define INTEL_PMC_IDX_TD_FETCH_LAT (INTEL_PMC_IDX_METRIC_BASE + 6) +#define INTEL_PMC_IDX_TD_MEM_BOUND (INTEL_PMC_IDX_METRIC_BASE + 7) +#define INTEL_PMC_IDX_METRIC_END INTEL_PMC_IDX_TD_MEM_BOUND +#define INTEL_PMC_MSK_TOPDOWN ((0xffull << INTEL_PMC_IDX_METRIC_BASE) | \ INTEL_PMC_MSK_FIXED_SLOTS) /* @@ -280,8 +284,14 @@ struct x86_pmu_capability { #define INTEL_TD_METRIC_BAD_SPEC 0x8100 /* Bad speculation metric */ #define INTEL_TD_METRIC_FE_BOUND 0x8200 /* FE bound metric */ #define INTEL_TD_METRIC_BE_BOUND 0x8300 /* BE bound metric */ -#define INTEL_TD_METRIC_MAX INTEL_TD_METRIC_BE_BOUND -#define INTEL_TD_METRIC_NUM 4 +/* Level 2 metrics */ +#define INTEL_TD_METRIC_HEAVY_OPS 0x8400 /* Heavy Operations metric */ +#define INTEL_TD_METRIC_BR_MISPREDICT 0x8500 /* Branch Mispredict metric */ +#define INTEL_TD_METRIC_FETCH_LAT 0x8600 /* Fetch Latency metric */ +#define INTEL_TD_METRIC_MEM_BOUND 0x8700 /* Memory bound metric */ + +#define INTEL_TD_METRIC_MAX INTEL_TD_METRIC_MEM_BOUND +#define INTEL_TD_METRIC_NUM 8 static inline bool is_metric_idx(int idx) { @@ -483,11 +493,7 @@ static inline void perf_check_microcode(void) { } extern struct perf_guest_switch_msr *perf_guest_get_msrs(int *nr); extern int x86_perf_get_lbr(struct x86_pmu_lbr *lbr); #else -static inline struct perf_guest_switch_msr *perf_guest_get_msrs(int *nr) -{ - *nr = 0; - return NULL; -} +struct perf_guest_switch_msr *perf_guest_get_msrs(int *nr); static inline int x86_perf_get_lbr(struct x86_pmu_lbr *lbr) { return -1; diff --git a/arch/x86/include/asm/pgtable_types.h b/arch/x86/include/asm/pgtable_types.h index 394757ee030a..f24d7ef8fffa 100644 --- a/arch/x86/include/asm/pgtable_types.h +++ b/arch/x86/include/asm/pgtable_types.h @@ -177,8 +177,6 @@ enum page_cache_mode { #define __pgprot(x) ((pgprot_t) { (x) } ) #define __pg(x) __pgprot(x) -#define _PAGE_PAT_LARGE (_AT(pteval_t, 1) << _PAGE_BIT_PAT_LARGE) - #define PAGE_NONE __pg( 0| 0| 0|___A| 0| 0| 0|___G) #define PAGE_SHARED __pg(__PP|__RW|_USR|___A|__NX| 0| 0| 0) #define PAGE_SHARED_EXEC __pg(__PP|__RW|_USR|___A| 0| 0| 0| 0) diff --git a/arch/x86/include/asm/platform_sst_audio.h b/arch/x86/include/asm/platform_sst_audio.h index 16b9f220bdeb..40f92270515b 100644 --- a/arch/x86/include/asm/platform_sst_audio.h +++ b/arch/x86/include/asm/platform_sst_audio.h @@ -10,8 +10,6 @@ #ifndef _PLATFORM_SST_AUDIO_H_ #define _PLATFORM_SST_AUDIO_H_ -#include <linux/sfi.h> - #define MAX_NUM_STREAMS_MRFLD 25 #define MAX_NUM_STREAMS MAX_NUM_STREAMS_MRFLD diff --git a/arch/x86/include/asm/preempt.h b/arch/x86/include/asm/preempt.h index 69485ca13665..f8cb8af4de5c 100644 --- a/arch/x86/include/asm/preempt.h +++ b/arch/x86/include/asm/preempt.h @@ -5,6 +5,7 @@ #include <asm/rmwcc.h> #include <asm/percpu.h> #include <linux/thread_info.h> +#include <linux/static_call_types.h> DECLARE_PER_CPU(int, __preempt_count); @@ -103,16 +104,45 @@ static __always_inline bool should_resched(int preempt_offset) } #ifdef CONFIG_PREEMPTION - extern asmlinkage void preempt_schedule_thunk(void); -# define __preempt_schedule() \ - asm volatile ("call preempt_schedule_thunk" : ASM_CALL_CONSTRAINT) - extern asmlinkage void preempt_schedule(void); - extern asmlinkage void preempt_schedule_notrace_thunk(void); -# define __preempt_schedule_notrace() \ - asm volatile ("call preempt_schedule_notrace_thunk" : ASM_CALL_CONSTRAINT) +extern asmlinkage void preempt_schedule(void); +extern asmlinkage void preempt_schedule_thunk(void); - extern asmlinkage void preempt_schedule_notrace(void); -#endif +#define __preempt_schedule_func preempt_schedule_thunk + +extern asmlinkage void preempt_schedule_notrace(void); +extern asmlinkage void preempt_schedule_notrace_thunk(void); + +#define __preempt_schedule_notrace_func preempt_schedule_notrace_thunk + +#ifdef CONFIG_PREEMPT_DYNAMIC + +DECLARE_STATIC_CALL(preempt_schedule, __preempt_schedule_func); + +#define __preempt_schedule() \ +do { \ + __STATIC_CALL_MOD_ADDRESSABLE(preempt_schedule); \ + asm volatile ("call " STATIC_CALL_TRAMP_STR(preempt_schedule) : ASM_CALL_CONSTRAINT); \ +} while (0) + +DECLARE_STATIC_CALL(preempt_schedule_notrace, __preempt_schedule_notrace_func); + +#define __preempt_schedule_notrace() \ +do { \ + __STATIC_CALL_MOD_ADDRESSABLE(preempt_schedule_notrace); \ + asm volatile ("call " STATIC_CALL_TRAMP_STR(preempt_schedule_notrace) : ASM_CALL_CONSTRAINT); \ +} while (0) + +#else /* PREEMPT_DYNAMIC */ + +#define __preempt_schedule() \ + asm volatile ("call preempt_schedule_thunk" : ASM_CALL_CONSTRAINT); + +#define __preempt_schedule_notrace() \ + asm volatile ("call preempt_schedule_notrace_thunk" : ASM_CALL_CONSTRAINT); + +#endif /* PREEMPT_DYNAMIC */ + +#endif /* PREEMPTION */ #endif /* __ASM_PREEMPT_H */ diff --git a/arch/x86/include/asm/processor.h b/arch/x86/include/asm/processor.h index c20a52b5534b..f1b9ed5efaa9 100644 --- a/arch/x86/include/asm/processor.h +++ b/arch/x86/include/asm/processor.h @@ -426,8 +426,6 @@ struct irq_stack { char stack[IRQ_STACK_SIZE]; } __aligned(IRQ_STACK_SIZE); -DECLARE_PER_CPU(struct irq_stack *, hardirq_stack_ptr); - #ifdef CONFIG_X86_32 DECLARE_PER_CPU(unsigned long, cpu_current_top_of_stack); #else @@ -454,7 +452,8 @@ static inline unsigned long cpu_kernelmode_gs_base(int cpu) return (unsigned long)per_cpu(fixed_percpu_data.gs_base, cpu); } -DECLARE_PER_CPU(unsigned int, irq_count); +DECLARE_PER_CPU(void *, hardirq_stack_ptr); +DECLARE_PER_CPU(bool, hardirq_stack_inuse); extern asmlinkage void ignore_sysret(void); /* Save actual FS/GS selectors and bases to current->thread */ @@ -473,9 +472,9 @@ struct stack_canary { }; DECLARE_PER_CPU_ALIGNED(struct stack_canary, stack_canary); #endif -/* Per CPU softirq stack pointer */ +DECLARE_PER_CPU(struct irq_stack *, hardirq_stack_ptr); DECLARE_PER_CPU(struct irq_stack *, softirq_stack_ptr); -#endif /* X86_64 */ +#endif /* !X86_64 */ extern unsigned int fpu_kernel_xstate_size; extern unsigned int fpu_user_xstate_size; @@ -552,15 +551,6 @@ static inline void arch_thread_struct_whitelist(unsigned long *offset, *size = fpu_kernel_xstate_size; } -/* - * Thread-synchronous status. - * - * This is different from the flags in that nobody else - * ever touches our thread-synchronous status, so we don't - * have to worry about atomic accesses. - */ -#define TS_COMPAT 0x0002 /* 32bit syscall active (64BIT)*/ - static inline void native_load_sp0(unsigned long sp0) { diff --git a/arch/x86/include/asm/proto.h b/arch/x86/include/asm/proto.h index 2c35f1c01a2d..b6a9d51d1d79 100644 --- a/arch/x86/include/asm/proto.h +++ b/arch/x86/include/asm/proto.h @@ -25,6 +25,7 @@ void __end_SYSENTER_singlestep_region(void); void entry_SYSENTER_compat(void); void __end_entry_SYSENTER_compat(void); void entry_SYSCALL_compat(void); +void entry_SYSCALL_compat_safe_stack(void); void entry_INT80_compat(void); #ifdef CONFIG_XEN_PV void xen_entry_INT80_compat(void); diff --git a/arch/x86/include/asm/ptrace.h b/arch/x86/include/asm/ptrace.h index d8324a236696..409f661481e1 100644 --- a/arch/x86/include/asm/ptrace.h +++ b/arch/x86/include/asm/ptrace.h @@ -94,6 +94,8 @@ struct pt_regs { #include <asm/paravirt_types.h> #endif +#include <asm/proto.h> + struct cpuinfo_x86; struct task_struct; @@ -175,6 +177,19 @@ static inline bool any_64bit_mode(struct pt_regs *regs) #ifdef CONFIG_X86_64 #define current_user_stack_pointer() current_pt_regs()->sp #define compat_user_stack_pointer() current_pt_regs()->sp + +static inline bool ip_within_syscall_gap(struct pt_regs *regs) +{ + bool ret = (regs->ip >= (unsigned long)entry_SYSCALL_64 && + regs->ip < (unsigned long)entry_SYSCALL_64_safe_stack); + +#ifdef CONFIG_IA32_EMULATION + ret = ret || (regs->ip >= (unsigned long)entry_SYSCALL_compat && + regs->ip < (unsigned long)entry_SYSCALL_compat_safe_stack); +#endif + + return ret; +} #endif static inline unsigned long kernel_stack_pointer(struct pt_regs *regs) diff --git a/arch/x86/include/asm/required-features.h b/arch/x86/include/asm/required-features.h index 3ff0d48469f2..b2d504f11937 100644 --- a/arch/x86/include/asm/required-features.h +++ b/arch/x86/include/asm/required-features.h @@ -101,6 +101,7 @@ #define REQUIRED_MASK16 0 #define REQUIRED_MASK17 0 #define REQUIRED_MASK18 0 -#define REQUIRED_MASK_CHECK BUILD_BUG_ON_ZERO(NCAPINTS != 19) +#define REQUIRED_MASK19 0 +#define REQUIRED_MASK_CHECK BUILD_BUG_ON_ZERO(NCAPINTS != 20) #endif /* _ASM_X86_REQUIRED_FEATURES_H */ diff --git a/arch/x86/include/asm/resctrl.h b/arch/x86/include/asm/resctrl.h index 07603064df8f..d60ed0668a59 100644 --- a/arch/x86/include/asm/resctrl.h +++ b/arch/x86/include/asm/resctrl.h @@ -56,19 +56,22 @@ static void __resctrl_sched_in(void) struct resctrl_pqr_state *state = this_cpu_ptr(&pqr_state); u32 closid = state->default_closid; u32 rmid = state->default_rmid; + u32 tmp; /* * If this task has a closid/rmid assigned, use it. * Else use the closid/rmid assigned to this cpu. */ if (static_branch_likely(&rdt_alloc_enable_key)) { - if (current->closid) - closid = current->closid; + tmp = READ_ONCE(current->closid); + if (tmp) + closid = tmp; } if (static_branch_likely(&rdt_mon_enable_key)) { - if (current->rmid) - rmid = current->rmid; + tmp = READ_ONCE(current->rmid); + if (tmp) + rmid = tmp; } if (closid != state->cur_closid || rmid != state->cur_rmid) { diff --git a/arch/x86/include/asm/smap.h b/arch/x86/include/asm/smap.h index 8b58d6975d5d..0bc9b0895f33 100644 --- a/arch/x86/include/asm/smap.h +++ b/arch/x86/include/asm/smap.h @@ -58,9 +58,8 @@ static __always_inline unsigned long smap_save(void) unsigned long flags; asm volatile ("# smap_save\n\t" - ALTERNATIVE("jmp 1f", "", X86_FEATURE_SMAP) - "pushf; pop %0; " __ASM_CLAC "\n\t" - "1:" + ALTERNATIVE("", "pushf; pop %0; " __ASM_CLAC "\n\t", + X86_FEATURE_SMAP) : "=rm" (flags) : : "memory", "cc"); return flags; @@ -69,9 +68,8 @@ static __always_inline unsigned long smap_save(void) static __always_inline void smap_restore(unsigned long flags) { asm volatile ("# smap_restore\n\t" - ALTERNATIVE("jmp 1f", "", X86_FEATURE_SMAP) - "push %0; popf\n\t" - "1:" + ALTERNATIVE("", "push %0; popf\n\t", + X86_FEATURE_SMAP) : : "g" (flags) : "memory", "cc"); } diff --git a/arch/x86/include/asm/softirq_stack.h b/arch/x86/include/asm/softirq_stack.h new file mode 100644 index 000000000000..889d53d6a0e1 --- /dev/null +++ b/arch/x86/include/asm/softirq_stack.h @@ -0,0 +1,11 @@ +/* SPDX-License-Identifier: GPL-2.0 */ +#ifndef _ASM_X86_SOFTIRQ_STACK_H +#define _ASM_X86_SOFTIRQ_STACK_H + +#ifdef CONFIG_X86_64 +# include <asm/irq_stack.h> +#else +# include <asm-generic/softirq_stack.h> +#endif + +#endif diff --git a/arch/x86/include/asm/special_insns.h b/arch/x86/include/asm/special_insns.h index cc177b4431ae..1d3cbaef4bb7 100644 --- a/arch/x86/include/asm/special_insns.h +++ b/arch/x86/include/asm/special_insns.h @@ -243,10 +243,10 @@ static inline void serialize(void) } /* The dst parameter must be 64-bytes aligned */ -static inline void movdir64b(void *dst, const void *src) +static inline void movdir64b(void __iomem *dst, const void *src) { const struct { char _[64]; } *__src = src; - struct { char _[64]; } *__dst = dst; + struct { char _[64]; } __iomem *__dst = dst; /* * MOVDIR64B %(rdx), rax. @@ -286,7 +286,7 @@ static inline void movdir64b(void *dst, const void *src) static inline int enqcmds(void __iomem *dst, const void *src) { const struct { char _[64]; } *__src = src; - struct { char _[64]; } *__dst = dst; + struct { char _[64]; } __iomem *__dst = dst; int zf; /* diff --git a/arch/x86/include/asm/static_call.h b/arch/x86/include/asm/static_call.h index c37f11999d0c..cbb67b6030f9 100644 --- a/arch/x86/include/asm/static_call.h +++ b/arch/x86/include/asm/static_call.h @@ -37,4 +37,11 @@ #define ARCH_DEFINE_STATIC_CALL_NULL_TRAMP(name) \ __ARCH_DEFINE_STATIC_CALL_TRAMP(name, "ret; nop; nop; nop; nop") + +#define ARCH_ADD_TRAMP_KEY(name) \ + asm(".pushsection .static_call_tramp_key, \"a\" \n" \ + ".long " STATIC_CALL_TRAMP_STR(name) " - . \n" \ + ".long " STATIC_CALL_KEY_STR(name) " - . \n" \ + ".popsection \n") + #endif /* _ASM_STATIC_CALL_H */ diff --git a/arch/x86/include/asm/thermal.h b/arch/x86/include/asm/thermal.h new file mode 100644 index 000000000000..ddbdefd5b94f --- /dev/null +++ b/arch/x86/include/asm/thermal.h @@ -0,0 +1,13 @@ +/* SPDX-License-Identifier: GPL-2.0 */ +#ifndef _ASM_X86_THERMAL_H +#define _ASM_X86_THERMAL_H + +#ifdef CONFIG_X86_THERMAL_VECTOR +void intel_init_thermal(struct cpuinfo_x86 *c); +bool x86_thermal_enabled(void); +void intel_thermal_interrupt(void); +#else +static inline void intel_init_thermal(struct cpuinfo_x86 *c) { } +#endif + +#endif /* _ASM_X86_THERMAL_H */ diff --git a/arch/x86/include/asm/thread_info.h b/arch/x86/include/asm/thread_info.h index 0d751d5da702..06b740bae431 100644 --- a/arch/x86/include/asm/thread_info.h +++ b/arch/x86/include/asm/thread_info.h @@ -205,10 +205,23 @@ static inline int arch_within_stack_frames(const void * const stack, #endif +/* + * Thread-synchronous status. + * + * This is different from the flags in that nobody else + * ever touches our thread-synchronous status, so we don't + * have to worry about atomic accesses. + */ +#define TS_COMPAT 0x0002 /* 32bit syscall active (64BIT)*/ + +#ifndef __ASSEMBLY__ #ifdef CONFIG_COMPAT #define TS_I386_REGS_POKED 0x0004 /* regs poked by 32-bit ptracer */ + +#define arch_set_restart_data(restart) \ + do { restart->arch_data = current_thread_info()->status; } while (0) + #endif -#ifndef __ASSEMBLY__ #ifdef CONFIG_X86_32 #define in_ia32_syscall() true diff --git a/arch/x86/include/asm/tlb.h b/arch/x86/include/asm/tlb.h index 820082bd6880..1bfe979bb9bc 100644 --- a/arch/x86/include/asm/tlb.h +++ b/arch/x86/include/asm/tlb.h @@ -4,7 +4,6 @@ #define tlb_start_vma(tlb, vma) do { } while (0) #define tlb_end_vma(tlb, vma) do { } while (0) -#define __tlb_remove_tlb_entry(tlb, ptep, address) do { } while (0) #define tlb_flush tlb_flush static inline void tlb_flush(struct mmu_gather *tlb); diff --git a/arch/x86/include/asm/unwind_hints.h b/arch/x86/include/asm/unwind_hints.h index 664d4610d700..8e574c0afef8 100644 --- a/arch/x86/include/asm/unwind_hints.h +++ b/arch/x86/include/asm/unwind_hints.h @@ -48,17 +48,8 @@ UNWIND_HINT_REGS base=\base offset=\offset partial=1 .endm -.macro UNWIND_HINT_FUNC sp_offset=8 - UNWIND_HINT sp_reg=ORC_REG_SP sp_offset=\sp_offset type=UNWIND_HINT_TYPE_CALL -.endm - -/* - * RET_OFFSET: Used on instructions that terminate a function; mostly RETURN - * and sibling calls. On these, sp_offset denotes the expected offset from - * initial_func_cfi. - */ -.macro UNWIND_HINT_RET_OFFSET sp_offset=8 - UNWIND_HINT sp_reg=ORC_REG_SP type=UNWIND_HINT_TYPE_RET_OFFSET sp_offset=\sp_offset +.macro UNWIND_HINT_FUNC + UNWIND_HINT sp_reg=ORC_REG_SP sp_offset=8 type=UNWIND_HINT_TYPE_FUNC .endm #endif /* __ASSEMBLY__ */ diff --git a/arch/x86/include/asm/virtext.h b/arch/x86/include/asm/virtext.h index 9aad0e0876fb..8757078d4442 100644 --- a/arch/x86/include/asm/virtext.h +++ b/arch/x86/include/asm/virtext.h @@ -30,16 +30,29 @@ static inline int cpu_has_vmx(void) } -/** Disable VMX on the current CPU +/** + * cpu_vmxoff() - Disable VMX on the current CPU * - * vmxoff causes a undefined-opcode exception if vmxon was not run - * on the CPU previously. Only call this function if you know VMX - * is enabled. + * Disable VMX and clear CR4.VMXE (even if VMXOFF faults) + * + * Note, VMXOFF causes a #UD if the CPU is !post-VMXON, but it's impossible to + * atomically track post-VMXON state, e.g. this may be called in NMI context. + * Eat all faults as all other faults on VMXOFF faults are mode related, i.e. + * faults are guaranteed to be due to the !post-VMXON check unless the CPU is + * magically in RM, VM86, compat mode, or at CPL>0. */ -static inline void cpu_vmxoff(void) +static inline int cpu_vmxoff(void) { - asm volatile ("vmxoff"); + asm_volatile_goto("1: vmxoff\n\t" + _ASM_EXTABLE(1b, %l[fault]) + ::: "cc", "memory" : fault); + + cr4_clear_bits(X86_CR4_VMXE); + return 0; + +fault: cr4_clear_bits(X86_CR4_VMXE); + return -EIO; } static inline int cpu_vmx_enabled(void) diff --git a/arch/x86/include/asm/vm86.h b/arch/x86/include/asm/vm86.h index 26efbec94448..9e8ac5073ecb 100644 --- a/arch/x86/include/asm/vm86.h +++ b/arch/x86/include/asm/vm86.h @@ -36,7 +36,6 @@ struct vm86 { unsigned long saved_sp0; unsigned long flags; - unsigned long screen_bitmap; unsigned long cpu_type; struct revectored_struct int_revectored; struct revectored_struct int21_revectored; diff --git a/arch/x86/include/asm/vmx.h b/arch/x86/include/asm/vmx.h index 38ca445a8429..358707f60d99 100644 --- a/arch/x86/include/asm/vmx.h +++ b/arch/x86/include/asm/vmx.h @@ -73,6 +73,7 @@ #define SECONDARY_EXEC_PT_USE_GPA VMCS_CONTROL_BIT(PT_USE_GPA) #define SECONDARY_EXEC_TSC_SCALING VMCS_CONTROL_BIT(TSC_SCALING) #define SECONDARY_EXEC_ENABLE_USR_WAIT_PAUSE VMCS_CONTROL_BIT(USR_WAIT_PAUSE) +#define SECONDARY_EXEC_BUS_LOCK_DETECTION VMCS_CONTROL_BIT(BUS_LOCK_DETECTION) #define PIN_BASED_EXT_INTR_MASK VMCS_CONTROL_BIT(INTR_EXITING) #define PIN_BASED_NMI_EXITING VMCS_CONTROL_BIT(NMI_EXITING) diff --git a/arch/x86/include/asm/vmxfeatures.h b/arch/x86/include/asm/vmxfeatures.h index 9915990fd8cf..d9a74681a77d 100644 --- a/arch/x86/include/asm/vmxfeatures.h +++ b/arch/x86/include/asm/vmxfeatures.h @@ -83,5 +83,6 @@ #define VMX_FEATURE_TSC_SCALING ( 2*32+ 25) /* Scale hardware TSC when read in guest */ #define VMX_FEATURE_USR_WAIT_PAUSE ( 2*32+ 26) /* Enable TPAUSE, UMONITOR, UMWAIT in guest */ #define VMX_FEATURE_ENCLV_EXITING ( 2*32+ 28) /* "" VM-Exit on ENCLV (leaf dependent) */ +#define VMX_FEATURE_BUS_LOCK_DETECTION ( 2*32+ 30) /* "" VM-Exit when bus lock caused */ #endif /* _ASM_X86_VMXFEATURES_H */ diff --git a/arch/x86/include/asm/xen/interface.h b/arch/x86/include/asm/xen/interface.h index 9139b3e86316..baca0b00ef76 100644 --- a/arch/x86/include/asm/xen/interface.h +++ b/arch/x86/include/asm/xen/interface.h @@ -182,6 +182,9 @@ struct arch_shared_info { unsigned long p2m_cr3; /* cr3 value of the p2m address space */ unsigned long p2m_vaddr; /* virtual address of the p2m list */ unsigned long p2m_generation; /* generation count of p2m mapping */ +#ifdef CONFIG_X86_32 + uint32_t wc_sec_hi; +#endif }; #endif /* !__ASSEMBLY__ */ diff --git a/arch/x86/include/asm/xen/page.h b/arch/x86/include/asm/xen/page.h index 1a162e559753..7068e4bb057d 100644 --- a/arch/x86/include/asm/xen/page.h +++ b/arch/x86/include/asm/xen/page.h @@ -87,6 +87,18 @@ clear_foreign_p2m_mapping(struct gnttab_unmap_grant_ref *unmap_ops, #endif /* + * The maximum amount of extra memory compared to the base size. The + * main scaling factor is the size of struct page. At extreme ratios + * of base:extra, all the base memory can be filled with page + * structures for the extra memory, leaving no space for anything + * else. + * + * 10x seems like a reasonable balance between scaling flexibility and + * leaving a practically usable system. + */ +#define XEN_EXTRA_MEM_RATIO (10) + +/* * Helper functions to write or read unsigned long values to/from * memory, when the access may fault. */ diff --git a/arch/x86/include/uapi/asm/kvm.h b/arch/x86/include/uapi/asm/kvm.h index 8e76d3701db3..5a3022c8af82 100644 --- a/arch/x86/include/uapi/asm/kvm.h +++ b/arch/x86/include/uapi/asm/kvm.h @@ -112,6 +112,7 @@ struct kvm_ioapic_state { #define KVM_NR_IRQCHIPS 3 #define KVM_RUN_X86_SMM (1 << 0) +#define KVM_RUN_X86_BUS_LOCK (1 << 1) /* for KVM_GET_REGS and KVM_SET_REGS */ struct kvm_regs { diff --git a/arch/x86/include/uapi/asm/vm86.h b/arch/x86/include/uapi/asm/vm86.h index d2ee4e307ef8..18909b8050bc 100644 --- a/arch/x86/include/uapi/asm/vm86.h +++ b/arch/x86/include/uapi/asm/vm86.h @@ -97,7 +97,7 @@ struct revectored_struct { struct vm86_struct { struct vm86_regs regs; unsigned long flags; - unsigned long screen_bitmap; + unsigned long screen_bitmap; /* unused, preserved by vm86() */ unsigned long cpu_type; struct revectored_struct int_revectored; struct revectored_struct int21_revectored; @@ -106,7 +106,7 @@ struct vm86_struct { /* * flags masks */ -#define VM86_SCREEN_BITMAP 0x0001 +#define VM86_SCREEN_BITMAP 0x0001 /* no longer supported */ struct vm86plus_info_struct { unsigned long force_return_for_pic:1; diff --git a/arch/x86/include/uapi/asm/vmx.h b/arch/x86/include/uapi/asm/vmx.h index ada955c5ebb6..b8e650a985e3 100644 --- a/arch/x86/include/uapi/asm/vmx.h +++ b/arch/x86/include/uapi/asm/vmx.h @@ -89,6 +89,7 @@ #define EXIT_REASON_XRSTORS 64 #define EXIT_REASON_UMWAIT 67 #define EXIT_REASON_TPAUSE 68 +#define EXIT_REASON_BUS_LOCK 74 #define VMX_EXIT_REASONS \ { EXIT_REASON_EXCEPTION_NMI, "EXCEPTION_NMI" }, \ @@ -150,7 +151,8 @@ { EXIT_REASON_XSAVES, "XSAVES" }, \ { EXIT_REASON_XRSTORS, "XRSTORS" }, \ { EXIT_REASON_UMWAIT, "UMWAIT" }, \ - { EXIT_REASON_TPAUSE, "TPAUSE" } + { EXIT_REASON_TPAUSE, "TPAUSE" }, \ + { EXIT_REASON_BUS_LOCK, "BUS_LOCK" } #define VMX_EXIT_REASON_FLAGS \ { VMX_EXIT_REASONS_FAILED_VMENTRY, "FAILED_VMENTRY" } diff --git a/arch/x86/kernel/Makefile b/arch/x86/kernel/Makefile index 5eeb808eb024..2ddf08351f0b 100644 --- a/arch/x86/kernel/Makefile +++ b/arch/x86/kernel/Makefile @@ -116,7 +116,6 @@ obj-$(CONFIG_VM86) += vm86_32.o obj-$(CONFIG_EARLY_PRINTK) += early_printk.o obj-$(CONFIG_HPET_TIMER) += hpet.o -obj-$(CONFIG_APB_TIMER) += apb_timer.o obj-$(CONFIG_AMD_NB) += amd_nb.o obj-$(CONFIG_DEBUG_NMI_SELFTEST) += nmi_selftest.o diff --git a/arch/x86/kernel/acpi/Makefile b/arch/x86/kernel/acpi/Makefile index f1bb57b0e41e..cf340d85946a 100644 --- a/arch/x86/kernel/acpi/Makefile +++ b/arch/x86/kernel/acpi/Makefile @@ -1,5 +1,4 @@ # SPDX-License-Identifier: GPL-2.0 -OBJECT_FILES_NON_STANDARD_wakeup_$(BITS).o := y obj-$(CONFIG_ACPI) += boot.o obj-$(CONFIG_ACPI_SLEEP) += sleep.o wakeup_$(BITS).o diff --git a/arch/x86/kernel/acpi/wakeup_64.S b/arch/x86/kernel/acpi/wakeup_64.S index 5d3a0b8fd379..56b6865afb2a 100644 --- a/arch/x86/kernel/acpi/wakeup_64.S +++ b/arch/x86/kernel/acpi/wakeup_64.S @@ -1,12 +1,14 @@ /* SPDX-License-Identifier: GPL-2.0-only */ .text #include <linux/linkage.h> +#include <linux/objtool.h> #include <asm/segment.h> #include <asm/pgtable_types.h> #include <asm/page_types.h> #include <asm/msr.h> #include <asm/asm-offsets.h> #include <asm/frame.h> +#include <asm/nospec-branch.h> # Copyright 2003 Pavel Machek <pavel@suse.cz @@ -39,6 +41,7 @@ SYM_FUNC_START(wakeup_long64) movq saved_rbp, %rbp movq saved_rip, %rax + ANNOTATE_RETPOLINE_SAFE jmp *%rax SYM_FUNC_END(wakeup_long64) @@ -126,6 +129,7 @@ SYM_FUNC_START(do_suspend_lowlevel) FRAME_END jmp restore_processor_state SYM_FUNC_END(do_suspend_lowlevel) +STACK_FRAME_NON_STANDARD do_suspend_lowlevel .data saved_rbp: .quad 0 diff --git a/arch/x86/kernel/apb_timer.c b/arch/x86/kernel/apb_timer.c deleted file mode 100644 index 263eeaddb0aa..000000000000 --- a/arch/x86/kernel/apb_timer.c +++ /dev/null @@ -1,347 +0,0 @@ -// SPDX-License-Identifier: GPL-2.0-only -/* - * apb_timer.c: Driver for Langwell APB timers - * - * (C) Copyright 2009 Intel Corporation - * Author: Jacob Pan (jacob.jun.pan@intel.com) - * - * Note: - * Langwell is the south complex of Intel Moorestown MID platform. There are - * eight external timers in total that can be used by the operating system. - * The timer information, such as frequency and addresses, is provided to the - * OS via SFI tables. - * Timer interrupts are routed via FW/HW emulated IOAPIC independently via - * individual redirection table entries (RTE). - * Unlike HPET, there is no master counter, therefore one of the timers are - * used as clocksource. The overall allocation looks like: - * - timer 0 - NR_CPUs for per cpu timer - * - one timer for clocksource - * - one timer for watchdog driver. - * It is also worth notice that APB timer does not support true one-shot mode, - * free-running mode will be used here to emulate one-shot mode. - * APB timer can also be used as broadcast timer along with per cpu local APIC - * timer, but by default APB timer has higher rating than local APIC timers. - */ - -#include <linux/delay.h> -#include <linux/dw_apb_timer.h> -#include <linux/errno.h> -#include <linux/init.h> -#include <linux/slab.h> -#include <linux/pm.h> -#include <linux/sfi.h> -#include <linux/interrupt.h> -#include <linux/cpu.h> -#include <linux/irq.h> - -#include <asm/fixmap.h> -#include <asm/apb_timer.h> -#include <asm/intel-mid.h> -#include <asm/time.h> - -#define APBT_CLOCKEVENT_RATING 110 -#define APBT_CLOCKSOURCE_RATING 250 - -#define APBT_CLOCKEVENT0_NUM (0) -#define APBT_CLOCKSOURCE_NUM (2) - -static phys_addr_t apbt_address; -static int apb_timer_block_enabled; -static void __iomem *apbt_virt_address; - -/* - * Common DW APB timer info - */ -static unsigned long apbt_freq; - -struct apbt_dev { - struct dw_apb_clock_event_device *timer; - unsigned int num; - int cpu; - unsigned int irq; - char name[10]; -}; - -static struct dw_apb_clocksource *clocksource_apbt; - -static inline void __iomem *adev_virt_addr(struct apbt_dev *adev) -{ - return apbt_virt_address + adev->num * APBTMRS_REG_SIZE; -} - -static DEFINE_PER_CPU(struct apbt_dev, cpu_apbt_dev); - -#ifdef CONFIG_SMP -static unsigned int apbt_num_timers_used; -#endif - -static inline void apbt_set_mapping(void) -{ - struct sfi_timer_table_entry *mtmr; - int phy_cs_timer_id = 0; - - if (apbt_virt_address) { - pr_debug("APBT base already mapped\n"); - return; - } - mtmr = sfi_get_mtmr(APBT_CLOCKEVENT0_NUM); - if (mtmr == NULL) { - printk(KERN_ERR "Failed to get MTMR %d from SFI\n", - APBT_CLOCKEVENT0_NUM); - return; - } - apbt_address = (phys_addr_t)mtmr->phys_addr; - if (!apbt_address) { - printk(KERN_WARNING "No timer base from SFI, use default\n"); - apbt_address = APBT_DEFAULT_BASE; - } - apbt_virt_address = ioremap(apbt_address, APBT_MMAP_SIZE); - if (!apbt_virt_address) { - pr_debug("Failed mapping APBT phy address at %lu\n",\ - (unsigned long)apbt_address); - goto panic_noapbt; - } - apbt_freq = mtmr->freq_hz; - sfi_free_mtmr(mtmr); - - /* Now figure out the physical timer id for clocksource device */ - mtmr = sfi_get_mtmr(APBT_CLOCKSOURCE_NUM); - if (mtmr == NULL) - goto panic_noapbt; - - /* Now figure out the physical timer id */ - pr_debug("Use timer %d for clocksource\n", - (int)(mtmr->phys_addr & 0xff) / APBTMRS_REG_SIZE); - phy_cs_timer_id = (unsigned int)(mtmr->phys_addr & 0xff) / - APBTMRS_REG_SIZE; - - clocksource_apbt = dw_apb_clocksource_init(APBT_CLOCKSOURCE_RATING, - "apbt0", apbt_virt_address + phy_cs_timer_id * - APBTMRS_REG_SIZE, apbt_freq); - return; - -panic_noapbt: - panic("Failed to setup APB system timer\n"); - -} - -static inline void apbt_clear_mapping(void) -{ - iounmap(apbt_virt_address); - apbt_virt_address = NULL; -} - -static int __init apbt_clockevent_register(void) -{ - struct sfi_timer_table_entry *mtmr; - struct apbt_dev *adev = this_cpu_ptr(&cpu_apbt_dev); - - mtmr = sfi_get_mtmr(APBT_CLOCKEVENT0_NUM); - if (mtmr == NULL) { - printk(KERN_ERR "Failed to get MTMR %d from SFI\n", - APBT_CLOCKEVENT0_NUM); - return -ENODEV; - } - - adev->num = smp_processor_id(); - adev->timer = dw_apb_clockevent_init(smp_processor_id(), "apbt0", - intel_mid_timer_options == INTEL_MID_TIMER_LAPIC_APBT ? - APBT_CLOCKEVENT_RATING - 100 : APBT_CLOCKEVENT_RATING, - adev_virt_addr(adev), 0, apbt_freq); - /* Firmware does EOI handling for us. */ - adev->timer->eoi = NULL; - - if (intel_mid_timer_options == INTEL_MID_TIMER_LAPIC_APBT) { - global_clock_event = &adev->timer->ced; - printk(KERN_DEBUG "%s clockevent registered as global\n", - global_clock_event->name); - } - - dw_apb_clockevent_register(adev->timer); - - sfi_free_mtmr(mtmr); - return 0; -} - -#ifdef CONFIG_SMP - -static void apbt_setup_irq(struct apbt_dev *adev) -{ - irq_modify_status(adev->irq, 0, IRQ_MOVE_PCNTXT); - irq_set_affinity(adev->irq, cpumask_of(adev->cpu)); -} - -/* Should be called with per cpu */ -void apbt_setup_secondary_clock(void) -{ - struct apbt_dev *adev; - int cpu; - - /* Don't register boot CPU clockevent */ - cpu = smp_processor_id(); - if (!cpu) - return; - - adev = this_cpu_ptr(&cpu_apbt_dev); - if (!adev->timer) { - adev->timer = dw_apb_clockevent_init(cpu, adev->name, - APBT_CLOCKEVENT_RATING, adev_virt_addr(adev), - adev->irq, apbt_freq); - adev->timer->eoi = NULL; - } else { - dw_apb_clockevent_resume(adev->timer); - } - - printk(KERN_INFO "Registering CPU %d clockevent device %s, cpu %08x\n", - cpu, adev->name, adev->cpu); - - apbt_setup_irq(adev); - dw_apb_clockevent_register(adev->timer); - - return; -} - -/* - * this notify handler process CPU hotplug events. in case of S0i3, nonboot - * cpus are disabled/enabled frequently, for performance reasons, we keep the - * per cpu timer irq registered so that we do need to do free_irq/request_irq. - * - * TODO: it might be more reliable to directly disable percpu clockevent device - * without the notifier chain. currently, cpu 0 may get interrupts from other - * cpu timers during the offline process due to the ordering of notification. - * the extra interrupt is harmless. - */ -static int apbt_cpu_dead(unsigned int cpu) -{ - struct apbt_dev *adev = &per_cpu(cpu_apbt_dev, cpu); - - dw_apb_clockevent_pause(adev->timer); - if (system_state == SYSTEM_RUNNING) { - pr_debug("skipping APBT CPU %u offline\n", cpu); - } else { - pr_debug("APBT clockevent for cpu %u offline\n", cpu); - dw_apb_clockevent_stop(adev->timer); - } - return 0; -} - -static __init int apbt_late_init(void) -{ - if (intel_mid_timer_options == INTEL_MID_TIMER_LAPIC_APBT || - !apb_timer_block_enabled) - return 0; - return cpuhp_setup_state(CPUHP_X86_APB_DEAD, "x86/apb:dead", NULL, - apbt_cpu_dead); -} -fs_initcall(apbt_late_init); -#else - -void apbt_setup_secondary_clock(void) {} - -#endif /* CONFIG_SMP */ - -static int apbt_clocksource_register(void) -{ - u64 start, now; - u64 t1; - - /* Start the counter, use timer 2 as source, timer 0/1 for event */ - dw_apb_clocksource_start(clocksource_apbt); - - /* Verify whether apbt counter works */ - t1 = dw_apb_clocksource_read(clocksource_apbt); - start = rdtsc(); - - /* - * We don't know the TSC frequency yet, but waiting for - * 200000 TSC cycles is safe: - * 4 GHz == 50us - * 1 GHz == 200us - */ - do { - rep_nop(); - now = rdtsc(); - } while ((now - start) < 200000UL); - - /* APBT is the only always on clocksource, it has to work! */ - if (t1 == dw_apb_clocksource_read(clocksource_apbt)) - panic("APBT counter not counting. APBT disabled\n"); - - dw_apb_clocksource_register(clocksource_apbt); - - return 0; -} - -/* - * Early setup the APBT timer, only use timer 0 for booting then switch to - * per CPU timer if possible. - * returns 1 if per cpu apbt is setup - * returns 0 if no per cpu apbt is chosen - * panic if set up failed, this is the only platform timer on Moorestown. - */ -void __init apbt_time_init(void) -{ -#ifdef CONFIG_SMP - int i; - struct sfi_timer_table_entry *p_mtmr; - struct apbt_dev *adev; -#endif - - if (apb_timer_block_enabled) - return; - apbt_set_mapping(); - if (!apbt_virt_address) - goto out_noapbt; - /* - * Read the frequency and check for a sane value, for ESL model - * we extend the possible clock range to allow time scaling. - */ - - if (apbt_freq < APBT_MIN_FREQ || apbt_freq > APBT_MAX_FREQ) { - pr_debug("APBT has invalid freq 0x%lx\n", apbt_freq); - goto out_noapbt; - } - if (apbt_clocksource_register()) { - pr_debug("APBT has failed to register clocksource\n"); - goto out_noapbt; - } - if (!apbt_clockevent_register()) - apb_timer_block_enabled = 1; - else { - pr_debug("APBT has failed to register clockevent\n"); - goto out_noapbt; - } -#ifdef CONFIG_SMP - /* kernel cmdline disable apb timer, so we will use lapic timers */ - if (intel_mid_timer_options == INTEL_MID_TIMER_LAPIC_APBT) { - printk(KERN_INFO "apbt: disabled per cpu timer\n"); - return; - } - pr_debug("%s: %d CPUs online\n", __func__, num_online_cpus()); - if (num_possible_cpus() <= sfi_mtimer_num) - apbt_num_timers_used = num_possible_cpus(); - else - apbt_num_timers_used = 1; - pr_debug("%s: %d APB timers used\n", __func__, apbt_num_timers_used); - - /* here we set up per CPU timer data structure */ - for (i = 0; i < apbt_num_timers_used; i++) { - adev = &per_cpu(cpu_apbt_dev, i); - adev->num = i; - adev->cpu = i; - p_mtmr = sfi_get_mtmr(i); - if (p_mtmr) - adev->irq = p_mtmr->irq; - else - printk(KERN_ERR "Failed to get timer for cpu %d\n", i); - snprintf(adev->name, sizeof(adev->name) - 1, "apbt%d", i); - } -#endif - - return; - -out_noapbt: - apbt_clear_mapping(); - apb_timer_block_enabled = 0; - panic("failed to enable APB timer\n"); -} diff --git a/arch/x86/kernel/apic/apic.c b/arch/x86/kernel/apic/apic.c index 7f4c081f59f0..4f26700f314d 100644 --- a/arch/x86/kernel/apic/apic.c +++ b/arch/x86/kernel/apic/apic.c @@ -1747,6 +1747,7 @@ void apic_ap_setup(void) #ifdef CONFIG_X86_X2APIC int x2apic_mode; +EXPORT_SYMBOL_GPL(x2apic_mode); enum { X2APIC_OFF, @@ -2137,18 +2138,11 @@ void __init register_lapic_address(unsigned long address) * Local APIC interrupts */ -/** - * spurious_interrupt - Catch all for interrupts raised on unused vectors - * @regs: Pointer to pt_regs on stack - * @vector: The vector number - * - * This is invoked from ASM entry code to catch all interrupts which - * trigger on an entry which is routed to the common_spurious idtentry - * point. - * - * Also called from sysvec_spurious_apic_interrupt(). +/* + * Common handling code for spurious_interrupt and spurious_vector entry + * points below. No point in allowing the compiler to inline it twice. */ -DEFINE_IDTENTRY_IRQ(spurious_interrupt) +static noinline void handle_spurious_interrupt(u8 vector) { u32 v; @@ -2183,9 +2177,23 @@ out: trace_spurious_apic_exit(vector); } +/** + * spurious_interrupt - Catch all for interrupts raised on unused vectors + * @regs: Pointer to pt_regs on stack + * @vector: The vector number + * + * This is invoked from ASM entry code to catch all interrupts which + * trigger on an entry which is routed to the common_spurious idtentry + * point. + */ +DEFINE_IDTENTRY_IRQ(spurious_interrupt) +{ + handle_spurious_interrupt(vector); +} + DEFINE_IDTENTRY_SYSVEC(sysvec_spurious_apic_interrupt) { - __spurious_interrupt(regs, SPURIOUS_APIC_VECTOR); + handle_spurious_interrupt(SPURIOUS_APIC_VECTOR); } /* @@ -2334,6 +2342,11 @@ static int cpuid_to_apicid[] = { [0 ... NR_CPUS - 1] = -1, }; +bool arch_match_cpu_phys_id(int cpu, u64 phys_id) +{ + return phys_id == cpuid_to_apicid[cpu]; +} + #ifdef CONFIG_SMP /** * apic_id_is_primary_thread - Check whether APIC ID belongs to a primary thread diff --git a/arch/x86/kernel/apic/io_apic.c b/arch/x86/kernel/apic/io_apic.c index e4ab4804b20d..73ff4dd426a8 100644 --- a/arch/x86/kernel/apic/io_apic.c +++ b/arch/x86/kernel/apic/io_apic.c @@ -198,7 +198,7 @@ static int __init parse_noapic(char *str) } early_param("noapic", parse_noapic); -/* Will be called in mpparse/acpi/sfi codes for saving IRQ info */ +/* Will be called in mpparse/ACPI codes for saving IRQ info */ void mp_save_irq(struct mpc_intsrc *m) { int i; @@ -1032,6 +1032,16 @@ static int mp_map_pin_to_irq(u32 gsi, int idx, int ioapic, int pin, if (idx >= 0 && test_bit(mp_irqs[idx].srcbus, mp_bus_not_pci)) { irq = mp_irqs[idx].srcbusirq; legacy = mp_is_legacy_irq(irq); + /* + * IRQ2 is unusable for historical reasons on systems which + * have a legacy PIC. See the comment vs. IRQ2 further down. + * + * If this gets removed at some point then the related code + * in lapic_assign_system_vectors() needs to be adjusted as + * well. + */ + if (legacy && irq == PIC_CASCADE_IR) + return -EINVAL; } mutex_lock(&ioapic_mutex); @@ -2863,7 +2873,7 @@ int mp_register_ioapic(int id, u32 address, u32 gsi_base, /* * If mp_register_ioapic() is called during early boot stage when - * walking ACPI/SFI/DT tables, it's too early to create irqdomain, + * walking ACPI/DT tables, it's too early to create irqdomain, * we are still using bootmem allocator. So delay it to setup_IO_APIC(). */ if (hotplug) { diff --git a/arch/x86/kernel/asm-offsets_64.c b/arch/x86/kernel/asm-offsets_64.c index 828be792231e..b14533af7676 100644 --- a/arch/x86/kernel/asm-offsets_64.c +++ b/arch/x86/kernel/asm-offsets_64.c @@ -13,9 +13,6 @@ int main(void) { #ifdef CONFIG_PARAVIRT #ifdef CONFIG_PARAVIRT_XXL - OFFSET(PV_CPU_usergs_sysret64, paravirt_patch_template, - cpu.usergs_sysret64); - OFFSET(PV_CPU_swapgs, paravirt_patch_template, cpu.swapgs); #ifdef CONFIG_DEBUG_ENTRY OFFSET(PV_IRQ_save_fl, paravirt_patch_template, irq.save_fl); #endif diff --git a/arch/x86/kernel/cpu/acrn.c b/arch/x86/kernel/cpu/acrn.c index 0b2c03943ac6..23f5f27b5a02 100644 --- a/arch/x86/kernel/cpu/acrn.c +++ b/arch/x86/kernel/cpu/acrn.c @@ -10,6 +10,8 @@ */ #include <linux/interrupt.h> + +#include <asm/acrn.h> #include <asm/apic.h> #include <asm/cpufeatures.h> #include <asm/desc.h> @@ -19,7 +21,7 @@ static u32 __init acrn_detect(void) { - return hypervisor_cpuid_base("ACRNACRNACRN", 0); + return acrn_cpuid_base(); } static void __init acrn_init_platform(void) @@ -55,6 +57,18 @@ DEFINE_IDTENTRY_SYSVEC(sysvec_acrn_hv_callback) set_irq_regs(old_regs); } +void acrn_setup_intr_handler(void (*handler)(void)) +{ + acrn_intr_handler = handler; +} +EXPORT_SYMBOL_GPL(acrn_setup_intr_handler); + +void acrn_remove_intr_handler(void) +{ + acrn_intr_handler = NULL; +} +EXPORT_SYMBOL_GPL(acrn_remove_intr_handler); + const __initconst struct hypervisor_x86 x86_hyper_acrn = { .name = "ACRN", .detect = acrn_detect, diff --git a/arch/x86/kernel/cpu/common.c b/arch/x86/kernel/cpu/common.c index 35ad8480c464..ab640abe26b6 100644 --- a/arch/x86/kernel/cpu/common.c +++ b/arch/x86/kernel/cpu/common.c @@ -960,6 +960,9 @@ void get_cpu_cap(struct cpuinfo_x86 *c) if (c->extended_cpuid_level >= 0x8000000a) c->x86_capability[CPUID_8000_000A_EDX] = cpuid_edx(0x8000000a); + if (c->extended_cpuid_level >= 0x8000001f) + c->x86_capability[CPUID_8000_001F_EAX] = cpuid_eax(0x8000001f); + init_scattered_cpuid_features(c); init_speculation_control(c); @@ -1739,8 +1742,8 @@ DEFINE_PER_CPU(struct task_struct *, current_task) ____cacheline_aligned = &init_task; EXPORT_PER_CPU_SYMBOL(current_task); -DEFINE_PER_CPU(struct irq_stack *, hardirq_stack_ptr); -DEFINE_PER_CPU(unsigned int, irq_count) __visible = -1; +DEFINE_PER_CPU(void *, hardirq_stack_ptr); +DEFINE_PER_CPU(bool, hardirq_stack_inuse); DEFINE_PER_CPU(int, __preempt_count) = INIT_PREEMPT_COUNT; EXPORT_PER_CPU_SYMBOL(__preempt_count); diff --git a/arch/x86/kernel/cpu/intel.c b/arch/x86/kernel/cpu/intel.c index 816fdbec795a..0e422a544835 100644 --- a/arch/x86/kernel/cpu/intel.c +++ b/arch/x86/kernel/cpu/intel.c @@ -24,6 +24,7 @@ #include <asm/traps.h> #include <asm/resctrl.h> #include <asm/numa.h> +#include <asm/thermal.h> #ifdef CONFIG_X86_64 #include <linux/topology.h> @@ -719,6 +720,8 @@ static void init_intel(struct cpuinfo_x86 *c) tsx_disable(); split_lock_init(); + + intel_init_thermal(c); } #ifdef CONFIG_X86_32 diff --git a/arch/x86/kernel/cpu/mce/Makefile b/arch/x86/kernel/cpu/mce/Makefile index 9f020c994154..015856abdbb1 100644 --- a/arch/x86/kernel/cpu/mce/Makefile +++ b/arch/x86/kernel/cpu/mce/Makefile @@ -9,8 +9,6 @@ obj-$(CONFIG_X86_MCE_THRESHOLD) += threshold.o mce-inject-y := inject.o obj-$(CONFIG_X86_MCE_INJECT) += mce-inject.o -obj-$(CONFIG_X86_THERMAL_VECTOR) += therm_throt.o - obj-$(CONFIG_ACPI_APEI) += apei.o obj-$(CONFIG_X86_MCELOG_LEGACY) += dev-mcelog.o diff --git a/arch/x86/kernel/cpu/mce/core.c b/arch/x86/kernel/cpu/mce/core.c index e133ce1e562b..7962355436da 100644 --- a/arch/x86/kernel/cpu/mce/core.c +++ b/arch/x86/kernel/cpu/mce/core.c @@ -878,6 +878,12 @@ static atomic_t mce_executing; static atomic_t mce_callin; /* + * Track which CPUs entered the MCA broadcast synchronization and which not in + * order to print holdouts. + */ +static cpumask_t mce_missing_cpus = CPU_MASK_ALL; + +/* * Check if a timeout waiting for other CPUs happened. */ static int mce_timed_out(u64 *t, const char *msg) @@ -894,8 +900,12 @@ static int mce_timed_out(u64 *t, const char *msg) if (!mca_cfg.monarch_timeout) goto out; if ((s64)*t < SPINUNIT) { - if (mca_cfg.tolerant <= 1) + if (mca_cfg.tolerant <= 1) { + if (cpumask_and(&mce_missing_cpus, cpu_online_mask, &mce_missing_cpus)) + pr_emerg("CPUs not responding to MCE broadcast (may include false positives): %*pbl\n", + cpumask_pr_args(&mce_missing_cpus)); mce_panic(msg, NULL, NULL); + } cpu_missing = 1; return 1; } @@ -1006,6 +1016,7 @@ static int mce_start(int *no_way_out) * is updated before mce_callin. */ order = atomic_inc_return(&mce_callin); + cpumask_clear_cpu(smp_processor_id(), &mce_missing_cpus); /* * Wait for everyone. @@ -1114,6 +1125,7 @@ static int mce_end(int order) reset: atomic_set(&global_nwo, 0); atomic_set(&mce_callin, 0); + cpumask_setall(&mce_missing_cpus); barrier(); /* @@ -2178,7 +2190,6 @@ __setup("mce", mcheck_enable); int __init mcheck_init(void) { - mcheck_intel_therm_init(); mce_register_decode_chain(&early_nb); mce_register_decode_chain(&mce_uc_nb); mce_register_decode_chain(&mce_default_nb); @@ -2713,6 +2724,7 @@ static void mce_reset(void) atomic_set(&mce_executing, 0); atomic_set(&mce_callin, 0); atomic_set(&global_nwo, 0); + cpumask_setall(&mce_missing_cpus); } static int fake_panic_get(void *data, u64 *val) diff --git a/arch/x86/kernel/cpu/mce/intel.c b/arch/x86/kernel/cpu/mce/intel.c index c2476fe0682e..e309476743b7 100644 --- a/arch/x86/kernel/cpu/mce/intel.c +++ b/arch/x86/kernel/cpu/mce/intel.c @@ -531,7 +531,6 @@ static void intel_imc_init(struct cpuinfo_x86 *c) void mce_intel_feature_init(struct cpuinfo_x86 *c) { - intel_init_thermal(c); intel_init_cmci(); intel_init_lmce(); intel_ppin_init(c); diff --git a/arch/x86/kernel/cpu/mce/therm_throt.c b/arch/x86/kernel/cpu/mce/therm_throt.c deleted file mode 100644 index a7cd2d203ced..000000000000 --- a/arch/x86/kernel/cpu/mce/therm_throt.c +++ /dev/null @@ -1,739 +0,0 @@ -// SPDX-License-Identifier: GPL-2.0-only -/* - * Thermal throttle event support code (such as syslog messaging and rate - * limiting) that was factored out from x86_64 (mce_intel.c) and i386 (p4.c). - * - * This allows consistent reporting of CPU thermal throttle events. - * - * Maintains a counter in /sys that keeps track of the number of thermal - * events, such that the user knows how bad the thermal problem might be - * (since the logging to syslog is rate limited). - * - * Author: Dmitriy Zavin (dmitriyz@google.com) - * - * Credits: Adapted from Zwane Mwaikambo's original code in mce_intel.c. - * Inspired by Ross Biro's and Al Borchers' counter code. - */ -#include <linux/interrupt.h> -#include <linux/notifier.h> -#include <linux/jiffies.h> -#include <linux/kernel.h> -#include <linux/percpu.h> -#include <linux/export.h> -#include <linux/types.h> -#include <linux/init.h> -#include <linux/smp.h> -#include <linux/cpu.h> - -#include <asm/processor.h> -#include <asm/traps.h> -#include <asm/apic.h> -#include <asm/mce.h> -#include <asm/msr.h> -#include <asm/trace/irq_vectors.h> - -#include "internal.h" - -/* How long to wait between reporting thermal events */ -#define CHECK_INTERVAL (300 * HZ) - -#define THERMAL_THROTTLING_EVENT 0 -#define POWER_LIMIT_EVENT 1 - -/** - * struct _thermal_state - Represent the current thermal event state - * @next_check: Stores the next timestamp, when it is allowed - * to log the next warning message. - * @last_interrupt_time: Stores the timestamp for the last threshold - * high event. - * @therm_work: Delayed workqueue structure - * @count: Stores the current running count for thermal - * or power threshold interrupts. - * @last_count: Stores the previous running count for thermal - * or power threshold interrupts. - * @max_time_ms: This shows the maximum amount of time CPU was - * in throttled state for a single thermal - * threshold high to low state. - * @total_time_ms: This is a cumulative time during which CPU was - * in the throttled state. - * @rate_control_active: Set when a throttling message is logged. - * This is used for the purpose of rate-control. - * @new_event: Stores the last high/low status of the - * THERM_STATUS_PROCHOT or - * THERM_STATUS_POWER_LIMIT. - * @level: Stores whether this _thermal_state instance is - * for a CORE level or for PACKAGE level. - * @sample_index: Index for storing the next sample in the buffer - * temp_samples[]. - * @sample_count: Total number of samples collected in the buffer - * temp_samples[]. - * @average: The last moving average of temperature samples - * @baseline_temp: Temperature at which thermal threshold high - * interrupt was generated. - * @temp_samples: Storage for temperature samples to calculate - * moving average. - * - * This structure is used to represent data related to thermal state for a CPU. - * There is a separate storage for core and package level for each CPU. - */ -struct _thermal_state { - u64 next_check; - u64 last_interrupt_time; - struct delayed_work therm_work; - unsigned long count; - unsigned long last_count; - unsigned long max_time_ms; - unsigned long total_time_ms; - bool rate_control_active; - bool new_event; - u8 level; - u8 sample_index; - u8 sample_count; - u8 average; - u8 baseline_temp; - u8 temp_samples[3]; -}; - -struct thermal_state { - struct _thermal_state core_throttle; - struct _thermal_state core_power_limit; - struct _thermal_state package_throttle; - struct _thermal_state package_power_limit; - struct _thermal_state core_thresh0; - struct _thermal_state core_thresh1; - struct _thermal_state pkg_thresh0; - struct _thermal_state pkg_thresh1; -}; - -/* Callback to handle core threshold interrupts */ -int (*platform_thermal_notify)(__u64 msr_val); -EXPORT_SYMBOL(platform_thermal_notify); - -/* Callback to handle core package threshold_interrupts */ -int (*platform_thermal_package_notify)(__u64 msr_val); -EXPORT_SYMBOL_GPL(platform_thermal_package_notify); - -/* Callback support of rate control, return true, if - * callback has rate control */ -bool (*platform_thermal_package_rate_control)(void); -EXPORT_SYMBOL_GPL(platform_thermal_package_rate_control); - - -static DEFINE_PER_CPU(struct thermal_state, thermal_state); - -static atomic_t therm_throt_en = ATOMIC_INIT(0); - -static u32 lvtthmr_init __read_mostly; - -#ifdef CONFIG_SYSFS -#define define_therm_throt_device_one_ro(_name) \ - static DEVICE_ATTR(_name, 0444, \ - therm_throt_device_show_##_name, \ - NULL) \ - -#define define_therm_throt_device_show_func(event, name) \ - \ -static ssize_t therm_throt_device_show_##event##_##name( \ - struct device *dev, \ - struct device_attribute *attr, \ - char *buf) \ -{ \ - unsigned int cpu = dev->id; \ - ssize_t ret; \ - \ - preempt_disable(); /* CPU hotplug */ \ - if (cpu_online(cpu)) { \ - ret = sprintf(buf, "%lu\n", \ - per_cpu(thermal_state, cpu).event.name); \ - } else \ - ret = 0; \ - preempt_enable(); \ - \ - return ret; \ -} - -define_therm_throt_device_show_func(core_throttle, count); -define_therm_throt_device_one_ro(core_throttle_count); - -define_therm_throt_device_show_func(core_power_limit, count); -define_therm_throt_device_one_ro(core_power_limit_count); - -define_therm_throt_device_show_func(package_throttle, count); -define_therm_throt_device_one_ro(package_throttle_count); - -define_therm_throt_device_show_func(package_power_limit, count); -define_therm_throt_device_one_ro(package_power_limit_count); - -define_therm_throt_device_show_func(core_throttle, max_time_ms); -define_therm_throt_device_one_ro(core_throttle_max_time_ms); - -define_therm_throt_device_show_func(package_throttle, max_time_ms); -define_therm_throt_device_one_ro(package_throttle_max_time_ms); - -define_therm_throt_device_show_func(core_throttle, total_time_ms); -define_therm_throt_device_one_ro(core_throttle_total_time_ms); - -define_therm_throt_device_show_func(package_throttle, total_time_ms); -define_therm_throt_device_one_ro(package_throttle_total_time_ms); - -static struct attribute *thermal_throttle_attrs[] = { - &dev_attr_core_throttle_count.attr, - &dev_attr_core_throttle_max_time_ms.attr, - &dev_attr_core_throttle_total_time_ms.attr, - NULL -}; - -static const struct attribute_group thermal_attr_group = { - .attrs = thermal_throttle_attrs, - .name = "thermal_throttle" -}; -#endif /* CONFIG_SYSFS */ - -#define CORE_LEVEL 0 -#define PACKAGE_LEVEL 1 - -#define THERM_THROT_POLL_INTERVAL HZ -#define THERM_STATUS_PROCHOT_LOG BIT(1) - -#define THERM_STATUS_CLEAR_CORE_MASK (BIT(1) | BIT(3) | BIT(5) | BIT(7) | BIT(9) | BIT(11) | BIT(13) | BIT(15)) -#define THERM_STATUS_CLEAR_PKG_MASK (BIT(1) | BIT(3) | BIT(5) | BIT(7) | BIT(9) | BIT(11)) - -static void clear_therm_status_log(int level) -{ - int msr; - u64 mask, msr_val; - - if (level == CORE_LEVEL) { - msr = MSR_IA32_THERM_STATUS; - mask = THERM_STATUS_CLEAR_CORE_MASK; - } else { - msr = MSR_IA32_PACKAGE_THERM_STATUS; - mask = THERM_STATUS_CLEAR_PKG_MASK; - } - - rdmsrl(msr, msr_val); - msr_val &= mask; - wrmsrl(msr, msr_val & ~THERM_STATUS_PROCHOT_LOG); -} - -static void get_therm_status(int level, bool *proc_hot, u8 *temp) -{ - int msr; - u64 msr_val; - - if (level == CORE_LEVEL) - msr = MSR_IA32_THERM_STATUS; - else - msr = MSR_IA32_PACKAGE_THERM_STATUS; - - rdmsrl(msr, msr_val); - if (msr_val & THERM_STATUS_PROCHOT_LOG) - *proc_hot = true; - else - *proc_hot = false; - - *temp = (msr_val >> 16) & 0x7F; -} - -static void __maybe_unused throttle_active_work(struct work_struct *work) -{ - struct _thermal_state *state = container_of(to_delayed_work(work), - struct _thermal_state, therm_work); - unsigned int i, avg, this_cpu = smp_processor_id(); - u64 now = get_jiffies_64(); - bool hot; - u8 temp; - - get_therm_status(state->level, &hot, &temp); - /* temperature value is offset from the max so lesser means hotter */ - if (!hot && temp > state->baseline_temp) { - if (state->rate_control_active) - pr_info("CPU%d: %s temperature/speed normal (total events = %lu)\n", - this_cpu, - state->level == CORE_LEVEL ? "Core" : "Package", - state->count); - - state->rate_control_active = false; - return; - } - - if (time_before64(now, state->next_check) && - state->rate_control_active) - goto re_arm; - - state->next_check = now + CHECK_INTERVAL; - - if (state->count != state->last_count) { - /* There was one new thermal interrupt */ - state->last_count = state->count; - state->average = 0; - state->sample_count = 0; - state->sample_index = 0; - } - - state->temp_samples[state->sample_index] = temp; - state->sample_count++; - state->sample_index = (state->sample_index + 1) % ARRAY_SIZE(state->temp_samples); - if (state->sample_count < ARRAY_SIZE(state->temp_samples)) - goto re_arm; - - avg = 0; - for (i = 0; i < ARRAY_SIZE(state->temp_samples); ++i) - avg += state->temp_samples[i]; - - avg /= ARRAY_SIZE(state->temp_samples); - - if (state->average > avg) { - pr_warn("CPU%d: %s temperature is above threshold, cpu clock is throttled (total events = %lu)\n", - this_cpu, - state->level == CORE_LEVEL ? "Core" : "Package", - state->count); - state->rate_control_active = true; - } - - state->average = avg; - -re_arm: - clear_therm_status_log(state->level); - schedule_delayed_work_on(this_cpu, &state->therm_work, THERM_THROT_POLL_INTERVAL); -} - -/*** - * therm_throt_process - Process thermal throttling event from interrupt - * @curr: Whether the condition is current or not (boolean), since the - * thermal interrupt normally gets called both when the thermal - * event begins and once the event has ended. - * - * This function is called by the thermal interrupt after the - * IRQ has been acknowledged. - * - * It will take care of rate limiting and printing messages to the syslog. - */ -static void therm_throt_process(bool new_event, int event, int level) -{ - struct _thermal_state *state; - unsigned int this_cpu = smp_processor_id(); - bool old_event; - u64 now; - struct thermal_state *pstate = &per_cpu(thermal_state, this_cpu); - - now = get_jiffies_64(); - if (level == CORE_LEVEL) { - if (event == THERMAL_THROTTLING_EVENT) - state = &pstate->core_throttle; - else if (event == POWER_LIMIT_EVENT) - state = &pstate->core_power_limit; - else - return; - } else if (level == PACKAGE_LEVEL) { - if (event == THERMAL_THROTTLING_EVENT) - state = &pstate->package_throttle; - else if (event == POWER_LIMIT_EVENT) - state = &pstate->package_power_limit; - else - return; - } else - return; - - old_event = state->new_event; - state->new_event = new_event; - - if (new_event) - state->count++; - - if (event != THERMAL_THROTTLING_EVENT) - return; - - if (new_event && !state->last_interrupt_time) { - bool hot; - u8 temp; - - get_therm_status(state->level, &hot, &temp); - /* - * Ignore short temperature spike as the system is not close - * to PROCHOT. 10C offset is large enough to ignore. It is - * already dropped from the high threshold temperature. - */ - if (temp > 10) - return; - - state->baseline_temp = temp; - state->last_interrupt_time = now; - schedule_delayed_work_on(this_cpu, &state->therm_work, THERM_THROT_POLL_INTERVAL); - } else if (old_event && state->last_interrupt_time) { - unsigned long throttle_time; - - throttle_time = jiffies_delta_to_msecs(now - state->last_interrupt_time); - if (throttle_time > state->max_time_ms) - state->max_time_ms = throttle_time; - state->total_time_ms += throttle_time; - state->last_interrupt_time = 0; - } -} - -static int thresh_event_valid(int level, int event) -{ - struct _thermal_state *state; - unsigned int this_cpu = smp_processor_id(); - struct thermal_state *pstate = &per_cpu(thermal_state, this_cpu); - u64 now = get_jiffies_64(); - - if (level == PACKAGE_LEVEL) - state = (event == 0) ? &pstate->pkg_thresh0 : - &pstate->pkg_thresh1; - else - state = (event == 0) ? &pstate->core_thresh0 : - &pstate->core_thresh1; - - if (time_before64(now, state->next_check)) - return 0; - - state->next_check = now + CHECK_INTERVAL; - - return 1; -} - -static bool int_pln_enable; -static int __init int_pln_enable_setup(char *s) -{ - int_pln_enable = true; - - return 1; -} -__setup("int_pln_enable", int_pln_enable_setup); - -#ifdef CONFIG_SYSFS -/* Add/Remove thermal_throttle interface for CPU device: */ -static int thermal_throttle_add_dev(struct device *dev, unsigned int cpu) -{ - int err; - struct cpuinfo_x86 *c = &cpu_data(cpu); - - err = sysfs_create_group(&dev->kobj, &thermal_attr_group); - if (err) - return err; - - if (cpu_has(c, X86_FEATURE_PLN) && int_pln_enable) { - err = sysfs_add_file_to_group(&dev->kobj, - &dev_attr_core_power_limit_count.attr, - thermal_attr_group.name); - if (err) - goto del_group; - } - - if (cpu_has(c, X86_FEATURE_PTS)) { - err = sysfs_add_file_to_group(&dev->kobj, - &dev_attr_package_throttle_count.attr, - thermal_attr_group.name); - if (err) - goto del_group; - - err = sysfs_add_file_to_group(&dev->kobj, - &dev_attr_package_throttle_max_time_ms.attr, - thermal_attr_group.name); - if (err) - goto del_group; - - err = sysfs_add_file_to_group(&dev->kobj, - &dev_attr_package_throttle_total_time_ms.attr, - thermal_attr_group.name); - if (err) - goto del_group; - - if (cpu_has(c, X86_FEATURE_PLN) && int_pln_enable) { - err = sysfs_add_file_to_group(&dev->kobj, - &dev_attr_package_power_limit_count.attr, - thermal_attr_group.name); - if (err) - goto del_group; - } - } - - return 0; - -del_group: - sysfs_remove_group(&dev->kobj, &thermal_attr_group); - - return err; -} - -static void thermal_throttle_remove_dev(struct device *dev) -{ - sysfs_remove_group(&dev->kobj, &thermal_attr_group); -} - -/* Get notified when a cpu comes on/off. Be hotplug friendly. */ -static int thermal_throttle_online(unsigned int cpu) -{ - struct thermal_state *state = &per_cpu(thermal_state, cpu); - struct device *dev = get_cpu_device(cpu); - u32 l; - - state->package_throttle.level = PACKAGE_LEVEL; - state->core_throttle.level = CORE_LEVEL; - - INIT_DELAYED_WORK(&state->package_throttle.therm_work, throttle_active_work); - INIT_DELAYED_WORK(&state->core_throttle.therm_work, throttle_active_work); - - /* Unmask the thermal vector after the above workqueues are initialized. */ - l = apic_read(APIC_LVTTHMR); - apic_write(APIC_LVTTHMR, l & ~APIC_LVT_MASKED); - - return thermal_throttle_add_dev(dev, cpu); -} - -static int thermal_throttle_offline(unsigned int cpu) -{ - struct thermal_state *state = &per_cpu(thermal_state, cpu); - struct device *dev = get_cpu_device(cpu); - u32 l; - - /* Mask the thermal vector before draining evtl. pending work */ - l = apic_read(APIC_LVTTHMR); - apic_write(APIC_LVTTHMR, l | APIC_LVT_MASKED); - - cancel_delayed_work_sync(&state->package_throttle.therm_work); - cancel_delayed_work_sync(&state->core_throttle.therm_work); - - state->package_throttle.rate_control_active = false; - state->core_throttle.rate_control_active = false; - - thermal_throttle_remove_dev(dev); - return 0; -} - -static __init int thermal_throttle_init_device(void) -{ - int ret; - - if (!atomic_read(&therm_throt_en)) - return 0; - - ret = cpuhp_setup_state(CPUHP_AP_ONLINE_DYN, "x86/therm:online", - thermal_throttle_online, - thermal_throttle_offline); - return ret < 0 ? ret : 0; -} -device_initcall(thermal_throttle_init_device); - -#endif /* CONFIG_SYSFS */ - -static void notify_package_thresholds(__u64 msr_val) -{ - bool notify_thres_0 = false; - bool notify_thres_1 = false; - - if (!platform_thermal_package_notify) - return; - - /* lower threshold check */ - if (msr_val & THERM_LOG_THRESHOLD0) - notify_thres_0 = true; - /* higher threshold check */ - if (msr_val & THERM_LOG_THRESHOLD1) - notify_thres_1 = true; - - if (!notify_thres_0 && !notify_thres_1) - return; - - if (platform_thermal_package_rate_control && - platform_thermal_package_rate_control()) { - /* Rate control is implemented in callback */ - platform_thermal_package_notify(msr_val); - return; - } - - /* lower threshold reached */ - if (notify_thres_0 && thresh_event_valid(PACKAGE_LEVEL, 0)) - platform_thermal_package_notify(msr_val); - /* higher threshold reached */ - if (notify_thres_1 && thresh_event_valid(PACKAGE_LEVEL, 1)) - platform_thermal_package_notify(msr_val); -} - -static void notify_thresholds(__u64 msr_val) -{ - /* check whether the interrupt handler is defined; - * otherwise simply return - */ - if (!platform_thermal_notify) - return; - - /* lower threshold reached */ - if ((msr_val & THERM_LOG_THRESHOLD0) && - thresh_event_valid(CORE_LEVEL, 0)) - platform_thermal_notify(msr_val); - /* higher threshold reached */ - if ((msr_val & THERM_LOG_THRESHOLD1) && - thresh_event_valid(CORE_LEVEL, 1)) - platform_thermal_notify(msr_val); -} - -/* Thermal transition interrupt handler */ -static void intel_thermal_interrupt(void) -{ - __u64 msr_val; - - if (static_cpu_has(X86_FEATURE_HWP)) - wrmsrl_safe(MSR_HWP_STATUS, 0); - - rdmsrl(MSR_IA32_THERM_STATUS, msr_val); - - /* Check for violation of core thermal thresholds*/ - notify_thresholds(msr_val); - - therm_throt_process(msr_val & THERM_STATUS_PROCHOT, - THERMAL_THROTTLING_EVENT, - CORE_LEVEL); - - if (this_cpu_has(X86_FEATURE_PLN) && int_pln_enable) - therm_throt_process(msr_val & THERM_STATUS_POWER_LIMIT, - POWER_LIMIT_EVENT, - CORE_LEVEL); - - if (this_cpu_has(X86_FEATURE_PTS)) { - rdmsrl(MSR_IA32_PACKAGE_THERM_STATUS, msr_val); - /* check violations of package thermal thresholds */ - notify_package_thresholds(msr_val); - therm_throt_process(msr_val & PACKAGE_THERM_STATUS_PROCHOT, - THERMAL_THROTTLING_EVENT, - PACKAGE_LEVEL); - if (this_cpu_has(X86_FEATURE_PLN) && int_pln_enable) - therm_throt_process(msr_val & - PACKAGE_THERM_STATUS_POWER_LIMIT, - POWER_LIMIT_EVENT, - PACKAGE_LEVEL); - } -} - -static void unexpected_thermal_interrupt(void) -{ - pr_err("CPU%d: Unexpected LVT thermal interrupt!\n", - smp_processor_id()); -} - -static void (*smp_thermal_vector)(void) = unexpected_thermal_interrupt; - -DEFINE_IDTENTRY_SYSVEC(sysvec_thermal) -{ - trace_thermal_apic_entry(THERMAL_APIC_VECTOR); - inc_irq_stat(irq_thermal_count); - smp_thermal_vector(); - trace_thermal_apic_exit(THERMAL_APIC_VECTOR); - ack_APIC_irq(); -} - -/* Thermal monitoring depends on APIC, ACPI and clock modulation */ -static int intel_thermal_supported(struct cpuinfo_x86 *c) -{ - if (!boot_cpu_has(X86_FEATURE_APIC)) - return 0; - if (!cpu_has(c, X86_FEATURE_ACPI) || !cpu_has(c, X86_FEATURE_ACC)) - return 0; - return 1; -} - -void __init mcheck_intel_therm_init(void) -{ - /* - * This function is only called on boot CPU. Save the init thermal - * LVT value on BSP and use that value to restore APs' thermal LVT - * entry BIOS programmed later - */ - if (intel_thermal_supported(&boot_cpu_data)) - lvtthmr_init = apic_read(APIC_LVTTHMR); -} - -void intel_init_thermal(struct cpuinfo_x86 *c) -{ - unsigned int cpu = smp_processor_id(); - int tm2 = 0; - u32 l, h; - - if (!intel_thermal_supported(c)) - return; - - /* - * First check if its enabled already, in which case there might - * be some SMM goo which handles it, so we can't even put a handler - * since it might be delivered via SMI already: - */ - rdmsr(MSR_IA32_MISC_ENABLE, l, h); - - h = lvtthmr_init; - /* - * The initial value of thermal LVT entries on all APs always reads - * 0x10000 because APs are woken up by BSP issuing INIT-SIPI-SIPI - * sequence to them and LVT registers are reset to 0s except for - * the mask bits which are set to 1s when APs receive INIT IPI. - * If BIOS takes over the thermal interrupt and sets its interrupt - * delivery mode to SMI (not fixed), it restores the value that the - * BIOS has programmed on AP based on BSP's info we saved since BIOS - * is always setting the same value for all threads/cores. - */ - if ((h & APIC_DM_FIXED_MASK) != APIC_DM_FIXED) - apic_write(APIC_LVTTHMR, lvtthmr_init); - - - if ((l & MSR_IA32_MISC_ENABLE_TM1) && (h & APIC_DM_SMI)) { - if (system_state == SYSTEM_BOOTING) - pr_debug("CPU%d: Thermal monitoring handled by SMI\n", cpu); - return; - } - - /* early Pentium M models use different method for enabling TM2 */ - if (cpu_has(c, X86_FEATURE_TM2)) { - if (c->x86 == 6 && (c->x86_model == 9 || c->x86_model == 13)) { - rdmsr(MSR_THERM2_CTL, l, h); - if (l & MSR_THERM2_CTL_TM_SELECT) - tm2 = 1; - } else if (l & MSR_IA32_MISC_ENABLE_TM2) - tm2 = 1; - } - - /* We'll mask the thermal vector in the lapic till we're ready: */ - h = THERMAL_APIC_VECTOR | APIC_DM_FIXED | APIC_LVT_MASKED; - apic_write(APIC_LVTTHMR, h); - - rdmsr(MSR_IA32_THERM_INTERRUPT, l, h); - if (cpu_has(c, X86_FEATURE_PLN) && !int_pln_enable) - wrmsr(MSR_IA32_THERM_INTERRUPT, - (l | (THERM_INT_LOW_ENABLE - | THERM_INT_HIGH_ENABLE)) & ~THERM_INT_PLN_ENABLE, h); - else if (cpu_has(c, X86_FEATURE_PLN) && int_pln_enable) - wrmsr(MSR_IA32_THERM_INTERRUPT, - l | (THERM_INT_LOW_ENABLE - | THERM_INT_HIGH_ENABLE | THERM_INT_PLN_ENABLE), h); - else - wrmsr(MSR_IA32_THERM_INTERRUPT, - l | (THERM_INT_LOW_ENABLE | THERM_INT_HIGH_ENABLE), h); - - if (cpu_has(c, X86_FEATURE_PTS)) { - rdmsr(MSR_IA32_PACKAGE_THERM_INTERRUPT, l, h); - if (cpu_has(c, X86_FEATURE_PLN) && !int_pln_enable) - wrmsr(MSR_IA32_PACKAGE_THERM_INTERRUPT, - (l | (PACKAGE_THERM_INT_LOW_ENABLE - | PACKAGE_THERM_INT_HIGH_ENABLE)) - & ~PACKAGE_THERM_INT_PLN_ENABLE, h); - else if (cpu_has(c, X86_FEATURE_PLN) && int_pln_enable) - wrmsr(MSR_IA32_PACKAGE_THERM_INTERRUPT, - l | (PACKAGE_THERM_INT_LOW_ENABLE - | PACKAGE_THERM_INT_HIGH_ENABLE - | PACKAGE_THERM_INT_PLN_ENABLE), h); - else - wrmsr(MSR_IA32_PACKAGE_THERM_INTERRUPT, - l | (PACKAGE_THERM_INT_LOW_ENABLE - | PACKAGE_THERM_INT_HIGH_ENABLE), h); - } - - smp_thermal_vector = intel_thermal_interrupt; - - rdmsr(MSR_IA32_MISC_ENABLE, l, h); - wrmsr(MSR_IA32_MISC_ENABLE, l | MSR_IA32_MISC_ENABLE_TM1, h); - - pr_info_once("CPU0: Thermal monitoring enabled (%s)\n", - tm2 ? "TM2" : "TM1"); - - /* enable thermal throttle processing */ - atomic_set(&therm_throt_en, 1); -} diff --git a/arch/x86/kernel/cpu/microcode/core.c b/arch/x86/kernel/cpu/microcode/core.c index ec6f0415bc6d..b935e1b5f115 100644 --- a/arch/x86/kernel/cpu/microcode/core.c +++ b/arch/x86/kernel/cpu/microcode/core.c @@ -830,7 +830,7 @@ static const struct attribute_group cpu_root_microcode_group = { .attrs = cpu_root_microcode_attrs, }; -int __init microcode_init(void) +static int __init microcode_init(void) { struct cpuinfo_x86 *c = &boot_cpu_data; int error; diff --git a/arch/x86/kernel/cpu/mshyperv.c b/arch/x86/kernel/cpu/mshyperv.c index 43b54bef5448..e88bc296afca 100644 --- a/arch/x86/kernel/cpu/mshyperv.c +++ b/arch/x86/kernel/cpu/mshyperv.c @@ -31,6 +31,11 @@ #include <asm/reboot.h> #include <asm/nmi.h> #include <clocksource/hyperv_timer.h> +#include <asm/numa.h> + +/* Is Linux running as the root partition? */ +bool hv_root_partition; +EXPORT_SYMBOL_GPL(hv_root_partition); struct ms_hyperv_info ms_hyperv; EXPORT_SYMBOL_GPL(ms_hyperv); @@ -226,6 +231,32 @@ static void __init hv_smp_prepare_boot_cpu(void) hv_init_spinlocks(); #endif } + +static void __init hv_smp_prepare_cpus(unsigned int max_cpus) +{ +#ifdef CONFIG_X86_64 + int i; + int ret; +#endif + + native_smp_prepare_cpus(max_cpus); + +#ifdef CONFIG_X86_64 + for_each_present_cpu(i) { + if (i == 0) + continue; + ret = hv_call_add_logical_proc(numa_cpu_node(i), i, cpu_physical_id(i)); + BUG_ON(ret); + } + + for_each_present_cpu(i) { + if (i == 0) + continue; + ret = hv_call_create_vp(numa_cpu_node(i), hv_current_partition_id, i, i); + BUG_ON(ret); + } +#endif +} #endif static void __init ms_hyperv_init_platform(void) @@ -243,6 +274,7 @@ static void __init ms_hyperv_init_platform(void) * Extract the features and hints */ ms_hyperv.features = cpuid_eax(HYPERV_CPUID_FEATURES); + ms_hyperv.features_b = cpuid_ebx(HYPERV_CPUID_FEATURES); ms_hyperv.misc_features = cpuid_edx(HYPERV_CPUID_FEATURES); ms_hyperv.hints = cpuid_eax(HYPERV_CPUID_ENLIGHTMENT_INFO); @@ -256,6 +288,22 @@ static void __init ms_hyperv_init_platform(void) ms_hyperv.max_vp_index, ms_hyperv.max_lp_index); /* + * Check CPU management privilege. + * + * To mirror what Windows does we should extract CPU management + * features and use the ReservedIdentityBit to detect if Linux is the + * root partition. But that requires negotiating CPU management + * interface (a process to be finalized). + * + * For now, use the privilege flag as the indicator for running as + * root. + */ + if (cpuid_ebx(HYPERV_CPUID_FEATURES) & HV_CPU_MANAGEMENT) { + hv_root_partition = true; + pr_info("Hyper-V: running as root partition\n"); + } + + /* * Extract host information. */ if (cpuid_eax(HYPERV_CPUID_VENDOR_AND_MAX_FUNCTIONS) >= @@ -277,6 +325,14 @@ static void __init ms_hyperv_init_platform(void) x86_platform.calibrate_cpu = hv_get_tsc_khz; } + if (ms_hyperv.features_b & HV_ISOLATION) { + ms_hyperv.isolation_config_a = cpuid_eax(HYPERV_CPUID_ISOLATION_CONFIG); + ms_hyperv.isolation_config_b = cpuid_ebx(HYPERV_CPUID_ISOLATION_CONFIG); + + pr_info("Hyper-V: Isolation Config: Group A 0x%x, Group B 0x%x\n", + ms_hyperv.isolation_config_a, ms_hyperv.isolation_config_b); + } + if (ms_hyperv.hints & HV_X64_ENLIGHTENED_VMCS_RECOMMENDED) { ms_hyperv.nested_features = cpuid_eax(HYPERV_CPUID_NESTED_FEATURES); @@ -366,6 +422,8 @@ static void __init ms_hyperv_init_platform(void) # ifdef CONFIG_SMP smp_ops.smp_prepare_boot_cpu = hv_smp_prepare_boot_cpu; + if (hv_root_partition) + smp_ops.smp_prepare_cpus = hv_smp_prepare_cpus; # endif /* diff --git a/arch/x86/kernel/cpu/mtrr/cleanup.c b/arch/x86/kernel/cpu/mtrr/cleanup.c index 5bd011737272..9231640782fa 100644 --- a/arch/x86/kernel/cpu/mtrr/cleanup.c +++ b/arch/x86/kernel/cpu/mtrr/cleanup.c @@ -537,9 +537,9 @@ static void __init print_out_mtrr_range_state(void) if (!size_base) continue; - size_base = to_size_factor(size_base, &size_factor), + size_base = to_size_factor(size_base, &size_factor); start_base = range_state[i].base_pfn << (PAGE_SHIFT - 10); - start_base = to_size_factor(start_base, &start_factor), + start_base = to_size_factor(start_base, &start_factor); type = range_state[i].type; pr_debug("reg %d, base: %ld%cB, range: %ld%cB, type %s\n", diff --git a/arch/x86/kernel/cpu/mtrr/generic.c b/arch/x86/kernel/cpu/mtrr/generic.c index a29997e6cf9e..b90f3f437765 100644 --- a/arch/x86/kernel/cpu/mtrr/generic.c +++ b/arch/x86/kernel/cpu/mtrr/generic.c @@ -3,7 +3,6 @@ * This only handles 32bit MTRR on 32bit hosts. This is strictly wrong * because MTRRs can span up to 40 bits (36bits on most modern x86) */ -#define DEBUG #include <linux/export.h> #include <linux/init.h> diff --git a/arch/x86/kernel/cpu/mtrr/mtrr.c b/arch/x86/kernel/cpu/mtrr/mtrr.c index 61eb26edc6d2..28c8a23aa42e 100644 --- a/arch/x86/kernel/cpu/mtrr/mtrr.c +++ b/arch/x86/kernel/cpu/mtrr/mtrr.c @@ -31,8 +31,6 @@ System Programming Guide; Section 9.11. (1997 edition - PPro). */ -#define DEBUG - #include <linux/types.h> /* FIXME: kvm_para.h needs this */ #include <linux/stop_machine.h> diff --git a/arch/x86/kernel/cpu/perfctr-watchdog.c b/arch/x86/kernel/cpu/perfctr-watchdog.c index a5ee607a3b89..3ef5868ac588 100644 --- a/arch/x86/kernel/cpu/perfctr-watchdog.c +++ b/arch/x86/kernel/cpu/perfctr-watchdog.c @@ -3,7 +3,7 @@ * local apic based NMI watchdog for various CPUs. * * This file also handles reservation of performance counters for coordination - * with other users (like oprofile). + * with other users. * * Note that these events normally don't tick when the CPU idles. This means * the frequency varies with CPU load. @@ -105,15 +105,6 @@ static inline unsigned int nmi_evntsel_msr_to_bit(unsigned int msr) } -/* checks for a bit availability (hack for oprofile) */ -int avail_to_resrv_perfctr_nmi_bit(unsigned int counter) -{ - BUG_ON(counter > NMI_MAX_COUNTER_BITS); - - return !test_bit(counter, perfctr_nmi_owner); -} -EXPORT_SYMBOL(avail_to_resrv_perfctr_nmi_bit); - int reserve_perfctr_nmi(unsigned int msr) { unsigned int counter; diff --git a/arch/x86/kernel/cpu/resctrl/internal.h b/arch/x86/kernel/cpu/resctrl/internal.h index ee71c47844cb..c4d320d02fd5 100644 --- a/arch/x86/kernel/cpu/resctrl/internal.h +++ b/arch/x86/kernel/cpu/resctrl/internal.h @@ -572,6 +572,7 @@ union cpuid_0x10_x_edx { void rdt_last_cmd_clear(void); void rdt_last_cmd_puts(const char *s); +__printf(1, 2) void rdt_last_cmd_printf(const char *fmt, ...); void rdt_ctrl_update(void *arg); diff --git a/arch/x86/kernel/cpu/resctrl/rdtgroup.c b/arch/x86/kernel/cpu/resctrl/rdtgroup.c index 460f3e0df106..f9190adc52cb 100644 --- a/arch/x86/kernel/cpu/resctrl/rdtgroup.c +++ b/arch/x86/kernel/cpu/resctrl/rdtgroup.c @@ -563,11 +563,11 @@ static int __rdtgroup_move_task(struct task_struct *tsk, */ if (rdtgrp->type == RDTCTRL_GROUP) { - tsk->closid = rdtgrp->closid; - tsk->rmid = rdtgrp->mon.rmid; + WRITE_ONCE(tsk->closid, rdtgrp->closid); + WRITE_ONCE(tsk->rmid, rdtgrp->mon.rmid); } else if (rdtgrp->type == RDTMON_GROUP) { if (rdtgrp->mon.parent->closid == tsk->closid) { - tsk->rmid = rdtgrp->mon.rmid; + WRITE_ONCE(tsk->rmid, rdtgrp->mon.rmid); } else { rdt_last_cmd_puts("Can't move task to different control group\n"); return -EINVAL; @@ -2310,22 +2310,18 @@ static void rdt_move_group_tasks(struct rdtgroup *from, struct rdtgroup *to, for_each_process_thread(p, t) { if (!from || is_closid_match(t, from) || is_rmid_match(t, from)) { - t->closid = to->closid; - t->rmid = to->mon.rmid; + WRITE_ONCE(t->closid, to->closid); + WRITE_ONCE(t->rmid, to->mon.rmid); -#ifdef CONFIG_SMP /* - * This is safe on x86 w/o barriers as the ordering - * of writing to task_cpu() and t->on_cpu is - * reverse to the reading here. The detection is - * inaccurate as tasks might move or schedule - * before the smp function call takes place. In - * such a case the function call is pointless, but + * If the task is on a CPU, set the CPU in the mask. + * The detection is inaccurate as tasks might move or + * schedule before the smp function call takes place. + * In such a case the function call is pointless, but * there is no other side effect. */ - if (mask && t->on_cpu) + if (IS_ENABLED(CONFIG_SMP) && mask && task_curr(t)) cpumask_set_cpu(task_cpu(t), mask); -#endif } } read_unlock(&tasklist_lock); diff --git a/arch/x86/kernel/cpu/scattered.c b/arch/x86/kernel/cpu/scattered.c index 236924930bf0..972ec3bfa9c0 100644 --- a/arch/x86/kernel/cpu/scattered.c +++ b/arch/x86/kernel/cpu/scattered.c @@ -40,11 +40,6 @@ static const struct cpuid_bit cpuid_bits[] = { { X86_FEATURE_CPB, CPUID_EDX, 9, 0x80000007, 0 }, { X86_FEATURE_PROC_FEEDBACK, CPUID_EDX, 11, 0x80000007, 0 }, { X86_FEATURE_MBA, CPUID_EBX, 6, 0x80000008, 0 }, - { X86_FEATURE_SME, CPUID_EAX, 0, 0x8000001f, 0 }, - { X86_FEATURE_SEV, CPUID_EAX, 1, 0x8000001f, 0 }, - { X86_FEATURE_SEV_ES, CPUID_EAX, 3, 0x8000001f, 0 }, - { X86_FEATURE_SME_COHERENT, CPUID_EAX, 10, 0x8000001f, 0 }, - { X86_FEATURE_VM_PAGE_FLUSH, CPUID_EAX, 2, 0x8000001f, 0 }, { 0, 0, 0, 0, 0 } }; diff --git a/arch/x86/kernel/cpu/sgx/encl.c b/arch/x86/kernel/cpu/sgx/encl.c index f65564a94b9b..7449ef33f081 100644 --- a/arch/x86/kernel/cpu/sgx/encl.c +++ b/arch/x86/kernel/cpu/sgx/encl.c @@ -141,7 +141,6 @@ static vm_fault_t sgx_vma_fault(struct vm_fault *vmf) struct sgx_encl_page *entry; unsigned long phys_addr; struct sgx_encl *encl; - unsigned long pfn; vm_fault_t ret; encl = vma->vm_private_data; @@ -168,13 +167,6 @@ static vm_fault_t sgx_vma_fault(struct vm_fault *vmf) phys_addr = sgx_get_epc_phys_addr(entry->epc_page); - /* Check if another thread got here first to insert the PTE. */ - if (!follow_pfn(vma, addr, &pfn)) { - mutex_unlock(&encl->lock); - - return VM_FAULT_NOPAGE; - } - ret = vmf_insert_pfn(vma, addr, PFN_DOWN(phys_addr)); if (ret != VM_FAULT_NOPAGE) { mutex_unlock(&encl->lock); diff --git a/arch/x86/kernel/cpu/sgx/main.c b/arch/x86/kernel/cpu/sgx/main.c index c519fc5f6948..8df81a3ed945 100644 --- a/arch/x86/kernel/cpu/sgx/main.c +++ b/arch/x86/kernel/cpu/sgx/main.c @@ -700,25 +700,27 @@ static bool __init sgx_page_cache_init(void) return true; } -static void __init sgx_init(void) +static int __init sgx_init(void) { int ret; int i; if (!cpu_feature_enabled(X86_FEATURE_SGX)) - return; + return -ENODEV; if (!sgx_page_cache_init()) - return; + return -ENOMEM; - if (!sgx_page_reclaimer_init()) + if (!sgx_page_reclaimer_init()) { + ret = -ENOMEM; goto err_page_cache; + } ret = sgx_drv_init(); if (ret) goto err_kthread; - return; + return 0; err_kthread: kthread_stop(ksgxd_tsk); @@ -728,6 +730,8 @@ err_page_cache: vfree(sgx_epc_sections[i].pages); memunmap(sgx_epc_sections[i].virt_addr); } + + return ret; } device_initcall(sgx_init); diff --git a/arch/x86/kernel/dumpstack_64.c b/arch/x86/kernel/dumpstack_64.c index 1dd851397bd9..5601b95944fa 100644 --- a/arch/x86/kernel/dumpstack_64.c +++ b/arch/x86/kernel/dumpstack_64.c @@ -128,12 +128,21 @@ static __always_inline bool in_exception_stack(unsigned long *stack, struct stac static __always_inline bool in_irq_stack(unsigned long *stack, struct stack_info *info) { - unsigned long *end = (unsigned long *)this_cpu_read(hardirq_stack_ptr); - unsigned long *begin = end - (IRQ_STACK_SIZE / sizeof(long)); + unsigned long *end = (unsigned long *)this_cpu_read(hardirq_stack_ptr); + unsigned long *begin; /* - * This is a software stack, so 'end' can be a valid stack pointer. - * It just means the stack is empty. + * @end points directly to the top most stack entry to avoid a -8 + * adjustment in the stack switch hotpath. Adjust it back before + * calculating @begin. + */ + end++; + begin = end - (IRQ_STACK_SIZE / sizeof(long)); + + /* + * Due to the switching logic RSP can never be == @end because the + * final operation is 'popq %rsp' which means after that RSP points + * to the original stack and not to @end. */ if (stack < begin || stack >= end) return false; @@ -143,8 +152,9 @@ static __always_inline bool in_irq_stack(unsigned long *stack, struct stack_info info->end = end; /* - * The next stack pointer is the first thing pushed by the entry code - * after switching to the irq stack. + * The next stack pointer is stored at the top of the irq stack + * before switching to the irq stack. Actual stack entries are all + * below that. */ info->next_sp = (unsigned long *)*(end - 1); diff --git a/arch/x86/kernel/fpu/xstate.c b/arch/x86/kernel/fpu/xstate.c index 5d8047441a0a..683749b80ae2 100644 --- a/arch/x86/kernel/fpu/xstate.c +++ b/arch/x86/kernel/fpu/xstate.c @@ -167,14 +167,14 @@ void fpstate_sanitize_xstate(struct fpu *fpu) fx->fop = 0; fx->rip = 0; fx->rdp = 0; - memset(&fx->st_space[0], 0, 128); + memset(fx->st_space, 0, sizeof(fx->st_space)); } /* * SSE is in init state */ if (!(xfeatures & XFEATURE_MASK_SSE)) - memset(&fx->xmm_space[0], 0, 256); + memset(fx->xmm_space, 0, sizeof(fx->xmm_space)); /* * First two features are FPU and SSE, which above we handled diff --git a/arch/x86/kernel/ftrace_64.S b/arch/x86/kernel/ftrace_64.S index 0d54099c2a3a..7c273846c687 100644 --- a/arch/x86/kernel/ftrace_64.S +++ b/arch/x86/kernel/ftrace_64.S @@ -184,6 +184,7 @@ SYM_INNER_LABEL(ftrace_graph_call, SYM_L_GLOBAL) * It is also used to copy the retq for trampolines. */ SYM_INNER_LABEL_ALIGN(ftrace_stub, SYM_L_WEAK) + UNWIND_HINT_FUNC retq SYM_FUNC_END(ftrace_epilogue) @@ -276,7 +277,7 @@ SYM_INNER_LABEL(ftrace_regs_caller_end, SYM_L_GLOBAL) restore_mcount_regs 8 /* Restore flags */ popfq - UNWIND_HINT_RET_OFFSET + UNWIND_HINT_FUNC jmp ftrace_epilogue SYM_FUNC_END(ftrace_regs_caller) @@ -333,8 +334,7 @@ SYM_FUNC_START(ftrace_graph_caller) retq SYM_FUNC_END(ftrace_graph_caller) -SYM_CODE_START(return_to_handler) - UNWIND_HINT_EMPTY +SYM_FUNC_START(return_to_handler) subq $24, %rsp /* Save the return values */ @@ -349,5 +349,5 @@ SYM_CODE_START(return_to_handler) movq (%rsp), %rax addq $24, %rsp JMP_NOSPEC rdi -SYM_CODE_END(return_to_handler) +SYM_FUNC_END(return_to_handler) #endif diff --git a/arch/x86/kernel/irq.c b/arch/x86/kernel/irq.c index c5dd50369e2f..58aa712973ac 100644 --- a/arch/x86/kernel/irq.c +++ b/arch/x86/kernel/irq.c @@ -21,6 +21,7 @@ #include <asm/hw_irq.h> #include <asm/desc.h> #include <asm/traps.h> +#include <asm/thermal.h> #define CREATE_TRACE_POINTS #include <asm/trace/irq_vectors.h> @@ -227,7 +228,7 @@ static __always_inline void handle_irq(struct irq_desc *desc, struct pt_regs *regs) { if (IS_ENABLED(CONFIG_X86_64)) - run_irq_on_irqstack_cond(desc->handle_irq, desc, regs); + generic_handle_irq_desc(desc); else __handle_irq(desc, regs); } @@ -374,3 +375,23 @@ void fixup_irqs(void) } } #endif + +#ifdef CONFIG_X86_THERMAL_VECTOR +static void smp_thermal_vector(void) +{ + if (x86_thermal_enabled()) + intel_thermal_interrupt(); + else + pr_err("CPU%d: Unexpected LVT thermal interrupt!\n", + smp_processor_id()); +} + +DEFINE_IDTENTRY_SYSVEC(sysvec_thermal) +{ + trace_thermal_apic_entry(THERMAL_APIC_VECTOR); + inc_irq_stat(irq_thermal_count); + smp_thermal_vector(); + trace_thermal_apic_exit(THERMAL_APIC_VECTOR); + ack_APIC_irq(); +} +#endif diff --git a/arch/x86/kernel/irq_32.c b/arch/x86/kernel/irq_32.c index 0b79efc87be5..044902d5a3c4 100644 --- a/arch/x86/kernel/irq_32.c +++ b/arch/x86/kernel/irq_32.c @@ -22,6 +22,7 @@ #include <asm/apic.h> #include <asm/nospec-branch.h> +#include <asm/softirq_stack.h> #ifdef CONFIG_DEBUG_STACKOVERFLOW diff --git a/arch/x86/kernel/irq_64.c b/arch/x86/kernel/irq_64.c index 440eed558558..1c0fb96b9e39 100644 --- a/arch/x86/kernel/irq_64.c +++ b/arch/x86/kernel/irq_64.c @@ -20,6 +20,7 @@ #include <linux/sched/task_stack.h> #include <asm/cpu_entry_area.h> +#include <asm/softirq_stack.h> #include <asm/irq_stack.h> #include <asm/io_apic.h> #include <asm/apic.h> @@ -48,7 +49,8 @@ static int map_irq_stack(unsigned int cpu) if (!va) return -ENOMEM; - per_cpu(hardirq_stack_ptr, cpu) = va + IRQ_STACK_SIZE; + /* Store actual TOS to avoid adjustment in the hotpath */ + per_cpu(hardirq_stack_ptr, cpu) = va + IRQ_STACK_SIZE - 8; return 0; } #else @@ -60,7 +62,8 @@ static int map_irq_stack(unsigned int cpu) { void *va = per_cpu_ptr(&irq_stack_backing_store, cpu); - per_cpu(hardirq_stack_ptr, cpu) = va + IRQ_STACK_SIZE; + /* Store actual TOS to avoid adjustment in the hotpath */ + per_cpu(hardirq_stack_ptr, cpu) = va + IRQ_STACK_SIZE - 8; return 0; } #endif @@ -71,8 +74,3 @@ int irq_init_percpu_irqstack(unsigned int cpu) return 0; return map_irq_stack(cpu); } - -void do_softirq_own_stack(void) -{ - run_on_irqstack_cond(__do_softirq, NULL); -} diff --git a/arch/x86/kernel/irqflags.S b/arch/x86/kernel/irqflags.S index 0db0375235b4..8ef35063964b 100644 --- a/arch/x86/kernel/irqflags.S +++ b/arch/x86/kernel/irqflags.S @@ -13,14 +13,3 @@ SYM_FUNC_START(native_save_fl) ret SYM_FUNC_END(native_save_fl) EXPORT_SYMBOL(native_save_fl) - -/* - * void native_restore_fl(unsigned long flags) - * %eax/%rdi: flags - */ -SYM_FUNC_START(native_restore_fl) - push %_ASM_ARG1 - popf - ret -SYM_FUNC_END(native_restore_fl) -EXPORT_SYMBOL(native_restore_fl) diff --git a/arch/x86/kernel/kprobes/core.c b/arch/x86/kernel/kprobes/core.c index a65e9e97857f..df776cdca327 100644 --- a/arch/x86/kernel/kprobes/core.c +++ b/arch/x86/kernel/kprobes/core.c @@ -133,26 +133,6 @@ void synthesize_relcall(void *dest, void *from, void *to) NOKPROBE_SYMBOL(synthesize_relcall); /* - * Skip the prefixes of the instruction. - */ -static kprobe_opcode_t *skip_prefixes(kprobe_opcode_t *insn) -{ - insn_attr_t attr; - - attr = inat_get_opcode_attribute((insn_byte_t)*insn); - while (inat_is_legacy_prefix(attr)) { - insn++; - attr = inat_get_opcode_attribute((insn_byte_t)*insn); - } -#ifdef CONFIG_X86_64 - if (inat_is_rex_prefix(attr)) - insn++; -#endif - return insn; -} -NOKPROBE_SYMBOL(skip_prefixes); - -/* * Returns non-zero if INSN is boostable. * RIP relative instructions are adjusted at copying time in 64 bits mode */ @@ -312,25 +292,6 @@ static int can_probe(unsigned long paddr) } /* - * Returns non-zero if opcode modifies the interrupt flag. - */ -static int is_IF_modifier(kprobe_opcode_t *insn) -{ - /* Skip prefixes */ - insn = skip_prefixes(insn); - - switch (*insn) { - case 0xfa: /* cli */ - case 0xfb: /* sti */ - case 0xcf: /* iret/iretd */ - case 0x9d: /* popf/popfd */ - return 1; - } - - return 0; -} - -/* * Copy an instruction with recovering modified instruction by kprobes * and adjust the displacement if the instruction uses the %rip-relative * addressing mode. Note that since @real will be the final place of copied @@ -411,9 +372,9 @@ static int prepare_boost(kprobe_opcode_t *buf, struct kprobe *p, synthesize_reljump(buf + len, p->ainsn.insn + len, p->addr + insn->length); len += JMP32_INSN_SIZE; - p->ainsn.boostable = true; + p->ainsn.boostable = 1; } else { - p->ainsn.boostable = false; + p->ainsn.boostable = 0; } return len; @@ -450,6 +411,67 @@ void free_insn_page(void *page) module_memfree(page); } +static void set_resume_flags(struct kprobe *p, struct insn *insn) +{ + insn_byte_t opcode = insn->opcode.bytes[0]; + + switch (opcode) { + case 0xfa: /* cli */ + case 0xfb: /* sti */ + case 0x9d: /* popf/popfd */ + /* Check whether the instruction modifies Interrupt Flag or not */ + p->ainsn.if_modifier = 1; + break; + case 0x9c: /* pushfl */ + p->ainsn.is_pushf = 1; + break; + case 0xcf: /* iret */ + p->ainsn.if_modifier = 1; + fallthrough; + case 0xc2: /* ret/lret */ + case 0xc3: + case 0xca: + case 0xcb: + case 0xea: /* jmp absolute -- ip is correct */ + /* ip is already adjusted, no more changes required */ + p->ainsn.is_abs_ip = 1; + /* Without resume jump, this is boostable */ + p->ainsn.boostable = 1; + break; + case 0xe8: /* call relative - Fix return addr */ + p->ainsn.is_call = 1; + break; +#ifdef CONFIG_X86_32 + case 0x9a: /* call absolute -- same as call absolute, indirect */ + p->ainsn.is_call = 1; + p->ainsn.is_abs_ip = 1; + break; +#endif + case 0xff: + opcode = insn->opcode.bytes[1]; + if ((opcode & 0x30) == 0x10) { + /* + * call absolute, indirect + * Fix return addr; ip is correct. + * But this is not boostable + */ + p->ainsn.is_call = 1; + p->ainsn.is_abs_ip = 1; + break; + } else if (((opcode & 0x31) == 0x20) || + ((opcode & 0x31) == 0x21)) { + /* + * jmp near and far, absolute indirect + * ip is correct. + */ + p->ainsn.is_abs_ip = 1; + /* Without resume jump, this is boostable */ + p->ainsn.boostable = 1; + } + break; + } +} + static int arch_copy_kprobe(struct kprobe *p) { struct insn insn; @@ -467,8 +489,8 @@ static int arch_copy_kprobe(struct kprobe *p) */ len = prepare_boost(buf, p, &insn); - /* Check whether the instruction modifies Interrupt Flag or not */ - p->ainsn.if_modifier = is_IF_modifier(buf); + /* Analyze the opcode and set resume flags */ + set_resume_flags(p, &insn); /* Also, displacement change doesn't affect the first byte */ p->opcode = buf[0]; @@ -491,6 +513,9 @@ int arch_prepare_kprobe(struct kprobe *p) if (!can_probe((unsigned long)p->addr)) return -EILSEQ; + + memset(&p->ainsn, 0, sizeof(p->ainsn)); + /* insn: must be on special executable page on x86. */ p->ainsn.insn = get_insn_slot(); if (!p->ainsn.insn) @@ -806,11 +831,6 @@ NOKPROBE_SYMBOL(trampoline_handler); * 2) If the single-stepped instruction was a call, the return address * that is atop the stack is the address following the copied instruction. * We need to make it the address following the original instruction. - * - * If this is the first time we've single-stepped the instruction at - * this probepoint, and the instruction is boostable, boost it: add a - * jump instruction after the copied instruction, that jumps to the next - * instruction after the probepoint. */ static void resume_execution(struct kprobe *p, struct pt_regs *regs, struct kprobe_ctlblk *kcb) @@ -818,60 +838,20 @@ static void resume_execution(struct kprobe *p, struct pt_regs *regs, unsigned long *tos = stack_addr(regs); unsigned long copy_ip = (unsigned long)p->ainsn.insn; unsigned long orig_ip = (unsigned long)p->addr; - kprobe_opcode_t *insn = p->ainsn.insn; - - /* Skip prefixes */ - insn = skip_prefixes(insn); regs->flags &= ~X86_EFLAGS_TF; - switch (*insn) { - case 0x9c: /* pushfl */ + + /* Fixup the contents of top of stack */ + if (p->ainsn.is_pushf) { *tos &= ~(X86_EFLAGS_TF | X86_EFLAGS_IF); *tos |= kcb->kprobe_old_flags; - break; - case 0xc2: /* iret/ret/lret */ - case 0xc3: - case 0xca: - case 0xcb: - case 0xcf: - case 0xea: /* jmp absolute -- ip is correct */ - /* ip is already adjusted, no more changes required */ - p->ainsn.boostable = true; - goto no_change; - case 0xe8: /* call relative - Fix return addr */ + } else if (p->ainsn.is_call) { *tos = orig_ip + (*tos - copy_ip); - break; -#ifdef CONFIG_X86_32 - case 0x9a: /* call absolute -- same as call absolute, indirect */ - *tos = orig_ip + (*tos - copy_ip); - goto no_change; -#endif - case 0xff: - if ((insn[1] & 0x30) == 0x10) { - /* - * call absolute, indirect - * Fix return addr; ip is correct. - * But this is not boostable - */ - *tos = orig_ip + (*tos - copy_ip); - goto no_change; - } else if (((insn[1] & 0x31) == 0x20) || - ((insn[1] & 0x31) == 0x21)) { - /* - * jmp near and far, absolute indirect - * ip is correct. And this is boostable - */ - p->ainsn.boostable = true; - goto no_change; - } - break; - default: - break; } - regs->ip += orig_ip - copy_ip; + if (!p->ainsn.is_abs_ip) + regs->ip += orig_ip - copy_ip; -no_change: restore_btf(); } NOKPROBE_SYMBOL(resume_execution); diff --git a/arch/x86/kernel/kprobes/ftrace.c b/arch/x86/kernel/kprobes/ftrace.c index 373e5fa3ce1f..51c7f5271aee 100644 --- a/arch/x86/kernel/kprobes/ftrace.c +++ b/arch/x86/kernel/kprobes/ftrace.c @@ -12,7 +12,7 @@ #include "common.h" -/* Ftrace callback handler for kprobes -- called under preepmt disabed */ +/* Ftrace callback handler for kprobes -- called under preepmt disabled */ void kprobe_ftrace_handler(unsigned long ip, unsigned long parent_ip, struct ftrace_ops *ops, struct ftrace_regs *fregs) { diff --git a/arch/x86/kernel/kvm.c b/arch/x86/kernel/kvm.c index 5e78e01ca3b4..78bb0fae3982 100644 --- a/arch/x86/kernel/kvm.c +++ b/arch/x86/kernel/kvm.c @@ -836,28 +836,25 @@ static void kvm_kick_cpu(int cpu) static void kvm_wait(u8 *ptr, u8 val) { - unsigned long flags; - if (in_nmi()) return; - local_irq_save(flags); - - if (READ_ONCE(*ptr) != val) - goto out; - /* * halt until it's our turn and kicked. Note that we do safe halt * for irq enabled case to avoid hang when lock info is overwritten * in irq spinlock slowpath and no spurious interrupt occur to save us. */ - if (arch_irqs_disabled_flags(flags)) - halt(); - else - safe_halt(); + if (irqs_disabled()) { + if (READ_ONCE(*ptr) == val) + halt(); + } else { + local_irq_disable(); -out: - local_irq_restore(flags); + if (READ_ONCE(*ptr) == val) + safe_halt(); + + local_irq_enable(); + } } #ifdef CONFIG_X86_32 diff --git a/arch/x86/kernel/kvmclock.c b/arch/x86/kernel/kvmclock.c index aa593743acf6..1fc0962c89c0 100644 --- a/arch/x86/kernel/kvmclock.c +++ b/arch/x86/kernel/kvmclock.c @@ -268,21 +268,20 @@ static void __init kvmclock_init_mem(void) static int __init kvm_setup_vsyscall_timeinfo(void) { -#ifdef CONFIG_X86_64 - u8 flags; + kvmclock_init_mem(); - if (!per_cpu(hv_clock_per_cpu, 0) || !kvmclock_vsyscall) - return 0; +#ifdef CONFIG_X86_64 + if (per_cpu(hv_clock_per_cpu, 0) && kvmclock_vsyscall) { + u8 flags; - flags = pvclock_read_flags(&hv_clock_boot[0].pvti); - if (!(flags & PVCLOCK_TSC_STABLE_BIT)) - return 0; + flags = pvclock_read_flags(&hv_clock_boot[0].pvti); + if (!(flags & PVCLOCK_TSC_STABLE_BIT)) + return 0; - kvm_clock.vdso_clock_mode = VDSO_CLOCKMODE_PVCLOCK; + kvm_clock.vdso_clock_mode = VDSO_CLOCKMODE_PVCLOCK; + } #endif - kvmclock_init_mem(); - return 0; } early_initcall(kvm_setup_vsyscall_timeinfo); diff --git a/arch/x86/kernel/ldt.c b/arch/x86/kernel/ldt.c index b8aee71840ae..aa15132228da 100644 --- a/arch/x86/kernel/ldt.c +++ b/arch/x86/kernel/ldt.c @@ -398,9 +398,15 @@ static void free_ldt_pgtables(struct mm_struct *mm) if (!boot_cpu_has(X86_FEATURE_PTI)) return; - tlb_gather_mmu(&tlb, mm, start, end); + /* + * Although free_pgd_range() is intended for freeing user + * page-tables, it also works out for kernel mappings on x86. + * We use tlb_gather_mmu_fullmm() to avoid confusing the + * range-tracking logic in __tlb_adjust_range(). + */ + tlb_gather_mmu_fullmm(&tlb, mm); free_pgd_range(&tlb, start, end, start, end); - tlb_finish_mmu(&tlb, start, end); + tlb_finish_mmu(&tlb); #endif } diff --git a/arch/x86/kernel/module.c b/arch/x86/kernel/module.c index 34b153cbd4ac..5e9a34b5bd74 100644 --- a/arch/x86/kernel/module.c +++ b/arch/x86/kernel/module.c @@ -114,6 +114,7 @@ int apply_relocate(Elf32_Shdr *sechdrs, *location += sym->st_value; break; case R_386_PC32: + case R_386_PLT32: /* Add the value, subtract its position */ *location += sym->st_value - (uint32_t)location; break; diff --git a/arch/x86/kernel/msr.c b/arch/x86/kernel/msr.c index 8a67d1fa8dc5..ed8ac6bcbafb 100644 --- a/arch/x86/kernel/msr.c +++ b/arch/x86/kernel/msr.c @@ -182,6 +182,13 @@ static long msr_ioctl(struct file *file, unsigned int ioc, unsigned long arg) err = security_locked_down(LOCKDOWN_MSR); if (err) break; + + err = filter_write(regs[1]); + if (err) + return err; + + add_taint(TAINT_CPU_OUT_OF_SPEC, LOCKDEP_STILL_OK); + err = wrmsr_safe_regs_on_cpu(cpu, regs); if (err) break; diff --git a/arch/x86/kernel/paravirt.c b/arch/x86/kernel/paravirt.c index 6c3407ba6ee9..c60222ab8ab9 100644 --- a/arch/x86/kernel/paravirt.c +++ b/arch/x86/kernel/paravirt.c @@ -135,8 +135,7 @@ unsigned paravirt_patch_default(u8 type, void *insn_buff, else if (opfunc == _paravirt_ident_64) ret = paravirt_patch_ident_64(insn_buff, len); - else if (type == PARAVIRT_PATCH(cpu.iret) || - type == PARAVIRT_PATCH(cpu.usergs_sysret64)) + else if (type == PARAVIRT_PATCH(cpu.iret)) /* If operation requires a jmp, then jmp */ ret = paravirt_patch_jmp(insn_buff, opfunc, addr, len); #endif @@ -170,7 +169,6 @@ static u64 native_steal_clock(int cpu) /* These are in entry.S */ extern void native_iret(void); -extern void native_usergs_sysret64(void); static struct resource reserve_ioports = { .start = 0, @@ -310,9 +308,7 @@ struct paravirt_patch_template pv_ops = { .cpu.load_sp0 = native_load_sp0, - .cpu.usergs_sysret64 = native_usergs_sysret64, .cpu.iret = native_iret, - .cpu.swapgs = native_swapgs, #ifdef CONFIG_X86_IOPL_IOPERM .cpu.invalidate_io_bitmap = native_tss_invalidate_io_bitmap, @@ -324,7 +320,6 @@ struct paravirt_patch_template pv_ops = { /* Irq ops. */ .irq.save_fl = __PV_IS_CALLEE_SAVE(native_save_fl), - .irq.restore_fl = __PV_IS_CALLEE_SAVE(native_restore_fl), .irq.irq_disable = __PV_IS_CALLEE_SAVE(native_irq_disable), .irq.irq_enable = __PV_IS_CALLEE_SAVE(native_irq_enable), .irq.safe_halt = native_safe_halt, diff --git a/arch/x86/kernel/paravirt_patch.c b/arch/x86/kernel/paravirt_patch.c index ace6e334cb39..abd27ec67397 100644 --- a/arch/x86/kernel/paravirt_patch.c +++ b/arch/x86/kernel/paravirt_patch.c @@ -25,10 +25,7 @@ struct patch_xxl { const unsigned char mmu_read_cr2[3]; const unsigned char mmu_read_cr3[3]; const unsigned char mmu_write_cr3[3]; - const unsigned char irq_restore_fl[2]; const unsigned char cpu_wbinvd[2]; - const unsigned char cpu_usergs_sysret64[6]; - const unsigned char cpu_swapgs[3]; const unsigned char mov64[3]; }; @@ -39,11 +36,7 @@ static const struct patch_xxl patch_data_xxl = { .mmu_read_cr2 = { 0x0f, 0x20, 0xd0 }, // mov %cr2, %[re]ax .mmu_read_cr3 = { 0x0f, 0x20, 0xd8 }, // mov %cr3, %[re]ax .mmu_write_cr3 = { 0x0f, 0x22, 0xdf }, // mov %rdi, %cr3 - .irq_restore_fl = { 0x57, 0x9d }, // push %rdi; popfq .cpu_wbinvd = { 0x0f, 0x09 }, // wbinvd - .cpu_usergs_sysret64 = { 0x0f, 0x01, 0xf8, - 0x48, 0x0f, 0x07 }, // swapgs; sysretq - .cpu_swapgs = { 0x0f, 0x01, 0xf8 }, // swapgs .mov64 = { 0x48, 0x89, 0xf8 }, // mov %rdi, %rax }; @@ -76,7 +69,6 @@ unsigned int native_patch(u8 type, void *insn_buff, unsigned long addr, switch (type) { #ifdef CONFIG_PARAVIRT_XXL - PATCH_CASE(irq, restore_fl, xxl, insn_buff, len); PATCH_CASE(irq, save_fl, xxl, insn_buff, len); PATCH_CASE(irq, irq_enable, xxl, insn_buff, len); PATCH_CASE(irq, irq_disable, xxl, insn_buff, len); @@ -85,8 +77,6 @@ unsigned int native_patch(u8 type, void *insn_buff, unsigned long addr, PATCH_CASE(mmu, read_cr3, xxl, insn_buff, len); PATCH_CASE(mmu, write_cr3, xxl, insn_buff, len); - PATCH_CASE(cpu, usergs_sysret64, xxl, insn_buff, len); - PATCH_CASE(cpu, swapgs, xxl, insn_buff, len); PATCH_CASE(cpu, wbinvd, xxl, insn_buff, len); #endif diff --git a/arch/x86/kernel/pci-iommu_table.c b/arch/x86/kernel/pci-iommu_table.c index 2e9006c1e240..42e92ec62973 100644 --- a/arch/x86/kernel/pci-iommu_table.c +++ b/arch/x86/kernel/pci-iommu_table.c @@ -4,9 +4,6 @@ #include <linux/string.h> #include <linux/kallsyms.h> - -#define DEBUG 1 - static struct iommu_table_entry * __init find_dependents_of(struct iommu_table_entry *start, struct iommu_table_entry *finish, diff --git a/arch/x86/kernel/process.c b/arch/x86/kernel/process.c index 145a7ac0c19a..9c214d7085a4 100644 --- a/arch/x86/kernel/process.c +++ b/arch/x86/kernel/process.c @@ -161,7 +161,7 @@ int copy_thread(unsigned long clone_flags, unsigned long sp, unsigned long arg, #endif /* Kernel thread ? */ - if (unlikely(p->flags & PF_KTHREAD)) { + if (unlikely(p->flags & (PF_KTHREAD | PF_IO_WORKER))) { memset(childregs, 0, sizeof(struct pt_regs)); kthread_frame_init(frame, sp, arg); return 0; diff --git a/arch/x86/kernel/process_64.c b/arch/x86/kernel/process_64.c index ad582f9ac5a6..d08307df69ad 100644 --- a/arch/x86/kernel/process_64.c +++ b/arch/x86/kernel/process_64.c @@ -539,7 +539,7 @@ __switch_to(struct task_struct *prev_p, struct task_struct *next_p) int cpu = smp_processor_id(); WARN_ON_ONCE(IS_ENABLED(CONFIG_DEBUG_ENTRY) && - this_cpu_read(irq_count) != -1); + this_cpu_read(hardirq_stack_inuse)); if (!test_thread_flag(TIF_NEED_FPU_LOAD)) switch_fpu_prepare(prev_fpu, cpu); diff --git a/arch/x86/kernel/ptrace.c b/arch/x86/kernel/ptrace.c index bedca011459c..87a4143aa7d7 100644 --- a/arch/x86/kernel/ptrace.c +++ b/arch/x86/kernel/ptrace.c @@ -704,6 +704,9 @@ void ptrace_disable(struct task_struct *child) #if defined CONFIG_X86_32 || defined CONFIG_IA32_EMULATION static const struct user_regset_view user_x86_32_view; /* Initialized below. */ #endif +#ifdef CONFIG_X86_64 +static const struct user_regset_view user_x86_64_view; /* Initialized below. */ +#endif long arch_ptrace(struct task_struct *child, long request, unsigned long addr, unsigned long data) @@ -711,6 +714,14 @@ long arch_ptrace(struct task_struct *child, long request, int ret; unsigned long __user *datap = (unsigned long __user *)data; +#ifdef CONFIG_X86_64 + /* This is native 64-bit ptrace() */ + const struct user_regset_view *regset_view = &user_x86_64_view; +#else + /* This is native 32-bit ptrace() */ + const struct user_regset_view *regset_view = &user_x86_32_view; +#endif + switch (request) { /* read the word at location addr in the USER area. */ case PTRACE_PEEKUSR: { @@ -749,28 +760,28 @@ long arch_ptrace(struct task_struct *child, long request, case PTRACE_GETREGS: /* Get all gp regs from the child. */ return copy_regset_to_user(child, - task_user_regset_view(current), + regset_view, 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_view, 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_view, 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_view, REGSET_FP, 0, sizeof(struct user_i387_struct), datap); @@ -1152,28 +1163,28 @@ static long x32_arch_ptrace(struct task_struct *child, case PTRACE_GETREGS: /* Get all gp regs from the child. */ return copy_regset_to_user(child, - task_user_regset_view(current), + &user_x86_64_view, 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), + &user_x86_64_view, 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), + &user_x86_64_view, 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), + &user_x86_64_view, REGSET_FP, 0, sizeof(struct user_i387_struct), datap); @@ -1309,6 +1320,25 @@ void __init update_regset_xstate_info(unsigned int size, u64 xstate_mask) xstate_fx_sw_bytes[USER_XSTATE_XCR0_WORD] = xstate_mask; } +/* + * This is used by the core dump code to decide which regset to dump. The + * core dump code writes out the resulting .e_machine and the corresponding + * regsets. This is suboptimal if the task is messing around with its CS.L + * field, but at worst the core dump will end up missing some information. + * + * Unfortunately, it is also used by the broken PTRACE_GETREGSET and + * PTRACE_SETREGSET APIs. These APIs look at the .regsets field but have + * no way to make sure that the e_machine they use matches the caller's + * expectations. The result is that the data format returned by + * PTRACE_GETREGSET depends on the returned CS field (and even the offset + * of the returned CS field depends on its value!) and the data format + * accepted by PTRACE_SETREGSET is determined by the old CS value. The + * upshot is that it is basically impossible to use these APIs correctly. + * + * The best way to fix it in the long run would probably be to add new + * improved ptrace() APIs to read and write registers reliably, possibly by + * allowing userspace to select the ELF e_machine variant that they expect. + */ const struct user_regset_view *task_user_regset_view(struct task_struct *task) { #ifdef CONFIG_IA32_EMULATION diff --git a/arch/x86/kernel/reboot.c b/arch/x86/kernel/reboot.c index db115943e8bd..b29657b76e3f 100644 --- a/arch/x86/kernel/reboot.c +++ b/arch/x86/kernel/reboot.c @@ -477,6 +477,15 @@ static const struct dmi_system_id reboot_dmi_table[] __initconst = { }, }, + { /* PCIe Wifi card isn't detected after reboot otherwise */ + .callback = set_pci_reboot, + .ident = "Zotac ZBOX CI327 nano", + .matches = { + DMI_MATCH(DMI_SYS_VENDOR, "NA"), + DMI_MATCH(DMI_PRODUCT_NAME, "ZBOX-CI327NANO-GS-01"), + }, + }, + /* Sony */ { /* Handle problems with rebooting on Sony VGN-Z540N */ .callback = set_bios_reboot, @@ -538,31 +547,21 @@ static void emergency_vmx_disable_all(void) local_irq_disable(); /* - * We need to disable VMX on all CPUs before rebooting, otherwise - * we risk hanging up the machine, because the CPU ignores INIT - * signals when VMX is enabled. - * - * We can't take any locks and we may be on an inconsistent - * state, so we use NMIs as IPIs to tell the other CPUs to disable - * VMX and halt. + * Disable VMX on all CPUs before rebooting, otherwise we risk hanging + * the machine, because the CPU blocks INIT when it's in VMX root. * - * For safety, we will avoid running the nmi_shootdown_cpus() - * stuff unnecessarily, but we don't have a way to check - * if other CPUs have VMX enabled. So we will call it only if the - * CPU we are running on has VMX enabled. + * We can't take any locks and we may be on an inconsistent state, so + * use NMIs as IPIs to tell the other CPUs to exit VMX root and halt. * - * We will miss cases where VMX is not enabled on all CPUs. This - * shouldn't do much harm because KVM always enable VMX on all - * CPUs anyway. But we can miss it on the small window where KVM - * is still enabling VMX. + * Do the NMI shootdown even if VMX if off on _this_ CPU, as that + * doesn't prevent a different CPU from being in VMX root operation. */ - if (cpu_has_vmx() && cpu_vmx_enabled()) { - /* Disable VMX on this CPU. */ - cpu_vmxoff(); + if (cpu_has_vmx()) { + /* Safely force _this_ CPU out of VMX root operation. */ + __cpu_emergency_vmxoff(); - /* Halt and disable VMX on the other CPUs */ + /* Halt and exit VMX root operation on the other CPUs. */ nmi_shootdown_cpus(vmxoff_nmi); - } } diff --git a/arch/x86/kernel/setup.c b/arch/x86/kernel/setup.c index 740f3bdb3f61..d883176ef2ce 100644 --- a/arch/x86/kernel/setup.c +++ b/arch/x86/kernel/setup.c @@ -16,7 +16,6 @@ #include <linux/memblock.h> #include <linux/pci.h> #include <linux/root_dev.h> -#include <linux/sfi.h> #include <linux/hugetlb.h> #include <linux/tboot.h> #include <linux/usb/xhci-dbgp.h> @@ -1185,7 +1184,6 @@ void __init setup_arch(char **cmdline_p) * Read APIC and some other early information from ACPI tables. */ acpi_boot_init(); - sfi_init(); x86_dtb_init(); /* diff --git a/arch/x86/kernel/sev-es.c b/arch/x86/kernel/sev-es.c index 84c1821819af..04a780abb512 100644 --- a/arch/x86/kernel/sev-es.c +++ b/arch/x86/kernel/sev-es.c @@ -121,8 +121,18 @@ static void __init setup_vc_stacks(int cpu) cea_set_pte((void *)vaddr, pa, PAGE_KERNEL); } -static __always_inline bool on_vc_stack(unsigned long sp) +static __always_inline bool on_vc_stack(struct pt_regs *regs) { + unsigned long sp = regs->sp; + + /* User-mode RSP is not trusted */ + if (user_mode(regs)) + return false; + + /* SYSCALL gap still has user-mode RSP */ + if (ip_within_syscall_gap(regs)) + return false; + return ((sp >= __this_cpu_ist_bottom_va(VC)) && (sp < __this_cpu_ist_top_va(VC))); } @@ -144,7 +154,7 @@ void noinstr __sev_es_ist_enter(struct pt_regs *regs) old_ist = __this_cpu_read(cpu_tss_rw.x86_tss.ist[IST_INDEX_VC]); /* Make room on the IST stack */ - if (on_vc_stack(regs->sp)) + if (on_vc_stack(regs)) new_ist = ALIGN_DOWN(regs->sp, 8) - sizeof(old_ist); else new_ist = old_ist - sizeof(old_ist); @@ -248,7 +258,7 @@ static enum es_result vc_decode_insn(struct es_em_ctxt *ctxt) int res; if (user_mode(ctxt->regs)) { - res = insn_fetch_from_user(ctxt->regs, buffer); + res = insn_fetch_from_user_inatomic(ctxt->regs, buffer); if (!res) { ctxt->fi.vector = X86_TRAP_PF; ctxt->fi.error_code = X86_PF_INSTR | X86_PF_USER; @@ -1248,13 +1258,12 @@ static __always_inline bool on_vc_fallback_stack(struct pt_regs *regs) DEFINE_IDTENTRY_VC_SAFE_STACK(exc_vmm_communication) { struct sev_es_runtime_data *data = this_cpu_read(runtime_data); + irqentry_state_t irq_state; struct ghcb_state state; struct es_em_ctxt ctxt; enum es_result result; struct ghcb *ghcb; - lockdep_assert_irqs_disabled(); - /* * Handle #DB before calling into !noinstr code to avoid recursive #DB. */ @@ -1263,6 +1272,8 @@ DEFINE_IDTENTRY_VC_SAFE_STACK(exc_vmm_communication) return; } + irq_state = irqentry_nmi_enter(regs); + lockdep_assert_irqs_disabled(); instrumentation_begin(); /* @@ -1325,6 +1336,7 @@ DEFINE_IDTENTRY_VC_SAFE_STACK(exc_vmm_communication) out: instrumentation_end(); + irqentry_nmi_exit(regs, irq_state); return; diff --git a/arch/x86/kernel/signal.c b/arch/x86/kernel/signal.c index ea794a083c44..f306e85a08a6 100644 --- a/arch/x86/kernel/signal.c +++ b/arch/x86/kernel/signal.c @@ -766,30 +766,8 @@ handle_signal(struct ksignal *ksig, struct pt_regs *regs) static inline unsigned long get_nr_restart_syscall(const struct pt_regs *regs) { - /* - * This function is fundamentally broken as currently - * implemented. - * - * The idea is that we want to trigger a call to the - * restart_block() syscall and that we want in_ia32_syscall(), - * in_x32_syscall(), etc. to match whatever they were in the - * syscall being restarted. We assume that the syscall - * instruction at (regs->ip - 2) matches whatever syscall - * instruction we used to enter in the first place. - * - * The problem is that we can get here when ptrace pokes - * syscall-like values into regs even if we're not in a syscall - * at all. - * - * For now, we maintain historical behavior and guess based on - * stored state. We could do better by saving the actual - * syscall arch in restart_block or (with caveats on x32) by - * checking if regs->ip points to 'int $0x80'. The current - * behavior is incorrect if a tracer has a different bitness - * than the tracee. - */ #ifdef CONFIG_IA32_EMULATION - if (current_thread_info()->status & (TS_COMPAT|TS_I386_REGS_POKED)) + if (current->restart_block.arch_data & TS_COMPAT) return __NR_ia32_restart_syscall; #endif #ifdef CONFIG_X86_X32_ABI diff --git a/arch/x86/kernel/static_call.c b/arch/x86/kernel/static_call.c index ca9a380d9c0b..9442c4136c38 100644 --- a/arch/x86/kernel/static_call.c +++ b/arch/x86/kernel/static_call.c @@ -11,14 +11,26 @@ enum insn_type { RET = 3, /* tramp / site cond-tail-call */ }; +/* + * data16 data16 xorq %rax, %rax - a single 5 byte instruction that clears %rax + * The REX.W cancels the effect of any data16. + */ +static const u8 xor5rax[] = { 0x66, 0x66, 0x48, 0x31, 0xc0 }; + static void __ref __static_call_transform(void *insn, enum insn_type type, void *func) { + const void *emulate = NULL; int size = CALL_INSN_SIZE; const void *code; switch (type) { case CALL: code = text_gen_insn(CALL_INSN_OPCODE, insn, func); + if (func == &__static_call_return0) { + emulate = code; + code = &xor5rax; + } + break; case NOP: @@ -41,7 +53,7 @@ static void __ref __static_call_transform(void *insn, enum insn_type type, void if (unlikely(system_state == SYSTEM_BOOTING)) return text_poke_early(insn, code, size); - text_poke_bp(insn, code, size, NULL); + text_poke_bp(insn, code, size, emulate); } static void __static_call_validate(void *insn, bool tail) @@ -54,7 +66,8 @@ static void __static_call_validate(void *insn, bool tail) return; } else { if (opcode == CALL_INSN_OPCODE || - !memcmp(insn, ideal_nops[NOP_ATOMIC5], 5)) + !memcmp(insn, ideal_nops[NOP_ATOMIC5], 5) || + !memcmp(insn, xor5rax, 5)) return; } diff --git a/arch/x86/kernel/sys_x86_64.c b/arch/x86/kernel/sys_x86_64.c index 504fa5425bce..660b78827638 100644 --- a/arch/x86/kernel/sys_x86_64.c +++ b/arch/x86/kernel/sys_x86_64.c @@ -90,14 +90,10 @@ SYSCALL_DEFINE6(mmap, unsigned long, addr, unsigned long, len, unsigned long, prot, unsigned long, flags, unsigned long, fd, unsigned long, off) { - long error; - error = -EINVAL; if (off & ~PAGE_MASK) - goto out; + return -EINVAL; - error = ksys_mmap_pgoff(addr, len, prot, flags, fd, off >> PAGE_SHIFT); -out: - return error; + return ksys_mmap_pgoff(addr, len, prot, flags, fd, off >> PAGE_SHIFT); } static void find_start_end(unsigned long addr, unsigned long flags, diff --git a/arch/x86/kernel/traps.c b/arch/x86/kernel/traps.c index 7f5aec758f0e..ac1874a2a70e 100644 --- a/arch/x86/kernel/traps.c +++ b/arch/x86/kernel/traps.c @@ -694,8 +694,7 @@ asmlinkage __visible noinstr struct pt_regs *vc_switch_off_ist(struct pt_regs *r * In the SYSCALL entry path the RSP value comes from user-space - don't * trust it and switch to the current kernel stack */ - if (regs->ip >= (unsigned long)entry_SYSCALL_64 && - regs->ip < (unsigned long)entry_SYSCALL_64_safe_stack) { + if (ip_within_syscall_gap(regs)) { sp = this_cpu_read(cpu_current_top_of_stack); goto sync; } diff --git a/arch/x86/kernel/unwind_orc.c b/arch/x86/kernel/unwind_orc.c index 73f800100066..a1202536fc57 100644 --- a/arch/x86/kernel/unwind_orc.c +++ b/arch/x86/kernel/unwind_orc.c @@ -13,7 +13,7 @@ #define orc_warn_current(args...) \ ({ \ - if (state->task == current) \ + if (state->task == current && !state->error) \ orc_warn(args); \ }) @@ -367,8 +367,8 @@ static bool deref_stack_regs(struct unwind_state *state, unsigned long addr, if (!stack_access_ok(state, addr, sizeof(struct pt_regs))) return false; - *ip = regs->ip; - *sp = regs->sp; + *ip = READ_ONCE_NOCHECK(regs->ip); + *sp = READ_ONCE_NOCHECK(regs->sp); return true; } @@ -380,8 +380,8 @@ static bool deref_stack_iret_regs(struct unwind_state *state, unsigned long addr if (!stack_access_ok(state, addr, IRET_FRAME_SIZE)) return false; - *ip = regs->ip; - *sp = regs->sp; + *ip = READ_ONCE_NOCHECK(regs->ip); + *sp = READ_ONCE_NOCHECK(regs->sp); return true; } @@ -402,12 +402,12 @@ static bool get_reg(struct unwind_state *state, unsigned int reg_off, return false; if (state->full_regs) { - *val = ((unsigned long *)state->regs)[reg]; + *val = READ_ONCE_NOCHECK(((unsigned long *)state->regs)[reg]); return true; } if (state->prev_regs) { - *val = ((unsigned long *)state->prev_regs)[reg]; + *val = READ_ONCE_NOCHECK(((unsigned long *)state->prev_regs)[reg]); return true; } @@ -471,7 +471,7 @@ bool unwind_next_frame(struct unwind_state *state) break; case ORC_REG_SP_INDIRECT: - sp = state->sp + orc->sp_offset; + sp = state->sp; indirect = true; break; @@ -521,6 +521,9 @@ bool unwind_next_frame(struct unwind_state *state) if (indirect) { if (!deref_stack_reg(state, sp, &sp)) goto err; + + if (orc->sp_reg == ORC_REG_SP_INDIRECT) + sp += orc->sp_offset; } /* Find IP, SP and possibly regs: */ diff --git a/arch/x86/kernel/vm86_32.c b/arch/x86/kernel/vm86_32.c index 764573de3996..e5a7a10a0164 100644 --- a/arch/x86/kernel/vm86_32.c +++ b/arch/x86/kernel/vm86_32.c @@ -134,7 +134,11 @@ void save_v86_state(struct kernel_vm86_regs *regs, int retval) unsafe_put_user(regs->ds, &user->regs.ds, Efault_end); unsafe_put_user(regs->fs, &user->regs.fs, Efault_end); unsafe_put_user(regs->gs, &user->regs.gs, Efault_end); - unsafe_put_user(vm86->screen_bitmap, &user->screen_bitmap, Efault_end); + + /* + * Don't write screen_bitmap in case some user had a value there + * and expected it to remain unchanged. + */ user_access_end(); @@ -160,49 +164,6 @@ Efault: do_exit(SIGSEGV); } -static void mark_screen_rdonly(struct mm_struct *mm) -{ - struct vm_area_struct *vma; - spinlock_t *ptl; - pgd_t *pgd; - p4d_t *p4d; - pud_t *pud; - pmd_t *pmd; - pte_t *pte; - int i; - - mmap_write_lock(mm); - pgd = pgd_offset(mm, 0xA0000); - if (pgd_none_or_clear_bad(pgd)) - goto out; - p4d = p4d_offset(pgd, 0xA0000); - if (p4d_none_or_clear_bad(p4d)) - goto out; - pud = pud_offset(p4d, 0xA0000); - if (pud_none_or_clear_bad(pud)) - goto out; - pmd = pmd_offset(pud, 0xA0000); - - if (pmd_trans_huge(*pmd)) { - vma = find_vma(mm, 0xA0000); - split_huge_pmd(vma, pmd, 0xA0000); - } - if (pmd_none_or_clear_bad(pmd)) - goto out; - pte = pte_offset_map_lock(mm, pmd, 0xA0000, &ptl); - for (i = 0; i < 32; i++) { - if (pte_present(*pte)) - set_pte(pte, pte_wrprotect(*pte)); - pte++; - } - pte_unmap_unlock(pte, ptl); -out: - mmap_write_unlock(mm); - flush_tlb_mm_range(mm, 0xA0000, 0xA0000 + 32*PAGE_SIZE, PAGE_SHIFT, false); -} - - - static int do_vm86_irq_handling(int subfunction, int irqnumber); static long do_sys_vm86(struct vm86plus_struct __user *user_vm86, bool plus); @@ -282,6 +243,15 @@ static long do_sys_vm86(struct vm86plus_struct __user *user_vm86, bool plus) offsetof(struct vm86_struct, int_revectored))) return -EFAULT; + + /* VM86_SCREEN_BITMAP had numerous bugs and appears to have no users. */ + if (v.flags & VM86_SCREEN_BITMAP) { + char comm[TASK_COMM_LEN]; + + pr_info_once("vm86: '%s' uses VM86_SCREEN_BITMAP, which is no longer supported\n", get_task_comm(comm, current)); + return -EINVAL; + } + memset(&vm86regs, 0, sizeof(vm86regs)); vm86regs.pt.bx = v.regs.ebx; @@ -302,7 +272,6 @@ static long do_sys_vm86(struct vm86plus_struct __user *user_vm86, bool plus) vm86regs.gs = v.regs.gs; vm86->flags = v.flags; - vm86->screen_bitmap = v.screen_bitmap; vm86->cpu_type = v.cpu_type; if (copy_from_user(&vm86->int_revectored, @@ -370,9 +339,6 @@ static long do_sys_vm86(struct vm86plus_struct __user *user_vm86, bool plus) update_task_stack(tsk); preempt_enable(); - if (vm86->flags & VM86_SCREEN_BITMAP) - mark_screen_rdonly(tsk->mm); - memcpy((struct kernel_vm86_regs *)regs, &vm86regs, sizeof(vm86regs)); return regs->ax; } diff --git a/arch/x86/kvm/Kconfig b/arch/x86/kvm/Kconfig index 7ac592664c52..a788d5120d4d 100644 --- a/arch/x86/kvm/Kconfig +++ b/arch/x86/kvm/Kconfig @@ -103,6 +103,15 @@ config KVM_AMD_SEV Provides support for launching Encrypted VMs (SEV) and Encrypted VMs with Encrypted State (SEV-ES) on AMD processors. +config KVM_XEN + bool "Support for Xen hypercall interface" + depends on KVM + help + Provides KVM support for the hosting Xen HVM guests and + passing Xen hypercalls to userspace. + + If in doubt, say "N". + config KVM_MMU_AUDIT bool "Audit KVM MMU" depends on KVM && TRACEPOINTS diff --git a/arch/x86/kvm/Makefile b/arch/x86/kvm/Makefile index 4bd14ab01323..1b4766fe1de2 100644 --- a/arch/x86/kvm/Makefile +++ b/arch/x86/kvm/Makefile @@ -17,7 +17,9 @@ kvm-$(CONFIG_KVM_ASYNC_PF) += $(KVM)/async_pf.o kvm-y += x86.o emulate.o i8259.o irq.o lapic.o \ i8254.o ioapic.o irq_comm.o cpuid.o pmu.o mtrr.o \ hyperv.o debugfs.o mmu/mmu.o mmu/page_track.o \ - mmu/spte.o mmu/tdp_iter.o mmu/tdp_mmu.o + mmu/spte.o +kvm-$(CONFIG_X86_64) += mmu/tdp_iter.o mmu/tdp_mmu.o +kvm-$(CONFIG_KVM_XEN) += xen.o kvm-intel-y += vmx/vmx.o vmx/vmenter.o vmx/pmu_intel.o vmx/vmcs12.o \ vmx/evmcs.o vmx/nested.o vmx/posted_intr.o diff --git a/arch/x86/kvm/cpuid.c b/arch/x86/kvm/cpuid.c index 38172ca627d3..6bd2f8b830e4 100644 --- a/arch/x86/kvm/cpuid.c +++ b/arch/x86/kvm/cpuid.c @@ -173,16 +173,22 @@ static void kvm_vcpu_after_set_cpuid(struct kvm_vcpu *vcpu) kvm_update_pv_runtime(vcpu); vcpu->arch.maxphyaddr = cpuid_query_maxphyaddr(vcpu); - kvm_mmu_reset_context(vcpu); + vcpu->arch.reserved_gpa_bits = kvm_vcpu_reserved_gpa_bits_raw(vcpu); kvm_pmu_refresh(vcpu); vcpu->arch.cr4_guest_rsvd_bits = __cr4_reserved_bits(guest_cpuid_has, vcpu); - vcpu->arch.cr3_lm_rsvd_bits = rsvd_bits(cpuid_maxphyaddr(vcpu), 63); + kvm_hv_set_cpuid(vcpu); /* Invoke the vendor callback only after the above state is updated. */ - kvm_x86_ops.vcpu_after_set_cpuid(vcpu); + static_call(kvm_x86_vcpu_after_set_cpuid)(vcpu); + + /* + * Except for the MMU, which needs to be reset after any vendor + * specific adjustments to the reserved GPA bits. + */ + kvm_mmu_reset_context(vcpu); } static int is_efer_nx(void) @@ -223,6 +229,16 @@ not_found: return 36; } +/* + * This "raw" version returns the reserved GPA bits without any adjustments for + * encryption technologies that usurp bits. The raw mask should be used if and + * only if hardware does _not_ strip the usurped bits, e.g. in virtual MTRRs. + */ +u64 kvm_vcpu_reserved_gpa_bits_raw(struct kvm_vcpu *vcpu) +{ + return rsvd_bits(cpuid_maxphyaddr(vcpu), 63); +} + /* when an old userspace process fills a new kernel module */ int kvm_vcpu_ioctl_set_cpuid(struct kvm_vcpu *vcpu, struct kvm_cpuid *cpuid, @@ -392,7 +408,7 @@ void kvm_set_cpu_caps(void) kvm_cpu_cap_mask(CPUID_7_0_EBX, F(FSGSBASE) | F(BMI1) | F(HLE) | F(AVX2) | F(SMEP) | - F(BMI2) | F(ERMS) | 0 /*INVPCID*/ | F(RTM) | 0 /*MPX*/ | F(RDSEED) | + F(BMI2) | F(ERMS) | F(INVPCID) | F(RTM) | 0 /*MPX*/ | F(RDSEED) | F(ADX) | F(SMAP) | F(AVX512IFMA) | F(AVX512F) | F(AVX512PF) | F(AVX512ER) | F(AVX512CD) | F(CLFLUSHOPT) | F(CLWB) | F(AVX512DQ) | F(SHA_NI) | F(AVX512BW) | F(AVX512VL) | 0 /*INTEL_PT*/ @@ -434,7 +450,7 @@ void kvm_set_cpu_caps(void) kvm_cpu_cap_set(X86_FEATURE_SPEC_CTRL_SSBD); kvm_cpu_cap_mask(CPUID_7_1_EAX, - F(AVX512_BF16) + F(AVX_VNNI) | F(AVX512_BF16) ); kvm_cpu_cap_mask(CPUID_D_1_EAX, diff --git a/arch/x86/kvm/cpuid.h b/arch/x86/kvm/cpuid.h index dc921d76e42e..2a0c5064497f 100644 --- a/arch/x86/kvm/cpuid.h +++ b/arch/x86/kvm/cpuid.h @@ -30,15 +30,32 @@ bool kvm_cpuid(struct kvm_vcpu *vcpu, u32 *eax, u32 *ebx, u32 *ecx, u32 *edx, bool exact_only); int cpuid_query_maxphyaddr(struct kvm_vcpu *vcpu); +u64 kvm_vcpu_reserved_gpa_bits_raw(struct kvm_vcpu *vcpu); static inline int cpuid_maxphyaddr(struct kvm_vcpu *vcpu) { return vcpu->arch.maxphyaddr; } +static inline bool kvm_vcpu_is_legal_gpa(struct kvm_vcpu *vcpu, gpa_t gpa) +{ + return !(gpa & vcpu->arch.reserved_gpa_bits); +} + static inline bool kvm_vcpu_is_illegal_gpa(struct kvm_vcpu *vcpu, gpa_t gpa) { - return (gpa >= BIT_ULL(cpuid_maxphyaddr(vcpu))); + return !kvm_vcpu_is_legal_gpa(vcpu, gpa); +} + +static inline bool kvm_vcpu_is_legal_aligned_gpa(struct kvm_vcpu *vcpu, + gpa_t gpa, gpa_t alignment) +{ + return IS_ALIGNED(gpa, alignment) && kvm_vcpu_is_legal_gpa(vcpu, gpa); +} + +static inline bool page_address_valid(struct kvm_vcpu *vcpu, gpa_t gpa) +{ + return kvm_vcpu_is_legal_aligned_gpa(vcpu, gpa, PAGE_SIZE); } struct cpuid_reg { @@ -324,11 +341,6 @@ static __always_inline void kvm_cpu_cap_check_and_set(unsigned int x86_feature) kvm_cpu_cap_set(x86_feature); } -static inline bool page_address_valid(struct kvm_vcpu *vcpu, gpa_t gpa) -{ - return PAGE_ALIGNED(gpa) && !(gpa >> cpuid_maxphyaddr(vcpu)); -} - static __always_inline bool guest_pv_has(struct kvm_vcpu *vcpu, unsigned int kvm_feature) { diff --git a/arch/x86/kvm/emulate.c b/arch/x86/kvm/emulate.c index 66a08322988f..f7970ba6219f 100644 --- a/arch/x86/kvm/emulate.c +++ b/arch/x86/kvm/emulate.c @@ -2506,12 +2506,12 @@ static int rsm_load_state_32(struct x86_emulate_ctxt *ctxt, val = GET_SMSTATE(u32, smstate, 0x7fcc); - if (ctxt->ops->set_dr(ctxt, 6, (val & DR6_VOLATILE) | DR6_FIXED_1)) + if (ctxt->ops->set_dr(ctxt, 6, val)) return X86EMUL_UNHANDLEABLE; val = GET_SMSTATE(u32, smstate, 0x7fc8); - if (ctxt->ops->set_dr(ctxt, 7, (val & DR7_VOLATILE) | DR7_FIXED_1)) + if (ctxt->ops->set_dr(ctxt, 7, val)) return X86EMUL_UNHANDLEABLE; selector = GET_SMSTATE(u32, smstate, 0x7fc4); @@ -2564,14 +2564,14 @@ static int rsm_load_state_64(struct x86_emulate_ctxt *ctxt, ctxt->_eip = GET_SMSTATE(u64, smstate, 0x7f78); ctxt->eflags = GET_SMSTATE(u32, smstate, 0x7f70) | X86_EFLAGS_FIXED; - val = GET_SMSTATE(u32, smstate, 0x7f68); + val = GET_SMSTATE(u64, smstate, 0x7f68); - if (ctxt->ops->set_dr(ctxt, 6, (val & DR6_VOLATILE) | DR6_FIXED_1)) + if (ctxt->ops->set_dr(ctxt, 6, val)) return X86EMUL_UNHANDLEABLE; - val = GET_SMSTATE(u32, smstate, 0x7f60); + val = GET_SMSTATE(u64, smstate, 0x7f60); - if (ctxt->ops->set_dr(ctxt, 7, (val & DR7_VOLATILE) | DR7_FIXED_1)) + if (ctxt->ops->set_dr(ctxt, 7, val)) return X86EMUL_UNHANDLEABLE; cr0 = GET_SMSTATE(u64, smstate, 0x7f58); @@ -4329,7 +4329,7 @@ static int check_dr_read(struct x86_emulate_ctxt *ctxt) ctxt->ops->get_dr(ctxt, 6, &dr6); dr6 &= ~DR_TRAP_BITS; - dr6 |= DR6_BD | DR6_RTM; + dr6 |= DR6_BD | DR6_ACTIVE_LOW; ctxt->ops->set_dr(ctxt, 6, dr6); return emulate_db(ctxt); } diff --git a/arch/x86/kvm/hyperv.c b/arch/x86/kvm/hyperv.c index 922c69dcca4d..f98370a39936 100644 --- a/arch/x86/kvm/hyperv.c +++ b/arch/x86/kvm/hyperv.c @@ -23,6 +23,7 @@ #include "ioapic.h" #include "cpuid.h" #include "hyperv.h" +#include "xen.h" #include <linux/cpu.h> #include <linux/kvm_host.h> @@ -36,6 +37,9 @@ #include "trace.h" #include "irq.h" +/* "Hv#1" signature */ +#define HYPERV_CPUID_SIGNATURE_EAX 0x31237648 + #define KVM_HV_MAX_SPARSE_VCPU_SET_BITS DIV_ROUND_UP(KVM_MAX_VCPUS, 64) static void stimer_mark_pending(struct kvm_vcpu_hv_stimer *stimer, @@ -128,7 +132,7 @@ static int synic_set_sint(struct kvm_vcpu_hv_synic *synic, int sint, synic_update_vector(synic, vector); /* Load SynIC vectors into EOI exit bitmap */ - kvm_make_request(KVM_REQ_SCAN_IOAPIC, synic_to_vcpu(synic)); + kvm_make_request(KVM_REQ_SCAN_IOAPIC, hv_synic_to_vcpu(synic)); return 0; } @@ -141,10 +145,10 @@ static struct kvm_vcpu *get_vcpu_by_vpidx(struct kvm *kvm, u32 vpidx) return NULL; vcpu = kvm_get_vcpu(kvm, vpidx); - if (vcpu && vcpu_to_hv_vcpu(vcpu)->vp_index == vpidx) + if (vcpu && kvm_hv_get_vpindex(vcpu) == vpidx) return vcpu; kvm_for_each_vcpu(i, vcpu, kvm) - if (vcpu_to_hv_vcpu(vcpu)->vp_index == vpidx) + if (kvm_hv_get_vpindex(vcpu) == vpidx) return vcpu; return NULL; } @@ -155,17 +159,17 @@ static struct kvm_vcpu_hv_synic *synic_get(struct kvm *kvm, u32 vpidx) struct kvm_vcpu_hv_synic *synic; vcpu = get_vcpu_by_vpidx(kvm, vpidx); - if (!vcpu) + if (!vcpu || !to_hv_vcpu(vcpu)) return NULL; - synic = vcpu_to_synic(vcpu); + synic = to_hv_synic(vcpu); return (synic->active) ? synic : NULL; } static void kvm_hv_notify_acked_sint(struct kvm_vcpu *vcpu, u32 sint) { struct kvm *kvm = vcpu->kvm; - struct kvm_vcpu_hv_synic *synic = vcpu_to_synic(vcpu); - struct kvm_vcpu_hv *hv_vcpu = vcpu_to_hv_vcpu(vcpu); + struct kvm_vcpu_hv_synic *synic = to_hv_synic(vcpu); + struct kvm_vcpu_hv *hv_vcpu = to_hv_vcpu(vcpu); struct kvm_vcpu_hv_stimer *stimer; int gsi, idx; @@ -189,8 +193,8 @@ static void kvm_hv_notify_acked_sint(struct kvm_vcpu *vcpu, u32 sint) static void synic_exit(struct kvm_vcpu_hv_synic *synic, u32 msr) { - struct kvm_vcpu *vcpu = synic_to_vcpu(synic); - struct kvm_vcpu_hv *hv_vcpu = &vcpu->arch.hyperv; + struct kvm_vcpu *vcpu = hv_synic_to_vcpu(synic); + struct kvm_vcpu_hv *hv_vcpu = to_hv_vcpu(vcpu); hv_vcpu->exit.type = KVM_EXIT_HYPERV_SYNIC; hv_vcpu->exit.u.synic.msr = msr; @@ -204,7 +208,7 @@ static void synic_exit(struct kvm_vcpu_hv_synic *synic, u32 msr) static int synic_set_msr(struct kvm_vcpu_hv_synic *synic, u32 msr, u64 data, bool host) { - struct kvm_vcpu *vcpu = synic_to_vcpu(synic); + struct kvm_vcpu *vcpu = hv_synic_to_vcpu(synic); int ret; if (!synic->active && !host) @@ -282,8 +286,7 @@ static bool kvm_hv_is_syndbg_enabled(struct kvm_vcpu *vcpu) static int kvm_hv_syndbg_complete_userspace(struct kvm_vcpu *vcpu) { - struct kvm *kvm = vcpu->kvm; - struct kvm_hv *hv = &kvm->arch.hyperv; + struct kvm_hv *hv = to_kvm_hv(vcpu->kvm); if (vcpu->run->hyperv.u.syndbg.msr == HV_X64_MSR_SYNDBG_CONTROL) hv->hv_syndbg.control.status = @@ -293,8 +296,8 @@ static int kvm_hv_syndbg_complete_userspace(struct kvm_vcpu *vcpu) static void syndbg_exit(struct kvm_vcpu *vcpu, u32 msr) { - struct kvm_hv_syndbg *syndbg = vcpu_to_hv_syndbg(vcpu); - struct kvm_vcpu_hv *hv_vcpu = &vcpu->arch.hyperv; + struct kvm_hv_syndbg *syndbg = to_hv_syndbg(vcpu); + struct kvm_vcpu_hv *hv_vcpu = to_hv_vcpu(vcpu); hv_vcpu->exit.type = KVM_EXIT_HYPERV_SYNDBG; hv_vcpu->exit.u.syndbg.msr = msr; @@ -310,13 +313,13 @@ static void syndbg_exit(struct kvm_vcpu *vcpu, u32 msr) static int syndbg_set_msr(struct kvm_vcpu *vcpu, u32 msr, u64 data, bool host) { - struct kvm_hv_syndbg *syndbg = vcpu_to_hv_syndbg(vcpu); + struct kvm_hv_syndbg *syndbg = to_hv_syndbg(vcpu); if (!kvm_hv_is_syndbg_enabled(vcpu) && !host) return 1; trace_kvm_hv_syndbg_set_msr(vcpu->vcpu_id, - vcpu_to_hv_vcpu(vcpu)->vp_index, msr, data); + to_hv_vcpu(vcpu)->vp_index, msr, data); switch (msr) { case HV_X64_MSR_SYNDBG_CONTROL: syndbg->control.control = data; @@ -349,7 +352,7 @@ static int syndbg_set_msr(struct kvm_vcpu *vcpu, u32 msr, u64 data, bool host) static int syndbg_get_msr(struct kvm_vcpu *vcpu, u32 msr, u64 *pdata, bool host) { - struct kvm_hv_syndbg *syndbg = vcpu_to_hv_syndbg(vcpu); + struct kvm_hv_syndbg *syndbg = to_hv_syndbg(vcpu); if (!kvm_hv_is_syndbg_enabled(vcpu) && !host) return 1; @@ -377,9 +380,7 @@ static int syndbg_get_msr(struct kvm_vcpu *vcpu, u32 msr, u64 *pdata, bool host) break; } - trace_kvm_hv_syndbg_get_msr(vcpu->vcpu_id, - vcpu_to_hv_vcpu(vcpu)->vp_index, msr, - *pdata); + trace_kvm_hv_syndbg_get_msr(vcpu->vcpu_id, kvm_hv_get_vpindex(vcpu), msr, *pdata); return 0; } @@ -421,7 +422,7 @@ static int synic_get_msr(struct kvm_vcpu_hv_synic *synic, u32 msr, u64 *pdata, static int synic_set_irq(struct kvm_vcpu_hv_synic *synic, u32 sint) { - struct kvm_vcpu *vcpu = synic_to_vcpu(synic); + struct kvm_vcpu *vcpu = hv_synic_to_vcpu(synic); struct kvm_lapic_irq irq; int ret, vector; @@ -457,7 +458,7 @@ int kvm_hv_synic_set_irq(struct kvm *kvm, u32 vpidx, u32 sint) void kvm_hv_synic_send_eoi(struct kvm_vcpu *vcpu, int vector) { - struct kvm_vcpu_hv_synic *synic = vcpu_to_synic(vcpu); + struct kvm_vcpu_hv_synic *synic = to_hv_synic(vcpu); int i; trace_kvm_hv_synic_send_eoi(vcpu->vcpu_id, vector); @@ -514,15 +515,15 @@ static void synic_init(struct kvm_vcpu_hv_synic *synic) static u64 get_time_ref_counter(struct kvm *kvm) { - struct kvm_hv *hv = &kvm->arch.hyperv; + struct kvm_hv *hv = to_kvm_hv(kvm); struct kvm_vcpu *vcpu; u64 tsc; /* - * The guest has not set up the TSC page or the clock isn't - * stable, fall back to get_kvmclock_ns. + * Fall back to get_kvmclock_ns() when TSC page hasn't been set up, + * is broken, disabled or being updated. */ - if (!hv->tsc_ref.tsc_sequence) + if (hv->hv_tsc_page_status != HV_TSC_PAGE_SET) return div_u64(get_kvmclock_ns(kvm), 100); vcpu = kvm_get_vcpu(kvm, 0); @@ -534,10 +535,10 @@ static u64 get_time_ref_counter(struct kvm *kvm) static void stimer_mark_pending(struct kvm_vcpu_hv_stimer *stimer, bool vcpu_kick) { - struct kvm_vcpu *vcpu = stimer_to_vcpu(stimer); + struct kvm_vcpu *vcpu = hv_stimer_to_vcpu(stimer); set_bit(stimer->index, - vcpu_to_hv_vcpu(vcpu)->stimer_pending_bitmap); + to_hv_vcpu(vcpu)->stimer_pending_bitmap); kvm_make_request(KVM_REQ_HV_STIMER, vcpu); if (vcpu_kick) kvm_vcpu_kick(vcpu); @@ -545,14 +546,14 @@ static void stimer_mark_pending(struct kvm_vcpu_hv_stimer *stimer, static void stimer_cleanup(struct kvm_vcpu_hv_stimer *stimer) { - struct kvm_vcpu *vcpu = stimer_to_vcpu(stimer); + struct kvm_vcpu *vcpu = hv_stimer_to_vcpu(stimer); - trace_kvm_hv_stimer_cleanup(stimer_to_vcpu(stimer)->vcpu_id, + trace_kvm_hv_stimer_cleanup(hv_stimer_to_vcpu(stimer)->vcpu_id, stimer->index); hrtimer_cancel(&stimer->timer); clear_bit(stimer->index, - vcpu_to_hv_vcpu(vcpu)->stimer_pending_bitmap); + to_hv_vcpu(vcpu)->stimer_pending_bitmap); stimer->msg_pending = false; stimer->exp_time = 0; } @@ -562,7 +563,7 @@ static enum hrtimer_restart stimer_timer_callback(struct hrtimer *timer) struct kvm_vcpu_hv_stimer *stimer; stimer = container_of(timer, struct kvm_vcpu_hv_stimer, timer); - trace_kvm_hv_stimer_callback(stimer_to_vcpu(stimer)->vcpu_id, + trace_kvm_hv_stimer_callback(hv_stimer_to_vcpu(stimer)->vcpu_id, stimer->index); stimer_mark_pending(stimer, true); @@ -579,7 +580,7 @@ static int stimer_start(struct kvm_vcpu_hv_stimer *stimer) u64 time_now; ktime_t ktime_now; - time_now = get_time_ref_counter(stimer_to_vcpu(stimer)->kvm); + time_now = get_time_ref_counter(hv_stimer_to_vcpu(stimer)->kvm); ktime_now = ktime_get(); if (stimer->config.periodic) { @@ -596,7 +597,7 @@ static int stimer_start(struct kvm_vcpu_hv_stimer *stimer) stimer->exp_time = time_now + stimer->count; trace_kvm_hv_stimer_start_periodic( - stimer_to_vcpu(stimer)->vcpu_id, + hv_stimer_to_vcpu(stimer)->vcpu_id, stimer->index, time_now, stimer->exp_time); @@ -618,7 +619,7 @@ static int stimer_start(struct kvm_vcpu_hv_stimer *stimer) return 0; } - trace_kvm_hv_stimer_start_one_shot(stimer_to_vcpu(stimer)->vcpu_id, + trace_kvm_hv_stimer_start_one_shot(hv_stimer_to_vcpu(stimer)->vcpu_id, stimer->index, time_now, stimer->count); @@ -633,13 +634,13 @@ static int stimer_set_config(struct kvm_vcpu_hv_stimer *stimer, u64 config, { union hv_stimer_config new_config = {.as_uint64 = config}, old_config = {.as_uint64 = stimer->config.as_uint64}; - struct kvm_vcpu *vcpu = stimer_to_vcpu(stimer); - struct kvm_vcpu_hv_synic *synic = vcpu_to_synic(vcpu); + struct kvm_vcpu *vcpu = hv_stimer_to_vcpu(stimer); + struct kvm_vcpu_hv_synic *synic = to_hv_synic(vcpu); if (!synic->active && !host) return 1; - trace_kvm_hv_stimer_set_config(stimer_to_vcpu(stimer)->vcpu_id, + trace_kvm_hv_stimer_set_config(hv_stimer_to_vcpu(stimer)->vcpu_id, stimer->index, config, host); stimer_cleanup(stimer); @@ -657,13 +658,13 @@ static int stimer_set_config(struct kvm_vcpu_hv_stimer *stimer, u64 config, static int stimer_set_count(struct kvm_vcpu_hv_stimer *stimer, u64 count, bool host) { - struct kvm_vcpu *vcpu = stimer_to_vcpu(stimer); - struct kvm_vcpu_hv_synic *synic = vcpu_to_synic(vcpu); + struct kvm_vcpu *vcpu = hv_stimer_to_vcpu(stimer); + struct kvm_vcpu_hv_synic *synic = to_hv_synic(vcpu); if (!synic->active && !host) return 1; - trace_kvm_hv_stimer_set_count(stimer_to_vcpu(stimer)->vcpu_id, + trace_kvm_hv_stimer_set_count(hv_stimer_to_vcpu(stimer)->vcpu_id, stimer->index, count, host); stimer_cleanup(stimer); @@ -694,7 +695,7 @@ static int stimer_get_count(struct kvm_vcpu_hv_stimer *stimer, u64 *pcount) static int synic_deliver_msg(struct kvm_vcpu_hv_synic *synic, u32 sint, struct hv_message *src_msg, bool no_retry) { - struct kvm_vcpu *vcpu = synic_to_vcpu(synic); + struct kvm_vcpu *vcpu = hv_synic_to_vcpu(synic); int msg_off = offsetof(struct hv_message_page, sint_message[sint]); gfn_t msg_page_gfn; struct hv_message_header hv_hdr; @@ -750,7 +751,7 @@ static int synic_deliver_msg(struct kvm_vcpu_hv_synic *synic, u32 sint, static int stimer_send_msg(struct kvm_vcpu_hv_stimer *stimer) { - struct kvm_vcpu *vcpu = stimer_to_vcpu(stimer); + struct kvm_vcpu *vcpu = hv_stimer_to_vcpu(stimer); struct hv_message *msg = &stimer->msg; struct hv_timer_message_payload *payload = (struct hv_timer_message_payload *)&msg->u.payload; @@ -763,14 +764,14 @@ static int stimer_send_msg(struct kvm_vcpu_hv_stimer *stimer) payload->expiration_time = stimer->exp_time; payload->delivery_time = get_time_ref_counter(vcpu->kvm); - return synic_deliver_msg(vcpu_to_synic(vcpu), + return synic_deliver_msg(to_hv_synic(vcpu), stimer->config.sintx, msg, no_retry); } static int stimer_notify_direct(struct kvm_vcpu_hv_stimer *stimer) { - struct kvm_vcpu *vcpu = stimer_to_vcpu(stimer); + struct kvm_vcpu *vcpu = hv_stimer_to_vcpu(stimer); struct kvm_lapic_irq irq = { .delivery_mode = APIC_DM_FIXED, .vector = stimer->config.apic_vector @@ -790,7 +791,7 @@ static void stimer_expiration(struct kvm_vcpu_hv_stimer *stimer) r = stimer_send_msg(stimer); else r = stimer_notify_direct(stimer); - trace_kvm_hv_stimer_expiration(stimer_to_vcpu(stimer)->vcpu_id, + trace_kvm_hv_stimer_expiration(hv_stimer_to_vcpu(stimer)->vcpu_id, stimer->index, direct, r); if (!r) { stimer->msg_pending = false; @@ -801,11 +802,14 @@ static void stimer_expiration(struct kvm_vcpu_hv_stimer *stimer) void kvm_hv_process_stimers(struct kvm_vcpu *vcpu) { - struct kvm_vcpu_hv *hv_vcpu = vcpu_to_hv_vcpu(vcpu); + struct kvm_vcpu_hv *hv_vcpu = to_hv_vcpu(vcpu); struct kvm_vcpu_hv_stimer *stimer; u64 time_now, exp_time; int i; + if (!hv_vcpu) + return; + for (i = 0; i < ARRAY_SIZE(hv_vcpu->stimer); i++) if (test_and_clear_bit(i, hv_vcpu->stimer_pending_bitmap)) { stimer = &hv_vcpu->stimer[i]; @@ -831,16 +835,27 @@ void kvm_hv_process_stimers(struct kvm_vcpu *vcpu) void kvm_hv_vcpu_uninit(struct kvm_vcpu *vcpu) { - struct kvm_vcpu_hv *hv_vcpu = vcpu_to_hv_vcpu(vcpu); + struct kvm_vcpu_hv *hv_vcpu = to_hv_vcpu(vcpu); int i; + if (!hv_vcpu) + return; + for (i = 0; i < ARRAY_SIZE(hv_vcpu->stimer); i++) stimer_cleanup(&hv_vcpu->stimer[i]); + + kfree(hv_vcpu); + vcpu->arch.hyperv = NULL; } bool kvm_hv_assist_page_enabled(struct kvm_vcpu *vcpu) { - if (!(vcpu->arch.hyperv.hv_vapic & HV_X64_MSR_VP_ASSIST_PAGE_ENABLE)) + struct kvm_vcpu_hv *hv_vcpu = to_hv_vcpu(vcpu); + + if (!hv_vcpu) + return false; + + if (!(hv_vcpu->hv_vapic & HV_X64_MSR_VP_ASSIST_PAGE_ENABLE)) return false; return vcpu->arch.pv_eoi.msr_val & KVM_MSR_ENABLED; } @@ -880,28 +895,41 @@ static void stimer_init(struct kvm_vcpu_hv_stimer *stimer, int timer_index) stimer_prepare_msg(stimer); } -void kvm_hv_vcpu_init(struct kvm_vcpu *vcpu) +static int kvm_hv_vcpu_init(struct kvm_vcpu *vcpu) { - struct kvm_vcpu_hv *hv_vcpu = vcpu_to_hv_vcpu(vcpu); + struct kvm_vcpu_hv *hv_vcpu; int i; + hv_vcpu = kzalloc(sizeof(struct kvm_vcpu_hv), GFP_KERNEL_ACCOUNT); + if (!hv_vcpu) + return -ENOMEM; + + vcpu->arch.hyperv = hv_vcpu; + hv_vcpu->vcpu = vcpu; + synic_init(&hv_vcpu->synic); bitmap_zero(hv_vcpu->stimer_pending_bitmap, HV_SYNIC_STIMER_COUNT); for (i = 0; i < ARRAY_SIZE(hv_vcpu->stimer); i++) stimer_init(&hv_vcpu->stimer[i], i); -} - -void kvm_hv_vcpu_postcreate(struct kvm_vcpu *vcpu) -{ - struct kvm_vcpu_hv *hv_vcpu = vcpu_to_hv_vcpu(vcpu); hv_vcpu->vp_index = kvm_vcpu_get_idx(vcpu); + + return 0; } int kvm_hv_activate_synic(struct kvm_vcpu *vcpu, bool dont_zero_synic_pages) { - struct kvm_vcpu_hv_synic *synic = vcpu_to_synic(vcpu); + struct kvm_vcpu_hv_synic *synic; + int r; + + if (!to_hv_vcpu(vcpu)) { + r = kvm_hv_vcpu_init(vcpu); + if (r) + return r; + } + + synic = to_hv_synic(vcpu); /* * Hyper-V SynIC auto EOI SINT's are @@ -939,10 +967,9 @@ static bool kvm_hv_msr_partition_wide(u32 msr) return r; } -static int kvm_hv_msr_get_crash_data(struct kvm_vcpu *vcpu, - u32 index, u64 *pdata) +static int kvm_hv_msr_get_crash_data(struct kvm *kvm, u32 index, u64 *pdata) { - struct kvm_hv *hv = &vcpu->kvm->arch.hyperv; + struct kvm_hv *hv = to_kvm_hv(kvm); size_t size = ARRAY_SIZE(hv->hv_crash_param); if (WARN_ON_ONCE(index >= size)) @@ -952,41 +979,26 @@ static int kvm_hv_msr_get_crash_data(struct kvm_vcpu *vcpu, return 0; } -static int kvm_hv_msr_get_crash_ctl(struct kvm_vcpu *vcpu, u64 *pdata) +static int kvm_hv_msr_get_crash_ctl(struct kvm *kvm, u64 *pdata) { - struct kvm_hv *hv = &vcpu->kvm->arch.hyperv; + struct kvm_hv *hv = to_kvm_hv(kvm); *pdata = hv->hv_crash_ctl; return 0; } -static int kvm_hv_msr_set_crash_ctl(struct kvm_vcpu *vcpu, u64 data, bool host) +static int kvm_hv_msr_set_crash_ctl(struct kvm *kvm, u64 data) { - struct kvm_hv *hv = &vcpu->kvm->arch.hyperv; - - if (host) - hv->hv_crash_ctl = data & HV_CRASH_CTL_CRASH_NOTIFY; + struct kvm_hv *hv = to_kvm_hv(kvm); - if (!host && (data & HV_CRASH_CTL_CRASH_NOTIFY)) { - - vcpu_debug(vcpu, "hv crash (0x%llx 0x%llx 0x%llx 0x%llx 0x%llx)\n", - hv->hv_crash_param[0], - hv->hv_crash_param[1], - hv->hv_crash_param[2], - hv->hv_crash_param[3], - hv->hv_crash_param[4]); - - /* Send notification about crash to user space */ - kvm_make_request(KVM_REQ_HV_CRASH, vcpu); - } + hv->hv_crash_ctl = data & HV_CRASH_CTL_CRASH_NOTIFY; return 0; } -static int kvm_hv_msr_set_crash_data(struct kvm_vcpu *vcpu, - u32 index, u64 data) +static int kvm_hv_msr_set_crash_data(struct kvm *kvm, u32 index, u64 data) { - struct kvm_hv *hv = &vcpu->kvm->arch.hyperv; + struct kvm_hv *hv = to_kvm_hv(kvm); size_t size = ARRAY_SIZE(hv->hv_crash_param); if (WARN_ON_ONCE(index >= size)) @@ -1065,20 +1077,36 @@ static bool compute_tsc_page_parameters(struct pvclock_vcpu_time_info *hv_clock, return true; } +/* + * Don't touch TSC page values if the guest has opted for TSC emulation after + * migration. KVM doesn't fully support reenlightenment notifications and TSC + * access emulation and Hyper-V is known to expect the values in TSC page to + * stay constant before TSC access emulation is disabled from guest side + * (HV_X64_MSR_TSC_EMULATION_STATUS). KVM userspace is expected to preserve TSC + * frequency and guest visible TSC value across migration (and prevent it when + * TSC scaling is unsupported). + */ +static inline bool tsc_page_update_unsafe(struct kvm_hv *hv) +{ + return (hv->hv_tsc_page_status != HV_TSC_PAGE_GUEST_CHANGED) && + hv->hv_tsc_emulation_control; +} + void kvm_hv_setup_tsc_page(struct kvm *kvm, struct pvclock_vcpu_time_info *hv_clock) { - struct kvm_hv *hv = &kvm->arch.hyperv; + struct kvm_hv *hv = to_kvm_hv(kvm); u32 tsc_seq; u64 gfn; BUILD_BUG_ON(sizeof(tsc_seq) != sizeof(hv->tsc_ref.tsc_sequence)); BUILD_BUG_ON(offsetof(struct ms_hyperv_tsc_page, tsc_sequence) != 0); - if (!(hv->hv_tsc_page & HV_X64_MSR_TSC_REFERENCE_ENABLE)) + if (hv->hv_tsc_page_status == HV_TSC_PAGE_BROKEN || + hv->hv_tsc_page_status == HV_TSC_PAGE_UNSET) return; - mutex_lock(&kvm->arch.hyperv.hv_lock); + mutex_lock(&hv->hv_lock); if (!(hv->hv_tsc_page & HV_X64_MSR_TSC_REFERENCE_ENABLE)) goto out_unlock; @@ -1089,7 +1117,15 @@ void kvm_hv_setup_tsc_page(struct kvm *kvm, */ if (unlikely(kvm_read_guest(kvm, gfn_to_gpa(gfn), &tsc_seq, sizeof(tsc_seq)))) + goto out_err; + + if (tsc_seq && tsc_page_update_unsafe(hv)) { + if (kvm_read_guest(kvm, gfn_to_gpa(gfn), &hv->tsc_ref, sizeof(hv->tsc_ref))) + goto out_err; + + hv->hv_tsc_page_status = HV_TSC_PAGE_SET; goto out_unlock; + } /* * While we're computing and writing the parameters, force the @@ -1098,15 +1134,15 @@ void kvm_hv_setup_tsc_page(struct kvm *kvm, hv->tsc_ref.tsc_sequence = 0; if (kvm_write_guest(kvm, gfn_to_gpa(gfn), &hv->tsc_ref, sizeof(hv->tsc_ref.tsc_sequence))) - goto out_unlock; + goto out_err; if (!compute_tsc_page_parameters(hv_clock, &hv->tsc_ref)) - goto out_unlock; + goto out_err; /* Ensure sequence is zero before writing the rest of the struct. */ smp_wmb(); if (kvm_write_guest(kvm, gfn_to_gpa(gfn), &hv->tsc_ref, sizeof(hv->tsc_ref))) - goto out_unlock; + goto out_err; /* * Now switch to the TSC page mechanism by writing the sequence. @@ -1119,17 +1155,54 @@ void kvm_hv_setup_tsc_page(struct kvm *kvm, smp_wmb(); hv->tsc_ref.tsc_sequence = tsc_seq; - kvm_write_guest(kvm, gfn_to_gpa(gfn), - &hv->tsc_ref, sizeof(hv->tsc_ref.tsc_sequence)); + if (kvm_write_guest(kvm, gfn_to_gpa(gfn), + &hv->tsc_ref, sizeof(hv->tsc_ref.tsc_sequence))) + goto out_err; + + hv->hv_tsc_page_status = HV_TSC_PAGE_SET; + goto out_unlock; + +out_err: + hv->hv_tsc_page_status = HV_TSC_PAGE_BROKEN; out_unlock: - mutex_unlock(&kvm->arch.hyperv.hv_lock); + mutex_unlock(&hv->hv_lock); +} + +void kvm_hv_invalidate_tsc_page(struct kvm *kvm) +{ + struct kvm_hv *hv = to_kvm_hv(kvm); + u64 gfn; + + if (hv->hv_tsc_page_status == HV_TSC_PAGE_BROKEN || + hv->hv_tsc_page_status == HV_TSC_PAGE_UNSET || + tsc_page_update_unsafe(hv)) + return; + + mutex_lock(&hv->hv_lock); + + if (!(hv->hv_tsc_page & HV_X64_MSR_TSC_REFERENCE_ENABLE)) + goto out_unlock; + + /* Preserve HV_TSC_PAGE_GUEST_CHANGED/HV_TSC_PAGE_HOST_CHANGED states */ + if (hv->hv_tsc_page_status == HV_TSC_PAGE_SET) + hv->hv_tsc_page_status = HV_TSC_PAGE_UPDATING; + + gfn = hv->hv_tsc_page >> HV_X64_MSR_TSC_REFERENCE_ADDRESS_SHIFT; + + hv->tsc_ref.tsc_sequence = 0; + if (kvm_write_guest(kvm, gfn_to_gpa(gfn), + &hv->tsc_ref, sizeof(hv->tsc_ref.tsc_sequence))) + hv->hv_tsc_page_status = HV_TSC_PAGE_BROKEN; + +out_unlock: + mutex_unlock(&hv->hv_lock); } static int kvm_hv_set_msr_pw(struct kvm_vcpu *vcpu, u32 msr, u64 data, bool host) { struct kvm *kvm = vcpu->kvm; - struct kvm_hv *hv = &kvm->arch.hyperv; + struct kvm_hv *hv = to_kvm_hv(kvm); switch (msr) { case HV_X64_MSR_GUEST_OS_ID: @@ -1139,9 +1212,9 @@ static int kvm_hv_set_msr_pw(struct kvm_vcpu *vcpu, u32 msr, u64 data, hv->hv_hypercall &= ~HV_X64_MSR_HYPERCALL_ENABLE; break; case HV_X64_MSR_HYPERCALL: { - u64 gfn; - unsigned long addr; - u8 instructions[4]; + u8 instructions[9]; + int i = 0; + u64 addr; /* if guest os id is not set hypercall should remain disabled */ if (!hv->hv_guest_os_id) @@ -1150,29 +1223,67 @@ static int kvm_hv_set_msr_pw(struct kvm_vcpu *vcpu, u32 msr, u64 data, hv->hv_hypercall = data; break; } - gfn = data >> HV_X64_MSR_HYPERCALL_PAGE_ADDRESS_SHIFT; - addr = gfn_to_hva(kvm, gfn); - if (kvm_is_error_hva(addr)) - return 1; - kvm_x86_ops.patch_hypercall(vcpu, instructions); - ((unsigned char *)instructions)[3] = 0xc3; /* ret */ - if (__copy_to_user((void __user *)addr, instructions, 4)) + + /* + * If Xen and Hyper-V hypercalls are both enabled, disambiguate + * the same way Xen itself does, by setting the bit 31 of EAX + * which is RsvdZ in the 32-bit Hyper-V hypercall ABI and just + * going to be clobbered on 64-bit. + */ + if (kvm_xen_hypercall_enabled(kvm)) { + /* orl $0x80000000, %eax */ + instructions[i++] = 0x0d; + instructions[i++] = 0x00; + instructions[i++] = 0x00; + instructions[i++] = 0x00; + instructions[i++] = 0x80; + } + + /* vmcall/vmmcall */ + static_call(kvm_x86_patch_hypercall)(vcpu, instructions + i); + i += 3; + + /* ret */ + ((unsigned char *)instructions)[i++] = 0xc3; + + addr = data & HV_X64_MSR_HYPERCALL_PAGE_ADDRESS_MASK; + if (kvm_vcpu_write_guest(vcpu, addr, instructions, i)) return 1; hv->hv_hypercall = data; - mark_page_dirty(kvm, gfn); break; } case HV_X64_MSR_REFERENCE_TSC: hv->hv_tsc_page = data; - if (hv->hv_tsc_page & HV_X64_MSR_TSC_REFERENCE_ENABLE) + if (hv->hv_tsc_page & HV_X64_MSR_TSC_REFERENCE_ENABLE) { + if (!host) + hv->hv_tsc_page_status = HV_TSC_PAGE_GUEST_CHANGED; + else + hv->hv_tsc_page_status = HV_TSC_PAGE_HOST_CHANGED; kvm_make_request(KVM_REQ_MASTERCLOCK_UPDATE, vcpu); + } else { + hv->hv_tsc_page_status = HV_TSC_PAGE_UNSET; + } break; case HV_X64_MSR_CRASH_P0 ... HV_X64_MSR_CRASH_P4: - return kvm_hv_msr_set_crash_data(vcpu, + return kvm_hv_msr_set_crash_data(kvm, msr - HV_X64_MSR_CRASH_P0, data); case HV_X64_MSR_CRASH_CTL: - return kvm_hv_msr_set_crash_ctl(vcpu, data, host); + if (host) + return kvm_hv_msr_set_crash_ctl(kvm, data); + + if (data & HV_CRASH_CTL_CRASH_NOTIFY) { + vcpu_debug(vcpu, "hv crash (0x%llx 0x%llx 0x%llx 0x%llx 0x%llx)\n", + hv->hv_crash_param[0], + hv->hv_crash_param[1], + hv->hv_crash_param[2], + hv->hv_crash_param[3], + hv->hv_crash_param[4]); + + /* Send notification about crash to user space */ + kvm_make_request(KVM_REQ_HV_CRASH, vcpu); + } + break; case HV_X64_MSR_RESET: if (data == 1) { vcpu_debug(vcpu, "hyper-v reset requested\n"); @@ -1186,6 +1297,9 @@ static int kvm_hv_set_msr_pw(struct kvm_vcpu *vcpu, u32 msr, u64 data, hv->hv_tsc_emulation_control = data; break; case HV_X64_MSR_TSC_EMULATION_STATUS: + if (data && !host) + return 1; + hv->hv_tsc_emulation_status = data; break; case HV_X64_MSR_TIME_REF_COUNT: @@ -1216,11 +1330,11 @@ static u64 current_task_runtime_100ns(void) static int kvm_hv_set_msr(struct kvm_vcpu *vcpu, u32 msr, u64 data, bool host) { - struct kvm_vcpu_hv *hv_vcpu = &vcpu->arch.hyperv; + struct kvm_vcpu_hv *hv_vcpu = to_hv_vcpu(vcpu); switch (msr) { case HV_X64_MSR_VP_INDEX: { - struct kvm_hv *hv = &vcpu->kvm->arch.hyperv; + struct kvm_hv *hv = to_kvm_hv(vcpu->kvm); int vcpu_idx = kvm_vcpu_get_idx(vcpu); u32 new_vp_index = (u32)data; @@ -1291,14 +1405,14 @@ static int kvm_hv_set_msr(struct kvm_vcpu *vcpu, u32 msr, u64 data, bool host) case HV_X64_MSR_SIMP: case HV_X64_MSR_EOM: case HV_X64_MSR_SINT0 ... HV_X64_MSR_SINT15: - return synic_set_msr(vcpu_to_synic(vcpu), msr, data, host); + return synic_set_msr(to_hv_synic(vcpu), msr, data, host); case HV_X64_MSR_STIMER0_CONFIG: case HV_X64_MSR_STIMER1_CONFIG: case HV_X64_MSR_STIMER2_CONFIG: case HV_X64_MSR_STIMER3_CONFIG: { int timer_index = (msr - HV_X64_MSR_STIMER0_CONFIG)/2; - return stimer_set_config(vcpu_to_stimer(vcpu, timer_index), + return stimer_set_config(to_hv_stimer(vcpu, timer_index), data, host); } case HV_X64_MSR_STIMER0_COUNT: @@ -1307,7 +1421,7 @@ static int kvm_hv_set_msr(struct kvm_vcpu *vcpu, u32 msr, u64 data, bool host) case HV_X64_MSR_STIMER3_COUNT: { int timer_index = (msr - HV_X64_MSR_STIMER0_COUNT)/2; - return stimer_set_count(vcpu_to_stimer(vcpu, timer_index), + return stimer_set_count(to_hv_stimer(vcpu, timer_index), data, host); } case HV_X64_MSR_TSC_FREQUENCY: @@ -1330,7 +1444,7 @@ static int kvm_hv_get_msr_pw(struct kvm_vcpu *vcpu, u32 msr, u64 *pdata, { u64 data = 0; struct kvm *kvm = vcpu->kvm; - struct kvm_hv *hv = &kvm->arch.hyperv; + struct kvm_hv *hv = to_kvm_hv(kvm); switch (msr) { case HV_X64_MSR_GUEST_OS_ID: @@ -1346,11 +1460,11 @@ static int kvm_hv_get_msr_pw(struct kvm_vcpu *vcpu, u32 msr, u64 *pdata, data = hv->hv_tsc_page; break; case HV_X64_MSR_CRASH_P0 ... HV_X64_MSR_CRASH_P4: - return kvm_hv_msr_get_crash_data(vcpu, + return kvm_hv_msr_get_crash_data(kvm, msr - HV_X64_MSR_CRASH_P0, pdata); case HV_X64_MSR_CRASH_CTL: - return kvm_hv_msr_get_crash_ctl(vcpu, pdata); + return kvm_hv_msr_get_crash_ctl(kvm, pdata); case HV_X64_MSR_RESET: data = 0; break; @@ -1379,7 +1493,7 @@ static int kvm_hv_get_msr(struct kvm_vcpu *vcpu, u32 msr, u64 *pdata, bool host) { u64 data = 0; - struct kvm_vcpu_hv *hv_vcpu = &vcpu->arch.hyperv; + struct kvm_vcpu_hv *hv_vcpu = to_hv_vcpu(vcpu); switch (msr) { case HV_X64_MSR_VP_INDEX: @@ -1403,14 +1517,14 @@ static int kvm_hv_get_msr(struct kvm_vcpu *vcpu, u32 msr, u64 *pdata, case HV_X64_MSR_SIMP: case HV_X64_MSR_EOM: case HV_X64_MSR_SINT0 ... HV_X64_MSR_SINT15: - return synic_get_msr(vcpu_to_synic(vcpu), msr, pdata, host); + return synic_get_msr(to_hv_synic(vcpu), msr, pdata, host); case HV_X64_MSR_STIMER0_CONFIG: case HV_X64_MSR_STIMER1_CONFIG: case HV_X64_MSR_STIMER2_CONFIG: case HV_X64_MSR_STIMER3_CONFIG: { int timer_index = (msr - HV_X64_MSR_STIMER0_CONFIG)/2; - return stimer_get_config(vcpu_to_stimer(vcpu, timer_index), + return stimer_get_config(to_hv_stimer(vcpu, timer_index), pdata); } case HV_X64_MSR_STIMER0_COUNT: @@ -1419,7 +1533,7 @@ static int kvm_hv_get_msr(struct kvm_vcpu *vcpu, u32 msr, u64 *pdata, case HV_X64_MSR_STIMER3_COUNT: { int timer_index = (msr - HV_X64_MSR_STIMER0_COUNT)/2; - return stimer_get_count(vcpu_to_stimer(vcpu, timer_index), + return stimer_get_count(to_hv_stimer(vcpu, timer_index), pdata); } case HV_X64_MSR_TSC_FREQUENCY: @@ -1438,12 +1552,22 @@ static int kvm_hv_get_msr(struct kvm_vcpu *vcpu, u32 msr, u64 *pdata, int kvm_hv_set_msr_common(struct kvm_vcpu *vcpu, u32 msr, u64 data, bool host) { + struct kvm_hv *hv = to_kvm_hv(vcpu->kvm); + + if (!host && !vcpu->arch.hyperv_enabled) + return 1; + + if (!to_hv_vcpu(vcpu)) { + if (kvm_hv_vcpu_init(vcpu)) + return 1; + } + if (kvm_hv_msr_partition_wide(msr)) { int r; - mutex_lock(&vcpu->kvm->arch.hyperv.hv_lock); + mutex_lock(&hv->hv_lock); r = kvm_hv_set_msr_pw(vcpu, msr, data, host); - mutex_unlock(&vcpu->kvm->arch.hyperv.hv_lock); + mutex_unlock(&hv->hv_lock); return r; } else return kvm_hv_set_msr(vcpu, msr, data, host); @@ -1451,12 +1575,22 @@ int kvm_hv_set_msr_common(struct kvm_vcpu *vcpu, u32 msr, u64 data, bool host) int kvm_hv_get_msr_common(struct kvm_vcpu *vcpu, u32 msr, u64 *pdata, bool host) { + struct kvm_hv *hv = to_kvm_hv(vcpu->kvm); + + if (!host && !vcpu->arch.hyperv_enabled) + return 1; + + if (!to_hv_vcpu(vcpu)) { + if (kvm_hv_vcpu_init(vcpu)) + return 1; + } + if (kvm_hv_msr_partition_wide(msr)) { int r; - mutex_lock(&vcpu->kvm->arch.hyperv.hv_lock); + mutex_lock(&hv->hv_lock); r = kvm_hv_get_msr_pw(vcpu, msr, pdata, host); - mutex_unlock(&vcpu->kvm->arch.hyperv.hv_lock); + mutex_unlock(&hv->hv_lock); return r; } else return kvm_hv_get_msr(vcpu, msr, pdata, host); @@ -1466,7 +1600,7 @@ static __always_inline unsigned long *sparse_set_to_vcpu_mask( struct kvm *kvm, u64 *sparse_banks, u64 valid_bank_mask, u64 *vp_bitmap, unsigned long *vcpu_bitmap) { - struct kvm_hv *hv = &kvm->arch.hyperv; + struct kvm_hv *hv = to_kvm_hv(kvm); struct kvm_vcpu *vcpu; int i, bank, sbank = 0; @@ -1483,18 +1617,16 @@ static __always_inline unsigned long *sparse_set_to_vcpu_mask( bitmap_zero(vcpu_bitmap, KVM_MAX_VCPUS); kvm_for_each_vcpu(i, vcpu, kvm) { - if (test_bit(vcpu_to_hv_vcpu(vcpu)->vp_index, - (unsigned long *)vp_bitmap)) + if (test_bit(kvm_hv_get_vpindex(vcpu), (unsigned long *)vp_bitmap)) __set_bit(i, vcpu_bitmap); } return vcpu_bitmap; } -static u64 kvm_hv_flush_tlb(struct kvm_vcpu *current_vcpu, u64 ingpa, - u16 rep_cnt, bool ex) +static u64 kvm_hv_flush_tlb(struct kvm_vcpu *vcpu, u64 ingpa, u16 rep_cnt, bool ex) { - struct kvm *kvm = current_vcpu->kvm; - struct kvm_vcpu_hv *hv_vcpu = ¤t_vcpu->arch.hyperv; + struct kvm *kvm = vcpu->kvm; + struct kvm_vcpu_hv *hv_vcpu = to_hv_vcpu(vcpu); struct hv_tlb_flush_ex flush_ex; struct hv_tlb_flush flush; u64 vp_bitmap[KVM_HV_MAX_SPARSE_VCPU_SET_BITS]; @@ -1592,10 +1724,10 @@ static void kvm_send_ipi_to_many(struct kvm *kvm, u32 vector, } } -static u64 kvm_hv_send_ipi(struct kvm_vcpu *current_vcpu, u64 ingpa, u64 outgpa, +static u64 kvm_hv_send_ipi(struct kvm_vcpu *vcpu, u64 ingpa, u64 outgpa, bool ex, bool fast) { - struct kvm *kvm = current_vcpu->kvm; + struct kvm *kvm = vcpu->kvm; struct hv_send_ipi_ex send_ipi_ex; struct hv_send_ipi send_ipi; u64 vp_bitmap[KVM_HV_MAX_SPARSE_VCPU_SET_BITS]; @@ -1666,9 +1798,20 @@ ret_success: return HV_STATUS_SUCCESS; } -bool kvm_hv_hypercall_enabled(struct kvm *kvm) +void kvm_hv_set_cpuid(struct kvm_vcpu *vcpu) { - return READ_ONCE(kvm->arch.hyperv.hv_guest_os_id) != 0; + struct kvm_cpuid_entry2 *entry; + + entry = kvm_find_cpuid_entry(vcpu, HYPERV_CPUID_INTERFACE, 0); + if (entry && entry->eax == HYPERV_CPUID_SIGNATURE_EAX) + vcpu->arch.hyperv_enabled = true; + else + vcpu->arch.hyperv_enabled = false; +} + +bool kvm_hv_hypercall_enabled(struct kvm_vcpu *vcpu) +{ + return vcpu->arch.hyperv_enabled && to_kvm_hv(vcpu->kvm)->hv_guest_os_id; } static void kvm_hv_hypercall_set_result(struct kvm_vcpu *vcpu, u64 result) @@ -1698,6 +1841,7 @@ static int kvm_hv_hypercall_complete_userspace(struct kvm_vcpu *vcpu) static u16 kvm_hvcall_signal_event(struct kvm_vcpu *vcpu, bool fast, u64 param) { + struct kvm_hv *hv = to_kvm_hv(vcpu->kvm); struct eventfd_ctx *eventfd; if (unlikely(!fast)) { @@ -1726,7 +1870,7 @@ static u16 kvm_hvcall_signal_event(struct kvm_vcpu *vcpu, bool fast, u64 param) /* the eventfd is protected by vcpu->kvm->srcu, but conn_to_evt isn't */ rcu_read_lock(); - eventfd = idr_find(&vcpu->kvm->arch.hyperv.conn_to_evt, param); + eventfd = idr_find(&hv->conn_to_evt, param); rcu_read_unlock(); if (!eventfd) return HV_STATUS_INVALID_PORT_ID; @@ -1745,7 +1889,7 @@ int kvm_hv_hypercall(struct kvm_vcpu *vcpu) * hypercall generates UD from non zero cpl and real mode * per HYPER-V spec */ - if (kvm_x86_ops.get_cpl(vcpu) != 0 || !is_protmode(vcpu)) { + if (static_call(kvm_x86_get_cpl)(vcpu) != 0 || !is_protmode(vcpu)) { kvm_queue_exception(vcpu, UD_VECTOR); return 1; } @@ -1793,7 +1937,7 @@ int kvm_hv_hypercall(struct kvm_vcpu *vcpu) fallthrough; /* maybe userspace knows this conn_id */ case HVCALL_POST_MESSAGE: /* don't bother userspace if it has no way to handle it */ - if (unlikely(rep || !vcpu_to_synic(vcpu)->active)) { + if (unlikely(rep || !to_hv_synic(vcpu)->active)) { ret = HV_STATUS_INVALID_HYPERCALL_INPUT; break; } @@ -1855,7 +1999,7 @@ int kvm_hv_hypercall(struct kvm_vcpu *vcpu) } fallthrough; case HVCALL_RESET_DEBUG_SESSION: { - struct kvm_hv_syndbg *syndbg = vcpu_to_hv_syndbg(vcpu); + struct kvm_hv_syndbg *syndbg = to_hv_syndbg(vcpu); if (!kvm_hv_is_syndbg_enabled(vcpu)) { ret = HV_STATUS_INVALID_HYPERCALL_CODE; @@ -1885,23 +2029,26 @@ int kvm_hv_hypercall(struct kvm_vcpu *vcpu) void kvm_hv_init_vm(struct kvm *kvm) { - mutex_init(&kvm->arch.hyperv.hv_lock); - idr_init(&kvm->arch.hyperv.conn_to_evt); + struct kvm_hv *hv = to_kvm_hv(kvm); + + mutex_init(&hv->hv_lock); + idr_init(&hv->conn_to_evt); } void kvm_hv_destroy_vm(struct kvm *kvm) { + struct kvm_hv *hv = to_kvm_hv(kvm); struct eventfd_ctx *eventfd; int i; - idr_for_each_entry(&kvm->arch.hyperv.conn_to_evt, eventfd, i) + idr_for_each_entry(&hv->conn_to_evt, eventfd, i) eventfd_ctx_put(eventfd); - idr_destroy(&kvm->arch.hyperv.conn_to_evt); + idr_destroy(&hv->conn_to_evt); } static int kvm_hv_eventfd_assign(struct kvm *kvm, u32 conn_id, int fd) { - struct kvm_hv *hv = &kvm->arch.hyperv; + struct kvm_hv *hv = to_kvm_hv(kvm); struct eventfd_ctx *eventfd; int ret; @@ -1925,7 +2072,7 @@ static int kvm_hv_eventfd_assign(struct kvm *kvm, u32 conn_id, int fd) static int kvm_hv_eventfd_deassign(struct kvm *kvm, u32 conn_id) { - struct kvm_hv *hv = &kvm->arch.hyperv; + struct kvm_hv *hv = to_kvm_hv(kvm); struct eventfd_ctx *eventfd; mutex_lock(&hv->hv_lock); @@ -1997,8 +2144,7 @@ int kvm_get_hv_cpuid(struct kvm_vcpu *vcpu, struct kvm_cpuid2 *cpuid, break; case HYPERV_CPUID_INTERFACE: - memcpy(signature, "Hv#1\0\0\0\0\0\0\0\0", 12); - ent->eax = signature[0]; + ent->eax = HYPERV_CPUID_SIGNATURE_EAX; break; case HYPERV_CPUID_VERSION: diff --git a/arch/x86/kvm/hyperv.h b/arch/x86/kvm/hyperv.h index 6d7def2b0aad..60547d5cb6d7 100644 --- a/arch/x86/kvm/hyperv.h +++ b/arch/x86/kvm/hyperv.h @@ -50,38 +50,46 @@ /* Hyper-V HV_X64_MSR_SYNDBG_OPTIONS bits */ #define HV_X64_SYNDBG_OPTION_USE_HCALLS BIT(2) -static inline struct kvm_vcpu_hv *vcpu_to_hv_vcpu(struct kvm_vcpu *vcpu) +static inline struct kvm_hv *to_kvm_hv(struct kvm *kvm) { - return &vcpu->arch.hyperv; + return &kvm->arch.hyperv; } -static inline struct kvm_vcpu *hv_vcpu_to_vcpu(struct kvm_vcpu_hv *hv_vcpu) +static inline struct kvm_vcpu_hv *to_hv_vcpu(struct kvm_vcpu *vcpu) { - struct kvm_vcpu_arch *arch; - - arch = container_of(hv_vcpu, struct kvm_vcpu_arch, hyperv); - return container_of(arch, struct kvm_vcpu, arch); + return vcpu->arch.hyperv; } -static inline struct kvm_vcpu_hv_synic *vcpu_to_synic(struct kvm_vcpu *vcpu) +static inline struct kvm_vcpu_hv_synic *to_hv_synic(struct kvm_vcpu *vcpu) { - return &vcpu->arch.hyperv.synic; + struct kvm_vcpu_hv *hv_vcpu = to_hv_vcpu(vcpu); + + return &hv_vcpu->synic; } -static inline struct kvm_vcpu *synic_to_vcpu(struct kvm_vcpu_hv_synic *synic) +static inline struct kvm_vcpu *hv_synic_to_vcpu(struct kvm_vcpu_hv_synic *synic) { - return hv_vcpu_to_vcpu(container_of(synic, struct kvm_vcpu_hv, synic)); + struct kvm_vcpu_hv *hv_vcpu = container_of(synic, struct kvm_vcpu_hv, synic); + + return hv_vcpu->vcpu; } -static inline struct kvm_hv_syndbg *vcpu_to_hv_syndbg(struct kvm_vcpu *vcpu) +static inline struct kvm_hv_syndbg *to_hv_syndbg(struct kvm_vcpu *vcpu) { return &vcpu->kvm->arch.hyperv.hv_syndbg; } +static inline u32 kvm_hv_get_vpindex(struct kvm_vcpu *vcpu) +{ + struct kvm_vcpu_hv *hv_vcpu = to_hv_vcpu(vcpu); + + return hv_vcpu ? hv_vcpu->vp_index : kvm_vcpu_get_idx(vcpu); +} + int kvm_hv_set_msr_common(struct kvm_vcpu *vcpu, u32 msr, u64 data, bool host); int kvm_hv_get_msr_common(struct kvm_vcpu *vcpu, u32 msr, u64 *pdata, bool host); -bool kvm_hv_hypercall_enabled(struct kvm *kvm); +bool kvm_hv_hypercall_enabled(struct kvm_vcpu *vcpu); int kvm_hv_hypercall(struct kvm_vcpu *vcpu); void kvm_hv_irq_routing_update(struct kvm *kvm); @@ -89,32 +97,35 @@ int kvm_hv_synic_set_irq(struct kvm *kvm, u32 vcpu_id, u32 sint); void kvm_hv_synic_send_eoi(struct kvm_vcpu *vcpu, int vector); int kvm_hv_activate_synic(struct kvm_vcpu *vcpu, bool dont_zero_synic_pages); -void kvm_hv_vcpu_init(struct kvm_vcpu *vcpu); -void kvm_hv_vcpu_postcreate(struct kvm_vcpu *vcpu); void kvm_hv_vcpu_uninit(struct kvm_vcpu *vcpu); bool kvm_hv_assist_page_enabled(struct kvm_vcpu *vcpu); bool kvm_hv_get_assist_page(struct kvm_vcpu *vcpu, struct hv_vp_assist_page *assist_page); -static inline struct kvm_vcpu_hv_stimer *vcpu_to_stimer(struct kvm_vcpu *vcpu, - int timer_index) +static inline struct kvm_vcpu_hv_stimer *to_hv_stimer(struct kvm_vcpu *vcpu, + int timer_index) { - return &vcpu_to_hv_vcpu(vcpu)->stimer[timer_index]; + return &to_hv_vcpu(vcpu)->stimer[timer_index]; } -static inline struct kvm_vcpu *stimer_to_vcpu(struct kvm_vcpu_hv_stimer *stimer) +static inline struct kvm_vcpu *hv_stimer_to_vcpu(struct kvm_vcpu_hv_stimer *stimer) { struct kvm_vcpu_hv *hv_vcpu; hv_vcpu = container_of(stimer - stimer->index, struct kvm_vcpu_hv, stimer[0]); - return hv_vcpu_to_vcpu(hv_vcpu); + return hv_vcpu->vcpu; } static inline bool kvm_hv_has_stimer_pending(struct kvm_vcpu *vcpu) { - return !bitmap_empty(vcpu->arch.hyperv.stimer_pending_bitmap, + struct kvm_vcpu_hv *hv_vcpu = to_hv_vcpu(vcpu); + + if (!hv_vcpu) + return false; + + return !bitmap_empty(hv_vcpu->stimer_pending_bitmap, HV_SYNIC_STIMER_COUNT); } @@ -122,9 +133,11 @@ void kvm_hv_process_stimers(struct kvm_vcpu *vcpu); void kvm_hv_setup_tsc_page(struct kvm *kvm, struct pvclock_vcpu_time_info *hv_clock); +void kvm_hv_invalidate_tsc_page(struct kvm *kvm); void kvm_hv_init_vm(struct kvm *kvm); void kvm_hv_destroy_vm(struct kvm *kvm); +void kvm_hv_set_cpuid(struct kvm_vcpu *vcpu); int kvm_vm_ioctl_hv_eventfd(struct kvm *kvm, struct kvm_hyperv_eventfd *args); int kvm_get_hv_cpuid(struct kvm_vcpu *vcpu, struct kvm_cpuid2 *cpuid, struct kvm_cpuid_entry2 __user *entries); diff --git a/arch/x86/kvm/irq.c b/arch/x86/kvm/irq.c index 814698e5b152..172b05343cfd 100644 --- a/arch/x86/kvm/irq.c +++ b/arch/x86/kvm/irq.c @@ -14,6 +14,7 @@ #include "irq.h" #include "i8254.h" #include "x86.h" +#include "xen.h" /* * check if there are pending timer events @@ -56,6 +57,9 @@ int kvm_cpu_has_extint(struct kvm_vcpu *v) if (!lapic_in_kernel(v)) return v->arch.interrupt.injected; + if (kvm_xen_has_interrupt(v)) + return 1; + if (!kvm_apic_accept_pic_intr(v)) return 0; @@ -110,6 +114,9 @@ static int kvm_cpu_get_extint(struct kvm_vcpu *v) if (!lapic_in_kernel(v)) return v->arch.interrupt.nr; + if (kvm_xen_has_interrupt(v)) + return v->kvm->arch.xen.upcall_vector; + if (irqchip_split(v->kvm)) { int vector = v->arch.pending_external_vector; @@ -143,8 +150,7 @@ void __kvm_migrate_timers(struct kvm_vcpu *vcpu) { __kvm_migrate_apic_timer(vcpu); __kvm_migrate_pit_timer(vcpu); - if (kvm_x86_ops.migrate_timers) - kvm_x86_ops.migrate_timers(vcpu); + static_call_cond(kvm_x86_migrate_timers)(vcpu); } bool kvm_arch_irqfd_allowed(struct kvm *kvm, struct kvm_irqfd *args) diff --git a/arch/x86/kvm/kvm_cache_regs.h b/arch/x86/kvm/kvm_cache_regs.h index a889563ad02d..2e11da2f5621 100644 --- a/arch/x86/kvm/kvm_cache_regs.h +++ b/arch/x86/kvm/kvm_cache_regs.h @@ -68,7 +68,7 @@ static inline unsigned long kvm_register_read(struct kvm_vcpu *vcpu, int reg) return 0; if (!kvm_register_is_available(vcpu, reg)) - kvm_x86_ops.cache_reg(vcpu, reg); + static_call(kvm_x86_cache_reg)(vcpu, reg); return vcpu->arch.regs[reg]; } @@ -108,7 +108,7 @@ static inline u64 kvm_pdptr_read(struct kvm_vcpu *vcpu, int index) might_sleep(); /* on svm */ if (!kvm_register_is_available(vcpu, VCPU_EXREG_PDPTR)) - kvm_x86_ops.cache_reg(vcpu, VCPU_EXREG_PDPTR); + static_call(kvm_x86_cache_reg)(vcpu, VCPU_EXREG_PDPTR); return vcpu->arch.walk_mmu->pdptrs[index]; } @@ -118,7 +118,7 @@ static inline ulong kvm_read_cr0_bits(struct kvm_vcpu *vcpu, ulong mask) ulong tmask = mask & KVM_POSSIBLE_CR0_GUEST_BITS; if ((tmask & vcpu->arch.cr0_guest_owned_bits) && !kvm_register_is_available(vcpu, VCPU_EXREG_CR0)) - kvm_x86_ops.cache_reg(vcpu, VCPU_EXREG_CR0); + static_call(kvm_x86_cache_reg)(vcpu, VCPU_EXREG_CR0); return vcpu->arch.cr0 & mask; } @@ -132,14 +132,14 @@ static inline ulong kvm_read_cr4_bits(struct kvm_vcpu *vcpu, ulong mask) ulong tmask = mask & KVM_POSSIBLE_CR4_GUEST_BITS; if ((tmask & vcpu->arch.cr4_guest_owned_bits) && !kvm_register_is_available(vcpu, VCPU_EXREG_CR4)) - kvm_x86_ops.cache_reg(vcpu, VCPU_EXREG_CR4); + static_call(kvm_x86_cache_reg)(vcpu, VCPU_EXREG_CR4); return vcpu->arch.cr4 & mask; } static inline ulong kvm_read_cr3(struct kvm_vcpu *vcpu) { if (!kvm_register_is_available(vcpu, VCPU_EXREG_CR3)) - kvm_x86_ops.cache_reg(vcpu, VCPU_EXREG_CR3); + static_call(kvm_x86_cache_reg)(vcpu, VCPU_EXREG_CR3); return vcpu->arch.cr3; } diff --git a/arch/x86/kvm/kvm_emulate.h b/arch/x86/kvm/kvm_emulate.h index 43c93ffa76ed..0d359115429a 100644 --- a/arch/x86/kvm/kvm_emulate.h +++ b/arch/x86/kvm/kvm_emulate.h @@ -205,7 +205,7 @@ struct x86_emulate_ops { ulong (*get_cr)(struct x86_emulate_ctxt *ctxt, int cr); int (*set_cr)(struct x86_emulate_ctxt *ctxt, int cr, ulong val); int (*cpl)(struct x86_emulate_ctxt *ctxt); - int (*get_dr)(struct x86_emulate_ctxt *ctxt, int dr, ulong *dest); + void (*get_dr)(struct x86_emulate_ctxt *ctxt, int dr, ulong *dest); int (*set_dr)(struct x86_emulate_ctxt *ctxt, int dr, ulong value); u64 (*get_smbase)(struct x86_emulate_ctxt *ctxt); void (*set_smbase)(struct x86_emulate_ctxt *ctxt, u64 smbase); diff --git a/arch/x86/kvm/lapic.c b/arch/x86/kvm/lapic.c index 43cceadd073e..cc369b9ad8f1 100644 --- a/arch/x86/kvm/lapic.c +++ b/arch/x86/kvm/lapic.c @@ -91,8 +91,8 @@ static inline int __apic_test_and_clear_vector(int vec, void *bitmap) return __test_and_clear_bit(VEC_POS(vec), (bitmap) + REG_POS(vec)); } -struct static_key_deferred apic_hw_disabled __read_mostly; -struct static_key_deferred apic_sw_disabled __read_mostly; +__read_mostly DEFINE_STATIC_KEY_DEFERRED_FALSE(apic_hw_disabled, HZ); +__read_mostly DEFINE_STATIC_KEY_DEFERRED_FALSE(apic_sw_disabled, HZ); static inline int apic_enabled(struct kvm_lapic *apic) { @@ -290,9 +290,9 @@ static inline void apic_set_spiv(struct kvm_lapic *apic, u32 val) if (enabled != apic->sw_enabled) { apic->sw_enabled = enabled; if (enabled) - static_key_slow_dec_deferred(&apic_sw_disabled); + static_branch_slow_dec_deferred(&apic_sw_disabled); else - static_key_slow_inc(&apic_sw_disabled.key); + static_branch_inc(&apic_sw_disabled.key); atomic_set_release(&apic->vcpu->kvm->arch.apic_map_dirty, DIRTY); } @@ -484,7 +484,7 @@ static inline void apic_clear_irr(int vec, struct kvm_lapic *apic) if (unlikely(vcpu->arch.apicv_active)) { /* need to update RVI */ kvm_lapic_clear_vector(vec, apic->regs + APIC_IRR); - kvm_x86_ops.hwapic_irr_update(vcpu, + static_call(kvm_x86_hwapic_irr_update)(vcpu, apic_find_highest_irr(apic)); } else { apic->irr_pending = false; @@ -515,7 +515,7 @@ static inline void apic_set_isr(int vec, struct kvm_lapic *apic) * just set SVI. */ if (unlikely(vcpu->arch.apicv_active)) - kvm_x86_ops.hwapic_isr_update(vcpu, vec); + static_call(kvm_x86_hwapic_isr_update)(vcpu, vec); else { ++apic->isr_count; BUG_ON(apic->isr_count > MAX_APIC_VECTOR); @@ -563,8 +563,8 @@ static inline void apic_clear_isr(int vec, struct kvm_lapic *apic) * and must be left alone. */ if (unlikely(vcpu->arch.apicv_active)) - kvm_x86_ops.hwapic_isr_update(vcpu, - apic_find_highest_isr(apic)); + static_call(kvm_x86_hwapic_isr_update)(vcpu, + apic_find_highest_isr(apic)); else { --apic->isr_count; BUG_ON(apic->isr_count < 0); @@ -701,7 +701,7 @@ static int apic_has_interrupt_for_ppr(struct kvm_lapic *apic, u32 ppr) { int highest_irr; if (apic->vcpu->arch.apicv_active) - highest_irr = kvm_x86_ops.sync_pir_to_irr(apic->vcpu); + highest_irr = static_call(kvm_x86_sync_pir_to_irr)(apic->vcpu); else highest_irr = apic_find_highest_irr(apic); if (highest_irr == -1 || (highest_irr & 0xF0) <= ppr) @@ -1090,7 +1090,7 @@ static int __apic_accept_irq(struct kvm_lapic *apic, int delivery_mode, apic->regs + APIC_TMR); } - if (kvm_x86_ops.deliver_posted_interrupt(vcpu, vector)) { + if (static_call(kvm_x86_deliver_posted_interrupt)(vcpu, vector)) { kvm_lapic_set_irr(vector, apic); kvm_make_request(KVM_REQ_EVENT, vcpu); kvm_vcpu_kick(vcpu); @@ -1245,7 +1245,8 @@ static int apic_set_eoi(struct kvm_lapic *apic) apic_clear_isr(vector, apic); apic_update_ppr(apic); - if (test_bit(vector, vcpu_to_synic(apic->vcpu)->vec_bitmap)) + if (to_hv_vcpu(apic->vcpu) && + test_bit(vector, to_hv_synic(apic->vcpu)->vec_bitmap)) kvm_hv_synic_send_eoi(apic->vcpu, vector); kvm_ioapic_send_eoi(apic, vector); @@ -1641,7 +1642,16 @@ static void apic_timer_expired(struct kvm_lapic *apic, bool from_timer_fn) } if (kvm_use_posted_timer_interrupt(apic->vcpu)) { - kvm_wait_lapic_expire(vcpu); + /* + * Ensure the guest's timer has truly expired before posting an + * interrupt. Open code the relevant checks to avoid querying + * lapic_timer_int_injected(), which will be false since the + * interrupt isn't yet injected. Waiting until after injecting + * is not an option since that won't help a posted interrupt. + */ + if (vcpu->arch.apic->lapic_timer.expired_tscdeadline && + vcpu->arch.apic->lapic_timer.timer_advance_ns) + __kvm_wait_lapic_expire(vcpu); kvm_apic_inject_pending_timer_irqs(apic); return; } @@ -1814,7 +1824,7 @@ static void cancel_hv_timer(struct kvm_lapic *apic) { WARN_ON(preemptible()); WARN_ON(!apic->lapic_timer.hv_timer_in_use); - kvm_x86_ops.cancel_hv_timer(apic->vcpu); + static_call(kvm_x86_cancel_hv_timer)(apic->vcpu); apic->lapic_timer.hv_timer_in_use = false; } @@ -1831,7 +1841,7 @@ static bool start_hv_timer(struct kvm_lapic *apic) if (!ktimer->tscdeadline) return false; - if (kvm_x86_ops.set_hv_timer(vcpu, ktimer->tscdeadline, &expired)) + if (static_call(kvm_x86_set_hv_timer)(vcpu, ktimer->tscdeadline, &expired)) return false; ktimer->hv_timer_in_use = true; @@ -2175,10 +2185,10 @@ void kvm_free_lapic(struct kvm_vcpu *vcpu) hrtimer_cancel(&apic->lapic_timer.timer); if (!(vcpu->arch.apic_base & MSR_IA32_APICBASE_ENABLE)) - static_key_slow_dec_deferred(&apic_hw_disabled); + static_branch_slow_dec_deferred(&apic_hw_disabled); if (!apic->sw_enabled) - static_key_slow_dec_deferred(&apic_sw_disabled); + static_branch_slow_dec_deferred(&apic_sw_disabled); if (apic->regs) free_page((unsigned long)apic->regs); @@ -2250,9 +2260,9 @@ void kvm_lapic_set_base(struct kvm_vcpu *vcpu, u64 value) if ((old_value ^ value) & MSR_IA32_APICBASE_ENABLE) { if (value & MSR_IA32_APICBASE_ENABLE) { kvm_apic_set_xapic_id(apic, vcpu->vcpu_id); - static_key_slow_dec_deferred(&apic_hw_disabled); + static_branch_slow_dec_deferred(&apic_hw_disabled); } else { - static_key_slow_inc(&apic_hw_disabled.key); + static_branch_inc(&apic_hw_disabled.key); atomic_set_release(&apic->vcpu->kvm->arch.apic_map_dirty, DIRTY); } } @@ -2261,7 +2271,7 @@ void kvm_lapic_set_base(struct kvm_vcpu *vcpu, u64 value) kvm_apic_set_x2apic_id(apic, vcpu->vcpu_id); if ((old_value ^ value) & (MSR_IA32_APICBASE_ENABLE | X2APIC_ENABLE)) - kvm_x86_ops.set_virtual_apic_mode(vcpu); + static_call(kvm_x86_set_virtual_apic_mode)(vcpu); apic->base_address = apic->vcpu->arch.apic_base & MSR_IA32_APICBASE_BASE; @@ -2338,9 +2348,9 @@ void kvm_lapic_reset(struct kvm_vcpu *vcpu, bool init_event) vcpu->arch.pv_eoi.msr_val = 0; apic_update_ppr(apic); if (vcpu->arch.apicv_active) { - kvm_x86_ops.apicv_post_state_restore(vcpu); - kvm_x86_ops.hwapic_irr_update(vcpu, -1); - kvm_x86_ops.hwapic_isr_update(vcpu, -1); + static_call(kvm_x86_apicv_post_state_restore)(vcpu); + static_call(kvm_x86_hwapic_irr_update)(vcpu, -1); + static_call(kvm_x86_hwapic_isr_update)(vcpu, -1); } vcpu->arch.apic_arb_prio = 0; @@ -2449,7 +2459,7 @@ int kvm_create_lapic(struct kvm_vcpu *vcpu, int timer_advance_ns) * thinking that APIC state has changed. */ vcpu->arch.apic_base = MSR_IA32_APICBASE_ENABLE; - static_key_slow_inc(&apic_sw_disabled.key); /* sw disabled at reset */ + static_branch_inc(&apic_sw_disabled.key); /* sw disabled at reset */ kvm_iodevice_init(&apic->dev, &apic_mmio_ops); return 0; @@ -2512,7 +2522,7 @@ int kvm_get_apic_interrupt(struct kvm_vcpu *vcpu) */ apic_clear_irr(vector, apic); - if (test_bit(vector, vcpu_to_synic(vcpu)->auto_eoi_bitmap)) { + if (to_hv_vcpu(vcpu) && test_bit(vector, to_hv_synic(vcpu)->auto_eoi_bitmap)) { /* * For auto-EOI interrupts, there might be another pending * interrupt above PPR, so check whether to raise another @@ -2594,6 +2604,7 @@ int kvm_apic_set_state(struct kvm_vcpu *vcpu, struct kvm_lapic_state *s) apic_update_ppr(apic); hrtimer_cancel(&apic->lapic_timer.timer); + apic->lapic_timer.expired_tscdeadline = 0; apic_update_lvtt(apic); apic_manage_nmi_watchdog(apic, kvm_lapic_get_reg(apic, APIC_LVT0)); update_divide_count(apic); @@ -2601,10 +2612,10 @@ int kvm_apic_set_state(struct kvm_vcpu *vcpu, struct kvm_lapic_state *s) kvm_apic_update_apicv(vcpu); apic->highest_isr_cache = -1; if (vcpu->arch.apicv_active) { - kvm_x86_ops.apicv_post_state_restore(vcpu); - kvm_x86_ops.hwapic_irr_update(vcpu, + static_call(kvm_x86_apicv_post_state_restore)(vcpu); + static_call(kvm_x86_hwapic_irr_update)(vcpu, apic_find_highest_irr(apic)); - kvm_x86_ops.hwapic_isr_update(vcpu, + static_call(kvm_x86_hwapic_isr_update)(vcpu, apic_find_highest_isr(apic)); } kvm_make_request(KVM_REQ_EVENT, vcpu); @@ -2904,13 +2915,6 @@ void kvm_apic_accept_events(struct kvm_vcpu *vcpu) } } -void kvm_lapic_init(void) -{ - /* do not patch jump label more than once per second */ - jump_label_rate_limit(&apic_hw_disabled, HZ); - jump_label_rate_limit(&apic_sw_disabled, HZ); -} - void kvm_lapic_exit(void) { static_key_deferred_flush(&apic_hw_disabled); diff --git a/arch/x86/kvm/lapic.h b/arch/x86/kvm/lapic.h index 4fb86e3a9dd3..997c45a5963a 100644 --- a/arch/x86/kvm/lapic.h +++ b/arch/x86/kvm/lapic.h @@ -6,6 +6,8 @@ #include <linux/kvm_host.h> +#include "hyperv.h" + #define KVM_APIC_INIT 0 #define KVM_APIC_SIPI 1 #define KVM_APIC_LVT_NUM 6 @@ -125,13 +127,7 @@ int kvm_x2apic_msr_read(struct kvm_vcpu *vcpu, u32 msr, u64 *data); int kvm_hv_vapic_msr_write(struct kvm_vcpu *vcpu, u32 msr, u64 data); int kvm_hv_vapic_msr_read(struct kvm_vcpu *vcpu, u32 msr, u64 *data); -static inline bool kvm_hv_vapic_assist_page_enabled(struct kvm_vcpu *vcpu) -{ - return vcpu->arch.hyperv.hv_vapic & HV_X64_MSR_VP_ASSIST_PAGE_ENABLE; -} - int kvm_lapic_enable_pv_eoi(struct kvm_vcpu *vcpu, u64 data, unsigned long len); -void kvm_lapic_init(void); void kvm_lapic_exit(void); #define VEC_POS(v) ((v) & (32 - 1)) @@ -172,29 +168,29 @@ static inline void kvm_lapic_set_reg(struct kvm_lapic *apic, int reg_off, u32 va __kvm_lapic_set_reg(apic->regs, reg_off, val); } -extern struct static_key kvm_no_apic_vcpu; +DECLARE_STATIC_KEY_FALSE(kvm_has_noapic_vcpu); static inline bool lapic_in_kernel(struct kvm_vcpu *vcpu) { - if (static_key_false(&kvm_no_apic_vcpu)) + if (static_branch_unlikely(&kvm_has_noapic_vcpu)) return vcpu->arch.apic; return true; } -extern struct static_key_deferred apic_hw_disabled; +extern struct static_key_false_deferred apic_hw_disabled; static inline int kvm_apic_hw_enabled(struct kvm_lapic *apic) { - if (static_key_false(&apic_hw_disabled.key)) + if (static_branch_unlikely(&apic_hw_disabled.key)) return apic->vcpu->arch.apic_base & MSR_IA32_APICBASE_ENABLE; return MSR_IA32_APICBASE_ENABLE; } -extern struct static_key_deferred apic_sw_disabled; +extern struct static_key_false_deferred apic_sw_disabled; static inline bool kvm_apic_sw_enabled(struct kvm_lapic *apic) { - if (static_key_false(&apic_sw_disabled.key)) + if (static_branch_unlikely(&apic_sw_disabled.key)) return apic->sw_enabled; return true; } diff --git a/arch/x86/kvm/mmu.h b/arch/x86/kvm/mmu.h index 261be1d2032b..c68bfc3e2402 100644 --- a/arch/x86/kvm/mmu.h +++ b/arch/x86/kvm/mmu.h @@ -102,7 +102,7 @@ static inline void kvm_mmu_load_pgd(struct kvm_vcpu *vcpu) if (!VALID_PAGE(root_hpa)) return; - kvm_x86_ops.load_mmu_pgd(vcpu, root_hpa | kvm_get_active_pcid(vcpu), + static_call(kvm_x86_load_mmu_pgd)(vcpu, root_hpa | kvm_get_active_pcid(vcpu), vcpu->arch.mmu->shadow_root_level); } @@ -152,7 +152,7 @@ static inline int kvm_mmu_do_page_fault(struct kvm_vcpu *vcpu, gpa_t cr2_or_gpa, * * TODO: introduce APIs to split these two cases. */ -static inline int is_writable_pte(unsigned long pte) +static inline bool is_writable_pte(unsigned long pte) { return pte & PT_WRITABLE_MASK; } @@ -174,8 +174,8 @@ static inline u8 permission_fault(struct kvm_vcpu *vcpu, struct kvm_mmu *mmu, unsigned pte_access, unsigned pte_pkey, unsigned pfec) { - int cpl = kvm_x86_ops.get_cpl(vcpu); - unsigned long rflags = kvm_x86_ops.get_rflags(vcpu); + int cpl = static_call(kvm_x86_get_cpl)(vcpu); + unsigned long rflags = static_call(kvm_x86_get_rflags)(vcpu); /* * If CPL < 3, SMAP prevention are disabled if EFLAGS.AC = 1. diff --git a/arch/x86/kvm/mmu/mmu.c b/arch/x86/kvm/mmu/mmu.c index 6d16481aa29d..d75524bc8423 100644 --- a/arch/x86/kvm/mmu/mmu.c +++ b/arch/x86/kvm/mmu/mmu.c @@ -190,7 +190,7 @@ static void kvm_flush_remote_tlbs_with_range(struct kvm *kvm, int ret = -ENOTSUPP; if (range && kvm_x86_ops.tlb_remote_flush_with_range) - ret = kvm_x86_ops.tlb_remote_flush_with_range(kvm, range); + ret = static_call(kvm_x86_tlb_remote_flush_with_range)(kvm, range); if (ret) kvm_flush_remote_tlbs(kvm); @@ -844,17 +844,17 @@ static int pte_list_add(struct kvm_vcpu *vcpu, u64 *spte, int i, count = 0; if (!rmap_head->val) { - rmap_printk("pte_list_add: %p %llx 0->1\n", spte, *spte); + rmap_printk("%p %llx 0->1\n", spte, *spte); rmap_head->val = (unsigned long)spte; } else if (!(rmap_head->val & 1)) { - rmap_printk("pte_list_add: %p %llx 1->many\n", spte, *spte); + rmap_printk("%p %llx 1->many\n", spte, *spte); desc = mmu_alloc_pte_list_desc(vcpu); desc->sptes[0] = (u64 *)rmap_head->val; desc->sptes[1] = spte; rmap_head->val = (unsigned long)desc | 1; ++count; } else { - rmap_printk("pte_list_add: %p %llx many->many\n", spte, *spte); + rmap_printk("%p %llx many->many\n", spte, *spte); desc = (struct pte_list_desc *)(rmap_head->val & ~1ul); while (desc->sptes[PTE_LIST_EXT-1]) { count += PTE_LIST_EXT; @@ -906,14 +906,14 @@ static void __pte_list_remove(u64 *spte, struct kvm_rmap_head *rmap_head) pr_err("%s: %p 0->BUG\n", __func__, spte); BUG(); } else if (!(rmap_head->val & 1)) { - rmap_printk("%s: %p 1->0\n", __func__, spte); + rmap_printk("%p 1->0\n", spte); if ((u64 *)rmap_head->val != spte) { pr_err("%s: %p 1->BUG\n", __func__, spte); BUG(); } rmap_head->val = 0; } else { - rmap_printk("%s: %p many->many\n", __func__, spte); + rmap_printk("%p many->many\n", spte); desc = (struct pte_list_desc *)(rmap_head->val & ~1ul); prev_desc = NULL; while (desc) { @@ -1115,7 +1115,7 @@ static bool spte_write_protect(u64 *sptep, bool pt_protect) !(pt_protect && spte_can_locklessly_be_made_writable(spte))) return false; - rmap_printk("rmap_write_protect: spte %p %llx\n", sptep, *sptep); + rmap_printk("spte %p %llx\n", sptep, *sptep); if (pt_protect) spte &= ~SPTE_MMU_WRITEABLE; @@ -1142,7 +1142,7 @@ static bool spte_clear_dirty(u64 *sptep) { u64 spte = *sptep; - rmap_printk("rmap_clear_dirty: spte %p %llx\n", sptep, *sptep); + rmap_printk("spte %p %llx\n", sptep, *sptep); MMU_WARN_ON(!spte_ad_enabled(spte)); spte &= ~shadow_dirty_mask; @@ -1165,7 +1165,8 @@ static bool spte_wrprot_for_clear_dirty(u64 *sptep) * - W bit on ad-disabled SPTEs. * Returns true iff any D or W bits were cleared. */ -static bool __rmap_clear_dirty(struct kvm *kvm, struct kvm_rmap_head *rmap_head) +static bool __rmap_clear_dirty(struct kvm *kvm, struct kvm_rmap_head *rmap_head, + struct kvm_memory_slot *slot) { u64 *sptep; struct rmap_iterator iter; @@ -1180,35 +1181,6 @@ static bool __rmap_clear_dirty(struct kvm *kvm, struct kvm_rmap_head *rmap_head) return flush; } -static bool spte_set_dirty(u64 *sptep) -{ - u64 spte = *sptep; - - rmap_printk("rmap_set_dirty: spte %p %llx\n", sptep, *sptep); - - /* - * Similar to the !kvm_x86_ops.slot_disable_log_dirty case, - * do not bother adding back write access to pages marked - * SPTE_AD_WRPROT_ONLY_MASK. - */ - spte |= shadow_dirty_mask; - - return mmu_spte_update(sptep, spte); -} - -static bool __rmap_set_dirty(struct kvm *kvm, struct kvm_rmap_head *rmap_head) -{ - u64 *sptep; - struct rmap_iterator iter; - bool flush = false; - - for_each_rmap_spte(rmap_head, &iter, sptep) - if (spte_ad_enabled(*sptep)) - flush |= spte_set_dirty(sptep); - - return flush; -} - /** * kvm_mmu_write_protect_pt_masked - write protect selected PT level pages * @kvm: kvm instance @@ -1225,7 +1197,7 @@ static void kvm_mmu_write_protect_pt_masked(struct kvm *kvm, { struct kvm_rmap_head *rmap_head; - if (kvm->arch.tdp_mmu_enabled) + if (is_tdp_mmu_enabled(kvm)) kvm_tdp_mmu_clear_dirty_pt_masked(kvm, slot, slot->base_gfn + gfn_offset, mask, true); while (mask) { @@ -1248,25 +1220,24 @@ static void kvm_mmu_write_protect_pt_masked(struct kvm *kvm, * * Used for PML to re-log the dirty GPAs after userspace querying dirty_bitmap. */ -void kvm_mmu_clear_dirty_pt_masked(struct kvm *kvm, - struct kvm_memory_slot *slot, - gfn_t gfn_offset, unsigned long mask) +static void kvm_mmu_clear_dirty_pt_masked(struct kvm *kvm, + struct kvm_memory_slot *slot, + gfn_t gfn_offset, unsigned long mask) { struct kvm_rmap_head *rmap_head; - if (kvm->arch.tdp_mmu_enabled) + if (is_tdp_mmu_enabled(kvm)) kvm_tdp_mmu_clear_dirty_pt_masked(kvm, slot, slot->base_gfn + gfn_offset, mask, false); while (mask) { rmap_head = __gfn_to_rmap(slot->base_gfn + gfn_offset + __ffs(mask), PG_LEVEL_4K, slot); - __rmap_clear_dirty(kvm, rmap_head); + __rmap_clear_dirty(kvm, rmap_head, slot); /* clear the first set bit */ mask &= mask - 1; } } -EXPORT_SYMBOL_GPL(kvm_mmu_clear_dirty_pt_masked); /** * kvm_arch_mmu_enable_log_dirty_pt_masked - enable dirty logging for selected @@ -1282,19 +1253,15 @@ void kvm_arch_mmu_enable_log_dirty_pt_masked(struct kvm *kvm, struct kvm_memory_slot *slot, gfn_t gfn_offset, unsigned long mask) { - if (kvm_x86_ops.enable_log_dirty_pt_masked) - kvm_x86_ops.enable_log_dirty_pt_masked(kvm, slot, gfn_offset, - mask); + if (kvm_x86_ops.cpu_dirty_log_size) + kvm_mmu_clear_dirty_pt_masked(kvm, slot, gfn_offset, mask); else kvm_mmu_write_protect_pt_masked(kvm, slot, gfn_offset, mask); } int kvm_cpu_dirty_log_size(void) { - if (kvm_x86_ops.cpu_dirty_log_size) - return kvm_x86_ops.cpu_dirty_log_size(); - - return 0; + return kvm_x86_ops.cpu_dirty_log_size; } bool kvm_mmu_slot_gfn_write_protect(struct kvm *kvm, @@ -1309,7 +1276,7 @@ bool kvm_mmu_slot_gfn_write_protect(struct kvm *kvm, write_protected |= __rmap_write_protect(kvm, rmap_head, true); } - if (kvm->arch.tdp_mmu_enabled) + if (is_tdp_mmu_enabled(kvm)) write_protected |= kvm_tdp_mmu_write_protect_gfn(kvm, slot, gfn); @@ -1324,14 +1291,15 @@ static bool rmap_write_protect(struct kvm_vcpu *vcpu, u64 gfn) return kvm_mmu_slot_gfn_write_protect(vcpu->kvm, slot, gfn); } -static bool kvm_zap_rmapp(struct kvm *kvm, struct kvm_rmap_head *rmap_head) +static bool kvm_zap_rmapp(struct kvm *kvm, struct kvm_rmap_head *rmap_head, + struct kvm_memory_slot *slot) { u64 *sptep; struct rmap_iterator iter; bool flush = false; while ((sptep = rmap_get_first(rmap_head, &iter))) { - rmap_printk("%s: spte %p %llx.\n", __func__, sptep, *sptep); + rmap_printk("spte %p %llx.\n", sptep, *sptep); pte_list_remove(rmap_head, sptep); flush = true; @@ -1344,7 +1312,7 @@ static int kvm_unmap_rmapp(struct kvm *kvm, struct kvm_rmap_head *rmap_head, struct kvm_memory_slot *slot, gfn_t gfn, int level, unsigned long data) { - return kvm_zap_rmapp(kvm, rmap_head); + return kvm_zap_rmapp(kvm, rmap_head, slot); } static int kvm_set_pte_rmapp(struct kvm *kvm, struct kvm_rmap_head *rmap_head, @@ -1363,7 +1331,7 @@ static int kvm_set_pte_rmapp(struct kvm *kvm, struct kvm_rmap_head *rmap_head, restart: for_each_rmap_spte(rmap_head, &iter, sptep) { - rmap_printk("kvm_set_pte_rmapp: spte %p %llx gfn %llx (%d)\n", + rmap_printk("spte %p %llx gfn %llx (%d)\n", sptep, *sptep, gfn, level); need_flush = 1; @@ -1456,16 +1424,17 @@ static void slot_rmap_walk_next(struct slot_rmap_walk_iterator *iterator) slot_rmap_walk_okay(_iter_); \ slot_rmap_walk_next(_iter_)) -static int kvm_handle_hva_range(struct kvm *kvm, - unsigned long start, - unsigned long end, - unsigned long data, - int (*handler)(struct kvm *kvm, - struct kvm_rmap_head *rmap_head, - struct kvm_memory_slot *slot, - gfn_t gfn, - int level, - unsigned long data)) +static __always_inline int +kvm_handle_hva_range(struct kvm *kvm, + unsigned long start, + unsigned long end, + unsigned long data, + int (*handler)(struct kvm *kvm, + struct kvm_rmap_head *rmap_head, + struct kvm_memory_slot *slot, + gfn_t gfn, + int level, + unsigned long data)) { struct kvm_memslots *slots; struct kvm_memory_slot *memslot; @@ -1521,7 +1490,7 @@ int kvm_unmap_hva_range(struct kvm *kvm, unsigned long start, unsigned long end, r = kvm_handle_hva_range(kvm, start, end, 0, kvm_unmap_rmapp); - if (kvm->arch.tdp_mmu_enabled) + if (is_tdp_mmu_enabled(kvm)) r |= kvm_tdp_mmu_zap_hva_range(kvm, start, end); return r; @@ -1533,7 +1502,7 @@ int kvm_set_spte_hva(struct kvm *kvm, unsigned long hva, pte_t pte) r = kvm_handle_hva(kvm, hva, (unsigned long)&pte, kvm_set_pte_rmapp); - if (kvm->arch.tdp_mmu_enabled) + if (is_tdp_mmu_enabled(kvm)) r |= kvm_tdp_mmu_set_spte_hva(kvm, hva, &pte); return r; @@ -1588,7 +1557,7 @@ int kvm_age_hva(struct kvm *kvm, unsigned long start, unsigned long end) int young = false; young = kvm_handle_hva_range(kvm, start, end, 0, kvm_age_rmapp); - if (kvm->arch.tdp_mmu_enabled) + if (is_tdp_mmu_enabled(kvm)) young |= kvm_tdp_mmu_age_hva_range(kvm, start, end); return young; @@ -1599,7 +1568,7 @@ int kvm_test_age_hva(struct kvm *kvm, unsigned long hva) int young = false; young = kvm_handle_hva(kvm, hva, 0, kvm_test_age_rmapp); - if (kvm->arch.tdp_mmu_enabled) + if (is_tdp_mmu_enabled(kvm)) young |= kvm_tdp_mmu_test_age_hva(kvm, hva); return young; @@ -1723,13 +1692,6 @@ static int nonpaging_sync_page(struct kvm_vcpu *vcpu, return 0; } -static void nonpaging_update_pte(struct kvm_vcpu *vcpu, - struct kvm_mmu_page *sp, u64 *spte, - const void *pte) -{ - WARN_ON(1); -} - #define KVM_PAGE_ARRAY_NR 16 struct kvm_mmu_pages { @@ -2016,9 +1978,9 @@ static void mmu_sync_children(struct kvm_vcpu *vcpu, flush |= kvm_sync_page(vcpu, sp, &invalid_list); mmu_pages_clear_parents(&parents); } - if (need_resched() || spin_needbreak(&vcpu->kvm->mmu_lock)) { + if (need_resched() || rwlock_needbreak(&vcpu->kvm->mmu_lock)) { kvm_mmu_flush_or_zap(vcpu, &invalid_list, false, flush); - cond_resched_lock(&vcpu->kvm->mmu_lock); + cond_resched_rwlock_write(&vcpu->kvm->mmu_lock); flush = false; } } @@ -2417,7 +2379,7 @@ static unsigned long kvm_mmu_zap_oldest_mmu_pages(struct kvm *kvm, return 0; restart: - list_for_each_entry_safe(sp, tmp, &kvm->arch.active_mmu_pages, link) { + list_for_each_entry_safe_reverse(sp, tmp, &kvm->arch.active_mmu_pages, link) { /* * Don't zap active root pages, the page itself can't be freed * and zapping it will just force vCPUs to realloc and reload. @@ -2470,7 +2432,7 @@ static int make_mmu_pages_available(struct kvm_vcpu *vcpu) */ void kvm_mmu_change_mmu_pages(struct kvm *kvm, unsigned long goal_nr_mmu_pages) { - spin_lock(&kvm->mmu_lock); + write_lock(&kvm->mmu_lock); if (kvm->arch.n_used_mmu_pages > goal_nr_mmu_pages) { kvm_mmu_zap_oldest_mmu_pages(kvm, kvm->arch.n_used_mmu_pages - @@ -2481,7 +2443,7 @@ void kvm_mmu_change_mmu_pages(struct kvm *kvm, unsigned long goal_nr_mmu_pages) kvm->arch.n_max_mmu_pages = goal_nr_mmu_pages; - spin_unlock(&kvm->mmu_lock); + write_unlock(&kvm->mmu_lock); } int kvm_mmu_unprotect_page(struct kvm *kvm, gfn_t gfn) @@ -2492,7 +2454,7 @@ int kvm_mmu_unprotect_page(struct kvm *kvm, gfn_t gfn) pgprintk("%s: looking for gfn %llx\n", __func__, gfn); r = 0; - spin_lock(&kvm->mmu_lock); + write_lock(&kvm->mmu_lock); for_each_gfn_indirect_valid_sp(kvm, sp, gfn) { pgprintk("%s: gfn %llx role %x\n", __func__, gfn, sp->role.word); @@ -2500,11 +2462,25 @@ int kvm_mmu_unprotect_page(struct kvm *kvm, gfn_t gfn) kvm_mmu_prepare_zap_page(kvm, sp, &invalid_list); } kvm_mmu_commit_zap_page(kvm, &invalid_list); - spin_unlock(&kvm->mmu_lock); + write_unlock(&kvm->mmu_lock); + + return r; +} + +static int kvm_mmu_unprotect_page_virt(struct kvm_vcpu *vcpu, gva_t gva) +{ + gpa_t gpa; + int r; + + if (vcpu->arch.mmu->direct_map) + return 0; + + gpa = kvm_mmu_gva_to_gpa_read(vcpu, gva, NULL); + + r = kvm_mmu_unprotect_page(vcpu->kvm, gpa >> PAGE_SHIFT); return r; } -EXPORT_SYMBOL_GPL(kvm_mmu_unprotect_page); static void kvm_unsync_page(struct kvm_vcpu *vcpu, struct kvm_mmu_page *sp) { @@ -2758,11 +2734,18 @@ static void direct_pte_prefetch(struct kvm_vcpu *vcpu, u64 *sptep) if (sp->role.level > PG_LEVEL_4K) return; + /* + * If addresses are being invalidated, skip prefetching to avoid + * accidentally prefetching those addresses. + */ + if (unlikely(vcpu->kvm->mmu_notifier_count)) + return; + __direct_pte_prefetch(vcpu, sp, sptep); } -static int host_pfn_mapping_level(struct kvm_vcpu *vcpu, gfn_t gfn, - kvm_pfn_t pfn, struct kvm_memory_slot *slot) +static int host_pfn_mapping_level(struct kvm *kvm, gfn_t gfn, kvm_pfn_t pfn, + struct kvm_memory_slot *slot) { unsigned long hva; pte_t *pte; @@ -2781,19 +2764,36 @@ static int host_pfn_mapping_level(struct kvm_vcpu *vcpu, gfn_t gfn, */ hva = __gfn_to_hva_memslot(slot, gfn); - pte = lookup_address_in_mm(vcpu->kvm->mm, hva, &level); + pte = lookup_address_in_mm(kvm->mm, hva, &level); if (unlikely(!pte)) return PG_LEVEL_4K; return level; } +int kvm_mmu_max_mapping_level(struct kvm *kvm, struct kvm_memory_slot *slot, + gfn_t gfn, kvm_pfn_t pfn, int max_level) +{ + struct kvm_lpage_info *linfo; + + max_level = min(max_level, max_huge_page_level); + for ( ; max_level > PG_LEVEL_4K; max_level--) { + linfo = lpage_info_slot(gfn, slot, max_level); + if (!linfo->disallow_lpage) + break; + } + + if (max_level == PG_LEVEL_4K) + return PG_LEVEL_4K; + + return host_pfn_mapping_level(kvm, gfn, pfn, slot); +} + int kvm_mmu_hugepage_adjust(struct kvm_vcpu *vcpu, gfn_t gfn, int max_level, kvm_pfn_t *pfnp, bool huge_page_disallowed, int *req_level) { struct kvm_memory_slot *slot; - struct kvm_lpage_info *linfo; kvm_pfn_t pfn = *pfnp; kvm_pfn_t mask; int level; @@ -2810,17 +2810,7 @@ int kvm_mmu_hugepage_adjust(struct kvm_vcpu *vcpu, gfn_t gfn, if (!slot) return PG_LEVEL_4K; - max_level = min(max_level, max_huge_page_level); - for ( ; max_level > PG_LEVEL_4K; max_level--) { - linfo = lpage_info_slot(gfn, slot, max_level); - if (!linfo->disallow_lpage) - break; - } - - if (max_level == PG_LEVEL_4K) - return PG_LEVEL_4K; - - level = host_pfn_mapping_level(vcpu, gfn, pfn, slot); + level = kvm_mmu_max_mapping_level(vcpu->kvm, slot, gfn, pfn, max_level); if (level == PG_LEVEL_4K) return level; @@ -3161,7 +3151,7 @@ static void mmu_free_root_page(struct kvm *kvm, hpa_t *root_hpa, sp = to_shadow_page(*root_hpa & PT64_BASE_ADDR_MASK); if (kvm_mmu_put_root(kvm, sp)) { - if (sp->tdp_mmu_page) + if (is_tdp_mmu_page(sp)) kvm_tdp_mmu_free_root(kvm, sp); else if (sp->role.invalid) kvm_mmu_prepare_zap_page(kvm, sp, invalid_list); @@ -3192,7 +3182,7 @@ void kvm_mmu_free_roots(struct kvm_vcpu *vcpu, struct kvm_mmu *mmu, return; } - spin_lock(&kvm->mmu_lock); + write_lock(&kvm->mmu_lock); for (i = 0; i < KVM_MMU_NUM_PREV_ROOTS; i++) if (roots_to_free & KVM_MMU_ROOT_PREVIOUS(i)) @@ -3215,7 +3205,7 @@ void kvm_mmu_free_roots(struct kvm_vcpu *vcpu, struct kvm_mmu *mmu, } kvm_mmu_commit_zap_page(kvm, &invalid_list); - spin_unlock(&kvm->mmu_lock); + write_unlock(&kvm->mmu_lock); } EXPORT_SYMBOL_GPL(kvm_mmu_free_roots); @@ -3236,16 +3226,16 @@ static hpa_t mmu_alloc_root(struct kvm_vcpu *vcpu, gfn_t gfn, gva_t gva, { struct kvm_mmu_page *sp; - spin_lock(&vcpu->kvm->mmu_lock); + write_lock(&vcpu->kvm->mmu_lock); if (make_mmu_pages_available(vcpu)) { - spin_unlock(&vcpu->kvm->mmu_lock); + write_unlock(&vcpu->kvm->mmu_lock); return INVALID_PAGE; } sp = kvm_mmu_get_page(vcpu, gfn, gva, level, direct, ACC_ALL); ++sp->root_count; - spin_unlock(&vcpu->kvm->mmu_lock); + write_unlock(&vcpu->kvm->mmu_lock); return __pa(sp->spt); } @@ -3255,7 +3245,7 @@ static int mmu_alloc_direct_roots(struct kvm_vcpu *vcpu) hpa_t root; unsigned i; - if (vcpu->kvm->arch.tdp_mmu_enabled) { + if (is_tdp_mmu_enabled(vcpu->kvm)) { root = kvm_tdp_mmu_get_vcpu_root_hpa(vcpu); if (!VALID_PAGE(root)) @@ -3416,17 +3406,17 @@ void kvm_mmu_sync_roots(struct kvm_vcpu *vcpu) !smp_load_acquire(&sp->unsync_children)) return; - spin_lock(&vcpu->kvm->mmu_lock); + write_lock(&vcpu->kvm->mmu_lock); kvm_mmu_audit(vcpu, AUDIT_PRE_SYNC); mmu_sync_children(vcpu, sp); kvm_mmu_audit(vcpu, AUDIT_POST_SYNC); - spin_unlock(&vcpu->kvm->mmu_lock); + write_unlock(&vcpu->kvm->mmu_lock); return; } - spin_lock(&vcpu->kvm->mmu_lock); + write_lock(&vcpu->kvm->mmu_lock); kvm_mmu_audit(vcpu, AUDIT_PRE_SYNC); for (i = 0; i < 4; ++i) { @@ -3440,9 +3430,8 @@ void kvm_mmu_sync_roots(struct kvm_vcpu *vcpu) } kvm_mmu_audit(vcpu, AUDIT_POST_SYNC); - spin_unlock(&vcpu->kvm->mmu_lock); + write_unlock(&vcpu->kvm->mmu_lock); } -EXPORT_SYMBOL_GPL(kvm_mmu_sync_roots); static gpa_t nonpaging_gva_to_gpa(struct kvm_vcpu *vcpu, gpa_t vaddr, u32 access, struct x86_exception *exception) @@ -3658,8 +3647,8 @@ static bool kvm_arch_setup_async_pf(struct kvm_vcpu *vcpu, gpa_t cr2_or_gpa, } static bool try_async_pf(struct kvm_vcpu *vcpu, bool prefault, gfn_t gfn, - gpa_t cr2_or_gpa, kvm_pfn_t *pfn, bool write, - bool *writable) + gpa_t cr2_or_gpa, kvm_pfn_t *pfn, hva_t *hva, + bool write, bool *writable) { struct kvm_memory_slot *slot = kvm_vcpu_gfn_to_memslot(vcpu, gfn); bool async; @@ -3672,7 +3661,8 @@ static bool try_async_pf(struct kvm_vcpu *vcpu, bool prefault, gfn_t gfn, } async = false; - *pfn = __gfn_to_pfn_memslot(slot, gfn, false, &async, write, writable); + *pfn = __gfn_to_pfn_memslot(slot, gfn, false, &async, + write, writable, hva); if (!async) return false; /* *pfn has correct page already */ @@ -3686,7 +3676,8 @@ static bool try_async_pf(struct kvm_vcpu *vcpu, bool prefault, gfn_t gfn, return true; } - *pfn = __gfn_to_pfn_memslot(slot, gfn, false, NULL, write, writable); + *pfn = __gfn_to_pfn_memslot(slot, gfn, false, NULL, + write, writable, hva); return false; } @@ -3699,6 +3690,7 @@ static int direct_page_fault(struct kvm_vcpu *vcpu, gpa_t gpa, u32 error_code, gfn_t gfn = gpa >> PAGE_SHIFT; unsigned long mmu_seq; kvm_pfn_t pfn; + hva_t hva; int r; if (page_fault_handle_page_track(vcpu, error_code, gfn)) @@ -3717,15 +3709,21 @@ static int direct_page_fault(struct kvm_vcpu *vcpu, gpa_t gpa, u32 error_code, mmu_seq = vcpu->kvm->mmu_notifier_seq; smp_rmb(); - if (try_async_pf(vcpu, prefault, gfn, gpa, &pfn, write, &map_writable)) + if (try_async_pf(vcpu, prefault, gfn, gpa, &pfn, &hva, + write, &map_writable)) return RET_PF_RETRY; if (handle_abnormal_pfn(vcpu, is_tdp ? 0 : gpa, gfn, pfn, ACC_ALL, &r)) return r; r = RET_PF_RETRY; - spin_lock(&vcpu->kvm->mmu_lock); - if (mmu_notifier_retry(vcpu->kvm, mmu_seq)) + + if (is_tdp_mmu_root(vcpu->kvm, vcpu->arch.mmu->root_hpa)) + read_lock(&vcpu->kvm->mmu_lock); + else + write_lock(&vcpu->kvm->mmu_lock); + + if (!is_noslot_pfn(pfn) && mmu_notifier_retry_hva(vcpu->kvm, mmu_seq, hva)) goto out_unlock; r = make_mmu_pages_available(vcpu); if (r) @@ -3739,7 +3737,10 @@ static int direct_page_fault(struct kvm_vcpu *vcpu, gpa_t gpa, u32 error_code, prefault, is_tdp); out_unlock: - spin_unlock(&vcpu->kvm->mmu_lock); + if (is_tdp_mmu_root(vcpu->kvm, vcpu->arch.mmu->root_hpa)) + read_unlock(&vcpu->kvm->mmu_lock); + else + write_unlock(&vcpu->kvm->mmu_lock); kvm_release_pfn_clean(pfn); return r; } @@ -3813,7 +3814,6 @@ static void nonpaging_init_context(struct kvm_vcpu *vcpu, context->gva_to_gpa = nonpaging_gva_to_gpa; context->sync_page = nonpaging_sync_page; context->invlpg = NULL; - context->update_pte = nonpaging_update_pte; context->root_level = 0; context->shadow_root_level = PT32E_ROOT_LEVEL; context->direct_map = true; @@ -3984,20 +3984,27 @@ static inline bool is_last_gpte(struct kvm_mmu *mmu, static void __reset_rsvds_bits_mask(struct kvm_vcpu *vcpu, struct rsvd_bits_validate *rsvd_check, - int maxphyaddr, int level, bool nx, bool gbpages, + u64 pa_bits_rsvd, int level, bool nx, bool gbpages, bool pse, bool amd) { - u64 exb_bit_rsvd = 0; u64 gbpages_bit_rsvd = 0; u64 nonleaf_bit8_rsvd = 0; + u64 high_bits_rsvd; rsvd_check->bad_mt_xwr = 0; - if (!nx) - exb_bit_rsvd = rsvd_bits(63, 63); if (!gbpages) gbpages_bit_rsvd = rsvd_bits(7, 7); + if (level == PT32E_ROOT_LEVEL) + high_bits_rsvd = pa_bits_rsvd & rsvd_bits(0, 62); + else + high_bits_rsvd = pa_bits_rsvd & rsvd_bits(0, 51); + + /* Note, NX doesn't exist in PDPTEs, this is handled below. */ + if (!nx) + high_bits_rsvd |= rsvd_bits(63, 63); + /* * Non-leaf PML4Es and PDPEs reserve bit 8 (which would be the G bit for * leaf entries) on AMD CPUs only. @@ -4026,45 +4033,39 @@ __reset_rsvds_bits_mask(struct kvm_vcpu *vcpu, rsvd_check->rsvd_bits_mask[1][1] = rsvd_bits(13, 21); break; case PT32E_ROOT_LEVEL: - rsvd_check->rsvd_bits_mask[0][2] = - rsvd_bits(maxphyaddr, 63) | - rsvd_bits(5, 8) | rsvd_bits(1, 2); /* PDPTE */ - rsvd_check->rsvd_bits_mask[0][1] = exb_bit_rsvd | - rsvd_bits(maxphyaddr, 62); /* PDE */ - rsvd_check->rsvd_bits_mask[0][0] = exb_bit_rsvd | - rsvd_bits(maxphyaddr, 62); /* PTE */ - rsvd_check->rsvd_bits_mask[1][1] = exb_bit_rsvd | - rsvd_bits(maxphyaddr, 62) | - rsvd_bits(13, 20); /* large page */ + rsvd_check->rsvd_bits_mask[0][2] = rsvd_bits(63, 63) | + high_bits_rsvd | + rsvd_bits(5, 8) | + rsvd_bits(1, 2); /* PDPTE */ + rsvd_check->rsvd_bits_mask[0][1] = high_bits_rsvd; /* PDE */ + rsvd_check->rsvd_bits_mask[0][0] = high_bits_rsvd; /* PTE */ + rsvd_check->rsvd_bits_mask[1][1] = high_bits_rsvd | + rsvd_bits(13, 20); /* large page */ rsvd_check->rsvd_bits_mask[1][0] = rsvd_check->rsvd_bits_mask[0][0]; break; case PT64_ROOT_5LEVEL: - rsvd_check->rsvd_bits_mask[0][4] = exb_bit_rsvd | - nonleaf_bit8_rsvd | rsvd_bits(7, 7) | - rsvd_bits(maxphyaddr, 51); + rsvd_check->rsvd_bits_mask[0][4] = high_bits_rsvd | + nonleaf_bit8_rsvd | + rsvd_bits(7, 7); rsvd_check->rsvd_bits_mask[1][4] = rsvd_check->rsvd_bits_mask[0][4]; fallthrough; case PT64_ROOT_4LEVEL: - rsvd_check->rsvd_bits_mask[0][3] = exb_bit_rsvd | - nonleaf_bit8_rsvd | rsvd_bits(7, 7) | - rsvd_bits(maxphyaddr, 51); - rsvd_check->rsvd_bits_mask[0][2] = exb_bit_rsvd | - gbpages_bit_rsvd | - rsvd_bits(maxphyaddr, 51); - rsvd_check->rsvd_bits_mask[0][1] = exb_bit_rsvd | - rsvd_bits(maxphyaddr, 51); - rsvd_check->rsvd_bits_mask[0][0] = exb_bit_rsvd | - rsvd_bits(maxphyaddr, 51); + rsvd_check->rsvd_bits_mask[0][3] = high_bits_rsvd | + nonleaf_bit8_rsvd | + rsvd_bits(7, 7); + rsvd_check->rsvd_bits_mask[0][2] = high_bits_rsvd | + gbpages_bit_rsvd; + rsvd_check->rsvd_bits_mask[0][1] = high_bits_rsvd; + rsvd_check->rsvd_bits_mask[0][0] = high_bits_rsvd; rsvd_check->rsvd_bits_mask[1][3] = rsvd_check->rsvd_bits_mask[0][3]; - rsvd_check->rsvd_bits_mask[1][2] = exb_bit_rsvd | - gbpages_bit_rsvd | rsvd_bits(maxphyaddr, 51) | - rsvd_bits(13, 29); - rsvd_check->rsvd_bits_mask[1][1] = exb_bit_rsvd | - rsvd_bits(maxphyaddr, 51) | - rsvd_bits(13, 20); /* large page */ + rsvd_check->rsvd_bits_mask[1][2] = high_bits_rsvd | + gbpages_bit_rsvd | + rsvd_bits(13, 29); + rsvd_check->rsvd_bits_mask[1][1] = high_bits_rsvd | + rsvd_bits(13, 20); /* large page */ rsvd_check->rsvd_bits_mask[1][0] = rsvd_check->rsvd_bits_mask[0][0]; break; @@ -4075,8 +4076,8 @@ static void reset_rsvds_bits_mask(struct kvm_vcpu *vcpu, struct kvm_mmu *context) { __reset_rsvds_bits_mask(vcpu, &context->guest_rsvd_check, - cpuid_maxphyaddr(vcpu), context->root_level, - context->nx, + vcpu->arch.reserved_gpa_bits, + context->root_level, context->nx, guest_cpuid_has(vcpu, X86_FEATURE_GBPAGES), is_pse(vcpu), guest_cpuid_is_amd_or_hygon(vcpu)); @@ -4084,27 +4085,22 @@ static void reset_rsvds_bits_mask(struct kvm_vcpu *vcpu, static void __reset_rsvds_bits_mask_ept(struct rsvd_bits_validate *rsvd_check, - int maxphyaddr, bool execonly) + u64 pa_bits_rsvd, bool execonly) { + u64 high_bits_rsvd = pa_bits_rsvd & rsvd_bits(0, 51); u64 bad_mt_xwr; - rsvd_check->rsvd_bits_mask[0][4] = - rsvd_bits(maxphyaddr, 51) | rsvd_bits(3, 7); - rsvd_check->rsvd_bits_mask[0][3] = - rsvd_bits(maxphyaddr, 51) | rsvd_bits(3, 7); - rsvd_check->rsvd_bits_mask[0][2] = - rsvd_bits(maxphyaddr, 51) | rsvd_bits(3, 6); - rsvd_check->rsvd_bits_mask[0][1] = - rsvd_bits(maxphyaddr, 51) | rsvd_bits(3, 6); - rsvd_check->rsvd_bits_mask[0][0] = rsvd_bits(maxphyaddr, 51); + rsvd_check->rsvd_bits_mask[0][4] = high_bits_rsvd | rsvd_bits(3, 7); + rsvd_check->rsvd_bits_mask[0][3] = high_bits_rsvd | rsvd_bits(3, 7); + rsvd_check->rsvd_bits_mask[0][2] = high_bits_rsvd | rsvd_bits(3, 6); + rsvd_check->rsvd_bits_mask[0][1] = high_bits_rsvd | rsvd_bits(3, 6); + rsvd_check->rsvd_bits_mask[0][0] = high_bits_rsvd; /* large page */ rsvd_check->rsvd_bits_mask[1][4] = rsvd_check->rsvd_bits_mask[0][4]; rsvd_check->rsvd_bits_mask[1][3] = rsvd_check->rsvd_bits_mask[0][3]; - rsvd_check->rsvd_bits_mask[1][2] = - rsvd_bits(maxphyaddr, 51) | rsvd_bits(12, 29); - rsvd_check->rsvd_bits_mask[1][1] = - rsvd_bits(maxphyaddr, 51) | rsvd_bits(12, 20); + rsvd_check->rsvd_bits_mask[1][2] = high_bits_rsvd | rsvd_bits(12, 29); + rsvd_check->rsvd_bits_mask[1][1] = high_bits_rsvd | rsvd_bits(12, 20); rsvd_check->rsvd_bits_mask[1][0] = rsvd_check->rsvd_bits_mask[0][0]; bad_mt_xwr = 0xFFull << (2 * 8); /* bits 3..5 must not be 2 */ @@ -4123,7 +4119,12 @@ static void reset_rsvds_bits_mask_ept(struct kvm_vcpu *vcpu, struct kvm_mmu *context, bool execonly) { __reset_rsvds_bits_mask_ept(&context->guest_rsvd_check, - cpuid_maxphyaddr(vcpu), execonly); + vcpu->arch.reserved_gpa_bits, execonly); +} + +static inline u64 reserved_hpa_bits(void) +{ + return rsvd_bits(shadow_phys_bits, 63); } /* @@ -4145,7 +4146,7 @@ reset_shadow_zero_bits_mask(struct kvm_vcpu *vcpu, struct kvm_mmu *context) */ shadow_zero_check = &context->shadow_zero_check; __reset_rsvds_bits_mask(vcpu, shadow_zero_check, - shadow_phys_bits, + reserved_hpa_bits(), context->shadow_root_level, uses_nx, guest_cpuid_has(vcpu, X86_FEATURE_GBPAGES), is_pse(vcpu), true); @@ -4182,14 +4183,13 @@ reset_tdp_shadow_zero_bits_mask(struct kvm_vcpu *vcpu, if (boot_cpu_is_amd()) __reset_rsvds_bits_mask(vcpu, shadow_zero_check, - shadow_phys_bits, + reserved_hpa_bits(), context->shadow_root_level, false, boot_cpu_has(X86_FEATURE_GBPAGES), true, true); else __reset_rsvds_bits_mask_ept(shadow_zero_check, - shadow_phys_bits, - false); + reserved_hpa_bits(), false); if (!shadow_me_mask) return; @@ -4209,7 +4209,7 @@ reset_ept_shadow_zero_bits_mask(struct kvm_vcpu *vcpu, struct kvm_mmu *context, bool execonly) { __reset_rsvds_bits_mask_ept(&context->shadow_zero_check, - shadow_phys_bits, execonly); + reserved_hpa_bits(), execonly); } #define BYTE_MASK(access) \ @@ -4395,7 +4395,6 @@ static void paging64_init_context_common(struct kvm_vcpu *vcpu, context->gva_to_gpa = paging64_gva_to_gpa; context->sync_page = paging64_sync_page; context->invlpg = paging64_invlpg; - context->update_pte = paging64_update_pte; context->shadow_root_level = level; context->direct_map = false; } @@ -4424,7 +4423,6 @@ static void paging32_init_context(struct kvm_vcpu *vcpu, context->gva_to_gpa = paging32_gva_to_gpa; context->sync_page = paging32_sync_page; context->invlpg = paging32_invlpg; - context->update_pte = paging32_update_pte; context->shadow_root_level = PT32E_ROOT_LEVEL; context->direct_map = false; } @@ -4506,7 +4504,6 @@ static void init_kvm_tdp_mmu(struct kvm_vcpu *vcpu) context->page_fault = kvm_tdp_page_fault; context->sync_page = nonpaging_sync_page; context->invlpg = NULL; - context->update_pte = nonpaging_update_pte; context->shadow_root_level = kvm_mmu_get_tdp_level(vcpu); context->direct_map = true; context->get_guest_pgd = get_cr3; @@ -4678,7 +4675,6 @@ void kvm_init_shadow_ept_mmu(struct kvm_vcpu *vcpu, bool execonly, context->gva_to_gpa = ept_gva_to_gpa; context->sync_page = ept_sync_page; context->invlpg = ept_invlpg; - context->update_pte = ept_update_pte; context->root_level = level; context->direct_map = false; context->mmu_role.as_u64 = new_role.as_u64; @@ -4811,7 +4807,7 @@ int kvm_mmu_load(struct kvm_vcpu *vcpu) if (r) goto out; kvm_mmu_load_pgd(vcpu); - kvm_x86_ops.tlb_flush_current(vcpu); + static_call(kvm_x86_tlb_flush_current)(vcpu); out: return r; } @@ -4826,19 +4822,6 @@ void kvm_mmu_unload(struct kvm_vcpu *vcpu) } EXPORT_SYMBOL_GPL(kvm_mmu_unload); -static void mmu_pte_write_new_pte(struct kvm_vcpu *vcpu, - struct kvm_mmu_page *sp, u64 *spte, - const void *new) -{ - if (sp->role.level != PG_LEVEL_4K) { - ++vcpu->kvm->stat.mmu_pde_zapped; - return; - } - - ++vcpu->kvm->stat.mmu_pte_updated; - vcpu->arch.mmu->update_pte(vcpu, sp, spte, new); -} - static bool need_remote_flush(u64 old, u64 new) { if (!is_shadow_present_pte(old)) @@ -4954,22 +4937,6 @@ static u64 *get_written_sptes(struct kvm_mmu_page *sp, gpa_t gpa, int *nspte) return spte; } -/* - * Ignore various flags when determining if a SPTE can be immediately - * overwritten for the current MMU. - * - level: explicitly checked in mmu_pte_write_new_pte(), and will never - * match the current MMU role, as MMU's level tracks the root level. - * - access: updated based on the new guest PTE - * - quadrant: handled by get_written_sptes() - * - invalid: always false (loop only walks valid shadow pages) - */ -static const union kvm_mmu_page_role role_ign = { - .level = 0xf, - .access = 0x7, - .quadrant = 0x3, - .invalid = 0x1, -}; - static void kvm_mmu_pte_write(struct kvm_vcpu *vcpu, gpa_t gpa, const u8 *new, int bytes, struct kvm_page_track_notifier_node *node) @@ -4999,7 +4966,7 @@ static void kvm_mmu_pte_write(struct kvm_vcpu *vcpu, gpa_t gpa, */ mmu_topup_memory_caches(vcpu, true); - spin_lock(&vcpu->kvm->mmu_lock); + write_lock(&vcpu->kvm->mmu_lock); gentry = mmu_pte_write_fetch_gpte(vcpu, &gpa, &bytes); @@ -5020,14 +4987,10 @@ static void kvm_mmu_pte_write(struct kvm_vcpu *vcpu, gpa_t gpa, local_flush = true; while (npte--) { - u32 base_role = vcpu->arch.mmu->mmu_role.base.word; - entry = *spte; mmu_page_zap_pte(vcpu->kvm, sp, spte, NULL); - if (gentry && - !((sp->role.word ^ base_role) & ~role_ign.word) && - rmap_can_add(vcpu)) - mmu_pte_write_new_pte(vcpu, sp, spte, &gentry); + if (gentry && sp->role.level != PG_LEVEL_4K) + ++vcpu->kvm->stat.mmu_pde_zapped; if (need_remote_flush(entry, *spte)) remote_flush = true; ++spte; @@ -5035,24 +4998,8 @@ static void kvm_mmu_pte_write(struct kvm_vcpu *vcpu, gpa_t gpa, } kvm_mmu_flush_or_zap(vcpu, &invalid_list, remote_flush, local_flush); kvm_mmu_audit(vcpu, AUDIT_POST_PTE_WRITE); - spin_unlock(&vcpu->kvm->mmu_lock); -} - -int kvm_mmu_unprotect_page_virt(struct kvm_vcpu *vcpu, gva_t gva) -{ - gpa_t gpa; - int r; - - if (vcpu->arch.mmu->direct_map) - return 0; - - gpa = kvm_mmu_gva_to_gpa_read(vcpu, gva, NULL); - - r = kvm_mmu_unprotect_page(vcpu->kvm, gpa >> PAGE_SHIFT); - - return r; + write_unlock(&vcpu->kvm->mmu_lock); } -EXPORT_SYMBOL_GPL(kvm_mmu_unprotect_page_virt); int kvm_mmu_page_fault(struct kvm_vcpu *vcpu, gpa_t cr2_or_gpa, u64 error_code, void *insn, int insn_len) @@ -5125,7 +5072,7 @@ void kvm_mmu_invalidate_gva(struct kvm_vcpu *vcpu, struct kvm_mmu *mmu, if (is_noncanonical_address(gva, vcpu)) return; - kvm_x86_ops.tlb_flush_gva(vcpu, gva); + static_call(kvm_x86_tlb_flush_gva)(vcpu, gva); } if (!mmu->invlpg) @@ -5152,7 +5099,6 @@ void kvm_mmu_invalidate_gva(struct kvm_vcpu *vcpu, struct kvm_mmu *mmu, mmu->invlpg(vcpu, gva, root_hpa); } } -EXPORT_SYMBOL_GPL(kvm_mmu_invalidate_gva); void kvm_mmu_invlpg(struct kvm_vcpu *vcpu, gva_t gva) { @@ -5182,7 +5128,7 @@ void kvm_mmu_invpcid_gva(struct kvm_vcpu *vcpu, gva_t gva, unsigned long pcid) } if (tlb_flush) - kvm_x86_ops.tlb_flush_gva(vcpu, gva); + static_call(kvm_x86_tlb_flush_gva)(vcpu, gva); ++vcpu->stat.invlpg; @@ -5192,7 +5138,6 @@ void kvm_mmu_invpcid_gva(struct kvm_vcpu *vcpu, gva_t gva, unsigned long pcid) * for them. */ } -EXPORT_SYMBOL_GPL(kvm_mmu_invpcid_gva); void kvm_configure_mmu(bool enable_tdp, int tdp_max_root_level, int tdp_huge_page_level) @@ -5217,7 +5162,8 @@ void kvm_configure_mmu(bool enable_tdp, int tdp_max_root_level, EXPORT_SYMBOL_GPL(kvm_configure_mmu); /* The return value indicates if tlb flush on all vcpus is needed. */ -typedef bool (*slot_level_handler) (struct kvm *kvm, struct kvm_rmap_head *rmap_head); +typedef bool (*slot_level_handler) (struct kvm *kvm, struct kvm_rmap_head *rmap_head, + struct kvm_memory_slot *slot); /* The caller should hold mmu-lock before calling this function. */ static __always_inline bool @@ -5231,16 +5177,16 @@ slot_handle_level_range(struct kvm *kvm, struct kvm_memory_slot *memslot, for_each_slot_rmap_range(memslot, start_level, end_level, start_gfn, end_gfn, &iterator) { if (iterator.rmap) - flush |= fn(kvm, iterator.rmap); + flush |= fn(kvm, iterator.rmap, memslot); - if (need_resched() || spin_needbreak(&kvm->mmu_lock)) { + if (need_resched() || rwlock_needbreak(&kvm->mmu_lock)) { if (flush && lock_flush_tlb) { kvm_flush_remote_tlbs_with_address(kvm, start_gfn, iterator.gfn - start_gfn + 1); flush = false; } - cond_resched_lock(&kvm->mmu_lock); + cond_resched_rwlock_write(&kvm->mmu_lock); } } @@ -5265,22 +5211,6 @@ slot_handle_level(struct kvm *kvm, struct kvm_memory_slot *memslot, } static __always_inline bool -slot_handle_all_level(struct kvm *kvm, struct kvm_memory_slot *memslot, - slot_level_handler fn, bool lock_flush_tlb) -{ - return slot_handle_level(kvm, memslot, fn, PG_LEVEL_4K, - KVM_MAX_HUGEPAGE_LEVEL, lock_flush_tlb); -} - -static __always_inline bool -slot_handle_large_level(struct kvm *kvm, struct kvm_memory_slot *memslot, - slot_level_handler fn, bool lock_flush_tlb) -{ - return slot_handle_level(kvm, memslot, fn, PG_LEVEL_4K + 1, - KVM_MAX_HUGEPAGE_LEVEL, lock_flush_tlb); -} - -static __always_inline bool slot_handle_leaf(struct kvm *kvm, struct kvm_memory_slot *memslot, slot_level_handler fn, bool lock_flush_tlb) { @@ -5390,7 +5320,7 @@ restart: * be in active use by the guest. */ if (batch >= BATCH_ZAP_PAGES && - cond_resched_lock(&kvm->mmu_lock)) { + cond_resched_rwlock_write(&kvm->mmu_lock)) { batch = 0; goto restart; } @@ -5423,7 +5353,7 @@ static void kvm_mmu_zap_all_fast(struct kvm *kvm) { lockdep_assert_held(&kvm->slots_lock); - spin_lock(&kvm->mmu_lock); + write_lock(&kvm->mmu_lock); trace_kvm_mmu_zap_all_fast(kvm); /* @@ -5447,10 +5377,10 @@ static void kvm_mmu_zap_all_fast(struct kvm *kvm) kvm_zap_obsolete_pages(kvm); - if (kvm->arch.tdp_mmu_enabled) + if (is_tdp_mmu_enabled(kvm)) kvm_tdp_mmu_zap_all(kvm); - spin_unlock(&kvm->mmu_lock); + write_unlock(&kvm->mmu_lock); } static bool kvm_has_zapped_obsolete_pages(struct kvm *kvm) @@ -5492,7 +5422,7 @@ void kvm_zap_gfn_range(struct kvm *kvm, gfn_t gfn_start, gfn_t gfn_end) int i; bool flush; - spin_lock(&kvm->mmu_lock); + write_lock(&kvm->mmu_lock); for (i = 0; i < KVM_ADDRESS_SPACE_NUM; i++) { slots = __kvm_memslots(kvm, i); kvm_for_each_memslot(memslot, slots) { @@ -5510,17 +5440,18 @@ void kvm_zap_gfn_range(struct kvm *kvm, gfn_t gfn_start, gfn_t gfn_end) } } - if (kvm->arch.tdp_mmu_enabled) { + if (is_tdp_mmu_enabled(kvm)) { flush = kvm_tdp_mmu_zap_gfn_range(kvm, gfn_start, gfn_end); if (flush) kvm_flush_remote_tlbs(kvm); } - spin_unlock(&kvm->mmu_lock); + write_unlock(&kvm->mmu_lock); } static bool slot_rmap_write_protect(struct kvm *kvm, - struct kvm_rmap_head *rmap_head) + struct kvm_rmap_head *rmap_head, + struct kvm_memory_slot *slot) { return __rmap_write_protect(kvm, rmap_head, false); } @@ -5531,12 +5462,12 @@ void kvm_mmu_slot_remove_write_access(struct kvm *kvm, { bool flush; - spin_lock(&kvm->mmu_lock); + write_lock(&kvm->mmu_lock); flush = slot_handle_level(kvm, memslot, slot_rmap_write_protect, start_level, KVM_MAX_HUGEPAGE_LEVEL, false); - if (kvm->arch.tdp_mmu_enabled) + if (is_tdp_mmu_enabled(kvm)) flush |= kvm_tdp_mmu_wrprot_slot(kvm, memslot, PG_LEVEL_4K); - spin_unlock(&kvm->mmu_lock); + write_unlock(&kvm->mmu_lock); /* * We can flush all the TLBs out of the mmu lock without TLB @@ -5554,7 +5485,8 @@ void kvm_mmu_slot_remove_write_access(struct kvm *kvm, } static bool kvm_mmu_zap_collapsible_spte(struct kvm *kvm, - struct kvm_rmap_head *rmap_head) + struct kvm_rmap_head *rmap_head, + struct kvm_memory_slot *slot) { u64 *sptep; struct rmap_iterator iter; @@ -5575,8 +5507,8 @@ restart: * mapping if the indirect sp has level = 1. */ if (sp->role.direct && !kvm_is_reserved_pfn(pfn) && - (kvm_is_zone_device_pfn(pfn) || - PageCompound(pfn_to_page(pfn)))) { + sp->role.level < kvm_mmu_max_mapping_level(kvm, slot, sp->gfn, + pfn, PG_LEVEL_NUM)) { pte_list_remove(rmap_head, sptep); if (kvm_available_flush_tlb_with_range()) @@ -5596,13 +5528,14 @@ void kvm_mmu_zap_collapsible_sptes(struct kvm *kvm, const struct kvm_memory_slot *memslot) { /* FIXME: const-ify all uses of struct kvm_memory_slot. */ - spin_lock(&kvm->mmu_lock); - slot_handle_leaf(kvm, (struct kvm_memory_slot *)memslot, - kvm_mmu_zap_collapsible_spte, true); + struct kvm_memory_slot *slot = (struct kvm_memory_slot *)memslot; - if (kvm->arch.tdp_mmu_enabled) - kvm_tdp_mmu_zap_collapsible_sptes(kvm, memslot); - spin_unlock(&kvm->mmu_lock); + write_lock(&kvm->mmu_lock); + slot_handle_leaf(kvm, slot, kvm_mmu_zap_collapsible_spte, true); + + if (is_tdp_mmu_enabled(kvm)) + kvm_tdp_mmu_zap_collapsible_sptes(kvm, slot); + write_unlock(&kvm->mmu_lock); } void kvm_arch_flush_remote_tlbs_memslot(struct kvm *kvm, @@ -5625,11 +5558,11 @@ void kvm_mmu_slot_leaf_clear_dirty(struct kvm *kvm, { bool flush; - spin_lock(&kvm->mmu_lock); + write_lock(&kvm->mmu_lock); flush = slot_handle_leaf(kvm, memslot, __rmap_clear_dirty, false); - if (kvm->arch.tdp_mmu_enabled) + if (is_tdp_mmu_enabled(kvm)) flush |= kvm_tdp_mmu_clear_dirty_slot(kvm, memslot); - spin_unlock(&kvm->mmu_lock); + write_unlock(&kvm->mmu_lock); /* * It's also safe to flush TLBs out of mmu lock here as currently this @@ -5640,40 +5573,6 @@ void kvm_mmu_slot_leaf_clear_dirty(struct kvm *kvm, if (flush) kvm_arch_flush_remote_tlbs_memslot(kvm, memslot); } -EXPORT_SYMBOL_GPL(kvm_mmu_slot_leaf_clear_dirty); - -void kvm_mmu_slot_largepage_remove_write_access(struct kvm *kvm, - struct kvm_memory_slot *memslot) -{ - bool flush; - - spin_lock(&kvm->mmu_lock); - flush = slot_handle_large_level(kvm, memslot, slot_rmap_write_protect, - false); - if (kvm->arch.tdp_mmu_enabled) - flush |= kvm_tdp_mmu_wrprot_slot(kvm, memslot, PG_LEVEL_2M); - spin_unlock(&kvm->mmu_lock); - - if (flush) - kvm_arch_flush_remote_tlbs_memslot(kvm, memslot); -} -EXPORT_SYMBOL_GPL(kvm_mmu_slot_largepage_remove_write_access); - -void kvm_mmu_slot_set_dirty(struct kvm *kvm, - struct kvm_memory_slot *memslot) -{ - bool flush; - - spin_lock(&kvm->mmu_lock); - flush = slot_handle_all_level(kvm, memslot, __rmap_set_dirty, false); - if (kvm->arch.tdp_mmu_enabled) - flush |= kvm_tdp_mmu_slot_set_dirty(kvm, memslot); - spin_unlock(&kvm->mmu_lock); - - if (flush) - kvm_arch_flush_remote_tlbs_memslot(kvm, memslot); -} -EXPORT_SYMBOL_GPL(kvm_mmu_slot_set_dirty); void kvm_mmu_zap_all(struct kvm *kvm) { @@ -5681,23 +5580,23 @@ void kvm_mmu_zap_all(struct kvm *kvm) LIST_HEAD(invalid_list); int ign; - spin_lock(&kvm->mmu_lock); + write_lock(&kvm->mmu_lock); restart: list_for_each_entry_safe(sp, node, &kvm->arch.active_mmu_pages, link) { if (WARN_ON(sp->role.invalid)) continue; if (__kvm_mmu_prepare_zap_page(kvm, sp, &invalid_list, &ign)) goto restart; - if (cond_resched_lock(&kvm->mmu_lock)) + if (cond_resched_rwlock_write(&kvm->mmu_lock)) goto restart; } kvm_mmu_commit_zap_page(kvm, &invalid_list); - if (kvm->arch.tdp_mmu_enabled) + if (is_tdp_mmu_enabled(kvm)) kvm_tdp_mmu_zap_all(kvm); - spin_unlock(&kvm->mmu_lock); + write_unlock(&kvm->mmu_lock); } void kvm_mmu_invalidate_mmio_sptes(struct kvm *kvm, u64 gen) @@ -5757,7 +5656,7 @@ mmu_shrink_scan(struct shrinker *shrink, struct shrink_control *sc) continue; idx = srcu_read_lock(&kvm->srcu); - spin_lock(&kvm->mmu_lock); + write_lock(&kvm->mmu_lock); if (kvm_has_zapped_obsolete_pages(kvm)) { kvm_mmu_commit_zap_page(kvm, @@ -5768,7 +5667,7 @@ mmu_shrink_scan(struct shrinker *shrink, struct shrink_control *sc) freed = kvm_mmu_zap_oldest_mmu_pages(kvm, sc->nr_to_scan); unlock: - spin_unlock(&kvm->mmu_lock); + write_unlock(&kvm->mmu_lock); srcu_read_unlock(&kvm->srcu, idx); /* @@ -5988,7 +5887,7 @@ static void kvm_recover_nx_lpages(struct kvm *kvm) ulong to_zap; rcu_idx = srcu_read_lock(&kvm->srcu); - spin_lock(&kvm->mmu_lock); + write_lock(&kvm->mmu_lock); ratio = READ_ONCE(nx_huge_pages_recovery_ratio); to_zap = ratio ? DIV_ROUND_UP(kvm->stat.nx_lpage_splits, ratio) : 0; @@ -6005,22 +5904,22 @@ static void kvm_recover_nx_lpages(struct kvm *kvm) struct kvm_mmu_page, lpage_disallowed_link); WARN_ON_ONCE(!sp->lpage_disallowed); - if (sp->tdp_mmu_page) + if (is_tdp_mmu_page(sp)) { kvm_tdp_mmu_zap_gfn_range(kvm, sp->gfn, sp->gfn + KVM_PAGES_PER_HPAGE(sp->role.level)); - else { + } else { kvm_mmu_prepare_zap_page(kvm, sp, &invalid_list); WARN_ON_ONCE(sp->lpage_disallowed); } - if (need_resched() || spin_needbreak(&kvm->mmu_lock)) { + if (need_resched() || rwlock_needbreak(&kvm->mmu_lock)) { kvm_mmu_commit_zap_page(kvm, &invalid_list); - cond_resched_lock(&kvm->mmu_lock); + cond_resched_rwlock_write(&kvm->mmu_lock); } } kvm_mmu_commit_zap_page(kvm, &invalid_list); - spin_unlock(&kvm->mmu_lock); + write_unlock(&kvm->mmu_lock); srcu_read_unlock(&kvm->srcu, rcu_idx); } diff --git a/arch/x86/kvm/mmu/mmu_audit.c b/arch/x86/kvm/mmu/mmu_audit.c index c8d51a37e2ce..ced15fd58fde 100644 --- a/arch/x86/kvm/mmu/mmu_audit.c +++ b/arch/x86/kvm/mmu/mmu_audit.c @@ -234,7 +234,7 @@ static void audit_vcpu_spte(struct kvm_vcpu *vcpu) } static bool mmu_audit; -static struct static_key mmu_audit_key; +static DEFINE_STATIC_KEY_FALSE(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_key_false((&mmu_audit_key))) + if (static_branch_unlikely((&mmu_audit_key))) __kvm_mmu_audit(vcpu, point); } @@ -259,7 +259,7 @@ static void mmu_audit_enable(void) if (mmu_audit) return; - static_key_slow_inc(&mmu_audit_key); + static_branch_inc(&mmu_audit_key); mmu_audit = true; } @@ -268,7 +268,7 @@ static void mmu_audit_disable(void) if (!mmu_audit) return; - static_key_slow_dec(&mmu_audit_key); + static_branch_dec(&mmu_audit_key); mmu_audit = false; } diff --git a/arch/x86/kvm/mmu/mmu_internal.h b/arch/x86/kvm/mmu/mmu_internal.h index bfc6389edc28..1f6f98c76bdf 100644 --- a/arch/x86/kvm/mmu/mmu_internal.h +++ b/arch/x86/kvm/mmu/mmu_internal.h @@ -12,7 +12,7 @@ extern bool dbg; #define pgprintk(x...) do { if (dbg) printk(x); } while (0) -#define rmap_printk(x...) do { if (dbg) printk(x); } while (0) +#define rmap_printk(fmt, args...) do { if (dbg) printk("%s: " fmt, __func__, ## args); } while (0) #define MMU_WARN_ON(x) WARN_ON(x) #else #define pgprintk(x...) do { } while (0) @@ -56,7 +56,12 @@ struct kvm_mmu_page { /* Number of writes since the last time traversal visited this page. */ atomic_t write_flooding_count; +#ifdef CONFIG_X86_64 bool tdp_mmu_page; + + /* Used for freeing the page asyncronously if it is a TDP MMU page. */ + struct rcu_head rcu_head; +#endif }; extern struct kmem_cache *mmu_page_header_cache; @@ -73,15 +78,23 @@ static inline struct kvm_mmu_page *sptep_to_sp(u64 *sptep) return to_shadow_page(__pa(sptep)); } +static inline int kvm_mmu_page_as_id(struct kvm_mmu_page *sp) +{ + return sp->role.smm ? 1 : 0; +} + static inline bool kvm_vcpu_ad_need_write_protect(struct kvm_vcpu *vcpu) { /* - * When using the EPT page-modification log, the GPAs in the log - * would come from L2 rather than L1. Therefore, we need to rely - * on write protection to record dirty pages. This also bypasses - * PML, since writes now result in a vmexit. + * When using the EPT page-modification log, the GPAs in the CPU dirty + * log would come from L2 rather than L1. Therefore, we need to rely + * on write protection to record dirty pages, which bypasses PML, since + * writes now result in a vmexit. Note, the check on CPU dirty logging + * being enabled is mandatory as the bits used to denote WP-only SPTEs + * are reserved for NPT w/ PAE (32-bit KVM). */ - return vcpu->arch.mmu == &vcpu->arch.guest_mmu; + return vcpu->arch.mmu == &vcpu->arch.guest_mmu && + kvm_x86_ops.cpu_dirty_log_size; } bool is_nx_huge_page_enabled(void); @@ -133,6 +146,8 @@ enum { #define SET_SPTE_NEED_REMOTE_TLB_FLUSH BIT(1) #define SET_SPTE_SPURIOUS BIT(2) +int kvm_mmu_max_mapping_level(struct kvm *kvm, struct kvm_memory_slot *slot, + gfn_t gfn, kvm_pfn_t pfn, int max_level); int kvm_mmu_hugepage_adjust(struct kvm_vcpu *vcpu, gfn_t gfn, int max_level, kvm_pfn_t *pfnp, bool huge_page_disallowed, int *req_level); diff --git a/arch/x86/kvm/mmu/page_track.c b/arch/x86/kvm/mmu/page_track.c index 8443a675715b..34bb0ec69bd8 100644 --- a/arch/x86/kvm/mmu/page_track.c +++ b/arch/x86/kvm/mmu/page_track.c @@ -184,9 +184,9 @@ kvm_page_track_register_notifier(struct kvm *kvm, head = &kvm->arch.track_notifier_head; - spin_lock(&kvm->mmu_lock); + write_lock(&kvm->mmu_lock); hlist_add_head_rcu(&n->node, &head->track_notifier_list); - spin_unlock(&kvm->mmu_lock); + write_unlock(&kvm->mmu_lock); } EXPORT_SYMBOL_GPL(kvm_page_track_register_notifier); @@ -202,9 +202,9 @@ kvm_page_track_unregister_notifier(struct kvm *kvm, head = &kvm->arch.track_notifier_head; - spin_lock(&kvm->mmu_lock); + write_lock(&kvm->mmu_lock); hlist_del_rcu(&n->node); - spin_unlock(&kvm->mmu_lock); + write_unlock(&kvm->mmu_lock); synchronize_srcu(&head->track_srcu); } EXPORT_SYMBOL_GPL(kvm_page_track_unregister_notifier); diff --git a/arch/x86/kvm/mmu/paging_tmpl.h b/arch/x86/kvm/mmu/paging_tmpl.h index 50e268eb8e1a..55d7b473ac44 100644 --- a/arch/x86/kvm/mmu/paging_tmpl.h +++ b/arch/x86/kvm/mmu/paging_tmpl.h @@ -601,6 +601,13 @@ static void FNAME(pte_prefetch)(struct kvm_vcpu *vcpu, struct guest_walker *gw, if (sp->role.level > PG_LEVEL_4K) return; + /* + * If addresses are being invalidated, skip prefetching to avoid + * accidentally prefetching those addresses. + */ + if (unlikely(vcpu->kvm->mmu_notifier_count)) + return; + if (sp->role.direct) return __direct_pte_prefetch(vcpu, sp, sptep); @@ -790,6 +797,7 @@ static int FNAME(page_fault)(struct kvm_vcpu *vcpu, gpa_t addr, u32 error_code, struct guest_walker walker; int r; kvm_pfn_t pfn; + hva_t hva; unsigned long mmu_seq; bool map_writable, is_self_change_mapping; int max_level; @@ -840,8 +848,8 @@ static int FNAME(page_fault)(struct kvm_vcpu *vcpu, gpa_t addr, u32 error_code, mmu_seq = vcpu->kvm->mmu_notifier_seq; smp_rmb(); - if (try_async_pf(vcpu, prefault, walker.gfn, addr, &pfn, write_fault, - &map_writable)) + if (try_async_pf(vcpu, prefault, walker.gfn, addr, &pfn, &hva, + write_fault, &map_writable)) return RET_PF_RETRY; if (handle_abnormal_pfn(vcpu, addr, walker.gfn, pfn, walker.pte_access, &r)) @@ -868,8 +876,8 @@ static int FNAME(page_fault)(struct kvm_vcpu *vcpu, gpa_t addr, u32 error_code, } r = RET_PF_RETRY; - spin_lock(&vcpu->kvm->mmu_lock); - if (mmu_notifier_retry(vcpu->kvm, mmu_seq)) + write_lock(&vcpu->kvm->mmu_lock); + if (!is_noslot_pfn(pfn) && mmu_notifier_retry_hva(vcpu->kvm, mmu_seq, hva)) goto out_unlock; kvm_mmu_audit(vcpu, AUDIT_PRE_PAGE_FAULT); @@ -881,7 +889,7 @@ static int FNAME(page_fault)(struct kvm_vcpu *vcpu, gpa_t addr, u32 error_code, kvm_mmu_audit(vcpu, AUDIT_POST_PAGE_FAULT); out_unlock: - spin_unlock(&vcpu->kvm->mmu_lock); + write_unlock(&vcpu->kvm->mmu_lock); kvm_release_pfn_clean(pfn); return r; } @@ -919,7 +927,7 @@ static void FNAME(invlpg)(struct kvm_vcpu *vcpu, gva_t gva, hpa_t root_hpa) return; } - spin_lock(&vcpu->kvm->mmu_lock); + write_lock(&vcpu->kvm->mmu_lock); for_each_shadow_entry_using_root(vcpu, root_hpa, gva, iterator) { level = iterator.level; sptep = iterator.sptep; @@ -954,7 +962,7 @@ static void FNAME(invlpg)(struct kvm_vcpu *vcpu, gva_t gva, hpa_t root_hpa) if (!is_shadow_present_pte(*sptep) || !sp->unsync_children) break; } - spin_unlock(&vcpu->kvm->mmu_lock); + write_unlock(&vcpu->kvm->mmu_lock); } /* Note, @addr is a GPA when gva_to_gpa() translates an L2 GPA to an L1 GPA. */ diff --git a/arch/x86/kvm/mmu/spte.c b/arch/x86/kvm/mmu/spte.c index c51ad544f25b..ef55f0bc4ccf 100644 --- a/arch/x86/kvm/mmu/spte.c +++ b/arch/x86/kvm/mmu/spte.c @@ -120,7 +120,7 @@ int make_spte(struct kvm_vcpu *vcpu, unsigned int pte_access, int level, if (level > PG_LEVEL_4K) spte |= PT_PAGE_SIZE_MASK; if (tdp_enabled) - spte |= kvm_x86_ops.get_mt_mask(vcpu, gfn, + spte |= static_call(kvm_x86_get_mt_mask)(vcpu, gfn, kvm_is_mmio_pfn(pfn)); if (host_writable) diff --git a/arch/x86/kvm/mmu/spte.h b/arch/x86/kvm/mmu/spte.h index 2b3a30bd38b0..6de3950fd704 100644 --- a/arch/x86/kvm/mmu/spte.h +++ b/arch/x86/kvm/mmu/spte.h @@ -131,6 +131,25 @@ extern u64 __read_mostly shadow_nonpresent_or_rsvd_mask; #define SHADOW_ACC_TRACK_SAVED_BITS_SHIFT PT64_SECOND_AVAIL_BITS_SHIFT /* + * If a thread running without exclusive control of the MMU lock must perform a + * multi-part operation on an SPTE, it can set the SPTE to REMOVED_SPTE as a + * non-present intermediate value. Other threads which encounter this value + * should not modify the SPTE. + * + * This constant works because it is considered non-present on both AMD and + * Intel CPUs and does not create a L1TF vulnerability because the pfn section + * is zeroed out. + * + * Only used by the TDP MMU. + */ +#define REMOVED_SPTE (1ull << 59) + +static inline bool is_removed_spte(u64 spte) +{ + return spte == REMOVED_SPTE; +} + +/* * In some cases, we need to preserve the GFN of a non-present or reserved * SPTE when we usurp the upper five bits of the physical address space to * defend against L1TF, e.g. for MMIO SPTEs. To preserve the GFN, we'll @@ -185,23 +204,19 @@ static inline bool is_access_track_spte(u64 spte) return !spte_ad_enabled(spte) && (spte & shadow_acc_track_mask) == 0; } -static inline int is_shadow_present_pte(u64 pte) +static inline bool is_shadow_present_pte(u64 pte) { - return (pte != 0) && !is_mmio_spte(pte); + return (pte != 0) && !is_mmio_spte(pte) && !is_removed_spte(pte); } -static inline int is_large_pte(u64 pte) +static inline bool is_large_pte(u64 pte) { return pte & PT_PAGE_SIZE_MASK; } -static inline int is_last_spte(u64 pte, int level) +static inline bool is_last_spte(u64 pte, int level) { - if (level == PG_LEVEL_4K) - return 1; - if (is_large_pte(pte)) - return 1; - return 0; + return (level == PG_LEVEL_4K) || is_large_pte(pte); } static inline bool is_executable_pte(u64 spte) diff --git a/arch/x86/kvm/mmu/tdp_iter.c b/arch/x86/kvm/mmu/tdp_iter.c index 87b7e16911db..b3ed302c1a35 100644 --- a/arch/x86/kvm/mmu/tdp_iter.c +++ b/arch/x86/kvm/mmu/tdp_iter.c @@ -12,7 +12,7 @@ static void tdp_iter_refresh_sptep(struct tdp_iter *iter) { iter->sptep = iter->pt_path[iter->level - 1] + SHADOW_PT_INDEX(iter->gfn << PAGE_SHIFT, iter->level); - iter->old_spte = READ_ONCE(*iter->sptep); + iter->old_spte = READ_ONCE(*rcu_dereference(iter->sptep)); } static gfn_t round_gfn_for_level(gfn_t gfn, int level) @@ -21,25 +21,37 @@ static gfn_t round_gfn_for_level(gfn_t gfn, int level) } /* + * Return the TDP iterator to the root PT and allow it to continue its + * traversal over the paging structure from there. + */ +void tdp_iter_restart(struct tdp_iter *iter) +{ + iter->yielded_gfn = iter->next_last_level_gfn; + iter->level = iter->root_level; + + iter->gfn = round_gfn_for_level(iter->next_last_level_gfn, iter->level); + tdp_iter_refresh_sptep(iter); + + iter->valid = true; +} + +/* * Sets a TDP iterator to walk a pre-order traversal of the paging structure - * rooted at root_pt, starting with the walk to translate goal_gfn. + * rooted at root_pt, starting with the walk to translate next_last_level_gfn. */ void tdp_iter_start(struct tdp_iter *iter, u64 *root_pt, int root_level, - int min_level, gfn_t goal_gfn) + int min_level, gfn_t next_last_level_gfn) { WARN_ON(root_level < 1); WARN_ON(root_level > PT64_ROOT_MAX_LEVEL); - iter->goal_gfn = goal_gfn; + iter->next_last_level_gfn = next_last_level_gfn; iter->root_level = root_level; iter->min_level = min_level; - iter->level = root_level; - iter->pt_path[iter->level - 1] = root_pt; - - iter->gfn = round_gfn_for_level(iter->goal_gfn, iter->level); - tdp_iter_refresh_sptep(iter); + iter->pt_path[iter->root_level - 1] = (tdp_ptep_t)root_pt; + iter->as_id = kvm_mmu_page_as_id(sptep_to_sp(root_pt)); - iter->valid = true; + tdp_iter_restart(iter); } /* @@ -47,7 +59,7 @@ void tdp_iter_start(struct tdp_iter *iter, u64 *root_pt, int root_level, * address of the child page table referenced by the SPTE. Returns null if * there is no such entry. */ -u64 *spte_to_child_pt(u64 spte, int level) +tdp_ptep_t spte_to_child_pt(u64 spte, int level) { /* * There's no child entry if this entry isn't present or is a @@ -56,7 +68,7 @@ u64 *spte_to_child_pt(u64 spte, int level) if (!is_shadow_present_pte(spte) || is_last_spte(spte, level)) return NULL; - return __va(spte_to_pfn(spte) << PAGE_SHIFT); + return (tdp_ptep_t)__va(spte_to_pfn(spte) << PAGE_SHIFT); } /* @@ -65,7 +77,7 @@ u64 *spte_to_child_pt(u64 spte, int level) */ static bool try_step_down(struct tdp_iter *iter) { - u64 *child_pt; + tdp_ptep_t child_pt; if (iter->level == iter->min_level) return false; @@ -74,7 +86,7 @@ static bool try_step_down(struct tdp_iter *iter) * Reread the SPTE before stepping down to avoid traversing into page * tables that are no longer linked from this entry. */ - iter->old_spte = READ_ONCE(*iter->sptep); + iter->old_spte = READ_ONCE(*rcu_dereference(iter->sptep)); child_pt = spte_to_child_pt(iter->old_spte, iter->level); if (!child_pt) @@ -82,7 +94,7 @@ static bool try_step_down(struct tdp_iter *iter) iter->level--; iter->pt_path[iter->level - 1] = child_pt; - iter->gfn = round_gfn_for_level(iter->goal_gfn, iter->level); + iter->gfn = round_gfn_for_level(iter->next_last_level_gfn, iter->level); tdp_iter_refresh_sptep(iter); return true; @@ -106,9 +118,9 @@ static bool try_step_side(struct tdp_iter *iter) return false; iter->gfn += KVM_PAGES_PER_HPAGE(iter->level); - iter->goal_gfn = iter->gfn; + iter->next_last_level_gfn = iter->gfn; iter->sptep++; - iter->old_spte = READ_ONCE(*iter->sptep); + iter->old_spte = READ_ONCE(*rcu_dereference(iter->sptep)); return true; } @@ -158,25 +170,3 @@ void tdp_iter_next(struct tdp_iter *iter) iter->valid = false; } -/* - * Restart the walk over the paging structure from the root, starting from the - * highest gfn the iterator had previously reached. Assumes that the entire - * paging structure, except the root page, may have been completely torn down - * and rebuilt. - */ -void tdp_iter_refresh_walk(struct tdp_iter *iter) -{ - gfn_t goal_gfn = iter->goal_gfn; - - if (iter->gfn > goal_gfn) - goal_gfn = iter->gfn; - - tdp_iter_start(iter, iter->pt_path[iter->root_level - 1], - iter->root_level, iter->min_level, goal_gfn); -} - -u64 *tdp_iter_root_pt(struct tdp_iter *iter) -{ - return iter->pt_path[iter->root_level - 1]; -} - diff --git a/arch/x86/kvm/mmu/tdp_iter.h b/arch/x86/kvm/mmu/tdp_iter.h index 47170d0dc98e..b1748b988d3a 100644 --- a/arch/x86/kvm/mmu/tdp_iter.h +++ b/arch/x86/kvm/mmu/tdp_iter.h @@ -7,6 +7,8 @@ #include "mmu.h" +typedef u64 __rcu *tdp_ptep_t; + /* * A TDP iterator performs a pre-order walk over a TDP paging structure. */ @@ -15,11 +17,17 @@ struct tdp_iter { * The iterator will traverse the paging structure towards the mapping * for this GFN. */ - gfn_t goal_gfn; + gfn_t next_last_level_gfn; + /* + * The next_last_level_gfn at the time when the thread last + * yielded. Only yielding when the next_last_level_gfn != + * yielded_gfn helps ensure forward progress. + */ + gfn_t yielded_gfn; /* Pointers to the page tables traversed to reach the current SPTE */ - u64 *pt_path[PT64_ROOT_MAX_LEVEL]; + tdp_ptep_t pt_path[PT64_ROOT_MAX_LEVEL]; /* A pointer to the current SPTE */ - u64 *sptep; + tdp_ptep_t sptep; /* The lowest GFN mapped by the current SPTE */ gfn_t gfn; /* The level of the root page given to the iterator */ @@ -28,6 +36,8 @@ struct tdp_iter { int min_level; /* The iterator's current level within the paging structure */ int level; + /* The address space ID, i.e. SMM vs. regular. */ + int as_id; /* A snapshot of the value at sptep */ u64 old_spte; /* @@ -49,12 +59,11 @@ struct tdp_iter { #define for_each_tdp_pte(iter, root, root_level, start, end) \ for_each_tdp_pte_min_level(iter, root, root_level, PG_LEVEL_4K, start, end) -u64 *spte_to_child_pt(u64 pte, int level); +tdp_ptep_t spte_to_child_pt(u64 pte, int level); void tdp_iter_start(struct tdp_iter *iter, u64 *root_pt, int root_level, - int min_level, gfn_t goal_gfn); + int min_level, gfn_t next_last_level_gfn); void tdp_iter_next(struct tdp_iter *iter); -void tdp_iter_refresh_walk(struct tdp_iter *iter); -u64 *tdp_iter_root_pt(struct tdp_iter *iter); +void tdp_iter_restart(struct tdp_iter *iter); #endif /* __KVM_X86_MMU_TDP_ITER_H */ diff --git a/arch/x86/kvm/mmu/tdp_mmu.c b/arch/x86/kvm/mmu/tdp_mmu.c index b56d604809b8..462b1f71c77f 100644 --- a/arch/x86/kvm/mmu/tdp_mmu.c +++ b/arch/x86/kvm/mmu/tdp_mmu.c @@ -7,32 +7,23 @@ #include "tdp_mmu.h" #include "spte.h" +#include <asm/cmpxchg.h> #include <trace/events/kvm.h> -#ifdef CONFIG_X86_64 static bool __read_mostly tdp_mmu_enabled = false; module_param_named(tdp_mmu, tdp_mmu_enabled, bool, 0644); -#endif - -static bool is_tdp_mmu_enabled(void) -{ -#ifdef CONFIG_X86_64 - return tdp_enabled && READ_ONCE(tdp_mmu_enabled); -#else - return false; -#endif /* CONFIG_X86_64 */ -} /* Initializes the TDP MMU for the VM, if enabled. */ void kvm_mmu_init_tdp_mmu(struct kvm *kvm) { - if (!is_tdp_mmu_enabled()) + if (!tdp_enabled || !READ_ONCE(tdp_mmu_enabled)) return; /* This should not be changed for the lifetime of the VM. */ kvm->arch.tdp_mmu_enabled = true; INIT_LIST_HEAD(&kvm->arch.tdp_mmu_roots); + spin_lock_init(&kvm->arch.tdp_mmu_pages_lock); INIT_LIST_HEAD(&kvm->arch.tdp_mmu_pages); } @@ -42,6 +33,12 @@ void kvm_mmu_uninit_tdp_mmu(struct kvm *kvm) return; WARN_ON(!list_empty(&kvm->arch.tdp_mmu_roots)); + + /* + * Ensure that all the outstanding RCU callbacks to free shadow pages + * can run before the VM is torn down. + */ + rcu_barrier(); } static void tdp_mmu_put_root(struct kvm *kvm, struct kvm_mmu_page *root) @@ -53,7 +50,7 @@ static void tdp_mmu_put_root(struct kvm *kvm, struct kvm_mmu_page *root) static inline bool tdp_mmu_next_root_valid(struct kvm *kvm, struct kvm_mmu_page *root) { - lockdep_assert_held(&kvm->mmu_lock); + lockdep_assert_held_write(&kvm->mmu_lock); if (list_entry_is_head(root, &kvm->arch.tdp_mmu_roots, link)) return false; @@ -88,22 +85,6 @@ static inline struct kvm_mmu_page *tdp_mmu_next_root(struct kvm *kvm, #define for_each_tdp_mmu_root(_kvm, _root) \ list_for_each_entry(_root, &_kvm->arch.tdp_mmu_roots, link) -bool is_tdp_mmu_root(struct kvm *kvm, hpa_t hpa) -{ - struct kvm_mmu_page *sp; - - if (!kvm->arch.tdp_mmu_enabled) - return false; - if (WARN_ON(!VALID_PAGE(hpa))) - return false; - - sp = to_shadow_page(hpa); - if (WARN_ON(!sp)) - return false; - - return sp->tdp_mmu_page && sp->root_count; -} - static bool zap_gfn_range(struct kvm *kvm, struct kvm_mmu_page *root, gfn_t start, gfn_t end, bool can_yield); @@ -111,7 +92,7 @@ void kvm_tdp_mmu_free_root(struct kvm *kvm, struct kvm_mmu_page *root) { gfn_t max_gfn = 1ULL << (shadow_phys_bits - PAGE_SHIFT); - lockdep_assert_held(&kvm->mmu_lock); + lockdep_assert_held_write(&kvm->mmu_lock); WARN_ON(root->root_count); WARN_ON(!root->tdp_mmu_page); @@ -164,13 +145,13 @@ static struct kvm_mmu_page *get_tdp_mmu_vcpu_root(struct kvm_vcpu *vcpu) role = page_role_for_level(vcpu, vcpu->arch.mmu->shadow_root_level); - spin_lock(&kvm->mmu_lock); + write_lock(&kvm->mmu_lock); /* Check for an existing root before allocating a new one. */ for_each_tdp_mmu_root(kvm, root) { if (root->role.word == role.word) { kvm_mmu_get_root(kvm, root); - spin_unlock(&kvm->mmu_lock); + write_unlock(&kvm->mmu_lock); return root; } } @@ -180,7 +161,7 @@ static struct kvm_mmu_page *get_tdp_mmu_vcpu_root(struct kvm_vcpu *vcpu) list_add(&root->link, &kvm->arch.tdp_mmu_roots); - spin_unlock(&kvm->mmu_lock); + write_unlock(&kvm->mmu_lock); return root; } @@ -196,14 +177,32 @@ hpa_t kvm_tdp_mmu_get_vcpu_root_hpa(struct kvm_vcpu *vcpu) return __pa(root->spt); } -static void handle_changed_spte(struct kvm *kvm, int as_id, gfn_t gfn, - u64 old_spte, u64 new_spte, int level); +static void tdp_mmu_free_sp(struct kvm_mmu_page *sp) +{ + free_page((unsigned long)sp->spt); + kmem_cache_free(mmu_page_header_cache, sp); +} -static int kvm_mmu_page_as_id(struct kvm_mmu_page *sp) +/* + * This is called through call_rcu in order to free TDP page table memory + * safely with respect to other kernel threads that may be operating on + * the memory. + * By only accessing TDP MMU page table memory in an RCU read critical + * section, and freeing it after a grace period, lockless access to that + * memory won't use it after it is freed. + */ +static void tdp_mmu_free_sp_rcu_callback(struct rcu_head *head) { - return sp->role.smm ? 1 : 0; + struct kvm_mmu_page *sp = container_of(head, struct kvm_mmu_page, + rcu_head); + + tdp_mmu_free_sp(sp); } +static void handle_changed_spte(struct kvm *kvm, int as_id, gfn_t gfn, + u64 old_spte, u64 new_spte, int level, + bool shared); + static void handle_changed_spte_acc_track(u64 old_spte, u64 new_spte, int level) { bool pfn_changed = spte_to_pfn(old_spte) != spte_to_pfn(new_spte); @@ -235,6 +234,144 @@ static void handle_changed_spte_dirty_log(struct kvm *kvm, int as_id, gfn_t gfn, } /** + * tdp_mmu_link_page - Add a new page to the list of pages used by the TDP MMU + * + * @kvm: kvm instance + * @sp: the new page + * @shared: This operation may not be running under the exclusive use of + * the MMU lock and the operation must synchronize with other + * threads that might be adding or removing pages. + * @account_nx: This page replaces a NX large page and should be marked for + * eventual reclaim. + */ +static void tdp_mmu_link_page(struct kvm *kvm, struct kvm_mmu_page *sp, + bool shared, bool account_nx) +{ + if (shared) + spin_lock(&kvm->arch.tdp_mmu_pages_lock); + else + lockdep_assert_held_write(&kvm->mmu_lock); + + list_add(&sp->link, &kvm->arch.tdp_mmu_pages); + if (account_nx) + account_huge_nx_page(kvm, sp); + + if (shared) + spin_unlock(&kvm->arch.tdp_mmu_pages_lock); +} + +/** + * tdp_mmu_unlink_page - Remove page from the list of pages used by the TDP MMU + * + * @kvm: kvm instance + * @sp: the page to be removed + * @shared: This operation may not be running under the exclusive use of + * the MMU lock and the operation must synchronize with other + * threads that might be adding or removing pages. + */ +static void tdp_mmu_unlink_page(struct kvm *kvm, struct kvm_mmu_page *sp, + bool shared) +{ + if (shared) + spin_lock(&kvm->arch.tdp_mmu_pages_lock); + else + lockdep_assert_held_write(&kvm->mmu_lock); + + list_del(&sp->link); + if (sp->lpage_disallowed) + unaccount_huge_nx_page(kvm, sp); + + if (shared) + spin_unlock(&kvm->arch.tdp_mmu_pages_lock); +} + +/** + * handle_removed_tdp_mmu_page - handle a pt removed from the TDP structure + * + * @kvm: kvm instance + * @pt: the page removed from the paging structure + * @shared: This operation may not be running under the exclusive use + * of the MMU lock and the operation must synchronize with other + * threads that might be modifying SPTEs. + * + * Given a page table that has been removed from the TDP paging structure, + * iterates through the page table to clear SPTEs and free child page tables. + * + * Note that pt is passed in as a tdp_ptep_t, but it does not need RCU + * protection. Since this thread removed it from the paging structure, + * this thread will be responsible for ensuring the page is freed. Hence the + * early rcu_dereferences in the function. + */ +static void handle_removed_tdp_mmu_page(struct kvm *kvm, tdp_ptep_t pt, + bool shared) +{ + struct kvm_mmu_page *sp = sptep_to_sp(rcu_dereference(pt)); + int level = sp->role.level; + gfn_t base_gfn = sp->gfn; + u64 old_child_spte; + u64 *sptep; + gfn_t gfn; + int i; + + trace_kvm_mmu_prepare_zap_page(sp); + + tdp_mmu_unlink_page(kvm, sp, shared); + + for (i = 0; i < PT64_ENT_PER_PAGE; i++) { + sptep = rcu_dereference(pt) + i; + gfn = base_gfn + (i * KVM_PAGES_PER_HPAGE(level - 1)); + + if (shared) { + /* + * Set the SPTE to a nonpresent value that other + * threads will not overwrite. If the SPTE was + * already marked as removed then another thread + * handling a page fault could overwrite it, so + * set the SPTE until it is set from some other + * value to the removed SPTE value. + */ + for (;;) { + old_child_spte = xchg(sptep, REMOVED_SPTE); + if (!is_removed_spte(old_child_spte)) + break; + cpu_relax(); + } + } else { + /* + * If the SPTE is not MMU-present, there is no backing + * page associated with the SPTE and so no side effects + * that need to be recorded, and exclusive ownership of + * mmu_lock ensures the SPTE can't be made present. + * Note, zapping MMIO SPTEs is also unnecessary as they + * are guarded by the memslots generation, not by being + * unreachable. + */ + old_child_spte = READ_ONCE(*sptep); + if (!is_shadow_present_pte(old_child_spte)) + continue; + + /* + * Marking the SPTE as a removed SPTE is not + * strictly necessary here as the MMU lock will + * stop other threads from concurrently modifying + * this SPTE. Using the removed SPTE value keeps + * the two branches consistent and simplifies + * the function. + */ + WRITE_ONCE(*sptep, REMOVED_SPTE); + } + handle_changed_spte(kvm, kvm_mmu_page_as_id(sp), gfn, + old_child_spte, REMOVED_SPTE, level - 1, + shared); + } + + kvm_flush_remote_tlbs_with_address(kvm, gfn, + KVM_PAGES_PER_HPAGE(level)); + + call_rcu(&sp->rcu_head, tdp_mmu_free_sp_rcu_callback); +} + +/** * handle_changed_spte - handle bookkeeping associated with an SPTE change * @kvm: kvm instance * @as_id: the address space of the paging structure the SPTE was a part of @@ -242,22 +379,22 @@ static void handle_changed_spte_dirty_log(struct kvm *kvm, int as_id, gfn_t gfn, * @old_spte: The value of the SPTE before the change * @new_spte: The value of the SPTE after the change * @level: the level of the PT the SPTE is part of in the paging structure + * @shared: This operation may not be running under the exclusive use of + * the MMU lock and the operation must synchronize with other + * threads that might be modifying SPTEs. * * Handle bookkeeping that might result from the modification of a SPTE. * This function must be called for all TDP SPTE modifications. */ static void __handle_changed_spte(struct kvm *kvm, int as_id, gfn_t gfn, - u64 old_spte, u64 new_spte, int level) + u64 old_spte, u64 new_spte, int level, + bool shared) { bool was_present = is_shadow_present_pte(old_spte); bool is_present = is_shadow_present_pte(new_spte); bool was_leaf = was_present && is_last_spte(old_spte, level); bool is_leaf = is_present && is_last_spte(new_spte, level); bool pfn_changed = spte_to_pfn(old_spte) != spte_to_pfn(new_spte); - u64 *pt; - struct kvm_mmu_page *sp; - u64 old_child_spte; - int i; WARN_ON(level > PT64_ROOT_MAX_LEVEL); WARN_ON(level < PG_LEVEL_4K); @@ -298,15 +435,19 @@ static void __handle_changed_spte(struct kvm *kvm, int as_id, gfn_t gfn, */ if (!was_present && !is_present) { /* - * If this change does not involve a MMIO SPTE, it is - * unexpected. Log the change, though it should not impact the - * guest since both the former and current SPTEs are nonpresent. + * If this change does not involve a MMIO SPTE or removed SPTE, + * it is unexpected. Log the change, though it should not + * impact the guest since both the former and current SPTEs + * are nonpresent. */ - if (WARN_ON(!is_mmio_spte(old_spte) && !is_mmio_spte(new_spte))) + if (WARN_ON(!is_mmio_spte(old_spte) && + !is_mmio_spte(new_spte) && + !is_removed_spte(new_spte))) pr_err("Unexpected SPTE change! Nonpresent SPTEs\n" "should not be replaced with another,\n" "different nonpresent SPTE, unless one or both\n" - "are MMIO SPTEs.\n" + "are MMIO SPTEs, or the new SPTE is\n" + "a temporary removed SPTE.\n" "as_id: %d gfn: %llx old_spte: %llx new_spte: %llx level: %d", as_id, gfn, old_spte, new_spte, level); return; @@ -321,59 +462,124 @@ static void __handle_changed_spte(struct kvm *kvm, int as_id, gfn_t gfn, * Recursively handle child PTs if the change removed a subtree from * the paging structure. */ - if (was_present && !was_leaf && (pfn_changed || !is_present)) { - pt = spte_to_child_pt(old_spte, level); - sp = sptep_to_sp(pt); + if (was_present && !was_leaf && (pfn_changed || !is_present)) + handle_removed_tdp_mmu_page(kvm, + spte_to_child_pt(old_spte, level), shared); +} - trace_kvm_mmu_prepare_zap_page(sp); +static void handle_changed_spte(struct kvm *kvm, int as_id, gfn_t gfn, + u64 old_spte, u64 new_spte, int level, + bool shared) +{ + __handle_changed_spte(kvm, as_id, gfn, old_spte, new_spte, level, + shared); + handle_changed_spte_acc_track(old_spte, new_spte, level); + handle_changed_spte_dirty_log(kvm, as_id, gfn, old_spte, + new_spte, level); +} - list_del(&sp->link); +/* + * tdp_mmu_set_spte_atomic - Set a TDP MMU SPTE atomically and handle the + * associated bookkeeping + * + * @kvm: kvm instance + * @iter: a tdp_iter instance currently on the SPTE that should be set + * @new_spte: The value the SPTE should be set to + * Returns: true if the SPTE was set, false if it was not. If false is returned, + * this function will have no side-effects. + */ +static inline bool tdp_mmu_set_spte_atomic(struct kvm *kvm, + struct tdp_iter *iter, + u64 new_spte) +{ + lockdep_assert_held_read(&kvm->mmu_lock); - if (sp->lpage_disallowed) - unaccount_huge_nx_page(kvm, sp); + /* + * Do not change removed SPTEs. Only the thread that froze the SPTE + * may modify it. + */ + if (iter->old_spte == REMOVED_SPTE) + return false; - for (i = 0; i < PT64_ENT_PER_PAGE; i++) { - old_child_spte = READ_ONCE(*(pt + i)); - WRITE_ONCE(*(pt + i), 0); - handle_changed_spte(kvm, as_id, - gfn + (i * KVM_PAGES_PER_HPAGE(level - 1)), - old_child_spte, 0, level - 1); - } + if (cmpxchg64(rcu_dereference(iter->sptep), iter->old_spte, + new_spte) != iter->old_spte) + return false; - kvm_flush_remote_tlbs_with_address(kvm, gfn, - KVM_PAGES_PER_HPAGE(level)); + handle_changed_spte(kvm, iter->as_id, iter->gfn, iter->old_spte, + new_spte, iter->level, true); - free_page((unsigned long)pt); - kmem_cache_free(mmu_page_header_cache, sp); - } + return true; } -static void handle_changed_spte(struct kvm *kvm, int as_id, gfn_t gfn, - u64 old_spte, u64 new_spte, int level) +static inline bool tdp_mmu_zap_spte_atomic(struct kvm *kvm, + struct tdp_iter *iter) { - __handle_changed_spte(kvm, as_id, gfn, old_spte, new_spte, level); - handle_changed_spte_acc_track(old_spte, new_spte, level); - handle_changed_spte_dirty_log(kvm, as_id, gfn, old_spte, - new_spte, level); + /* + * Freeze the SPTE by setting it to a special, + * non-present value. This will stop other threads from + * immediately installing a present entry in its place + * before the TLBs are flushed. + */ + if (!tdp_mmu_set_spte_atomic(kvm, iter, REMOVED_SPTE)) + return false; + + kvm_flush_remote_tlbs_with_address(kvm, iter->gfn, + KVM_PAGES_PER_HPAGE(iter->level)); + + /* + * No other thread can overwrite the removed SPTE as they + * must either wait on the MMU lock or use + * tdp_mmu_set_spte_atomic which will not overrite the + * special removed SPTE value. No bookkeeping is needed + * here since the SPTE is going from non-present + * to non-present. + */ + WRITE_ONCE(*rcu_dereference(iter->sptep), 0); + + return true; } + +/* + * __tdp_mmu_set_spte - Set a TDP MMU SPTE and handle the associated bookkeeping + * @kvm: kvm instance + * @iter: a tdp_iter instance currently on the SPTE that should be set + * @new_spte: The value the SPTE should be set to + * @record_acc_track: Notify the MM subsystem of changes to the accessed state + * of the page. Should be set unless handling an MMU + * notifier for access tracking. Leaving record_acc_track + * unset in that case prevents page accesses from being + * double counted. + * @record_dirty_log: Record the page as dirty in the dirty bitmap if + * appropriate for the change being made. Should be set + * unless performing certain dirty logging operations. + * Leaving record_dirty_log unset in that case prevents page + * writes from being double counted. + */ static inline void __tdp_mmu_set_spte(struct kvm *kvm, struct tdp_iter *iter, u64 new_spte, bool record_acc_track, bool record_dirty_log) { - u64 *root_pt = tdp_iter_root_pt(iter); - struct kvm_mmu_page *root = sptep_to_sp(root_pt); - int as_id = kvm_mmu_page_as_id(root); + lockdep_assert_held_write(&kvm->mmu_lock); + + /* + * No thread should be using this function to set SPTEs to the + * temporary removed SPTE value. + * If operating under the MMU lock in read mode, tdp_mmu_set_spte_atomic + * should be used. If operating under the MMU lock in write mode, the + * use of the removed SPTE should not be necessary. + */ + WARN_ON(iter->old_spte == REMOVED_SPTE); - WRITE_ONCE(*iter->sptep, new_spte); + WRITE_ONCE(*rcu_dereference(iter->sptep), new_spte); - __handle_changed_spte(kvm, as_id, iter->gfn, iter->old_spte, new_spte, - iter->level); + __handle_changed_spte(kvm, iter->as_id, iter->gfn, iter->old_spte, + new_spte, iter->level, false); if (record_acc_track) handle_changed_spte_acc_track(iter->old_spte, new_spte, iter->level); if (record_dirty_log) - handle_changed_spte_dirty_log(kvm, as_id, iter->gfn, + handle_changed_spte_dirty_log(kvm, iter->as_id, iter->gfn, iter->old_spte, new_spte, iter->level); } @@ -413,27 +619,44 @@ static inline void tdp_mmu_set_spte_no_dirty_log(struct kvm *kvm, _mmu->shadow_root_level, _start, _end) /* - * Flush the TLB if the process should drop kvm->mmu_lock. - * Return whether the caller still needs to flush the tlb. + * Yield if the MMU lock is contended or this thread needs to return control + * to the scheduler. + * + * If this function should yield and flush is set, it will perform a remote + * TLB flush before yielding. + * + * If this function yields, it will also reset the tdp_iter's walk over the + * paging structure and the calling function should skip to the next + * iteration to allow the iterator to continue its traversal from the + * paging structure root. + * + * Return true if this function yielded and the iterator's traversal was reset. + * Return false if a yield was not needed. */ -static bool tdp_mmu_iter_flush_cond_resched(struct kvm *kvm, struct tdp_iter *iter) +static inline bool tdp_mmu_iter_cond_resched(struct kvm *kvm, + struct tdp_iter *iter, bool flush) { - if (need_resched() || spin_needbreak(&kvm->mmu_lock)) { - kvm_flush_remote_tlbs(kvm); - cond_resched_lock(&kvm->mmu_lock); - tdp_iter_refresh_walk(iter); + /* Ensure forward progress has been made before yielding. */ + if (iter->next_last_level_gfn == iter->yielded_gfn) return false; - } else { + + if (need_resched() || rwlock_needbreak(&kvm->mmu_lock)) { + rcu_read_unlock(); + + if (flush) + kvm_flush_remote_tlbs(kvm); + + cond_resched_rwlock_write(&kvm->mmu_lock); + rcu_read_lock(); + + WARN_ON(iter->gfn > iter->next_last_level_gfn); + + tdp_iter_restart(iter); + return true; } -} -static void tdp_mmu_iter_cond_resched(struct kvm *kvm, struct tdp_iter *iter) -{ - if (need_resched() || spin_needbreak(&kvm->mmu_lock)) { - cond_resched_lock(&kvm->mmu_lock); - tdp_iter_refresh_walk(iter); - } + return false; } /* @@ -453,7 +676,15 @@ static bool zap_gfn_range(struct kvm *kvm, struct kvm_mmu_page *root, struct tdp_iter iter; bool flush_needed = false; + rcu_read_lock(); + tdp_root_for_each_pte(iter, root, start, end) { + if (can_yield && + tdp_mmu_iter_cond_resched(kvm, &iter, flush_needed)) { + flush_needed = false; + continue; + } + if (!is_shadow_present_pte(iter.old_spte)) continue; @@ -468,12 +699,10 @@ static bool zap_gfn_range(struct kvm *kvm, struct kvm_mmu_page *root, continue; tdp_mmu_set_spte(kvm, &iter, 0); - - if (can_yield) - flush_needed = tdp_mmu_iter_flush_cond_resched(kvm, &iter); - else - flush_needed = true; + flush_needed = true; } + + rcu_read_unlock(); return flush_needed; } @@ -517,21 +746,18 @@ static int tdp_mmu_map_handle_target_level(struct kvm_vcpu *vcpu, int write, int ret = 0; int make_spte_ret = 0; - if (unlikely(is_noslot_pfn(pfn))) { + if (unlikely(is_noslot_pfn(pfn))) new_spte = make_mmio_spte(vcpu, iter->gfn, ACC_ALL); - trace_mark_mmio_spte(iter->sptep, iter->gfn, new_spte); - } else { + else make_spte_ret = make_spte(vcpu, ACC_ALL, iter->level, iter->gfn, pfn, iter->old_spte, prefault, true, map_writable, !shadow_accessed_mask, &new_spte); - trace_kvm_mmu_set_spte(iter->level, iter->gfn, iter->sptep); - } if (new_spte == iter->old_spte) ret = RET_PF_SPURIOUS; - else - tdp_mmu_set_spte(vcpu->kvm, iter, new_spte); + else if (!tdp_mmu_set_spte_atomic(vcpu->kvm, iter, new_spte)) + return RET_PF_RETRY; /* * If the page fault was caused by a write but the page is write @@ -545,10 +771,16 @@ static int tdp_mmu_map_handle_target_level(struct kvm_vcpu *vcpu, int write, } /* If a MMIO SPTE is installed, the MMIO will need to be emulated. */ - if (unlikely(is_mmio_spte(new_spte))) + if (unlikely(is_mmio_spte(new_spte))) { + trace_mark_mmio_spte(rcu_dereference(iter->sptep), iter->gfn, + new_spte); ret = RET_PF_EMULATE; + } else + trace_kvm_mmu_set_spte(iter->level, iter->gfn, + rcu_dereference(iter->sptep)); - trace_kvm_mmu_set_spte(iter->level, iter->gfn, iter->sptep); + trace_kvm_mmu_set_spte(iter->level, iter->gfn, + rcu_dereference(iter->sptep)); if (!prefault) vcpu->stat.pf_fixed++; @@ -586,6 +818,9 @@ int kvm_tdp_mmu_map(struct kvm_vcpu *vcpu, gpa_t gpa, u32 error_code, huge_page_disallowed, &req_level); trace_kvm_mmu_spte_requested(gpa, level, pfn); + + rcu_read_lock(); + tdp_mmu_for_each_pte(iter, mmu, gfn, gfn + 1) { if (nx_huge_page_workaround_enabled) disallowed_hugepage_adjust(iter.old_spte, gfn, @@ -601,49 +836,61 @@ int kvm_tdp_mmu_map(struct kvm_vcpu *vcpu, gpa_t gpa, u32 error_code, */ if (is_shadow_present_pte(iter.old_spte) && is_large_pte(iter.old_spte)) { - tdp_mmu_set_spte(vcpu->kvm, &iter, 0); - - kvm_flush_remote_tlbs_with_address(vcpu->kvm, iter.gfn, - KVM_PAGES_PER_HPAGE(iter.level)); + if (!tdp_mmu_zap_spte_atomic(vcpu->kvm, &iter)) + break; /* * The iter must explicitly re-read the spte here * because the new value informs the !present * path below. */ - iter.old_spte = READ_ONCE(*iter.sptep); + iter.old_spte = READ_ONCE(*rcu_dereference(iter.sptep)); } if (!is_shadow_present_pte(iter.old_spte)) { sp = alloc_tdp_mmu_page(vcpu, iter.gfn, iter.level); - list_add(&sp->link, &vcpu->kvm->arch.tdp_mmu_pages); child_pt = sp->spt; - clear_page(child_pt); + new_spte = make_nonleaf_spte(child_pt, !shadow_accessed_mask); - trace_kvm_mmu_get_page(sp, true); - if (huge_page_disallowed && req_level >= iter.level) - account_huge_nx_page(vcpu->kvm, sp); - - tdp_mmu_set_spte(vcpu->kvm, &iter, new_spte); + if (tdp_mmu_set_spte_atomic(vcpu->kvm, &iter, + new_spte)) { + tdp_mmu_link_page(vcpu->kvm, sp, true, + huge_page_disallowed && + req_level >= iter.level); + + trace_kvm_mmu_get_page(sp, true); + } else { + tdp_mmu_free_sp(sp); + break; + } } } - if (WARN_ON(iter.level != level)) + if (iter.level != level) { + rcu_read_unlock(); return RET_PF_RETRY; + } ret = tdp_mmu_map_handle_target_level(vcpu, write, map_writable, &iter, pfn, prefault); + rcu_read_unlock(); return ret; } -static int kvm_tdp_mmu_handle_hva_range(struct kvm *kvm, unsigned long start, - unsigned long end, unsigned long data, - int (*handler)(struct kvm *kvm, struct kvm_memory_slot *slot, - struct kvm_mmu_page *root, gfn_t start, - gfn_t end, unsigned long data)) +static __always_inline int +kvm_tdp_mmu_handle_hva_range(struct kvm *kvm, + unsigned long start, + unsigned long end, + unsigned long data, + int (*handler)(struct kvm *kvm, + struct kvm_memory_slot *slot, + struct kvm_mmu_page *root, + gfn_t start, + gfn_t end, + unsigned long data)) { struct kvm_memslots *slots; struct kvm_memory_slot *memslot; @@ -705,6 +952,8 @@ static int age_gfn_range(struct kvm *kvm, struct kvm_memory_slot *slot, int young = 0; u64 new_spte = 0; + rcu_read_lock(); + tdp_root_for_each_leaf_pte(iter, root, start, end) { /* * If we have a non-accessed entry we don't need to change the @@ -736,6 +985,8 @@ static int age_gfn_range(struct kvm *kvm, struct kvm_memory_slot *slot, trace_kvm_age_page(iter.gfn, iter.level, slot, young); } + rcu_read_unlock(); + return young; } @@ -781,6 +1032,8 @@ static int set_tdp_spte(struct kvm *kvm, struct kvm_memory_slot *slot, u64 new_spte; int need_flush = 0; + rcu_read_lock(); + WARN_ON(pte_huge(*ptep)); new_pfn = pte_pfn(*ptep); @@ -809,6 +1062,8 @@ static int set_tdp_spte(struct kvm *kvm, struct kvm_memory_slot *slot, if (need_flush) kvm_flush_remote_tlbs_with_address(kvm, gfn, 1); + rcu_read_unlock(); + return 0; } @@ -832,21 +1087,27 @@ static bool wrprot_gfn_range(struct kvm *kvm, struct kvm_mmu_page *root, u64 new_spte; bool spte_set = false; + rcu_read_lock(); + BUG_ON(min_level > KVM_MAX_HUGEPAGE_LEVEL); for_each_tdp_pte_min_level(iter, root->spt, root->role.level, min_level, start, end) { + if (tdp_mmu_iter_cond_resched(kvm, &iter, false)) + continue; + if (!is_shadow_present_pte(iter.old_spte) || - !is_last_spte(iter.old_spte, iter.level)) + !is_last_spte(iter.old_spte, iter.level) || + !(iter.old_spte & PT_WRITABLE_MASK)) continue; new_spte = iter.old_spte & ~PT_WRITABLE_MASK; tdp_mmu_set_spte_no_dirty_log(kvm, &iter, new_spte); spte_set = true; - - tdp_mmu_iter_cond_resched(kvm, &iter); } + + rcu_read_unlock(); return spte_set; } @@ -888,7 +1149,12 @@ static bool clear_dirty_gfn_range(struct kvm *kvm, struct kvm_mmu_page *root, u64 new_spte; bool spte_set = false; + rcu_read_lock(); + tdp_root_for_each_leaf_pte(iter, root, start, end) { + if (tdp_mmu_iter_cond_resched(kvm, &iter, false)) + continue; + if (spte_ad_need_write_protect(iter.old_spte)) { if (is_writable_pte(iter.old_spte)) new_spte = iter.old_spte & ~PT_WRITABLE_MASK; @@ -903,9 +1169,9 @@ static bool clear_dirty_gfn_range(struct kvm *kvm, struct kvm_mmu_page *root, tdp_mmu_set_spte_no_dirty_log(kvm, &iter, new_spte); spte_set = true; - - tdp_mmu_iter_cond_resched(kvm, &iter); } + + rcu_read_unlock(); return spte_set; } @@ -947,6 +1213,8 @@ static void clear_dirty_pt_masked(struct kvm *kvm, struct kvm_mmu_page *root, struct tdp_iter iter; u64 new_spte; + rcu_read_lock(); + tdp_root_for_each_leaf_pte(iter, root, gfn + __ffs(mask), gfn + BITS_PER_LONG) { if (!mask) @@ -956,6 +1224,8 @@ static void clear_dirty_pt_masked(struct kvm *kvm, struct kvm_mmu_page *root, !(mask & (1UL << (iter.gfn - gfn)))) continue; + mask &= ~(1UL << (iter.gfn - gfn)); + if (wrprot || spte_ad_need_write_protect(iter.old_spte)) { if (is_writable_pte(iter.old_spte)) new_spte = iter.old_spte & ~PT_WRITABLE_MASK; @@ -969,9 +1239,9 @@ static void clear_dirty_pt_masked(struct kvm *kvm, struct kvm_mmu_page *root, } tdp_mmu_set_spte_no_dirty_log(kvm, &iter, new_spte); - - mask &= ~(1UL << (iter.gfn - gfn)); } + + rcu_read_unlock(); } /* @@ -989,7 +1259,7 @@ void kvm_tdp_mmu_clear_dirty_pt_masked(struct kvm *kvm, struct kvm_mmu_page *root; int root_as_id; - lockdep_assert_held(&kvm->mmu_lock); + lockdep_assert_held_write(&kvm->mmu_lock); for_each_tdp_mmu_root(kvm, root) { root_as_id = kvm_mmu_page_as_id(root); if (root_as_id != slot->as_id) @@ -1000,81 +1270,43 @@ void kvm_tdp_mmu_clear_dirty_pt_masked(struct kvm *kvm, } /* - * Set the dirty status of all the SPTEs mapping GFNs in the memslot. This is - * only used for PML, and so will involve setting the dirty bit on each SPTE. - * Returns true if an SPTE has been changed and the TLBs need to be flushed. - */ -static bool set_dirty_gfn_range(struct kvm *kvm, struct kvm_mmu_page *root, - gfn_t start, gfn_t end) -{ - struct tdp_iter iter; - u64 new_spte; - bool spte_set = false; - - tdp_root_for_each_pte(iter, root, start, end) { - if (!is_shadow_present_pte(iter.old_spte)) - continue; - - new_spte = iter.old_spte | shadow_dirty_mask; - - tdp_mmu_set_spte(kvm, &iter, new_spte); - spte_set = true; - - tdp_mmu_iter_cond_resched(kvm, &iter); - } - - return spte_set; -} - -/* - * Set the dirty status of all the SPTEs mapping GFNs in the memslot. This is - * only used for PML, and so will involve setting the dirty bit on each SPTE. - * Returns true if an SPTE has been changed and the TLBs need to be flushed. - */ -bool kvm_tdp_mmu_slot_set_dirty(struct kvm *kvm, struct kvm_memory_slot *slot) -{ - struct kvm_mmu_page *root; - int root_as_id; - bool spte_set = false; - - for_each_tdp_mmu_root_yield_safe(kvm, root) { - root_as_id = kvm_mmu_page_as_id(root); - if (root_as_id != slot->as_id) - continue; - - spte_set |= set_dirty_gfn_range(kvm, root, slot->base_gfn, - slot->base_gfn + slot->npages); - } - return spte_set; -} - -/* * Clear leaf entries which could be replaced by large mappings, for * GFNs within the slot. */ static void zap_collapsible_spte_range(struct kvm *kvm, struct kvm_mmu_page *root, - gfn_t start, gfn_t end) + struct kvm_memory_slot *slot) { + gfn_t start = slot->base_gfn; + gfn_t end = start + slot->npages; struct tdp_iter iter; kvm_pfn_t pfn; bool spte_set = false; + rcu_read_lock(); + tdp_root_for_each_pte(iter, root, start, end) { + if (tdp_mmu_iter_cond_resched(kvm, &iter, spte_set)) { + spte_set = false; + continue; + } + if (!is_shadow_present_pte(iter.old_spte) || !is_last_spte(iter.old_spte, iter.level)) continue; pfn = spte_to_pfn(iter.old_spte); if (kvm_is_reserved_pfn(pfn) || - !PageTransCompoundMap(pfn_to_page(pfn))) + iter.level >= kvm_mmu_max_mapping_level(kvm, slot, iter.gfn, + pfn, PG_LEVEL_NUM)) continue; tdp_mmu_set_spte(kvm, &iter, 0); - spte_set = tdp_mmu_iter_flush_cond_resched(kvm, &iter); + spte_set = true; } + rcu_read_unlock(); if (spte_set) kvm_flush_remote_tlbs(kvm); } @@ -1084,7 +1316,7 @@ static void zap_collapsible_spte_range(struct kvm *kvm, * be replaced by large mappings, for GFNs within the slot. */ void kvm_tdp_mmu_zap_collapsible_sptes(struct kvm *kvm, - const struct kvm_memory_slot *slot) + struct kvm_memory_slot *slot) { struct kvm_mmu_page *root; int root_as_id; @@ -1094,8 +1326,7 @@ void kvm_tdp_mmu_zap_collapsible_sptes(struct kvm *kvm, if (root_as_id != slot->as_id) continue; - zap_collapsible_spte_range(kvm, root, slot->base_gfn, - slot->base_gfn + slot->npages); + zap_collapsible_spte_range(kvm, root, slot); } } @@ -1111,6 +1342,8 @@ static bool write_protect_gfn(struct kvm *kvm, struct kvm_mmu_page *root, u64 new_spte; bool spte_set = false; + rcu_read_lock(); + tdp_root_for_each_leaf_pte(iter, root, gfn, gfn + 1) { if (!is_writable_pte(iter.old_spte)) break; @@ -1122,6 +1355,8 @@ static bool write_protect_gfn(struct kvm *kvm, struct kvm_mmu_page *root, spte_set = true; } + rcu_read_unlock(); + return spte_set; } @@ -1137,7 +1372,7 @@ bool kvm_tdp_mmu_write_protect_gfn(struct kvm *kvm, int root_as_id; bool spte_set = false; - lockdep_assert_held(&kvm->mmu_lock); + lockdep_assert_held_write(&kvm->mmu_lock); for_each_tdp_mmu_root(kvm, root) { root_as_id = kvm_mmu_page_as_id(root); if (root_as_id != slot->as_id) @@ -1162,10 +1397,14 @@ int kvm_tdp_mmu_get_walk(struct kvm_vcpu *vcpu, u64 addr, u64 *sptes, *root_level = vcpu->arch.mmu->shadow_root_level; + rcu_read_lock(); + tdp_mmu_for_each_pte(iter, mmu, gfn, gfn + 1) { leaf = iter.level; sptes[leaf] = iter.old_spte; } + rcu_read_unlock(); + return leaf; } diff --git a/arch/x86/kvm/mmu/tdp_mmu.h b/arch/x86/kvm/mmu/tdp_mmu.h index cbbdbadd1526..3b761c111bff 100644 --- a/arch/x86/kvm/mmu/tdp_mmu.h +++ b/arch/x86/kvm/mmu/tdp_mmu.h @@ -5,10 +5,6 @@ #include <linux/kvm_host.h> -void kvm_mmu_init_tdp_mmu(struct kvm *kvm); -void kvm_mmu_uninit_tdp_mmu(struct kvm *kvm); - -bool is_tdp_mmu_root(struct kvm *kvm, hpa_t root); hpa_t kvm_tdp_mmu_get_vcpu_root_hpa(struct kvm_vcpu *vcpu); void kvm_tdp_mmu_free_root(struct kvm *kvm, struct kvm_mmu_page *root); @@ -37,9 +33,8 @@ void kvm_tdp_mmu_clear_dirty_pt_masked(struct kvm *kvm, struct kvm_memory_slot *slot, gfn_t gfn, unsigned long mask, bool wrprot); -bool kvm_tdp_mmu_slot_set_dirty(struct kvm *kvm, struct kvm_memory_slot *slot); void kvm_tdp_mmu_zap_collapsible_sptes(struct kvm *kvm, - const struct kvm_memory_slot *slot); + struct kvm_memory_slot *slot); bool kvm_tdp_mmu_write_protect_gfn(struct kvm *kvm, struct kvm_memory_slot *slot, gfn_t gfn); @@ -47,4 +42,32 @@ bool kvm_tdp_mmu_write_protect_gfn(struct kvm *kvm, int kvm_tdp_mmu_get_walk(struct kvm_vcpu *vcpu, u64 addr, u64 *sptes, int *root_level); +#ifdef CONFIG_X86_64 +void kvm_mmu_init_tdp_mmu(struct kvm *kvm); +void kvm_mmu_uninit_tdp_mmu(struct kvm *kvm); +static inline bool is_tdp_mmu_enabled(struct kvm *kvm) { return kvm->arch.tdp_mmu_enabled; } +static inline bool is_tdp_mmu_page(struct kvm_mmu_page *sp) { return sp->tdp_mmu_page; } +#else +static inline void kvm_mmu_init_tdp_mmu(struct kvm *kvm) {} +static inline void kvm_mmu_uninit_tdp_mmu(struct kvm *kvm) {} +static inline bool is_tdp_mmu_enabled(struct kvm *kvm) { return false; } +static inline bool is_tdp_mmu_page(struct kvm_mmu_page *sp) { return false; } +#endif + +static inline bool is_tdp_mmu_root(struct kvm *kvm, hpa_t hpa) +{ + struct kvm_mmu_page *sp; + + if (!is_tdp_mmu_enabled(kvm)) + return false; + if (WARN_ON(!VALID_PAGE(hpa))) + return false; + + sp = to_shadow_page(hpa); + if (WARN_ON(!sp)) + return false; + + return is_tdp_mmu_page(sp) && sp->root_count; +} + #endif /* __KVM_X86_MMU_TDP_MMU_H */ diff --git a/arch/x86/kvm/mtrr.c b/arch/x86/kvm/mtrr.c index f472fdb6ae7e..a8502e02f479 100644 --- a/arch/x86/kvm/mtrr.c +++ b/arch/x86/kvm/mtrr.c @@ -75,7 +75,7 @@ bool kvm_mtrr_valid(struct kvm_vcpu *vcpu, u32 msr, u64 data) /* variable MTRRs */ WARN_ON(!(msr >= 0x200 && msr < 0x200 + 2 * KVM_NR_VAR_MTRR)); - mask = (~0ULL) << cpuid_maxphyaddr(vcpu); + mask = kvm_vcpu_reserved_gpa_bits_raw(vcpu); if ((msr & 1) == 0) { /* MTRR base */ if (!valid_mtrr_type(data & 0xff)) @@ -351,14 +351,14 @@ static void set_var_mtrr_msr(struct kvm_vcpu *vcpu, u32 msr, u64 data) if (var_mtrr_range_is_valid(cur)) list_del(&mtrr_state->var_ranges[index].node); - /* Extend the mask with all 1 bits to the left, since those - * bits must implicitly be 0. The bits are then cleared - * when reading them. + /* + * Set all illegal GPA bits in the mask, since those bits must + * implicitly be 0. The bits are then cleared when reading them. */ if (!is_mtrr_mask) cur->base = data; else - cur->mask = data | (-1LL << cpuid_maxphyaddr(vcpu)); + cur->mask = data | kvm_vcpu_reserved_gpa_bits_raw(vcpu); /* add it to the list if it's enabled. */ if (var_mtrr_range_is_valid(cur)) { @@ -426,7 +426,7 @@ int kvm_mtrr_get_msr(struct kvm_vcpu *vcpu, u32 msr, u64 *pdata) else *pdata = vcpu->arch.mtrr_state.var_ranges[index].mask; - *pdata &= (1ULL << cpuid_maxphyaddr(vcpu)) - 1; + *pdata &= ~kvm_vcpu_reserved_gpa_bits_raw(vcpu); } return 0; diff --git a/arch/x86/kvm/pmu.c b/arch/x86/kvm/pmu.c index 67741d2a0308..827886c12c16 100644 --- a/arch/x86/kvm/pmu.c +++ b/arch/x86/kvm/pmu.c @@ -373,7 +373,7 @@ int kvm_pmu_rdpmc(struct kvm_vcpu *vcpu, unsigned idx, u64 *data) return 1; if (!(kvm_read_cr4(vcpu) & X86_CR4_PCE) && - (kvm_x86_ops.get_cpl(vcpu) != 0) && + (static_call(kvm_x86_get_cpl)(vcpu) != 0) && (kvm_read_cr0(vcpu) & X86_CR0_PE)) return 1; @@ -383,8 +383,11 @@ int kvm_pmu_rdpmc(struct kvm_vcpu *vcpu, unsigned idx, u64 *data) void kvm_pmu_deliver_pmi(struct kvm_vcpu *vcpu) { - if (lapic_in_kernel(vcpu)) + if (lapic_in_kernel(vcpu)) { + if (kvm_x86_ops.pmu_ops->deliver_pmi) + kvm_x86_ops.pmu_ops->deliver_pmi(vcpu); kvm_apic_local_deliver(vcpu->arch.apic, APIC_LVTPC); + } } bool kvm_pmu_is_valid_msr(struct kvm_vcpu *vcpu, u32 msr) @@ -473,6 +476,9 @@ void kvm_pmu_cleanup(struct kvm_vcpu *vcpu) pmc_stop_counter(pmc); } + if (kvm_x86_ops.pmu_ops->cleanup) + kvm_x86_ops.pmu_ops->cleanup(vcpu); + bitmap_zero(pmu->pmc_in_use, X86_PMC_IDX_MAX); } diff --git a/arch/x86/kvm/pmu.h b/arch/x86/kvm/pmu.h index 067fef51760c..7b30bc967af3 100644 --- a/arch/x86/kvm/pmu.h +++ b/arch/x86/kvm/pmu.h @@ -39,6 +39,8 @@ struct kvm_pmu_ops { void (*refresh)(struct kvm_vcpu *vcpu); void (*init)(struct kvm_vcpu *vcpu); void (*reset)(struct kvm_vcpu *vcpu); + void (*deliver_pmi)(struct kvm_vcpu *vcpu); + void (*cleanup)(struct kvm_vcpu *vcpu); }; static inline u64 pmc_bitmask(struct kvm_pmc *pmc) diff --git a/arch/x86/kvm/svm/avic.c b/arch/x86/kvm/svm/avic.c index 0ef84d57b72e..78bdcfac4e40 100644 --- a/arch/x86/kvm/svm/avic.c +++ b/arch/x86/kvm/svm/avic.c @@ -298,6 +298,23 @@ static int avic_init_backing_page(struct kvm_vcpu *vcpu) return 0; } +static void avic_kick_target_vcpus(struct kvm *kvm, struct kvm_lapic *source, + u32 icrl, u32 icrh) +{ + struct kvm_vcpu *vcpu; + int i; + + kvm_for_each_vcpu(i, vcpu, kvm) { + bool m = kvm_apic_match_dest(vcpu, source, + icrl & APIC_SHORT_MASK, + GET_APIC_DEST_FIELD(icrh), + icrl & APIC_DEST_MASK); + + if (m && !avic_vcpu_is_running(vcpu)) + kvm_vcpu_wake_up(vcpu); + } +} + int avic_incomplete_ipi_interception(struct vcpu_svm *svm) { u32 icrh = svm->vmcb->control.exit_info_1 >> 32; @@ -324,28 +341,14 @@ int avic_incomplete_ipi_interception(struct vcpu_svm *svm) kvm_lapic_reg_write(apic, APIC_ICR2, icrh); kvm_lapic_reg_write(apic, APIC_ICR, icrl); break; - case AVIC_IPI_FAILURE_TARGET_NOT_RUNNING: { - int i; - struct kvm_vcpu *vcpu; - struct kvm *kvm = svm->vcpu.kvm; - struct kvm_lapic *apic = svm->vcpu.arch.apic; - + case AVIC_IPI_FAILURE_TARGET_NOT_RUNNING: /* * At this point, we expect that the AVIC HW has already * set the appropriate IRR bits on the valid target * vcpus. So, we just need to kick the appropriate vcpu. */ - kvm_for_each_vcpu(i, vcpu, kvm) { - bool m = kvm_apic_match_dest(vcpu, apic, - icrl & APIC_SHORT_MASK, - GET_APIC_DEST_FIELD(icrh), - icrl & APIC_DEST_MASK); - - if (m && !avic_vcpu_is_running(vcpu)) - kvm_vcpu_wake_up(vcpu); - } + avic_kick_target_vcpus(svm->vcpu.kvm, apic, icrl, icrh); break; - } case AVIC_IPI_FAILURE_INVALID_TARGET: WARN_ONCE(1, "Invalid IPI target: index=%u, vcpu=%d, icr=%#0x:%#0x\n", index, svm->vcpu.vcpu_id, icrh, icrl); diff --git a/arch/x86/kvm/svm/nested.c b/arch/x86/kvm/svm/nested.c index db30670dd8c4..35891d9a1099 100644 --- a/arch/x86/kvm/svm/nested.c +++ b/arch/x86/kvm/svm/nested.c @@ -51,6 +51,23 @@ static void nested_svm_inject_npf_exit(struct kvm_vcpu *vcpu, nested_svm_vmexit(svm); } +static void svm_inject_page_fault_nested(struct kvm_vcpu *vcpu, struct x86_exception *fault) +{ + struct vcpu_svm *svm = to_svm(vcpu); + WARN_ON(!is_guest_mode(vcpu)); + + if (vmcb_is_intercept(&svm->nested.ctl, INTERCEPT_EXCEPTION_OFFSET + PF_VECTOR) && + !svm->nested.nested_run_pending) { + svm->vmcb->control.exit_code = SVM_EXIT_EXCP_BASE + PF_VECTOR; + svm->vmcb->control.exit_code_hi = 0; + svm->vmcb->control.exit_info_1 = fault->error_code; + svm->vmcb->control.exit_info_2 = fault->address; + nested_svm_vmexit(svm); + } else { + kvm_inject_page_fault(vcpu, fault); + } +} + static u64 nested_svm_get_tdp_pdptr(struct kvm_vcpu *vcpu, int index) { struct vcpu_svm *svm = to_svm(vcpu); @@ -58,7 +75,7 @@ static u64 nested_svm_get_tdp_pdptr(struct kvm_vcpu *vcpu, int index) u64 pdpte; int ret; - ret = kvm_vcpu_read_guest_page(vcpu, gpa_to_gfn(__sme_clr(cr3)), &pdpte, + ret = kvm_vcpu_read_guest_page(vcpu, gpa_to_gfn(cr3), &pdpte, offset_in_page(cr3) + index * 8, 8); if (ret) return 0; @@ -248,7 +265,7 @@ static bool nested_vmcb_checks(struct vcpu_svm *svm, struct vmcb *vmcb12) if (vmcb12_lma) { if (!(vmcb12->save.cr4 & X86_CR4_PAE) || !(vmcb12->save.cr0 & X86_CR0_PE) || - (vmcb12->save.cr3 & vcpu->arch.cr3_lm_rsvd_bits)) + kvm_vcpu_is_illegal_gpa(vcpu, vmcb12->save.cr3)) return false; } if (!kvm_is_valid_cr4(&svm->vcpu, vmcb12->save.cr4)) @@ -345,7 +362,7 @@ static inline bool nested_npt_enabled(struct vcpu_svm *svm) static int nested_svm_load_cr3(struct kvm_vcpu *vcpu, unsigned long cr3, bool nested_npt) { - if (cr3 & rsvd_bits(cpuid_maxphyaddr(vcpu), 63)) + if (kvm_vcpu_is_illegal_gpa(vcpu, cr3)) return -EINVAL; if (!nested_npt && is_pae_paging(vcpu) && @@ -392,7 +409,7 @@ static void nested_prepare_vmcb_save(struct vcpu_svm *svm, struct vmcb *vmcb12) svm->vmcb->save.rsp = vmcb12->save.rsp; svm->vmcb->save.rip = vmcb12->save.rip; svm->vmcb->save.dr7 = vmcb12->save.dr7 | DR7_FIXED_1; - svm->vcpu.arch.dr6 = vmcb12->save.dr6 | DR6_FIXED_1 | DR6_RTM; + svm->vcpu.arch.dr6 = vmcb12->save.dr6 | DR6_ACTIVE_LOW; svm->vmcb->save.cpl = vmcb12->save.cpl; } @@ -436,16 +453,33 @@ int enter_svm_guest_mode(struct vcpu_svm *svm, u64 vmcb12_gpa, { int ret; + trace_kvm_nested_vmrun(svm->vmcb->save.rip, vmcb12_gpa, + vmcb12->save.rip, + vmcb12->control.int_ctl, + vmcb12->control.event_inj, + vmcb12->control.nested_ctl); + + trace_kvm_nested_intercepts(vmcb12->control.intercepts[INTERCEPT_CR] & 0xffff, + vmcb12->control.intercepts[INTERCEPT_CR] >> 16, + vmcb12->control.intercepts[INTERCEPT_EXCEPTION], + vmcb12->control.intercepts[INTERCEPT_WORD3], + vmcb12->control.intercepts[INTERCEPT_WORD4], + vmcb12->control.intercepts[INTERCEPT_WORD5]); + + svm->nested.vmcb12_gpa = vmcb12_gpa; load_nested_vmcb_control(svm, &vmcb12->control); - nested_prepare_vmcb_save(svm, vmcb12); nested_prepare_vmcb_control(svm); + nested_prepare_vmcb_save(svm, vmcb12); ret = nested_svm_load_cr3(&svm->vcpu, vmcb12->save.cr3, nested_npt_enabled(svm)); if (ret) return ret; + if (!npt_enabled) + svm->vcpu.arch.mmu->inject_page_fault = svm_inject_page_fault_nested; + svm_set_gif(svm, true); return 0; @@ -489,18 +523,6 @@ int nested_svm_vmrun(struct vcpu_svm *svm) goto out; } - trace_kvm_nested_vmrun(svm->vmcb->save.rip, vmcb12_gpa, - vmcb12->save.rip, - vmcb12->control.int_ctl, - vmcb12->control.event_inj, - vmcb12->control.nested_ctl); - - trace_kvm_nested_intercepts(vmcb12->control.intercepts[INTERCEPT_CR] & 0xffff, - vmcb12->control.intercepts[INTERCEPT_CR] >> 16, - vmcb12->control.intercepts[INTERCEPT_EXCEPTION], - vmcb12->control.intercepts[INTERCEPT_WORD3], - vmcb12->control.intercepts[INTERCEPT_WORD4], - vmcb12->control.intercepts[INTERCEPT_WORD5]); /* Clear internal status */ kvm_clear_exception_queue(&svm->vcpu); diff --git a/arch/x86/kvm/svm/sev.c b/arch/x86/kvm/svm/sev.c index 48017fef1cd9..874ea309279f 100644 --- a/arch/x86/kvm/svm/sev.c +++ b/arch/x86/kvm/svm/sev.c @@ -22,6 +22,7 @@ #include "x86.h" #include "svm.h" +#include "svm_ops.h" #include "cpuid.h" #include "trace.h" @@ -1041,6 +1042,74 @@ e_unpin_memory: return ret; } +static int sev_get_attestation_report(struct kvm *kvm, struct kvm_sev_cmd *argp) +{ + void __user *report = (void __user *)(uintptr_t)argp->data; + struct kvm_sev_info *sev = &to_kvm_svm(kvm)->sev_info; + struct sev_data_attestation_report *data; + struct kvm_sev_attestation_report params; + void __user *p; + void *blob = NULL; + int ret; + + if (!sev_guest(kvm)) + return -ENOTTY; + + if (copy_from_user(¶ms, (void __user *)(uintptr_t)argp->data, sizeof(params))) + return -EFAULT; + + data = kzalloc(sizeof(*data), GFP_KERNEL_ACCOUNT); + if (!data) + return -ENOMEM; + + /* User wants to query the blob length */ + if (!params.len) + goto cmd; + + p = (void __user *)(uintptr_t)params.uaddr; + if (p) { + if (params.len > SEV_FW_BLOB_MAX_SIZE) { + ret = -EINVAL; + goto e_free; + } + + ret = -ENOMEM; + blob = kmalloc(params.len, GFP_KERNEL); + if (!blob) + goto e_free; + + data->address = __psp_pa(blob); + data->len = params.len; + memcpy(data->mnonce, params.mnonce, sizeof(params.mnonce)); + } +cmd: + data->handle = sev->handle; + ret = sev_issue_cmd(kvm, SEV_CMD_ATTESTATION_REPORT, data, &argp->error); + /* + * If we query the session length, FW responded with expected data. + */ + if (!params.len) + goto done; + + if (ret) + goto e_free_blob; + + if (blob) { + if (copy_to_user(p, blob, params.len)) + ret = -EFAULT; + } + +done: + params.len = data->len; + if (copy_to_user(report, ¶ms, sizeof(params))) + ret = -EFAULT; +e_free_blob: + kfree(blob); +e_free: + kfree(data); + return ret; +} + int svm_mem_enc_op(struct kvm *kvm, void __user *argp) { struct kvm_sev_cmd sev_cmd; @@ -1091,6 +1160,9 @@ int svm_mem_enc_op(struct kvm *kvm, void __user *argp) case KVM_SEV_LAUNCH_SECRET: r = sev_launch_secret(kvm, &sev_cmd); break; + case KVM_SEV_GET_ATTESTATION_REPORT: + r = sev_get_attestation_report(kvm, &sev_cmd); + break; default: r = -EINVAL; goto out; @@ -1994,29 +2066,17 @@ void sev_es_create_vcpu(struct vcpu_svm *svm) sev_enc_bit)); } -void sev_es_vcpu_load(struct vcpu_svm *svm, int cpu) +void sev_es_prepare_guest_switch(struct vcpu_svm *svm, unsigned int cpu) { struct svm_cpu_data *sd = per_cpu(svm_data, cpu); struct vmcb_save_area *hostsa; - unsigned int i; /* * As an SEV-ES guest, hardware will restore the host state on VMEXIT, * of which one step is to perform a VMLOAD. Since hardware does not * perform a VMSAVE on VMRUN, the host savearea must be updated. */ - asm volatile(__ex("vmsave %0") : : "a" (__sme_page_pa(sd->save_area)) : "memory"); - - /* - * Certain MSRs are restored on VMEXIT, only save ones that aren't - * restored. - */ - for (i = 0; i < NR_HOST_SAVE_USER_MSRS; i++) { - if (host_save_user_msrs[i].sev_es_restored) - continue; - - rdmsrl(host_save_user_msrs[i].index, svm->host_user_msrs[i]); - } + vmsave(__sme_page_pa(sd->save_area)); /* XCR0 is restored on VMEXIT, save the current host value */ hostsa = (struct vmcb_save_area *)(page_address(sd->save_area) + 0x400); @@ -2029,22 +2089,6 @@ void sev_es_vcpu_load(struct vcpu_svm *svm, int cpu) hostsa->xss = host_xss; } -void sev_es_vcpu_put(struct vcpu_svm *svm) -{ - unsigned int i; - - /* - * Certain MSRs are restored on VMEXIT and were saved with vmsave in - * sev_es_vcpu_load() above. Only restore ones that weren't. - */ - for (i = 0; i < NR_HOST_SAVE_USER_MSRS; i++) { - if (host_save_user_msrs[i].sev_es_restored) - continue; - - wrmsrl(host_save_user_msrs[i].index, svm->host_user_msrs[i]); - } -} - void sev_vcpu_deliver_sipi_vector(struct kvm_vcpu *vcpu, u8 vector) { struct vcpu_svm *svm = to_svm(vcpu); diff --git a/arch/x86/kvm/svm/svm.c b/arch/x86/kvm/svm/svm.c index 3442d44ca53b..58a45bb139f8 100644 --- a/arch/x86/kvm/svm/svm.c +++ b/arch/x86/kvm/svm/svm.c @@ -41,6 +41,7 @@ #include "trace.h" #include "svm.h" +#include "svm_ops.h" #define __ex(x) __kvm_handle_fault_on_reboot(x) @@ -114,13 +115,6 @@ static const struct svm_direct_access_msrs { { .index = MSR_INVALID, .always = false }, }; -/* enable NPT for AMD64 and X86 with PAE */ -#if defined(CONFIG_X86_64) || defined(CONFIG_X86_PAE) -bool npt_enabled = true; -#else -bool npt_enabled; -#endif - /* * These 2 parameters are used to config the controls for Pause-Loop Exiting: * pause_filter_count: On processors that support Pause filtering(indicated @@ -169,9 +163,12 @@ module_param(pause_filter_count_shrink, ushort, 0444); static unsigned short pause_filter_count_max = KVM_SVM_DEFAULT_PLE_WINDOW_MAX; module_param(pause_filter_count_max, ushort, 0444); -/* allow nested paging (virtualized MMU) for all guests */ -static int npt = true; -module_param(npt, int, S_IRUGO); +/* + * Use nested page tables by default. Note, NPT may get forced off by + * svm_hardware_setup() if it's unsupported by hardware or the host kernel. + */ +bool npt_enabled = true; +module_param_named(npt, npt_enabled, bool, 0444); /* allow nested virtualization in KVM/SVM */ static int nested = true; @@ -200,9 +197,9 @@ module_param(sev_es, int, 0444); bool __read_mostly dump_invalid_vmcb; module_param(dump_invalid_vmcb, bool, 0644); -static u8 rsm_ins_bytes[] = "\x0f\xaa"; +static bool svm_gp_erratum_intercept = true; -static void svm_complete_interrupts(struct vcpu_svm *svm); +static u8 rsm_ins_bytes[] = "\x0f\xaa"; static unsigned long iopm_base; @@ -246,21 +243,6 @@ u32 svm_msrpm_offset(u32 msr) #define MAX_INST_SIZE 15 -static inline void clgi(void) -{ - asm volatile (__ex("clgi")); -} - -static inline void stgi(void) -{ - asm volatile (__ex("stgi")); -} - -static inline void invlpga(unsigned long addr, u32 asid) -{ - asm volatile (__ex("invlpga %1, %0") : : "c"(asid), "a"(addr)); -} - static int get_max_npt_level(void) { #ifdef CONFIG_X86_64 @@ -288,6 +270,9 @@ int svm_set_efer(struct kvm_vcpu *vcpu, u64 efer) if (!(efer & EFER_SVME)) { svm_leave_nested(svm); svm_set_gif(svm, true); + /* #GP intercept is still needed for vmware backdoor */ + if (!enable_vmware_backdoor) + clr_exception_intercept(svm, GP_VECTOR); /* * Free the nested guest state, unless we are in SMM. @@ -304,6 +289,9 @@ int svm_set_efer(struct kvm_vcpu *vcpu, u64 efer) vcpu->arch.efer = old_efer; return ret; } + + if (svm_gp_erratum_intercept) + set_exception_intercept(svm, GP_VECTOR); } } @@ -925,15 +913,15 @@ static __init void svm_set_cpu_caps(void) if (npt_enabled) kvm_cpu_cap_set(X86_FEATURE_NPT); + + /* Nested VM can receive #VMEXIT instead of triggering #GP */ + kvm_cpu_cap_set(X86_FEATURE_SVME_ADDR_CHK); } /* CPUID 0x80000008 */ if (boot_cpu_has(X86_FEATURE_LS_CFG_SSBD) || boot_cpu_has(X86_FEATURE_AMD_SSBD)) kvm_cpu_cap_set(X86_FEATURE_VIRT_SSBD); - - /* Enable INVPCID feature */ - kvm_cpu_cap_check_and_set(X86_FEATURE_INVPCID); } static __init int svm_hardware_setup(void) @@ -996,10 +984,15 @@ static __init int svm_hardware_setup(void) goto err; } - if (!boot_cpu_has(X86_FEATURE_NPT)) + /* + * KVM's MMU doesn't support using 2-level paging for itself, and thus + * NPT isn't supported if the host is using 2-level paging since host + * CR4 is unchanged on VMRUN. + */ + if (!IS_ENABLED(CONFIG_X86_64) && !IS_ENABLED(CONFIG_X86_PAE)) npt_enabled = false; - if (npt_enabled && !npt) + if (!boot_cpu_has(X86_FEATURE_NPT)) npt_enabled = false; kvm_configure_mmu(npt_enabled, get_max_npt_level(), PG_LEVEL_1G); @@ -1032,6 +1025,9 @@ static __init int svm_hardware_setup(void) } } + if (boot_cpu_has(X86_FEATURE_SVME_ADDR_CHK)) + svm_gp_erratum_intercept = false; + if (vgif) { if (!boot_cpu_has(X86_FEATURE_VGIF)) vgif = false; @@ -1105,12 +1101,12 @@ static u64 svm_write_l1_tsc_offset(struct kvm_vcpu *vcpu, u64 offset) static void svm_check_invpcid(struct vcpu_svm *svm) { /* - * Intercept INVPCID instruction only if shadow page table is - * enabled. Interception is not required with nested page table - * enabled. + * Intercept INVPCID if shadow paging is enabled to sync/free shadow + * roots, or if INVPCID is disabled in the guest to inject #UD. */ if (kvm_cpu_cap_has(X86_FEATURE_INVPCID)) { - if (!npt_enabled) + if (!npt_enabled || + !guest_cpuid_has(&svm->vcpu, X86_FEATURE_INVPCID)) svm_set_intercept(svm, INTERCEPT_INVPCID); else svm_clr_intercept(svm, INTERCEPT_INVPCID); @@ -1205,9 +1201,10 @@ static void init_vmcb(struct vcpu_svm *svm) init_sys_seg(&save->ldtr, SEG_TYPE_LDT); init_sys_seg(&save->tr, SEG_TYPE_BUSY_TSS16); + svm_set_cr4(&svm->vcpu, 0); svm_set_efer(&svm->vcpu, 0); save->dr6 = 0xffff0ff0; - kvm_set_rflags(&svm->vcpu, 2); + kvm_set_rflags(&svm->vcpu, X86_EFLAGS_FIXED); save->rip = 0x0000fff0; svm->vcpu.arch.regs[VCPU_REGS_RIP] = save->rip; @@ -1366,6 +1363,7 @@ static int svm_create_vcpu(struct kvm_vcpu *vcpu) svm->vmsa = page_address(vmsa_page); svm->asid_generation = 0; + svm->guest_state_loaded = false; init_vmcb(svm); svm_init_osvw(vcpu); @@ -1413,30 +1411,31 @@ static void svm_free_vcpu(struct kvm_vcpu *vcpu) __free_pages(virt_to_page(svm->msrpm), MSRPM_ALLOC_ORDER); } -static void svm_vcpu_load(struct kvm_vcpu *vcpu, int cpu) +static void svm_prepare_guest_switch(struct kvm_vcpu *vcpu) { struct vcpu_svm *svm = to_svm(vcpu); - struct svm_cpu_data *sd = per_cpu(svm_data, cpu); - int i; + struct svm_cpu_data *sd = per_cpu(svm_data, vcpu->cpu); + unsigned int i; - if (unlikely(cpu != vcpu->cpu)) { - svm->asid_generation = 0; - vmcb_mark_all_dirty(svm->vmcb); - } + if (svm->guest_state_loaded) + return; + + /* + * Certain MSRs are restored on VMEXIT (sev-es), or vmload of host save + * area (non-sev-es). Save ones that aren't so we can restore them + * individually later. + */ + for (i = 0; i < NR_HOST_SAVE_USER_MSRS; i++) + rdmsrl(host_save_user_msrs[i], svm->host_user_msrs[i]); + /* + * Save additional host state that will be restored on VMEXIT (sev-es) + * or subsequent vmload of host save area. + */ if (sev_es_guest(svm->vcpu.kvm)) { - sev_es_vcpu_load(svm, cpu); + sev_es_prepare_guest_switch(svm, vcpu->cpu); } else { -#ifdef CONFIG_X86_64 - rdmsrl(MSR_GS_BASE, to_svm(vcpu)->host.gs_base); -#endif - savesegment(fs, svm->host.fs); - savesegment(gs, svm->host.gs); - svm->host.ldt = kvm_read_ldt(); - - for (i = 0; i < NR_HOST_SAVE_USER_MSRS; i++) - rdmsrl(host_save_user_msrs[i].index, - svm->host_user_msrs[i]); + vmsave(__sme_page_pa(sd->save_area)); } if (static_cpu_has(X86_FEATURE_TSCRATEMSR)) { @@ -1446,10 +1445,42 @@ static void svm_vcpu_load(struct kvm_vcpu *vcpu, int cpu) wrmsrl(MSR_AMD64_TSC_RATIO, tsc_ratio); } } + /* This assumes that the kernel never uses MSR_TSC_AUX */ if (static_cpu_has(X86_FEATURE_RDTSCP)) wrmsrl(MSR_TSC_AUX, svm->tsc_aux); + svm->guest_state_loaded = true; +} + +static void svm_prepare_host_switch(struct kvm_vcpu *vcpu) +{ + struct vcpu_svm *svm = to_svm(vcpu); + unsigned int i; + + if (!svm->guest_state_loaded) + return; + + /* + * Certain MSRs are restored on VMEXIT (sev-es), or vmload of host save + * area (non-sev-es). Restore the ones that weren't. + */ + for (i = 0; i < NR_HOST_SAVE_USER_MSRS; i++) + wrmsrl(host_save_user_msrs[i], svm->host_user_msrs[i]); + + svm->guest_state_loaded = false; +} + +static void svm_vcpu_load(struct kvm_vcpu *vcpu, int cpu) +{ + struct vcpu_svm *svm = to_svm(vcpu); + struct svm_cpu_data *sd = per_cpu(svm_data, cpu); + + if (unlikely(cpu != vcpu->cpu)) { + svm->asid_generation = 0; + vmcb_mark_all_dirty(svm->vmcb); + } + if (sd->current_vmcb != svm->vmcb) { sd->current_vmcb = svm->vmcb; indirect_branch_prediction_barrier(); @@ -1459,30 +1490,10 @@ static void svm_vcpu_load(struct kvm_vcpu *vcpu, int cpu) static void svm_vcpu_put(struct kvm_vcpu *vcpu) { - struct vcpu_svm *svm = to_svm(vcpu); - int i; - avic_vcpu_put(vcpu); + svm_prepare_host_switch(vcpu); ++vcpu->stat.host_state_reload; - if (sev_es_guest(svm->vcpu.kvm)) { - sev_es_vcpu_put(svm); - } else { - kvm_load_ldt(svm->host.ldt); -#ifdef CONFIG_X86_64 - loadsegment(fs, svm->host.fs); - wrmsrl(MSR_KERNEL_GS_BASE, current->thread.gsbase); - load_gs_index(svm->host.gs); -#else -#ifdef CONFIG_X86_32_LAZY_GS - loadsegment(gs, svm->host.gs); -#endif -#endif - - for (i = 0; i < NR_HOST_SAVE_USER_MSRS; i++) - wrmsrl(host_save_user_msrs[i].index, - svm->host_user_msrs[i]); - } } static unsigned long svm_get_rflags(struct kvm_vcpu *vcpu) @@ -1815,7 +1826,7 @@ static void svm_set_segment(struct kvm_vcpu *vcpu, vmcb_mark_dirty(svm->vmcb, VMCB_SEG); } -static void update_exception_bitmap(struct kvm_vcpu *vcpu) +static void svm_update_exception_bitmap(struct kvm_vcpu *vcpu) { struct vcpu_svm *svm = to_svm(vcpu); @@ -1865,7 +1876,7 @@ static void svm_sync_dirty_debug_regs(struct kvm_vcpu *vcpu) get_debugreg(vcpu->arch.db[2], 2); get_debugreg(vcpu->arch.db[3], 3); /* - * We cannot reset svm->vmcb->save.dr6 to DR6_FIXED_1|DR6_RTM here, + * We cannot reset svm->vmcb->save.dr6 to DR6_ACTIVE_LOW here, * because db_interception might need it. We can do it before vmentry. */ vcpu->arch.dr6 = svm->vmcb->save.dr6; @@ -1916,7 +1927,7 @@ static int db_interception(struct vcpu_svm *svm) if (!(svm->vcpu.guest_debug & (KVM_GUESTDBG_SINGLESTEP | KVM_GUESTDBG_USE_HW_BP)) && !svm->nmi_singlestep) { - u32 payload = (svm->vmcb->save.dr6 ^ DR6_RTM) & ~DR6_FIXED_1; + u32 payload = svm->vmcb->save.dr6 ^ DR6_ACTIVE_LOW; kvm_queue_exception_p(&svm->vcpu, DB_VECTOR, payload); return 1; } @@ -1962,24 +1973,6 @@ static int ac_interception(struct vcpu_svm *svm) return 1; } -static int gp_interception(struct vcpu_svm *svm) -{ - struct kvm_vcpu *vcpu = &svm->vcpu; - u32 error_code = svm->vmcb->control.exit_info_1; - - WARN_ON_ONCE(!enable_vmware_backdoor); - - /* - * VMware backdoor emulation on #GP interception only handles IN{S}, - * OUT{S}, and RDPMC, none of which generate a non-zero error code. - */ - if (error_code) { - kvm_queue_exception_e(vcpu, GP_VECTOR, error_code); - return 1; - } - return kvm_emulate_instruction(vcpu, EMULTYPE_VMWARE_GP); -} - static bool is_erratum_383(void) { int err, i; @@ -2178,6 +2171,107 @@ static int vmrun_interception(struct vcpu_svm *svm) return nested_svm_vmrun(svm); } +enum { + NONE_SVM_INSTR, + SVM_INSTR_VMRUN, + SVM_INSTR_VMLOAD, + SVM_INSTR_VMSAVE, +}; + +/* Return NONE_SVM_INSTR if not SVM instrs, otherwise return decode result */ +static int svm_instr_opcode(struct kvm_vcpu *vcpu) +{ + struct x86_emulate_ctxt *ctxt = vcpu->arch.emulate_ctxt; + + if (ctxt->b != 0x1 || ctxt->opcode_len != 2) + return NONE_SVM_INSTR; + + switch (ctxt->modrm) { + case 0xd8: /* VMRUN */ + return SVM_INSTR_VMRUN; + case 0xda: /* VMLOAD */ + return SVM_INSTR_VMLOAD; + case 0xdb: /* VMSAVE */ + return SVM_INSTR_VMSAVE; + default: + break; + } + + return NONE_SVM_INSTR; +} + +static int emulate_svm_instr(struct kvm_vcpu *vcpu, int opcode) +{ + const int guest_mode_exit_codes[] = { + [SVM_INSTR_VMRUN] = SVM_EXIT_VMRUN, + [SVM_INSTR_VMLOAD] = SVM_EXIT_VMLOAD, + [SVM_INSTR_VMSAVE] = SVM_EXIT_VMSAVE, + }; + int (*const svm_instr_handlers[])(struct vcpu_svm *svm) = { + [SVM_INSTR_VMRUN] = vmrun_interception, + [SVM_INSTR_VMLOAD] = vmload_interception, + [SVM_INSTR_VMSAVE] = vmsave_interception, + }; + struct vcpu_svm *svm = to_svm(vcpu); + int ret; + + if (is_guest_mode(vcpu)) { + svm->vmcb->control.exit_code = guest_mode_exit_codes[opcode]; + svm->vmcb->control.exit_info_1 = 0; + svm->vmcb->control.exit_info_2 = 0; + + /* Returns '1' or -errno on failure, '0' on success. */ + ret = nested_svm_vmexit(svm); + if (ret) + return ret; + return 1; + } + return svm_instr_handlers[opcode](svm); +} + +/* + * #GP handling code. Note that #GP can be triggered under the following two + * cases: + * 1) SVM VM-related instructions (VMRUN/VMSAVE/VMLOAD) that trigger #GP on + * some AMD CPUs when EAX of these instructions are in the reserved memory + * regions (e.g. SMM memory on host). + * 2) VMware backdoor + */ +static int gp_interception(struct vcpu_svm *svm) +{ + struct kvm_vcpu *vcpu = &svm->vcpu; + u32 error_code = svm->vmcb->control.exit_info_1; + int opcode; + + /* Both #GP cases have zero error_code */ + if (error_code) + goto reinject; + + /* Decode the instruction for usage later */ + if (x86_decode_emulated_instruction(vcpu, 0, NULL, 0) != EMULATION_OK) + goto reinject; + + opcode = svm_instr_opcode(vcpu); + + if (opcode == NONE_SVM_INSTR) { + if (!enable_vmware_backdoor) + goto reinject; + + /* + * VMware backdoor emulation on #GP interception only handles + * IN{S}, OUT{S}, and RDPMC. + */ + if (!is_guest_mode(vcpu)) + return kvm_emulate_instruction(vcpu, + EMULTYPE_VMWARE_GP | EMULTYPE_NO_DECODE); + } else + return emulate_svm_instr(vcpu, opcode); + +reinject: + kvm_queue_exception_e(vcpu, GP_VECTOR, error_code); + return 1; +} + void svm_set_gif(struct vcpu_svm *svm, bool value) { if (value) { @@ -2265,11 +2359,8 @@ static int xsetbv_interception(struct vcpu_svm *svm) u64 new_bv = kvm_read_edx_eax(&svm->vcpu); u32 index = kvm_rcx_read(&svm->vcpu); - if (kvm_set_xcr(&svm->vcpu, index, new_bv) == 0) { - return kvm_skip_emulated_instruction(&svm->vcpu); - } - - return 1; + int err = kvm_set_xcr(&svm->vcpu, index, new_bv); + return kvm_complete_insn_gp(&svm->vcpu, err); } static int rdpru_interception(struct vcpu_svm *svm) @@ -2530,6 +2621,7 @@ static int dr_interception(struct vcpu_svm *svm) { int reg, dr; unsigned long val; + int err = 0; if (svm->vcpu.guest_debug == 0) { /* @@ -2547,20 +2639,16 @@ static int dr_interception(struct vcpu_svm *svm) reg = svm->vmcb->control.exit_info_1 & SVM_EXITINFO_REG_MASK; dr = svm->vmcb->control.exit_code - SVM_EXIT_READ_DR0; - - if (dr >= 16) { /* mov to DRn */ - if (!kvm_require_dr(&svm->vcpu, dr - 16)) - return 1; + if (dr >= 16) { /* mov to DRn */ + dr -= 16; val = kvm_register_read(&svm->vcpu, reg); - kvm_set_dr(&svm->vcpu, dr - 16, val); + err = kvm_set_dr(&svm->vcpu, dr, val); } else { - if (!kvm_require_dr(&svm->vcpu, dr)) - return 1; kvm_get_dr(&svm->vcpu, dr, &val); kvm_register_write(&svm->vcpu, reg, val); } - return kvm_skip_emulated_instruction(&svm->vcpu); + return kvm_complete_insn_gp(&svm->vcpu, err); } static int cr8_write_interception(struct vcpu_svm *svm) @@ -3354,7 +3442,7 @@ static void svm_set_irq(struct kvm_vcpu *vcpu) SVM_EVTINJ_VALID | SVM_EVTINJ_TYPE_INTR; } -static void update_cr8_intercept(struct kvm_vcpu *vcpu, int tpr, int irr) +static void svm_update_cr8_intercept(struct kvm_vcpu *vcpu, int tpr, int irr) { struct vcpu_svm *svm = to_svm(vcpu); @@ -3479,7 +3567,7 @@ static int svm_interrupt_allowed(struct kvm_vcpu *vcpu, bool for_injection) return !svm_interrupt_blocked(vcpu); } -static void enable_irq_window(struct kvm_vcpu *vcpu) +static void svm_enable_irq_window(struct kvm_vcpu *vcpu) { struct vcpu_svm *svm = to_svm(vcpu); @@ -3503,7 +3591,7 @@ static void enable_irq_window(struct kvm_vcpu *vcpu) } } -static void enable_nmi_window(struct kvm_vcpu *vcpu) +static void svm_enable_nmi_window(struct kvm_vcpu *vcpu) { struct vcpu_svm *svm = to_svm(vcpu); @@ -3560,10 +3648,6 @@ static void svm_flush_tlb_gva(struct kvm_vcpu *vcpu, gva_t gva) invlpga(gva, svm->vmcb->control.asid); } -static void svm_prepare_guest_switch(struct kvm_vcpu *vcpu) -{ -} - static inline void sync_cr8_to_lapic(struct kvm_vcpu *vcpu) { struct vcpu_svm *svm = to_svm(vcpu); @@ -3708,16 +3792,11 @@ static noinstr void svm_vcpu_enter_exit(struct kvm_vcpu *vcpu, if (sev_es_guest(svm->vcpu.kvm)) { __svm_sev_es_vcpu_run(svm->vmcb_pa); } else { + struct svm_cpu_data *sd = per_cpu(svm_data, vcpu->cpu); + __svm_vcpu_run(svm->vmcb_pa, (unsigned long *)&svm->vcpu.arch.regs); -#ifdef CONFIG_X86_64 - native_wrmsrl(MSR_GS_BASE, svm->host.gs_base); -#else - loadsegment(fs, svm->host.fs); -#ifndef CONFIG_X86_32_LAZY_GS - loadsegment(gs, svm->host.gs); -#endif -#endif + vmload(__sme_page_pa(sd->save_area)); } /* @@ -3783,7 +3862,7 @@ static __no_kcsan fastpath_t svm_vcpu_run(struct kvm_vcpu *vcpu) if (unlikely(svm->vcpu.arch.switch_db_regs & KVM_DEBUGREG_WONT_EXIT)) svm_set_dr6(svm, vcpu->arch.dr6); else - svm_set_dr6(svm, DR6_FIXED_1 | DR6_RTM); + svm_set_dr6(svm, DR6_ACTIVE_LOW); clgi(); kvm_load_guest_xsave_state(vcpu); @@ -3978,7 +4057,7 @@ static void svm_vcpu_after_set_cpuid(struct kvm_vcpu *vcpu) if (sev_guest(vcpu->kvm)) { best = kvm_find_cpuid_entry(vcpu, 0x8000001F, 0); if (best) - vcpu->arch.cr3_lm_rsvd_bits &= ~(1UL << (best->ebx & 0x3f)); + vcpu->arch.reserved_gpa_bits &= ~(1UL << (best->ebx & 0x3f)); } if (!kvm_vcpu_apicv_active(vcpu)) @@ -4285,7 +4364,7 @@ static int svm_pre_leave_smm(struct kvm_vcpu *vcpu, const char *smstate) return ret; } -static void enable_smi_window(struct kvm_vcpu *vcpu) +static void svm_enable_smi_window(struct kvm_vcpu *vcpu) { struct vcpu_svm *svm = to_svm(vcpu); @@ -4439,7 +4518,7 @@ static struct kvm_x86_ops svm_x86_ops __initdata = { .vcpu_blocking = svm_vcpu_blocking, .vcpu_unblocking = svm_vcpu_unblocking, - .update_exception_bitmap = update_exception_bitmap, + .update_exception_bitmap = svm_update_exception_bitmap, .get_msr_feature = svm_get_msr_feature, .get_msr = svm_get_msr, .set_msr = svm_set_msr, @@ -4482,9 +4561,9 @@ static struct kvm_x86_ops svm_x86_ops __initdata = { .nmi_allowed = svm_nmi_allowed, .get_nmi_mask = svm_get_nmi_mask, .set_nmi_mask = svm_set_nmi_mask, - .enable_nmi_window = enable_nmi_window, - .enable_irq_window = enable_irq_window, - .update_cr8_intercept = update_cr8_intercept, + .enable_nmi_window = svm_enable_nmi_window, + .enable_irq_window = svm_enable_irq_window, + .update_cr8_intercept = svm_update_cr8_intercept, .set_virtual_apic_mode = svm_set_virtual_apic_mode, .refresh_apicv_exec_ctrl = svm_refresh_apicv_exec_ctrl, .check_apicv_inhibit_reasons = svm_check_apicv_inhibit_reasons, @@ -4527,7 +4606,7 @@ static struct kvm_x86_ops svm_x86_ops __initdata = { .smi_allowed = svm_smi_allowed, .pre_enter_smm = svm_pre_enter_smm, .pre_leave_smm = svm_pre_leave_smm, - .enable_smi_window = enable_smi_window, + .enable_smi_window = svm_enable_smi_window, .mem_enc_op = svm_mem_enc_op, .mem_enc_reg_region = svm_register_enc_region, diff --git a/arch/x86/kvm/svm/svm.h b/arch/x86/kvm/svm/svm.h index 6e7d070f8b86..39e071fdab0c 100644 --- a/arch/x86/kvm/svm/svm.h +++ b/arch/x86/kvm/svm/svm.h @@ -23,22 +23,8 @@ #define __sme_page_pa(x) __sme_set(page_to_pfn(x) << PAGE_SHIFT) -static const struct svm_host_save_msrs { - u32 index; /* Index of the MSR */ - bool sev_es_restored; /* True if MSR is restored on SEV-ES VMEXIT */ -} host_save_user_msrs[] = { -#ifdef CONFIG_X86_64 - { .index = MSR_STAR, .sev_es_restored = true }, - { .index = MSR_LSTAR, .sev_es_restored = true }, - { .index = MSR_CSTAR, .sev_es_restored = true }, - { .index = MSR_SYSCALL_MASK, .sev_es_restored = true }, - { .index = MSR_KERNEL_GS_BASE, .sev_es_restored = true }, - { .index = MSR_FS_BASE, .sev_es_restored = true }, -#endif - { .index = MSR_IA32_SYSENTER_CS, .sev_es_restored = true }, - { .index = MSR_IA32_SYSENTER_ESP, .sev_es_restored = true }, - { .index = MSR_IA32_SYSENTER_EIP, .sev_es_restored = true }, - { .index = MSR_TSC_AUX, .sev_es_restored = false }, +static const u32 host_save_user_msrs[] = { + MSR_TSC_AUX, }; #define NR_HOST_SAVE_USER_MSRS ARRAY_SIZE(host_save_user_msrs) @@ -130,12 +116,6 @@ struct vcpu_svm { u64 next_rip; u64 host_user_msrs[NR_HOST_SAVE_USER_MSRS]; - struct { - u16 fs; - u16 gs; - u16 ldt; - u64 gs_base; - } host; u64 spec_ctrl; /* @@ -192,6 +172,8 @@ struct vcpu_svm { u64 ghcb_sa_len; bool ghcb_sa_sync; bool ghcb_sa_free; + + bool guest_state_loaded; }; struct svm_cpu_data { @@ -587,9 +569,8 @@ int sev_handle_vmgexit(struct vcpu_svm *svm); int sev_es_string_io(struct vcpu_svm *svm, int size, unsigned int port, int in); void sev_es_init_vmcb(struct vcpu_svm *svm); void sev_es_create_vcpu(struct vcpu_svm *svm); -void sev_es_vcpu_load(struct vcpu_svm *svm, int cpu); -void sev_es_vcpu_put(struct vcpu_svm *svm); void sev_vcpu_deliver_sipi_vector(struct kvm_vcpu *vcpu, u8 vector); +void sev_es_prepare_guest_switch(struct vcpu_svm *svm, unsigned int cpu); /* vmenter.S */ diff --git a/arch/x86/kvm/svm/svm_ops.h b/arch/x86/kvm/svm/svm_ops.h new file mode 100644 index 000000000000..8170f2a5a16f --- /dev/null +++ b/arch/x86/kvm/svm/svm_ops.h @@ -0,0 +1,69 @@ +/* SPDX-License-Identifier: GPL-2.0 */ +#ifndef __KVM_X86_SVM_OPS_H +#define __KVM_X86_SVM_OPS_H + +#include <linux/compiler_types.h> + +#include <asm/kvm_host.h> + +#define svm_asm(insn, clobber...) \ +do { \ + asm_volatile_goto("1: " __stringify(insn) "\n\t" \ + _ASM_EXTABLE(1b, %l[fault]) \ + ::: clobber : fault); \ + return; \ +fault: \ + kvm_spurious_fault(); \ +} while (0) + +#define svm_asm1(insn, op1, clobber...) \ +do { \ + asm_volatile_goto("1: " __stringify(insn) " %0\n\t" \ + _ASM_EXTABLE(1b, %l[fault]) \ + :: op1 : clobber : fault); \ + return; \ +fault: \ + kvm_spurious_fault(); \ +} while (0) + +#define svm_asm2(insn, op1, op2, clobber...) \ +do { \ + asm_volatile_goto("1: " __stringify(insn) " %1, %0\n\t" \ + _ASM_EXTABLE(1b, %l[fault]) \ + :: op1, op2 : clobber : fault); \ + return; \ +fault: \ + kvm_spurious_fault(); \ +} while (0) + +static inline void clgi(void) +{ + svm_asm(clgi); +} + +static inline void stgi(void) +{ + svm_asm(stgi); +} + +static inline void invlpga(unsigned long addr, u32 asid) +{ + svm_asm2(invlpga, "c"(asid), "a"(addr)); +} + +/* + * Despite being a physical address, the portion of rAX that is consumed by + * VMSAVE, VMLOAD, etc... is still controlled by the effective address size, + * hence 'unsigned long' instead of 'hpa_t'. + */ +static inline void vmsave(unsigned long pa) +{ + svm_asm1(vmsave, "a" (pa), "memory"); +} + +static inline void vmload(unsigned long pa) +{ + svm_asm1(vmload, "a" (pa), "memory"); +} + +#endif /* __KVM_X86_SVM_OPS_H */ diff --git a/arch/x86/kvm/trace.h b/arch/x86/kvm/trace.h index 2de30c20bc26..a61c015870e3 100644 --- a/arch/x86/kvm/trace.h +++ b/arch/x86/kvm/trace.h @@ -93,6 +93,42 @@ TRACE_EVENT(kvm_hv_hypercall, ); /* + * Tracepoint for Xen hypercall. + */ +TRACE_EVENT(kvm_xen_hypercall, + TP_PROTO(unsigned long nr, unsigned long a0, unsigned long a1, + unsigned long a2, unsigned long a3, unsigned long a4, + unsigned long a5), + TP_ARGS(nr, a0, a1, a2, a3, a4, a5), + + TP_STRUCT__entry( + __field(unsigned long, nr) + __field(unsigned long, a0) + __field(unsigned long, a1) + __field(unsigned long, a2) + __field(unsigned long, a3) + __field(unsigned long, a4) + __field(unsigned long, a5) + ), + + TP_fast_assign( + __entry->nr = nr; + __entry->a0 = a0; + __entry->a1 = a1; + __entry->a2 = a2; + __entry->a3 = a3; + __entry->a4 = a4; + __entry->a4 = a5; + ), + + TP_printk("nr 0x%lx a0 0x%lx a1 0x%lx a2 0x%lx a3 0x%lx a4 0x%lx a5 %lx", + __entry->nr, __entry->a0, __entry->a1, __entry->a2, + __entry->a3, __entry->a4, __entry->a5) +); + + + +/* * Tracepoint for PIO. */ @@ -256,7 +292,7 @@ TRACE_EVENT(name, \ __entry->guest_rip = kvm_rip_read(vcpu); \ __entry->isa = isa; \ __entry->vcpu_id = vcpu->vcpu_id; \ - kvm_x86_ops.get_exit_info(vcpu, &__entry->info1, \ + static_call(kvm_x86_get_exit_info)(vcpu, &__entry->info1, \ &__entry->info2, \ &__entry->intr_info, \ &__entry->error_code); \ @@ -738,7 +774,7 @@ TRACE_EVENT(kvm_emulate_insn, ), TP_fast_assign( - __entry->csbase = kvm_x86_ops.get_segment_base(vcpu, VCPU_SREG_CS); + __entry->csbase = static_call(kvm_x86_get_segment_base)(vcpu, VCPU_SREG_CS); __entry->len = vcpu->arch.emulate_ctxt->fetch.ptr - vcpu->arch.emulate_ctxt->fetch.data; __entry->rip = vcpu->arch.emulate_ctxt->_eip - __entry->len; diff --git a/arch/x86/kvm/vmx/capabilities.h b/arch/x86/kvm/vmx/capabilities.h index 3a1861403d73..d1d77985e889 100644 --- a/arch/x86/kvm/vmx/capabilities.h +++ b/arch/x86/kvm/vmx/capabilities.h @@ -19,6 +19,9 @@ extern int __read_mostly pt_mode; #define PT_MODE_HOST_GUEST 1 #define PMU_CAP_FW_WRITES (1ULL << 13) +#define PMU_CAP_LBR_FMT 0x3f + +#define DEBUGCTLMSR_LBR_MASK (DEBUGCTLMSR_LBR | DEBUGCTLMSR_FREEZE_LBRS_ON_PMI) struct nested_vmx_msrs { /* @@ -262,6 +265,12 @@ static inline bool cpu_has_vmx_tsc_scaling(void) SECONDARY_EXEC_TSC_SCALING; } +static inline bool cpu_has_vmx_bus_lock_detection(void) +{ + return vmcs_config.cpu_based_2nd_exec_ctrl & + SECONDARY_EXEC_BUS_LOCK_DETECTION; +} + static inline bool cpu_has_vmx_apicv(void) { return cpu_has_vmx_apic_register_virt() && @@ -371,11 +380,28 @@ static inline bool vmx_pt_mode_is_host_guest(void) static inline u64 vmx_get_perf_capabilities(void) { + u64 perf_cap = 0; + + if (boot_cpu_has(X86_FEATURE_PDCM)) + rdmsrl(MSR_IA32_PERF_CAPABILITIES, perf_cap); + + perf_cap &= PMU_CAP_LBR_FMT; + /* * Since counters are virtualized, KVM would support full * width counting unconditionally, even if the host lacks it. */ - return PMU_CAP_FW_WRITES; + return PMU_CAP_FW_WRITES | perf_cap; +} + +static inline u64 vmx_supported_debugctl(void) +{ + u64 debugctl = 0; + + if (vmx_get_perf_capabilities() & PMU_CAP_LBR_FMT) + debugctl |= DEBUGCTLMSR_LBR_MASK; + + return debugctl; } #endif /* __KVM_X86_VMX_CAPS_H */ diff --git a/arch/x86/kvm/vmx/nested.c b/arch/x86/kvm/vmx/nested.c index f2b9bfb58206..bcca0b80e0d0 100644 --- a/arch/x86/kvm/vmx/nested.c +++ b/arch/x86/kvm/vmx/nested.c @@ -12,6 +12,7 @@ #include "nested.h" #include "pmu.h" #include "trace.h" +#include "vmx.h" #include "x86.h" static bool __read_mostly enable_shadow_vmcs = 1; @@ -411,8 +412,8 @@ static int nested_vmx_check_exception(struct kvm_vcpu *vcpu, unsigned long *exit if (nr == DB_VECTOR) { if (!has_payload) { payload = vcpu->arch.dr6; - payload &= ~(DR6_FIXED_1 | DR6_BT); - payload ^= DR6_RTM; + payload &= ~DR6_BT; + payload ^= DR6_ACTIVE_LOW; } *exit_qual = payload; } else @@ -744,8 +745,7 @@ static int nested_vmx_check_apicv_controls(struct kvm_vcpu *vcpu, (CC(!nested_cpu_has_vid(vmcs12)) || CC(!nested_exit_intr_ack_set(vcpu)) || CC((vmcs12->posted_intr_nv & 0xff00)) || - CC((vmcs12->posted_intr_desc_addr & 0x3f)) || - CC((vmcs12->posted_intr_desc_addr >> cpuid_maxphyaddr(vcpu))))) + CC(!kvm_vcpu_is_legal_aligned_gpa(vcpu, vmcs12->posted_intr_desc_addr, 64)))) return -EINVAL; /* tpr shadow is needed by all apicv features. */ @@ -758,13 +758,11 @@ static int nested_vmx_check_apicv_controls(struct kvm_vcpu *vcpu, static int nested_vmx_check_msr_switch(struct kvm_vcpu *vcpu, u32 count, u64 addr) { - int maxphyaddr; - if (count == 0) return 0; - maxphyaddr = cpuid_maxphyaddr(vcpu); - if (!IS_ALIGNED(addr, 16) || addr >> maxphyaddr || - (addr + count * sizeof(struct vmx_msr_entry) - 1) >> maxphyaddr) + + if (!kvm_vcpu_is_legal_aligned_gpa(vcpu, addr, 16) || + !kvm_vcpu_is_legal_gpa(vcpu, (addr + count * sizeof(struct vmx_msr_entry) - 1))) return -EINVAL; return 0; @@ -1062,14 +1060,6 @@ static void prepare_vmx_msr_autostore_list(struct kvm_vcpu *vcpu, } } -static bool nested_cr3_valid(struct kvm_vcpu *vcpu, unsigned long val) -{ - unsigned long invalid_mask; - - invalid_mask = (~0ULL) << cpuid_maxphyaddr(vcpu); - return (val & invalid_mask) == 0; -} - /* * Returns true if the MMU needs to be sync'd on nested VM-Enter/VM-Exit. * tl;dr: the MMU needs a sync if L0 is using shadow paging and L1 didn't @@ -1121,7 +1111,7 @@ static bool nested_vmx_transition_mmu_sync(struct kvm_vcpu *vcpu) static int nested_vmx_load_cr3(struct kvm_vcpu *vcpu, unsigned long cr3, bool nested_ept, enum vm_entry_failure_code *entry_failure_code) { - if (CC(!nested_cr3_valid(vcpu, cr3))) { + if (CC(kvm_vcpu_is_illegal_gpa(vcpu, cr3))) { *entry_failure_code = ENTRY_FAIL_DEFAULT; return -EINVAL; } @@ -2177,15 +2167,13 @@ static void prepare_vmcs02_constant_state(struct vcpu_vmx *vmx) vmcs_write64(MSR_BITMAP, __pa(vmx->nested.vmcs02.msr_bitmap)); /* - * The PML address never changes, so it is constant in vmcs02. - * Conceptually we want to copy the PML index from vmcs01 here, - * and then back to vmcs01 on nested vmexit. But since we flush - * the log and reset GUEST_PML_INDEX on each vmexit, the PML - * index is also effectively constant in vmcs02. + * PML is emulated for L2, but never enabled in hardware as the MMU + * handles A/D emulation. Disabling PML for L2 also avoids having to + * deal with filtering out L2 GPAs from the buffer. */ if (enable_pml) { - vmcs_write64(PML_ADDRESS, page_to_phys(vmx->pml_pg)); - vmcs_write16(GUEST_PML_INDEX, PML_ENTITY_NUM - 1); + vmcs_write64(PML_ADDRESS, 0); + vmcs_write16(GUEST_PML_INDEX, -1); } if (cpu_has_vmx_encls_vmexit()) @@ -2220,7 +2208,7 @@ static void prepare_vmcs02_early_rare(struct vcpu_vmx *vmx, static void prepare_vmcs02_early(struct vcpu_vmx *vmx, struct vmcs12 *vmcs12) { - u32 exec_control, vmcs12_exec_ctrl; + u32 exec_control; u64 guest_efer = nested_vmx_calc_efer(vmx, vmcs12); if (vmx->nested.dirty_vmcs12 || vmx->nested.hv_evmcs) @@ -2294,11 +2282,11 @@ static void prepare_vmcs02_early(struct vcpu_vmx *vmx, struct vmcs12 *vmcs12) SECONDARY_EXEC_APIC_REGISTER_VIRT | SECONDARY_EXEC_ENABLE_VMFUNC); if (nested_cpu_has(vmcs12, - CPU_BASED_ACTIVATE_SECONDARY_CONTROLS)) { - vmcs12_exec_ctrl = vmcs12->secondary_vm_exec_control & - ~SECONDARY_EXEC_ENABLE_PML; - exec_control |= vmcs12_exec_ctrl; - } + CPU_BASED_ACTIVATE_SECONDARY_CONTROLS)) + exec_control |= vmcs12->secondary_vm_exec_control; + + /* PML is emulated and never enabled in hardware for L2. */ + exec_control &= ~SECONDARY_EXEC_ENABLE_PML; /* VMCS shadowing for L2 is emulated for now */ exec_control &= ~SECONDARY_EXEC_SHADOW_VMCS; @@ -2532,7 +2520,7 @@ static int prepare_vmcs02(struct kvm_vcpu *vcpu, struct vmcs12 *vmcs12, * bitwise-or of what L1 wants to trap for L2, and what we want to * trap. Note that CR0.TS also needs updating - we do this later. */ - update_exception_bitmap(vcpu); + vmx_update_exception_bitmap(vcpu); vcpu->arch.cr0_guest_owned_bits &= ~vmcs12->cr0_guest_host_mask; vmcs_writel(CR0_GUEST_HOST_MASK, ~vcpu->arch.cr0_guest_owned_bits); @@ -2635,7 +2623,6 @@ static int nested_vmx_check_nmi_controls(struct vmcs12 *vmcs12) static bool nested_vmx_check_eptp(struct kvm_vcpu *vcpu, u64 new_eptp) { struct vcpu_vmx *vmx = to_vmx(vcpu); - int maxphyaddr = cpuid_maxphyaddr(vcpu); /* Check for memory type validity */ switch (new_eptp & VMX_EPTP_MT_MASK) { @@ -2666,7 +2653,7 @@ static bool nested_vmx_check_eptp(struct kvm_vcpu *vcpu, u64 new_eptp) } /* Reserved bits should not be set */ - if (CC(new_eptp >> maxphyaddr || ((new_eptp >> 7) & 0x1f))) + if (CC(kvm_vcpu_is_illegal_gpa(vcpu, new_eptp) || ((new_eptp >> 7) & 0x1f))) return false; /* AD, if set, should be supported */ @@ -2850,7 +2837,7 @@ static int nested_vmx_check_host_state(struct kvm_vcpu *vcpu, if (CC(!nested_host_cr0_valid(vcpu, vmcs12->host_cr0)) || CC(!nested_host_cr4_valid(vcpu, vmcs12->host_cr4)) || - CC(!nested_cr3_valid(vcpu, vmcs12->host_cr3))) + CC(kvm_vcpu_is_illegal_gpa(vcpu, vmcs12->host_cr3))) return -EINVAL; if (CC(is_noncanonical_address(vmcs12->host_ia32_sysenter_esp, vcpu)) || @@ -3057,35 +3044,8 @@ static int nested_vmx_check_vmentry_hw(struct kvm_vcpu *vcpu) vmx->loaded_vmcs->host_state.cr4 = cr4; } - asm( - "sub $%c[wordsize], %%" _ASM_SP "\n\t" /* temporarily adjust RSP for CALL */ - "cmp %%" _ASM_SP ", %c[host_state_rsp](%[loaded_vmcs]) \n\t" - "je 1f \n\t" - __ex("vmwrite %%" _ASM_SP ", %[HOST_RSP]") "\n\t" - "mov %%" _ASM_SP ", %c[host_state_rsp](%[loaded_vmcs]) \n\t" - "1: \n\t" - "add $%c[wordsize], %%" _ASM_SP "\n\t" /* un-adjust RSP */ - - /* Check if vmlaunch or vmresume is needed */ - "cmpb $0, %c[launched](%[loaded_vmcs])\n\t" - - /* - * VMLAUNCH and VMRESUME clear RFLAGS.{CF,ZF} on VM-Exit, set - * RFLAGS.CF on VM-Fail Invalid and set RFLAGS.ZF on VM-Fail - * Valid. vmx_vmenter() directly "returns" RFLAGS, and so the - * results of VM-Enter is captured via CC_{SET,OUT} to vm_fail. - */ - "call vmx_vmenter\n\t" - - CC_SET(be) - : ASM_CALL_CONSTRAINT, CC_OUT(be) (vm_fail) - : [HOST_RSP]"r"((unsigned long)HOST_RSP), - [loaded_vmcs]"r"(vmx->loaded_vmcs), - [launched]"i"(offsetof(struct loaded_vmcs, launched)), - [host_state_rsp]"i"(offsetof(struct loaded_vmcs, host_state.rsp)), - [wordsize]"i"(sizeof(ulong)) - : "memory" - ); + vm_fail = __vmx_vcpu_run(vmx, (unsigned long *)&vcpu->arch.regs, + vmx->loaded_vmcs->launched); if (vmx->msr_autoload.host.nr) vmcs_write32(VM_EXIT_MSR_LOAD_COUNT, vmx->msr_autoload.host.nr); @@ -3330,7 +3290,11 @@ enum nvmx_vmentry_status nested_vmx_enter_non_root_mode(struct kvm_vcpu *vcpu, struct vmcs12 *vmcs12 = get_vmcs12(vcpu); enum vm_entry_failure_code entry_failure_code; bool evaluate_pending_interrupts; - u32 exit_reason, failed_index; + union vmx_exit_reason exit_reason = { + .basic = EXIT_REASON_INVALID_STATE, + .failed_vmentry = 1, + }; + u32 failed_index; if (kvm_check_request(KVM_REQ_TLB_FLUSH_CURRENT, vcpu)) kvm_vcpu_flush_tlb_current(vcpu); @@ -3382,7 +3346,7 @@ enum nvmx_vmentry_status nested_vmx_enter_non_root_mode(struct kvm_vcpu *vcpu, if (nested_vmx_check_guest_state(vcpu, vmcs12, &entry_failure_code)) { - exit_reason = EXIT_REASON_INVALID_STATE; + exit_reason.basic = EXIT_REASON_INVALID_STATE; vmcs12->exit_qualification = entry_failure_code; goto vmentry_fail_vmexit; } @@ -3393,7 +3357,7 @@ enum nvmx_vmentry_status nested_vmx_enter_non_root_mode(struct kvm_vcpu *vcpu, vcpu->arch.tsc_offset += vmcs12->tsc_offset; if (prepare_vmcs02(vcpu, vmcs12, &entry_failure_code)) { - exit_reason = EXIT_REASON_INVALID_STATE; + exit_reason.basic = EXIT_REASON_INVALID_STATE; vmcs12->exit_qualification = entry_failure_code; goto vmentry_fail_vmexit_guest_mode; } @@ -3403,7 +3367,7 @@ enum nvmx_vmentry_status nested_vmx_enter_non_root_mode(struct kvm_vcpu *vcpu, vmcs12->vm_entry_msr_load_addr, vmcs12->vm_entry_msr_load_count); if (failed_index) { - exit_reason = EXIT_REASON_MSR_LOAD_FAIL; + exit_reason.basic = EXIT_REASON_MSR_LOAD_FAIL; vmcs12->exit_qualification = failed_index; goto vmentry_fail_vmexit_guest_mode; } @@ -3471,7 +3435,7 @@ vmentry_fail_vmexit: return NVMX_VMENTRY_VMEXIT; load_vmcs12_host_state(vcpu, vmcs12); - vmcs12->vm_exit_reason = exit_reason | VMX_EXIT_REASONS_FAILED_VMENTRY; + vmcs12->vm_exit_reason = exit_reason.full; if (enable_shadow_vmcs || vmx->nested.hv_evmcs) vmx->nested.need_vmcs12_to_shadow_sync = true; return NVMX_VMENTRY_VMEXIT; @@ -4234,9 +4198,6 @@ static void load_vmcs12_host_state(struct kvm_vcpu *vcpu, if (nested_vmx_load_cr3(vcpu, vmcs12->host_cr3, false, &ignored)) nested_vmx_abort(vcpu, VMX_ABORT_LOAD_HOST_PDPTE_FAIL); - if (!enable_ept) - vcpu->arch.walk_mmu->inject_page_fault = kvm_inject_page_fault; - nested_vmx_transition_tlb_flush(vcpu, vmcs12, false); vmcs_write32(GUEST_SYSENTER_CS, vmcs12->host_ia32_sysenter_cs); @@ -4529,6 +4490,11 @@ void nested_vmx_vmexit(struct kvm_vcpu *vcpu, u32 vm_exit_reason, vmx_set_virtual_apic_mode(vcpu); } + if (vmx->nested.update_vmcs01_cpu_dirty_logging) { + vmx->nested.update_vmcs01_cpu_dirty_logging = false; + vmx_update_cpu_dirty_logging(vcpu); + } + /* Unpin physical memory we referred to in vmcs02 */ if (vmx->nested.apic_access_page) { kvm_release_page_clean(vmx->nested.apic_access_page); @@ -5559,7 +5525,12 @@ static int handle_vmfunc(struct kvm_vcpu *vcpu) return kvm_skip_emulated_instruction(vcpu); fail: - nested_vmx_vmexit(vcpu, vmx->exit_reason, + /* + * This is effectively a reflected VM-Exit, as opposed to a synthesized + * nested VM-Exit. Pass the original exit reason, i.e. don't hardcode + * EXIT_REASON_VMFUNC as the exit reason. + */ + nested_vmx_vmexit(vcpu, vmx->exit_reason.full, vmx_get_intr_info(vcpu), vmx_get_exit_qual(vcpu)); return 1; @@ -5627,7 +5598,8 @@ static bool nested_vmx_exit_handled_io(struct kvm_vcpu *vcpu, * MSR bitmap. This may be the case even when L0 doesn't use MSR bitmaps. */ static bool nested_vmx_exit_handled_msr(struct kvm_vcpu *vcpu, - struct vmcs12 *vmcs12, u32 exit_reason) + struct vmcs12 *vmcs12, + union vmx_exit_reason exit_reason) { u32 msr_index = kvm_rcx_read(vcpu); gpa_t bitmap; @@ -5641,7 +5613,7 @@ static bool nested_vmx_exit_handled_msr(struct kvm_vcpu *vcpu, * First we need to figure out which of the four to use: */ bitmap = vmcs12->msr_bitmap; - if (exit_reason == EXIT_REASON_MSR_WRITE) + if (exit_reason.basic == EXIT_REASON_MSR_WRITE) bitmap += 2048; if (msr_index >= 0xc0000000) { msr_index -= 0xc0000000; @@ -5778,11 +5750,12 @@ static bool nested_vmx_exit_handled_mtf(struct vmcs12 *vmcs12) * Return true if L0 wants to handle an exit from L2 regardless of whether or not * L1 wants the exit. Only call this when in is_guest_mode (L2). */ -static bool nested_vmx_l0_wants_exit(struct kvm_vcpu *vcpu, u32 exit_reason) +static bool nested_vmx_l0_wants_exit(struct kvm_vcpu *vcpu, + union vmx_exit_reason exit_reason) { u32 intr_info; - switch ((u16)exit_reason) { + switch ((u16)exit_reason.basic) { case EXIT_REASON_EXCEPTION_NMI: intr_info = vmx_get_intr_info(vcpu); if (is_nmi(intr_info)) @@ -5820,7 +5793,10 @@ static bool nested_vmx_l0_wants_exit(struct kvm_vcpu *vcpu, u32 exit_reason) case EXIT_REASON_PREEMPTION_TIMER: return true; case EXIT_REASON_PML_FULL: - /* We emulate PML support to L1. */ + /* + * PML is emulated for an L1 VMM and should never be enabled in + * vmcs02, always "handle" PML_FULL by exiting to userspace. + */ return true; case EXIT_REASON_VMFUNC: /* VM functions are emulated through L2->L0 vmexits. */ @@ -5838,12 +5814,13 @@ static bool nested_vmx_l0_wants_exit(struct kvm_vcpu *vcpu, u32 exit_reason) * Return 1 if L1 wants to intercept an exit from L2. Only call this when in * is_guest_mode (L2). */ -static bool nested_vmx_l1_wants_exit(struct kvm_vcpu *vcpu, u32 exit_reason) +static bool nested_vmx_l1_wants_exit(struct kvm_vcpu *vcpu, + union vmx_exit_reason exit_reason) { struct vmcs12 *vmcs12 = get_vmcs12(vcpu); u32 intr_info; - switch ((u16)exit_reason) { + switch ((u16)exit_reason.basic) { case EXIT_REASON_EXCEPTION_NMI: intr_info = vmx_get_intr_info(vcpu); if (is_nmi(intr_info)) @@ -5962,7 +5939,7 @@ static bool nested_vmx_l1_wants_exit(struct kvm_vcpu *vcpu, u32 exit_reason) bool nested_vmx_reflect_vmexit(struct kvm_vcpu *vcpu) { struct vcpu_vmx *vmx = to_vmx(vcpu); - u32 exit_reason = vmx->exit_reason; + union vmx_exit_reason exit_reason = vmx->exit_reason; unsigned long exit_qual; u32 exit_intr_info; @@ -5981,7 +5958,7 @@ bool nested_vmx_reflect_vmexit(struct kvm_vcpu *vcpu) goto reflect_vmexit; } - trace_kvm_nested_vmexit(exit_reason, vcpu, KVM_ISA_VMX); + trace_kvm_nested_vmexit(exit_reason.full, vcpu, KVM_ISA_VMX); /* If L0 (KVM) wants the exit, it trumps L1's desires. */ if (nested_vmx_l0_wants_exit(vcpu, exit_reason)) @@ -6007,7 +5984,7 @@ bool nested_vmx_reflect_vmexit(struct kvm_vcpu *vcpu) exit_qual = vmx_get_exit_qual(vcpu); reflect_vmexit: - nested_vmx_vmexit(vcpu, exit_reason, exit_intr_info, exit_qual); + nested_vmx_vmexit(vcpu, exit_reason.full, exit_intr_info, exit_qual); return true; } diff --git a/arch/x86/kvm/vmx/pmu_intel.c b/arch/x86/kvm/vmx/pmu_intel.c index cdf5f34518f4..9efc1a6b8693 100644 --- a/arch/x86/kvm/vmx/pmu_intel.c +++ b/arch/x86/kvm/vmx/pmu_intel.c @@ -152,12 +152,17 @@ static struct kvm_pmc *intel_rdpmc_ecx_to_pmc(struct kvm_vcpu *vcpu, return &counters[array_index_nospec(idx, num_counters)]; } -static inline bool fw_writes_is_enabled(struct kvm_vcpu *vcpu) +static inline u64 vcpu_get_perf_capabilities(struct kvm_vcpu *vcpu) { if (!guest_cpuid_has(vcpu, X86_FEATURE_PDCM)) - return false; + return 0; - return vcpu->arch.perf_capabilities & PMU_CAP_FW_WRITES; + return vcpu->arch.perf_capabilities; +} + +static inline bool fw_writes_is_enabled(struct kvm_vcpu *vcpu) +{ + return (vcpu_get_perf_capabilities(vcpu) & PMU_CAP_FW_WRITES) != 0; } static inline struct kvm_pmc *get_fw_gp_pmc(struct kvm_pmu *pmu, u32 msr) @@ -168,6 +173,41 @@ static inline struct kvm_pmc *get_fw_gp_pmc(struct kvm_pmu *pmu, u32 msr) return get_gp_pmc(pmu, msr, MSR_IA32_PMC0); } +bool intel_pmu_lbr_is_compatible(struct kvm_vcpu *vcpu) +{ + /* + * As a first step, a guest could only enable LBR feature if its + * cpu model is the same as the host because the LBR registers + * would be pass-through to the guest and they're model specific. + */ + return boot_cpu_data.x86_model == guest_cpuid_model(vcpu); +} + +bool intel_pmu_lbr_is_enabled(struct kvm_vcpu *vcpu) +{ + struct x86_pmu_lbr *lbr = vcpu_to_lbr_records(vcpu); + + return lbr->nr && (vcpu_get_perf_capabilities(vcpu) & PMU_CAP_LBR_FMT); +} + +static bool intel_pmu_is_valid_lbr_msr(struct kvm_vcpu *vcpu, u32 index) +{ + struct x86_pmu_lbr *records = vcpu_to_lbr_records(vcpu); + bool ret = false; + + if (!intel_pmu_lbr_is_enabled(vcpu)) + return ret; + + ret = (index == MSR_LBR_SELECT) || (index == MSR_LBR_TOS) || + (index >= records->from && index < records->from + records->nr) || + (index >= records->to && index < records->to + records->nr); + + if (!ret && records->info) + ret = (index >= records->info && index < records->info + records->nr); + + return ret; +} + static bool intel_is_valid_msr(struct kvm_vcpu *vcpu, u32 msr) { struct kvm_pmu *pmu = vcpu_to_pmu(vcpu); @@ -183,7 +223,8 @@ static bool intel_is_valid_msr(struct kvm_vcpu *vcpu, u32 msr) default: ret = get_gp_pmc(pmu, msr, MSR_IA32_PERFCTR0) || get_gp_pmc(pmu, msr, MSR_P6_EVNTSEL0) || - get_fixed_pmc(pmu, msr) || get_fw_gp_pmc(pmu, msr); + get_fixed_pmc(pmu, msr) || get_fw_gp_pmc(pmu, msr) || + intel_pmu_is_valid_lbr_msr(vcpu, msr); break; } @@ -202,6 +243,111 @@ static struct kvm_pmc *intel_msr_idx_to_pmc(struct kvm_vcpu *vcpu, u32 msr) return pmc; } +static inline void intel_pmu_release_guest_lbr_event(struct kvm_vcpu *vcpu) +{ + struct lbr_desc *lbr_desc = vcpu_to_lbr_desc(vcpu); + + if (lbr_desc->event) { + perf_event_release_kernel(lbr_desc->event); + lbr_desc->event = NULL; + vcpu_to_pmu(vcpu)->event_count--; + } +} + +int intel_pmu_create_guest_lbr_event(struct kvm_vcpu *vcpu) +{ + struct lbr_desc *lbr_desc = vcpu_to_lbr_desc(vcpu); + struct kvm_pmu *pmu = vcpu_to_pmu(vcpu); + struct perf_event *event; + + /* + * The perf_event_attr is constructed in the minimum efficient way: + * - set 'pinned = true' to make it task pinned so that if another + * cpu pinned event reclaims LBR, the event->oncpu will be set to -1; + * - set '.exclude_host = true' to record guest branches behavior; + * + * - set '.config = INTEL_FIXED_VLBR_EVENT' to indicates host perf + * schedule the event without a real HW counter but a fake one; + * check is_guest_lbr_event() and __intel_get_event_constraints(); + * + * - set 'sample_type = PERF_SAMPLE_BRANCH_STACK' and + * 'branch_sample_type = PERF_SAMPLE_BRANCH_CALL_STACK | + * PERF_SAMPLE_BRANCH_USER' to configure it as a LBR callstack + * event, which helps KVM to save/restore guest LBR records + * during host context switches and reduces quite a lot overhead, + * check branch_user_callstack() and intel_pmu_lbr_sched_task(); + */ + struct perf_event_attr attr = { + .type = PERF_TYPE_RAW, + .size = sizeof(attr), + .config = INTEL_FIXED_VLBR_EVENT, + .sample_type = PERF_SAMPLE_BRANCH_STACK, + .pinned = true, + .exclude_host = true, + .branch_sample_type = PERF_SAMPLE_BRANCH_CALL_STACK | + PERF_SAMPLE_BRANCH_USER, + }; + + if (unlikely(lbr_desc->event)) { + __set_bit(INTEL_PMC_IDX_FIXED_VLBR, pmu->pmc_in_use); + return 0; + } + + event = perf_event_create_kernel_counter(&attr, -1, + current, NULL, NULL); + if (IS_ERR(event)) { + pr_debug_ratelimited("%s: failed %ld\n", + __func__, PTR_ERR(event)); + return PTR_ERR(event); + } + lbr_desc->event = event; + pmu->event_count++; + __set_bit(INTEL_PMC_IDX_FIXED_VLBR, pmu->pmc_in_use); + return 0; +} + +/* + * It's safe to access LBR msrs from guest when they have not + * been passthrough since the host would help restore or reset + * the LBR msrs records when the guest LBR event is scheduled in. + */ +static bool intel_pmu_handle_lbr_msrs_access(struct kvm_vcpu *vcpu, + struct msr_data *msr_info, bool read) +{ + struct lbr_desc *lbr_desc = vcpu_to_lbr_desc(vcpu); + u32 index = msr_info->index; + + if (!intel_pmu_is_valid_lbr_msr(vcpu, index)) + return false; + + if (!lbr_desc->event && intel_pmu_create_guest_lbr_event(vcpu) < 0) + goto dummy; + + /* + * Disable irq to ensure the LBR feature doesn't get reclaimed by the + * host at the time the value is read from the msr, and this avoids the + * host LBR value to be leaked to the guest. If LBR has been reclaimed, + * return 0 on guest reads. + */ + local_irq_disable(); + if (lbr_desc->event->state == PERF_EVENT_STATE_ACTIVE) { + if (read) + rdmsrl(index, msr_info->data); + else + wrmsrl(index, msr_info->data); + __set_bit(INTEL_PMC_IDX_FIXED_VLBR, vcpu_to_pmu(vcpu)->pmc_in_use); + local_irq_enable(); + return true; + } + clear_bit(INTEL_PMC_IDX_FIXED_VLBR, vcpu_to_pmu(vcpu)->pmc_in_use); + local_irq_enable(); + +dummy: + if (read) + msr_info->data = 0; + return true; +} + static int intel_pmu_get_msr(struct kvm_vcpu *vcpu, struct msr_data *msr_info) { struct kvm_pmu *pmu = vcpu_to_pmu(vcpu); @@ -236,7 +382,8 @@ static int intel_pmu_get_msr(struct kvm_vcpu *vcpu, struct msr_data *msr_info) } else if ((pmc = get_gp_pmc(pmu, msr, MSR_P6_EVNTSEL0))) { msr_info->data = pmc->eventsel; return 0; - } + } else if (intel_pmu_handle_lbr_msrs_access(vcpu, msr_info, true)) + return 0; } return 1; @@ -307,7 +454,8 @@ static int intel_pmu_set_msr(struct kvm_vcpu *vcpu, struct msr_data *msr_info) reprogram_gp_counter(pmc, data); return 0; } - } + } else if (intel_pmu_handle_lbr_msrs_access(vcpu, msr_info, false)) + return 0; } return 1; @@ -316,6 +464,8 @@ static int intel_pmu_set_msr(struct kvm_vcpu *vcpu, struct msr_data *msr_info) static void intel_pmu_refresh(struct kvm_vcpu *vcpu) { struct kvm_pmu *pmu = vcpu_to_pmu(vcpu); + struct lbr_desc *lbr_desc = vcpu_to_lbr_desc(vcpu); + struct x86_pmu_capability x86_pmu; struct kvm_cpuid_entry2 *entry; union cpuid10_eax eax; @@ -327,7 +477,6 @@ static void intel_pmu_refresh(struct kvm_vcpu *vcpu) pmu->counter_bitmask[KVM_PMC_FIXED] = 0; pmu->version = 0; pmu->reserved_bits = 0xffffffff00200000ull; - vcpu->arch.perf_capabilities = 0; entry = kvm_find_cpuid_entry(vcpu, 0xa, 0); if (!entry) @@ -340,8 +489,6 @@ static void intel_pmu_refresh(struct kvm_vcpu *vcpu) return; perf_get_x86_pmu_capability(&x86_pmu); - if (guest_cpuid_has(vcpu, X86_FEATURE_PDCM)) - vcpu->arch.perf_capabilities = vmx_get_perf_capabilities(); pmu->nr_arch_gp_counters = min_t(int, eax.split.num_counters, x86_pmu.num_counters_gp); @@ -385,12 +532,21 @@ static void intel_pmu_refresh(struct kvm_vcpu *vcpu) INTEL_PMC_MAX_GENERIC, pmu->nr_arch_fixed_counters); nested_vmx_pmu_entry_exit_ctls_update(vcpu); + + if (intel_pmu_lbr_is_compatible(vcpu)) + x86_perf_get_lbr(&lbr_desc->records); + else + lbr_desc->records.nr = 0; + + if (lbr_desc->records.nr) + bitmap_set(pmu->all_valid_pmc_idx, INTEL_PMC_IDX_FIXED_VLBR, 1); } static void intel_pmu_init(struct kvm_vcpu *vcpu) { int i; struct kvm_pmu *pmu = vcpu_to_pmu(vcpu); + struct lbr_desc *lbr_desc = vcpu_to_lbr_desc(vcpu); for (i = 0; i < INTEL_PMC_MAX_GENERIC; i++) { pmu->gp_counters[i].type = KVM_PMC_GP; @@ -405,6 +561,11 @@ static void intel_pmu_init(struct kvm_vcpu *vcpu) pmu->fixed_counters[i].idx = i + INTEL_PMC_IDX_FIXED; pmu->fixed_counters[i].current_config = 0; } + + vcpu->arch.perf_capabilities = vmx_get_perf_capabilities(); + lbr_desc->records.nr = 0; + lbr_desc->event = NULL; + lbr_desc->msr_passthrough = false; } static void intel_pmu_reset(struct kvm_vcpu *vcpu) @@ -429,6 +590,119 @@ static void intel_pmu_reset(struct kvm_vcpu *vcpu) pmu->fixed_ctr_ctrl = pmu->global_ctrl = pmu->global_status = pmu->global_ovf_ctrl = 0; + + intel_pmu_release_guest_lbr_event(vcpu); +} + +/* + * Emulate LBR_On_PMI behavior for 1 < pmu.version < 4. + * + * If Freeze_LBR_On_PMI = 1, the LBR is frozen on PMI and + * the KVM emulates to clear the LBR bit (bit 0) in IA32_DEBUGCTL. + * + * Guest needs to re-enable LBR to resume branches recording. + */ +static void intel_pmu_legacy_freezing_lbrs_on_pmi(struct kvm_vcpu *vcpu) +{ + u64 data = vmcs_read64(GUEST_IA32_DEBUGCTL); + + if (data & DEBUGCTLMSR_FREEZE_LBRS_ON_PMI) { + data &= ~DEBUGCTLMSR_LBR; + vmcs_write64(GUEST_IA32_DEBUGCTL, data); + } +} + +static void intel_pmu_deliver_pmi(struct kvm_vcpu *vcpu) +{ + u8 version = vcpu_to_pmu(vcpu)->version; + + if (!intel_pmu_lbr_is_enabled(vcpu)) + return; + + if (version > 1 && version < 4) + intel_pmu_legacy_freezing_lbrs_on_pmi(vcpu); +} + +static void vmx_update_intercept_for_lbr_msrs(struct kvm_vcpu *vcpu, bool set) +{ + struct x86_pmu_lbr *lbr = vcpu_to_lbr_records(vcpu); + int i; + + for (i = 0; i < lbr->nr; i++) { + vmx_set_intercept_for_msr(vcpu, lbr->from + i, MSR_TYPE_RW, set); + vmx_set_intercept_for_msr(vcpu, lbr->to + i, MSR_TYPE_RW, set); + if (lbr->info) + vmx_set_intercept_for_msr(vcpu, lbr->info + i, MSR_TYPE_RW, set); + } + + vmx_set_intercept_for_msr(vcpu, MSR_LBR_SELECT, MSR_TYPE_RW, set); + vmx_set_intercept_for_msr(vcpu, MSR_LBR_TOS, MSR_TYPE_RW, set); +} + +static inline void vmx_disable_lbr_msrs_passthrough(struct kvm_vcpu *vcpu) +{ + struct lbr_desc *lbr_desc = vcpu_to_lbr_desc(vcpu); + + if (!lbr_desc->msr_passthrough) + return; + + vmx_update_intercept_for_lbr_msrs(vcpu, true); + lbr_desc->msr_passthrough = false; +} + +static inline void vmx_enable_lbr_msrs_passthrough(struct kvm_vcpu *vcpu) +{ + struct lbr_desc *lbr_desc = vcpu_to_lbr_desc(vcpu); + + if (lbr_desc->msr_passthrough) + return; + + vmx_update_intercept_for_lbr_msrs(vcpu, false); + lbr_desc->msr_passthrough = true; +} + +/* + * Higher priority host perf events (e.g. cpu pinned) could reclaim the + * pmu resources (e.g. LBR) that were assigned to the guest. This is + * usually done via ipi calls (more details in perf_install_in_context). + * + * Before entering the non-root mode (with irq disabled here), double + * confirm that the pmu features enabled to the guest are not reclaimed + * by higher priority host events. Otherwise, disallow vcpu's access to + * the reclaimed features. + */ +void vmx_passthrough_lbr_msrs(struct kvm_vcpu *vcpu) +{ + struct kvm_pmu *pmu = vcpu_to_pmu(vcpu); + struct lbr_desc *lbr_desc = vcpu_to_lbr_desc(vcpu); + + if (!lbr_desc->event) { + vmx_disable_lbr_msrs_passthrough(vcpu); + if (vmcs_read64(GUEST_IA32_DEBUGCTL) & DEBUGCTLMSR_LBR) + goto warn; + if (test_bit(INTEL_PMC_IDX_FIXED_VLBR, pmu->pmc_in_use)) + goto warn; + return; + } + + if (lbr_desc->event->state < PERF_EVENT_STATE_ACTIVE) { + vmx_disable_lbr_msrs_passthrough(vcpu); + __clear_bit(INTEL_PMC_IDX_FIXED_VLBR, pmu->pmc_in_use); + goto warn; + } else + vmx_enable_lbr_msrs_passthrough(vcpu); + + return; + +warn: + pr_warn_ratelimited("kvm: vcpu-%d: fail to passthrough LBR.\n", + vcpu->vcpu_id); +} + +static void intel_pmu_cleanup(struct kvm_vcpu *vcpu) +{ + if (!(vmcs_read64(GUEST_IA32_DEBUGCTL) & DEBUGCTLMSR_LBR)) + intel_pmu_release_guest_lbr_event(vcpu); } struct kvm_pmu_ops intel_pmu_ops = { @@ -445,4 +719,6 @@ struct kvm_pmu_ops intel_pmu_ops = { .refresh = intel_pmu_refresh, .init = intel_pmu_init, .reset = intel_pmu_reset, + .deliver_pmi = intel_pmu_deliver_pmi, + .cleanup = intel_pmu_cleanup, }; diff --git a/arch/x86/kvm/vmx/posted_intr.c b/arch/x86/kvm/vmx/posted_intr.c index f02962dcc72c..4831bc44ce66 100644 --- a/arch/x86/kvm/vmx/posted_intr.c +++ b/arch/x86/kvm/vmx/posted_intr.c @@ -54,7 +54,7 @@ void vmx_vcpu_pi_load(struct kvm_vcpu *vcpu, int cpu) dest = cpu_physical_id(cpu); - if (x2apic_enabled()) + if (x2apic_mode) new.ndst = dest; else new.ndst = (dest << 8) & 0xFF00; @@ -104,7 +104,7 @@ static void __pi_post_block(struct kvm_vcpu *vcpu) dest = cpu_physical_id(vcpu->cpu); - if (x2apic_enabled()) + if (x2apic_mode) new.ndst = dest; else new.ndst = (dest << 8) & 0xFF00; @@ -174,7 +174,7 @@ int pi_pre_block(struct kvm_vcpu *vcpu) */ dest = cpu_physical_id(vcpu->pre_pcpu); - if (x2apic_enabled()) + if (x2apic_mode) new.ndst = dest; else new.ndst = (dest << 8) & 0xFF00; diff --git a/arch/x86/kvm/vmx/vmenter.S b/arch/x86/kvm/vmx/vmenter.S index e85aa5faa22d..3a6461694fc2 100644 --- a/arch/x86/kvm/vmx/vmenter.S +++ b/arch/x86/kvm/vmx/vmenter.S @@ -44,7 +44,7 @@ * they VM-Fail, whereas a successful VM-Enter + VM-Exit will jump * to vmx_vmexit. */ -SYM_FUNC_START(vmx_vmenter) +SYM_FUNC_START_LOCAL(vmx_vmenter) /* EFLAGS.ZF is set if VMCS.LAUNCHED == 0 */ je 2f diff --git a/arch/x86/kvm/vmx/vmx.c b/arch/x86/kvm/vmx/vmx.c index eb69fef57485..32cf8287d4a7 100644 --- a/arch/x86/kvm/vmx/vmx.c +++ b/arch/x86/kvm/vmx/vmx.c @@ -50,6 +50,7 @@ #include "capabilities.h" #include "cpuid.h" #include "evmcs.h" +#include "hyperv.h" #include "irq.h" #include "kvm_cache_regs.h" #include "lapic.h" @@ -552,7 +553,7 @@ static int hv_enable_direct_tlbflush(struct kvm_vcpu *vcpu) { struct hv_enlightened_vmcs *evmcs; struct hv_partition_assist_pg **p_hv_pa_pg = - &vcpu->kvm->arch.hyperv.hv_pa_pg; + &to_kvm_hv(vcpu->kvm)->hv_pa_pg; /* * Synthetic VM-Exit is not enabled in current code and so All * evmcs in singe VM shares same assist page. @@ -658,6 +659,14 @@ static bool is_valid_passthrough_msr(u32 msr) case MSR_IA32_RTIT_CR3_MATCH: case MSR_IA32_RTIT_ADDR0_A ... MSR_IA32_RTIT_ADDR3_B: /* PT MSRs. These are handled in pt_update_intercept_for_msr() */ + case MSR_LBR_SELECT: + case MSR_LBR_TOS: + case MSR_LBR_INFO_0 ... MSR_LBR_INFO_0 + 31: + case MSR_LBR_NHM_FROM ... MSR_LBR_NHM_FROM + 31: + case MSR_LBR_NHM_TO ... MSR_LBR_NHM_TO + 31: + case MSR_LBR_CORE_FROM ... MSR_LBR_CORE_FROM + 8: + case MSR_LBR_CORE_TO ... MSR_LBR_CORE_TO + 8: + /* LBR MSRs. These are handled in vmx_update_intercept_for_lbr_msrs() */ return true; } @@ -806,7 +815,7 @@ static u32 vmx_read_guest_seg_ar(struct vcpu_vmx *vmx, unsigned seg) return *p; } -void update_exception_bitmap(struct kvm_vcpu *vcpu) +void vmx_update_exception_bitmap(struct kvm_vcpu *vcpu) { u32 eb; @@ -1102,7 +1111,7 @@ static inline bool pt_can_write_msr(struct vcpu_vmx *vmx) static inline bool pt_output_base_valid(struct kvm_vcpu *vcpu, u64 base) { /* The base must be 128-byte aligned and a legal physical address. */ - return !kvm_vcpu_is_illegal_gpa(vcpu, base) && !(base & 0x7f); + return kvm_vcpu_is_legal_aligned_gpa(vcpu, base, 128); } static inline void pt_load_msr(struct pt_ctx *ctx, u32 addr_range) @@ -1577,7 +1586,7 @@ static int skip_emulated_instruction(struct kvm_vcpu *vcpu) * i.e. we end up advancing IP with some random value. */ if (!static_cpu_has(X86_FEATURE_HYPERVISOR) || - to_vmx(vcpu)->exit_reason != EXIT_REASON_EPT_MISCONFIG) { + to_vmx(vcpu)->exit_reason.basic != EXIT_REASON_EPT_MISCONFIG) { orig_rip = kvm_rip_read(vcpu); rip = orig_rip + vmcs_read32(VM_EXIT_INSTRUCTION_LEN); #ifdef CONFIG_X86_64 @@ -1924,6 +1933,9 @@ static int vmx_get_msr(struct kvm_vcpu *vcpu, struct msr_data *msr_info) !guest_cpuid_has(vcpu, X86_FEATURE_RDTSCP)) return 1; goto find_uret_msr; + case MSR_IA32_DEBUGCTLMSR: + msr_info->data = vmcs_read64(GUEST_IA32_DEBUGCTL); + break; default: find_uret_msr: msr = vmx_find_uret_msr(vmx, msr_info->index); @@ -1947,6 +1959,16 @@ static u64 nested_vmx_truncate_sysenter_addr(struct kvm_vcpu *vcpu, return (unsigned long)data; } +static u64 vcpu_supported_debugctl(struct kvm_vcpu *vcpu) +{ + u64 debugctl = vmx_supported_debugctl(); + + if (!intel_pmu_lbr_is_enabled(vcpu)) + debugctl &= ~DEBUGCTLMSR_LBR_MASK; + + return debugctl; +} + /* * Writes msr value into the appropriate "register". * Returns 0 on success, non-0 otherwise. @@ -1997,14 +2019,29 @@ static int vmx_set_msr(struct kvm_vcpu *vcpu, struct msr_data *msr_info) } vmcs_writel(GUEST_SYSENTER_ESP, data); break; - case MSR_IA32_DEBUGCTLMSR: + case MSR_IA32_DEBUGCTLMSR: { + u64 invalid = data & ~vcpu_supported_debugctl(vcpu); + if (invalid & (DEBUGCTLMSR_BTF|DEBUGCTLMSR_LBR)) { + if (report_ignored_msrs) + vcpu_unimpl(vcpu, "%s: BTF|LBR in IA32_DEBUGCTLMSR 0x%llx, nop\n", + __func__, data); + data &= ~(DEBUGCTLMSR_BTF|DEBUGCTLMSR_LBR); + invalid &= ~(DEBUGCTLMSR_BTF|DEBUGCTLMSR_LBR); + } + + if (invalid) + return 1; + if (is_guest_mode(vcpu) && get_vmcs12(vcpu)->vm_exit_controls & VM_EXIT_SAVE_DEBUG_CONTROLS) get_vmcs12(vcpu)->guest_ia32_debugctl = data; - ret = kvm_set_msr_common(vcpu, msr_info); - break; - + vmcs_write64(GUEST_IA32_DEBUGCTL, data); + if (intel_pmu_lbr_is_enabled(vcpu) && !to_vmx(vcpu)->lbr_desc.event && + (data & DEBUGCTLMSR_LBR)) + intel_pmu_create_guest_lbr_event(vcpu); + return 0; + } case MSR_IA32_BNDCFGS: if (!kvm_mpx_supported() || (!msr_info->host_initiated && @@ -2196,6 +2233,18 @@ static int vmx_set_msr(struct kvm_vcpu *vcpu, struct msr_data *msr_info) if ((data >> 32) != 0) return 1; goto find_uret_msr; + case MSR_IA32_PERF_CAPABILITIES: + if (data && !vcpu_to_pmu(vcpu)->version) + return 1; + if (data & PMU_CAP_LBR_FMT) { + if ((data & PMU_CAP_LBR_FMT) != + (vmx_get_perf_capabilities() & PMU_CAP_LBR_FMT)) + return 1; + if (!intel_pmu_lbr_is_compatible(vcpu)) + return 1; + } + ret = kvm_set_msr_common(vcpu, msr_info); + break; default: find_uret_msr: @@ -2265,7 +2314,6 @@ static int kvm_cpu_vmxon(u64 vmxon_pointer) u64 msr; cr4_set_bits(X86_CR4_VMXE); - intel_pt_handle_vmx(1); asm_volatile_goto("1: vmxon %[vmxon_pointer]\n\t" _ASM_EXTABLE(1b, %l[fault]) @@ -2276,7 +2324,6 @@ static int kvm_cpu_vmxon(u64 vmxon_pointer) fault: WARN_ONCE(1, "VMXON faulted, MSR_IA32_FEAT_CTL (0x3a) = 0x%llx\n", rdmsrl_safe(MSR_IA32_FEAT_CTL, &msr) ? 0xdeadbeef : msr); - intel_pt_handle_vmx(0); cr4_clear_bits(X86_CR4_VMXE); return -EFAULT; @@ -2299,9 +2346,13 @@ static int hardware_enable(void) !hv_get_vp_assist_page(cpu)) return -EFAULT; + intel_pt_handle_vmx(1); + r = kvm_cpu_vmxon(phys_addr); - if (r) + if (r) { + intel_pt_handle_vmx(0); return r; + } if (enable_ept) ept_sync_global(); @@ -2319,22 +2370,14 @@ static void vmclear_local_loaded_vmcss(void) __loaded_vmcs_clear(v); } - -/* Just like cpu_vmxoff(), but with the __kvm_handle_fault_on_reboot() - * tricks. - */ -static void kvm_cpu_vmxoff(void) -{ - asm volatile (__ex("vmxoff")); - - intel_pt_handle_vmx(0); - cr4_clear_bits(X86_CR4_VMXE); -} - static void hardware_disable(void) { vmclear_local_loaded_vmcss(); - kvm_cpu_vmxoff(); + + if (cpu_vmxoff()) + kvm_spurious_fault(); + + intel_pt_handle_vmx(0); } /* @@ -2428,7 +2471,8 @@ static __init int setup_vmcs_config(struct vmcs_config *vmcs_conf, SECONDARY_EXEC_ENABLE_USR_WAIT_PAUSE | SECONDARY_EXEC_PT_USE_GPA | SECONDARY_EXEC_PT_CONCEAL_VMX | - SECONDARY_EXEC_ENABLE_VMFUNC; + SECONDARY_EXEC_ENABLE_VMFUNC | + SECONDARY_EXEC_BUS_LOCK_DETECTION; if (cpu_has_sgx()) opt2 |= SECONDARY_EXEC_ENCLS_EXITING; if (adjust_vmx_controls(min2, opt2, @@ -2739,7 +2783,7 @@ static void enter_pmode(struct kvm_vcpu *vcpu) vmcs_writel(GUEST_CR4, (vmcs_readl(GUEST_CR4) & ~X86_CR4_VME) | (vmcs_readl(CR4_READ_SHADOW) & X86_CR4_VME)); - update_exception_bitmap(vcpu); + vmx_update_exception_bitmap(vcpu); fix_pmode_seg(vcpu, VCPU_SREG_CS, &vmx->rmode.segs[VCPU_SREG_CS]); fix_pmode_seg(vcpu, VCPU_SREG_SS, &vmx->rmode.segs[VCPU_SREG_SS]); @@ -2819,7 +2863,7 @@ static void enter_rmode(struct kvm_vcpu *vcpu) vmcs_writel(GUEST_RFLAGS, flags); vmcs_writel(GUEST_CR4, vmcs_readl(GUEST_CR4) | X86_CR4_VME); - update_exception_bitmap(vcpu); + vmx_update_exception_bitmap(vcpu); fix_rmode_seg(VCPU_SREG_SS, &vmx->rmode.segs[VCPU_SREG_SS]); fix_rmode_seg(VCPU_SREG_CS, &vmx->rmode.segs[VCPU_SREG_CS]); @@ -3774,7 +3818,7 @@ static __always_inline void vmx_enable_intercept_for_msr(struct kvm_vcpu *vcpu, vmx_set_msr_bitmap_write(msr_bitmap, msr); } -static __always_inline void vmx_set_intercept_for_msr(struct kvm_vcpu *vcpu, +void vmx_set_intercept_for_msr(struct kvm_vcpu *vcpu, u32 msr, int type, bool value) { if (value) @@ -4233,7 +4277,12 @@ static void vmx_compute_secondary_exec_control(struct vcpu_vmx *vmx) */ exec_control &= ~SECONDARY_EXEC_SHADOW_VMCS; - if (!enable_pml) + /* + * PML is enabled/disabled when dirty logging of memsmlots changes, but + * it needs to be set here when dirty logging is already active, e.g. + * if this vCPU was created after dirty logging was enabled. + */ + if (!vcpu->kvm->arch.cpu_dirty_logging_count) exec_control &= ~SECONDARY_EXEC_ENABLE_PML; if (cpu_has_vmx_xsaves()) { @@ -4251,24 +4300,17 @@ static void vmx_compute_secondary_exec_control(struct vcpu_vmx *vmx) } vmx_adjust_sec_exec_feature(vmx, &exec_control, rdtscp, RDTSCP); - - /* - * Expose INVPCID if and only if PCID is also exposed to the guest. - * INVPCID takes a #UD when it's disabled in the VMCS, but a #GP or #PF - * if CR4.PCIDE=0. Enumerating CPUID.INVPCID=1 would lead to incorrect - * behavior from the guest perspective (it would expect #GP or #PF). - */ - if (!guest_cpuid_has(vcpu, X86_FEATURE_PCID)) - guest_cpuid_clear(vcpu, X86_FEATURE_INVPCID); vmx_adjust_sec_exec_feature(vmx, &exec_control, invpcid, INVPCID); - vmx_adjust_sec_exec_exiting(vmx, &exec_control, rdrand, RDRAND); vmx_adjust_sec_exec_exiting(vmx, &exec_control, rdseed, RDSEED); vmx_adjust_sec_exec_control(vmx, &exec_control, waitpkg, WAITPKG, ENABLE_USR_WAIT_PAUSE, false); + if (!vcpu->kvm->arch.bus_lock_detection_enabled) + exec_control &= ~SECONDARY_EXEC_BUS_LOCK_DETECTION; + vmx->secondary_exec_control = exec_control; } @@ -4467,23 +4509,23 @@ static void vmx_vcpu_reset(struct kvm_vcpu *vcpu, bool init_event) vmx_set_cr4(vcpu, 0); vmx_set_efer(vcpu, 0); - update_exception_bitmap(vcpu); + vmx_update_exception_bitmap(vcpu); vpid_sync_context(vmx->vpid); if (init_event) vmx_clear_hlt(vcpu); } -static void enable_irq_window(struct kvm_vcpu *vcpu) +static void vmx_enable_irq_window(struct kvm_vcpu *vcpu) { exec_controls_setbit(to_vmx(vcpu), CPU_BASED_INTR_WINDOW_EXITING); } -static void enable_nmi_window(struct kvm_vcpu *vcpu) +static void vmx_enable_nmi_window(struct kvm_vcpu *vcpu) { if (!enable_vnmi || vmcs_read32(GUEST_INTERRUPTIBILITY_INFO) & GUEST_INTR_STATE_STI) { - enable_irq_window(vcpu); + vmx_enable_irq_window(vcpu); return; } @@ -4824,7 +4866,7 @@ static int handle_exception_nmi(struct kvm_vcpu *vcpu) kvm_queue_exception_p(vcpu, DB_VECTOR, dr6); return 1; } - kvm_run->debug.arch.dr6 = dr6 | DR6_FIXED_1 | DR6_RTM; + kvm_run->debug.arch.dr6 = dr6 | DR6_ACTIVE_LOW; kvm_run->debug.arch.dr7 = vmcs_readl(GUEST_DR7); fallthrough; case BP_VECTOR: @@ -5049,6 +5091,7 @@ static int handle_dr(struct kvm_vcpu *vcpu) { unsigned long exit_qualification; int dr, dr7, reg; + int err = 1; exit_qualification = vmx_get_exit_qual(vcpu); dr = exit_qualification & DEBUG_REG_ACCESS_NUM; @@ -5057,9 +5100,9 @@ static int handle_dr(struct kvm_vcpu *vcpu) if (!kvm_require_dr(vcpu, dr)) return 1; - /* Do not handle if the CPL > 0, will trigger GP on re-entry */ - if (!kvm_require_cpl(vcpu, 0)) - return 1; + if (kvm_x86_ops.get_cpl(vcpu) > 0) + goto out; + dr7 = vmcs_readl(GUEST_DR7); if (dr7 & DR7_GD) { /* @@ -5068,7 +5111,7 @@ static int handle_dr(struct kvm_vcpu *vcpu) * guest debugging itself. */ if (vcpu->guest_debug & KVM_GUESTDBG_USE_HW_BP) { - vcpu->run->debug.arch.dr6 = DR6_BD | DR6_RTM | DR6_FIXED_1; + vcpu->run->debug.arch.dr6 = DR6_BD | DR6_ACTIVE_LOW; vcpu->run->debug.arch.dr7 = dr7; vcpu->run->debug.arch.pc = kvm_get_linear_rip(vcpu); vcpu->run->debug.arch.exception = DB_VECTOR; @@ -5096,14 +5139,15 @@ static int handle_dr(struct kvm_vcpu *vcpu) if (exit_qualification & TYPE_MOV_FROM_DR) { unsigned long val; - if (kvm_get_dr(vcpu, dr, &val)) - return 1; + kvm_get_dr(vcpu, dr, &val); kvm_register_write(vcpu, reg, val); - } else - if (kvm_set_dr(vcpu, dr, kvm_register_readl(vcpu, reg))) - return 1; + err = 0; + } else { + err = kvm_set_dr(vcpu, dr, kvm_register_readl(vcpu, reg)); + } - return kvm_skip_emulated_instruction(vcpu); +out: + return kvm_complete_insn_gp(vcpu, err); } static void vmx_sync_dirty_debug_regs(struct kvm_vcpu *vcpu) @@ -5177,9 +5221,8 @@ static int handle_xsetbv(struct kvm_vcpu *vcpu) u64 new_bv = kvm_read_edx_eax(vcpu); u32 index = kvm_rcx_read(vcpu); - if (kvm_set_xcr(vcpu, index, new_bv) == 0) - return kvm_skip_emulated_instruction(vcpu); - return 1; + int err = kvm_set_xcr(vcpu, index, new_bv); + return kvm_complete_insn_gp(vcpu, err); } static int handle_apic_access(struct kvm_vcpu *vcpu) @@ -5600,6 +5643,13 @@ static int handle_encls(struct kvm_vcpu *vcpu) return 1; } +static int handle_bus_lock_vmexit(struct kvm_vcpu *vcpu) +{ + vcpu->run->exit_reason = KVM_EXIT_X86_BUS_LOCK; + vcpu->run->flags |= KVM_RUN_X86_BUS_LOCK; + return 0; +} + /* * The exit handlers return 1 if the exit was handled fully and guest execution * may resume. Otherwise they set the kvm_run parameter to indicate what needs @@ -5656,6 +5706,7 @@ static int (*kvm_vmx_exit_handlers[])(struct kvm_vcpu *vcpu) = { [EXIT_REASON_VMFUNC] = handle_vmx_instruction, [EXIT_REASON_PREEMPTION_TIMER] = handle_preemption_timer, [EXIT_REASON_ENCLS] = handle_encls, + [EXIT_REASON_BUS_LOCK] = handle_bus_lock_vmexit, }; static const int kvm_vmx_max_exit_handlers = @@ -5667,7 +5718,7 @@ static void vmx_get_exit_info(struct kvm_vcpu *vcpu, u64 *info1, u64 *info2, struct vcpu_vmx *vmx = to_vmx(vcpu); *info1 = vmx_get_exit_qual(vcpu); - if (!(vmx->exit_reason & VMX_EXIT_REASONS_FAILED_VMENTRY)) { + if (!(vmx->exit_reason.failed_vmentry)) { *info2 = vmx->idt_vectoring_info; *intr_info = vmx_get_intr_info(vcpu); if (is_exception_with_error_code(*intr_info)) @@ -5720,24 +5771,6 @@ static void vmx_flush_pml_buffer(struct kvm_vcpu *vcpu) vmcs_write16(GUEST_PML_INDEX, PML_ENTITY_NUM - 1); } -/* - * Flush all vcpus' PML buffer and update logged GPAs to dirty_bitmap. - * Called before reporting dirty_bitmap to userspace. - */ -static void kvm_flush_pml_buffers(struct kvm *kvm) -{ - int i; - struct kvm_vcpu *vcpu; - /* - * We only need to kick vcpu out of guest mode here, as PML buffer - * is flushed at beginning of all VMEXITs, and it's obvious that only - * vcpus running in guest are possible to have unflushed GPAs in PML - * buffer. - */ - kvm_for_each_vcpu(i, vcpu, kvm) - kvm_vcpu_kick(vcpu); -} - static void vmx_dump_sel(char *name, uint32_t sel) { pr_err("%s sel=0x%04x, attr=0x%05x, limit=0x%08x, base=0x%016lx\n", @@ -5908,20 +5941,22 @@ void dump_vmcs(void) * The guest has exited. See if we can fix it or if we need userspace * assistance. */ -static int vmx_handle_exit(struct kvm_vcpu *vcpu, fastpath_t exit_fastpath) +static int __vmx_handle_exit(struct kvm_vcpu *vcpu, fastpath_t exit_fastpath) { struct vcpu_vmx *vmx = to_vmx(vcpu); - u32 exit_reason = vmx->exit_reason; + union vmx_exit_reason exit_reason = vmx->exit_reason; u32 vectoring_info = vmx->idt_vectoring_info; + u16 exit_handler_index; /* * Flush logged GPAs PML buffer, this will make dirty_bitmap more * updated. Another good is, in kvm_vm_ioctl_get_dirty_log, before * querying dirty_bitmap, we only need to kick all vcpus out of guest * mode as if vcpus is in root mode, the PML buffer must has been - * flushed already. + * flushed already. Note, PML is never enabled in hardware while + * running L2. */ - if (enable_pml) + if (enable_pml && !is_guest_mode(vcpu)) vmx_flush_pml_buffer(vcpu); /* @@ -5938,6 +5973,13 @@ static int vmx_handle_exit(struct kvm_vcpu *vcpu, fastpath_t exit_fastpath) if (is_guest_mode(vcpu)) { /* + * PML is never enabled when running L2, bail immediately if a + * PML full exit occurs as something is horribly wrong. + */ + if (exit_reason.basic == EXIT_REASON_PML_FULL) + goto unexpected_vmexit; + + /* * The host physical addresses of some pages of guest memory * are loaded into the vmcs02 (e.g. vmcs12's Virtual APIC * Page). The CPU may write to these pages via their host @@ -5954,11 +5996,11 @@ static int vmx_handle_exit(struct kvm_vcpu *vcpu, fastpath_t exit_fastpath) return 1; } - if (exit_reason & VMX_EXIT_REASONS_FAILED_VMENTRY) { + if (exit_reason.failed_vmentry) { dump_vmcs(); vcpu->run->exit_reason = KVM_EXIT_FAIL_ENTRY; vcpu->run->fail_entry.hardware_entry_failure_reason - = exit_reason; + = exit_reason.full; vcpu->run->fail_entry.cpu = vcpu->arch.last_vmentry_cpu; return 0; } @@ -5980,18 +6022,18 @@ static int vmx_handle_exit(struct kvm_vcpu *vcpu, fastpath_t exit_fastpath) * will cause infinite loop. */ if ((vectoring_info & VECTORING_INFO_VALID_MASK) && - (exit_reason != EXIT_REASON_EXCEPTION_NMI && - exit_reason != EXIT_REASON_EPT_VIOLATION && - exit_reason != EXIT_REASON_PML_FULL && - exit_reason != EXIT_REASON_APIC_ACCESS && - exit_reason != EXIT_REASON_TASK_SWITCH)) { + (exit_reason.basic != EXIT_REASON_EXCEPTION_NMI && + exit_reason.basic != EXIT_REASON_EPT_VIOLATION && + exit_reason.basic != EXIT_REASON_PML_FULL && + exit_reason.basic != EXIT_REASON_APIC_ACCESS && + exit_reason.basic != EXIT_REASON_TASK_SWITCH)) { vcpu->run->exit_reason = KVM_EXIT_INTERNAL_ERROR; vcpu->run->internal.suberror = KVM_INTERNAL_ERROR_DELIVERY_EV; vcpu->run->internal.ndata = 3; vcpu->run->internal.data[0] = vectoring_info; - vcpu->run->internal.data[1] = exit_reason; + vcpu->run->internal.data[1] = exit_reason.full; vcpu->run->internal.data[2] = vcpu->arch.exit_qualification; - if (exit_reason == EXIT_REASON_EPT_MISCONFIG) { + if (exit_reason.basic == EXIT_REASON_EPT_MISCONFIG) { vcpu->run->internal.ndata++; vcpu->run->internal.data[3] = vmcs_read64(GUEST_PHYSICAL_ADDRESS); @@ -6023,42 +6065,62 @@ static int vmx_handle_exit(struct kvm_vcpu *vcpu, fastpath_t exit_fastpath) if (exit_fastpath != EXIT_FASTPATH_NONE) return 1; - if (exit_reason >= kvm_vmx_max_exit_handlers) + if (exit_reason.basic >= kvm_vmx_max_exit_handlers) goto unexpected_vmexit; #ifdef CONFIG_RETPOLINE - if (exit_reason == EXIT_REASON_MSR_WRITE) + if (exit_reason.basic == EXIT_REASON_MSR_WRITE) return kvm_emulate_wrmsr(vcpu); - else if (exit_reason == EXIT_REASON_PREEMPTION_TIMER) + else if (exit_reason.basic == EXIT_REASON_PREEMPTION_TIMER) return handle_preemption_timer(vcpu); - else if (exit_reason == EXIT_REASON_INTERRUPT_WINDOW) + else if (exit_reason.basic == EXIT_REASON_INTERRUPT_WINDOW) return handle_interrupt_window(vcpu); - else if (exit_reason == EXIT_REASON_EXTERNAL_INTERRUPT) + else if (exit_reason.basic == EXIT_REASON_EXTERNAL_INTERRUPT) return handle_external_interrupt(vcpu); - else if (exit_reason == EXIT_REASON_HLT) + else if (exit_reason.basic == EXIT_REASON_HLT) return kvm_emulate_halt(vcpu); - else if (exit_reason == EXIT_REASON_EPT_MISCONFIG) + else if (exit_reason.basic == EXIT_REASON_EPT_MISCONFIG) return handle_ept_misconfig(vcpu); #endif - exit_reason = array_index_nospec(exit_reason, - kvm_vmx_max_exit_handlers); - if (!kvm_vmx_exit_handlers[exit_reason]) + exit_handler_index = array_index_nospec((u16)exit_reason.basic, + kvm_vmx_max_exit_handlers); + if (!kvm_vmx_exit_handlers[exit_handler_index]) goto unexpected_vmexit; - return kvm_vmx_exit_handlers[exit_reason](vcpu); + return kvm_vmx_exit_handlers[exit_handler_index](vcpu); unexpected_vmexit: - vcpu_unimpl(vcpu, "vmx: unexpected exit reason 0x%x\n", exit_reason); + vcpu_unimpl(vcpu, "vmx: unexpected exit reason 0x%x\n", + exit_reason.full); dump_vmcs(); vcpu->run->exit_reason = KVM_EXIT_INTERNAL_ERROR; vcpu->run->internal.suberror = KVM_INTERNAL_ERROR_UNEXPECTED_EXIT_REASON; vcpu->run->internal.ndata = 2; - vcpu->run->internal.data[0] = exit_reason; + vcpu->run->internal.data[0] = exit_reason.full; vcpu->run->internal.data[1] = vcpu->arch.last_vmentry_cpu; return 0; } +static int vmx_handle_exit(struct kvm_vcpu *vcpu, fastpath_t exit_fastpath) +{ + int ret = __vmx_handle_exit(vcpu, exit_fastpath); + + /* + * Even when current exit reason is handled by KVM internally, we + * still need to exit to user space when bus lock detected to inform + * that there is a bus lock in guest. + */ + if (to_vmx(vcpu)->exit_reason.bus_lock_detected) { + if (ret > 0) + vcpu->run->exit_reason = KVM_EXIT_X86_BUS_LOCK; + + vcpu->run->flags |= KVM_RUN_X86_BUS_LOCK; + return 0; + } + return ret; +} + /* * Software based L1D cache flush which is used when microcode providing * the cache control MSR is not loaded. @@ -6129,7 +6191,7 @@ static noinstr void vmx_l1d_flush(struct kvm_vcpu *vcpu) : "eax", "ebx", "ecx", "edx"); } -static void update_cr8_intercept(struct kvm_vcpu *vcpu, int tpr, int irr) +static void vmx_update_cr8_intercept(struct kvm_vcpu *vcpu, int tpr, int irr) { struct vmcs12 *vmcs12 = get_vmcs12(vcpu); int tpr_threshold; @@ -6373,9 +6435,9 @@ static void vmx_handle_exit_irqoff(struct kvm_vcpu *vcpu) { struct vcpu_vmx *vmx = to_vmx(vcpu); - if (vmx->exit_reason == EXIT_REASON_EXTERNAL_INTERRUPT) + if (vmx->exit_reason.basic == EXIT_REASON_EXTERNAL_INTERRUPT) handle_external_interrupt_irqoff(vcpu); - else if (vmx->exit_reason == EXIT_REASON_EXCEPTION_NMI) + else if (vmx->exit_reason.basic == EXIT_REASON_EXCEPTION_NMI) handle_exception_nmi_irqoff(vmx); } @@ -6518,8 +6580,8 @@ static void atomic_switch_perf_msrs(struct vcpu_vmx *vmx) int i, nr_msrs; struct perf_guest_switch_msr *msrs; + /* Note, nr_msrs may be garbage if perf_guest_get_msrs() returns NULL. */ msrs = perf_guest_get_msrs(&nr_msrs); - if (!msrs) return; @@ -6567,7 +6629,7 @@ void noinstr vmx_update_host_rsp(struct vcpu_vmx *vmx, unsigned long host_rsp) static fastpath_t vmx_exit_handlers_fastpath(struct kvm_vcpu *vcpu) { - switch (to_vmx(vcpu)->exit_reason) { + switch (to_vmx(vcpu)->exit_reason.basic) { case EXIT_REASON_MSR_WRITE: return handle_fastpath_set_msr_irqoff(vcpu); case EXIT_REASON_PREEMPTION_TIMER: @@ -6577,8 +6639,6 @@ static fastpath_t vmx_exit_handlers_fastpath(struct kvm_vcpu *vcpu) } } -bool __vmx_vcpu_run(struct vcpu_vmx *vmx, unsigned long *regs, bool launched); - static noinstr void vmx_vcpu_enter_exit(struct kvm_vcpu *vcpu, struct vcpu_vmx *vmx) { @@ -6638,11 +6698,9 @@ static noinstr void vmx_vcpu_enter_exit(struct kvm_vcpu *vcpu, static fastpath_t vmx_vcpu_run(struct kvm_vcpu *vcpu) { - fastpath_t exit_fastpath; struct vcpu_vmx *vmx = to_vmx(vcpu); unsigned long cr3, cr4; -reenter_guest: /* Record the guest's net vcpu time for enforced NMI injections. */ if (unlikely(!enable_vnmi && vmx->loaded_vmcs->soft_vnmi_blocked)) @@ -6696,6 +6754,8 @@ reenter_guest: pt_guest_enter(vmx); atomic_switch_perf_msrs(vmx); + if (intel_pmu_lbr_is_enabled(vcpu)) + vmx_passthrough_lbr_msrs(vcpu); if (enable_preemption_timer) vmx_update_hv_timer(vcpu); @@ -6734,12 +6794,12 @@ reenter_guest: x86_spec_ctrl_restore_host(vmx->spec_ctrl, 0); /* All fields are clean at this point */ - if (static_branch_unlikely(&enable_evmcs)) + if (static_branch_unlikely(&enable_evmcs)) { current_evmcs->hv_clean_fields |= HV_VMX_ENLIGHTENED_CLEAN_FIELD_ALL; - if (static_branch_unlikely(&enable_evmcs)) - current_evmcs->hv_vp_id = vcpu->arch.hyperv.vp_index; + current_evmcs->hv_vp_id = kvm_hv_get_vpindex(vcpu); + } /* MSR_IA32_DEBUGCTLMSR is zeroed on vmexit. Restore it if needed */ if (vmx->host_debugctlmsr) @@ -6768,21 +6828,23 @@ reenter_guest: vmx->idt_vectoring_info = 0; if (unlikely(vmx->fail)) { - vmx->exit_reason = 0xdead; + vmx->exit_reason.full = 0xdead; return EXIT_FASTPATH_NONE; } - vmx->exit_reason = vmcs_read32(VM_EXIT_REASON); - if (unlikely((u16)vmx->exit_reason == EXIT_REASON_MCE_DURING_VMENTRY)) + vmx->exit_reason.full = vmcs_read32(VM_EXIT_REASON); + if (unlikely((u16)vmx->exit_reason.basic == EXIT_REASON_MCE_DURING_VMENTRY)) kvm_machine_check(); - trace_kvm_exit(vmx->exit_reason, vcpu, KVM_ISA_VMX); + if (likely(!vmx->exit_reason.failed_vmentry)) + vmx->idt_vectoring_info = vmcs_read32(IDT_VECTORING_INFO_FIELD); + + trace_kvm_exit(vmx->exit_reason.full, vcpu, KVM_ISA_VMX); - if (unlikely(vmx->exit_reason & VMX_EXIT_REASONS_FAILED_VMENTRY)) + if (unlikely(vmx->exit_reason.failed_vmentry)) return EXIT_FASTPATH_NONE; vmx->loaded_vmcs->launched = 1; - vmx->idt_vectoring_info = vmcs_read32(IDT_VECTORING_INFO_FIELD); vmx_recover_nmi_blocking(vmx); vmx_complete_interrupts(vmx); @@ -6790,22 +6852,7 @@ reenter_guest: if (is_guest_mode(vcpu)) return EXIT_FASTPATH_NONE; - exit_fastpath = vmx_exit_handlers_fastpath(vcpu); - if (exit_fastpath == EXIT_FASTPATH_REENTER_GUEST) { - if (!kvm_vcpu_exit_request(vcpu)) { - /* - * FIXME: this goto should be a loop in vcpu_enter_guest, - * but it would incur the cost of a retpoline for now. - * Revisit once static calls are available. - */ - if (vcpu->arch.apicv_active) - vmx_sync_pir_to_irr(vcpu); - goto reenter_guest; - } - exit_fastpath = EXIT_FASTPATH_EXIT_HANDLED; - } - - return exit_fastpath; + return vmx_exit_handlers_fastpath(vcpu); } static void vmx_free_vcpu(struct kvm_vcpu *vcpu) @@ -7256,7 +7303,7 @@ static void vmx_vcpu_after_set_cpuid(struct kvm_vcpu *vcpu) set_cr4_guest_host_mask(vmx); /* Refresh #PF interception to account for MAXPHYADDR changes. */ - update_exception_bitmap(vcpu); + vmx_update_exception_bitmap(vcpu); } static __init void vmx_set_cpu_caps(void) @@ -7270,8 +7317,8 @@ static __init void vmx_set_cpu_caps(void) /* CPUID 0x7 */ if (kvm_mpx_supported()) kvm_cpu_cap_check_and_set(X86_FEATURE_MPX); - if (cpu_has_vmx_invpcid()) - kvm_cpu_cap_check_and_set(X86_FEATURE_INVPCID); + if (!cpu_has_vmx_invpcid()) + kvm_cpu_cap_clear(X86_FEATURE_INVPCID); if (vmx_pt_mode_is_host_guest()) kvm_cpu_cap_check_and_set(X86_FEATURE_INTEL_PT); @@ -7449,30 +7496,24 @@ static void vmx_sched_in(struct kvm_vcpu *vcpu, int cpu) shrink_ple_window(vcpu); } -static void vmx_slot_enable_log_dirty(struct kvm *kvm, - struct kvm_memory_slot *slot) -{ - if (!kvm_dirty_log_manual_protect_and_init_set(kvm)) - kvm_mmu_slot_leaf_clear_dirty(kvm, slot); - kvm_mmu_slot_largepage_remove_write_access(kvm, slot); -} - -static void vmx_slot_disable_log_dirty(struct kvm *kvm, - struct kvm_memory_slot *slot) +void vmx_update_cpu_dirty_logging(struct kvm_vcpu *vcpu) { - kvm_mmu_slot_set_dirty(kvm, slot); -} + struct vcpu_vmx *vmx = to_vmx(vcpu); -static void vmx_flush_log_dirty(struct kvm *kvm) -{ - kvm_flush_pml_buffers(kvm); -} + if (is_guest_mode(vcpu)) { + vmx->nested.update_vmcs01_cpu_dirty_logging = true; + return; + } -static void vmx_enable_log_dirty_pt_masked(struct kvm *kvm, - struct kvm_memory_slot *memslot, - gfn_t offset, unsigned long mask) -{ - kvm_mmu_clear_dirty_pt_masked(kvm, memslot, offset, mask); + /* + * Note, cpu_dirty_logging_count can be changed concurrent with this + * code, but in that case another update request will be made and so + * the guest will never run with a stale PML value. + */ + if (vcpu->kvm->arch.cpu_dirty_logging_count) + secondary_exec_controls_setbit(vmx, SECONDARY_EXEC_ENABLE_PML); + else + secondary_exec_controls_clearbit(vmx, SECONDARY_EXEC_ENABLE_PML); } static int vmx_pre_block(struct kvm_vcpu *vcpu) @@ -7546,7 +7587,7 @@ static int vmx_pre_leave_smm(struct kvm_vcpu *vcpu, const char *smstate) return 0; } -static void enable_smi_window(struct kvm_vcpu *vcpu) +static void vmx_enable_smi_window(struct kvm_vcpu *vcpu) { /* RSM will cause a vmexit anyway. */ } @@ -7582,11 +7623,6 @@ static bool vmx_check_apicv_inhibit_reasons(ulong bit) return supported & BIT(bit); } -static int vmx_cpu_dirty_log_size(void) -{ - return enable_pml ? PML_ENTITY_NUM : 0; -} - static struct kvm_x86_ops vmx_x86_ops __initdata = { .hardware_unsetup = hardware_unsetup, @@ -7606,7 +7642,7 @@ static struct kvm_x86_ops vmx_x86_ops __initdata = { .vcpu_load = vmx_vcpu_load, .vcpu_put = vmx_vcpu_put, - .update_exception_bitmap = update_exception_bitmap, + .update_exception_bitmap = vmx_update_exception_bitmap, .get_msr_feature = vmx_get_msr_feature, .get_msr = vmx_get_msr, .set_msr = vmx_set_msr, @@ -7649,9 +7685,9 @@ static struct kvm_x86_ops vmx_x86_ops __initdata = { .nmi_allowed = vmx_nmi_allowed, .get_nmi_mask = vmx_get_nmi_mask, .set_nmi_mask = vmx_set_nmi_mask, - .enable_nmi_window = enable_nmi_window, - .enable_irq_window = enable_irq_window, - .update_cr8_intercept = update_cr8_intercept, + .enable_nmi_window = vmx_enable_nmi_window, + .enable_irq_window = vmx_enable_irq_window, + .update_cr8_intercept = vmx_update_cr8_intercept, .set_virtual_apic_mode = vmx_set_virtual_apic_mode, .set_apic_access_page_addr = vmx_set_apic_access_page_addr, .refresh_apicv_exec_ctrl = vmx_refresh_apicv_exec_ctrl, @@ -7686,10 +7722,8 @@ static struct kvm_x86_ops vmx_x86_ops __initdata = { .sched_in = vmx_sched_in, - .slot_enable_log_dirty = vmx_slot_enable_log_dirty, - .slot_disable_log_dirty = vmx_slot_disable_log_dirty, - .flush_log_dirty = vmx_flush_log_dirty, - .enable_log_dirty_pt_masked = vmx_enable_log_dirty_pt_masked, + .cpu_dirty_log_size = PML_ENTITY_NUM, + .update_cpu_dirty_logging = vmx_update_cpu_dirty_logging, .pre_block = vmx_pre_block, .post_block = vmx_post_block, @@ -7709,7 +7743,7 @@ static struct kvm_x86_ops vmx_x86_ops __initdata = { .smi_allowed = vmx_smi_allowed, .pre_enter_smm = vmx_pre_enter_smm, .pre_leave_smm = vmx_pre_leave_smm, - .enable_smi_window = enable_smi_window, + .enable_smi_window = vmx_enable_smi_window, .can_emulate_instruction = vmx_can_emulate_instruction, .apic_init_signal_blocked = vmx_apic_init_signal_blocked, @@ -7717,7 +7751,6 @@ static struct kvm_x86_ops vmx_x86_ops __initdata = { .msr_filter_changed = vmx_msr_filter_changed, .complete_emulated_msr = kvm_complete_insn_gp, - .cpu_dirty_log_size = vmx_cpu_dirty_log_size, .vcpu_deliver_sipi_vector = kvm_vcpu_deliver_sipi_vector, }; @@ -7810,6 +7843,8 @@ static __init int hardware_setup(void) kvm_tsc_scaling_ratio_frac_bits = 48; } + kvm_has_bus_lock_exit = cpu_has_vmx_bus_lock_detection(); + set_bit(0, vmx_vpid_bitmap); /* 0 is reserved for host */ if (enable_ept) @@ -7832,13 +7867,8 @@ static __init int hardware_setup(void) if (!enable_ept || !enable_ept_ad_bits || !cpu_has_vmx_pml()) enable_pml = 0; - if (!enable_pml) { - vmx_x86_ops.slot_enable_log_dirty = NULL; - vmx_x86_ops.slot_disable_log_dirty = NULL; - vmx_x86_ops.flush_log_dirty = NULL; - vmx_x86_ops.enable_log_dirty_pt_masked = NULL; - vmx_x86_ops.cpu_dirty_log_size = NULL; - } + if (!enable_pml) + vmx_x86_ops.cpu_dirty_log_size = 0; if (!cpu_has_vmx_preemption_timer()) enable_preemption_timer = false; diff --git a/arch/x86/kvm/vmx/vmx.h b/arch/x86/kvm/vmx/vmx.h index 9d3a557949ac..89da5e1251f1 100644 --- a/arch/x86/kvm/vmx/vmx.h +++ b/arch/x86/kvm/vmx/vmx.h @@ -70,6 +70,54 @@ struct pt_desc { struct pt_ctx guest; }; +union vmx_exit_reason { + struct { + u32 basic : 16; + u32 reserved16 : 1; + u32 reserved17 : 1; + u32 reserved18 : 1; + u32 reserved19 : 1; + u32 reserved20 : 1; + u32 reserved21 : 1; + u32 reserved22 : 1; + u32 reserved23 : 1; + u32 reserved24 : 1; + u32 reserved25 : 1; + u32 bus_lock_detected : 1; + u32 enclave_mode : 1; + u32 smi_pending_mtf : 1; + u32 smi_from_vmx_root : 1; + u32 reserved30 : 1; + u32 failed_vmentry : 1; + }; + u32 full; +}; + +#define vcpu_to_lbr_desc(vcpu) (&to_vmx(vcpu)->lbr_desc) +#define vcpu_to_lbr_records(vcpu) (&to_vmx(vcpu)->lbr_desc.records) + +bool intel_pmu_lbr_is_compatible(struct kvm_vcpu *vcpu); +bool intel_pmu_lbr_is_enabled(struct kvm_vcpu *vcpu); + +int intel_pmu_create_guest_lbr_event(struct kvm_vcpu *vcpu); +void vmx_passthrough_lbr_msrs(struct kvm_vcpu *vcpu); + +struct lbr_desc { + /* Basic info about guest LBR records. */ + struct x86_pmu_lbr records; + + /* + * Emulate LBR feature via passthrough LBR registers when the + * per-vcpu guest LBR event is scheduled on the current pcpu. + * + * The records may be inaccurate if the host reclaims the LBR. + */ + struct perf_event *event; + + /* True if LBRs are marked as not intercepted in the MSR bitmap */ + bool msr_passthrough; +}; + /* * The nested_vmx structure is part of vcpu_vmx, and holds information we need * for correct emulation of VMX (i.e., nested VMX) on this vcpu. @@ -117,6 +165,7 @@ struct nested_vmx { bool change_vmcs01_virtual_apic_mode; bool reload_vmcs01_apic_access_page; + bool update_vmcs01_cpu_dirty_logging; /* * Enlightened VMCS has been enabled. It does not mean that L1 has to @@ -244,7 +293,7 @@ struct vcpu_vmx { int vpid; bool emulation_required; - u32 exit_reason; + union vmx_exit_reason exit_reason; /* Posted interrupt descriptor */ struct pi_desc pi_desc; @@ -279,6 +328,7 @@ struct vcpu_vmx { u64 ept_pointer; struct pt_desc pt_desc; + struct lbr_desc lbr_desc; /* Save desired MSR intercept (read: pass-through) state */ #define MAX_POSSIBLE_PASSTHROUGH_MSRS 13 @@ -329,7 +379,7 @@ void vmx_set_segment(struct kvm_vcpu *vcpu, struct kvm_segment *var, int seg); u64 construct_eptp(struct kvm_vcpu *vcpu, unsigned long root_hpa, int root_level); -void update_exception_bitmap(struct kvm_vcpu *vcpu); +void vmx_update_exception_bitmap(struct kvm_vcpu *vcpu); void vmx_update_msr_bitmap(struct kvm_vcpu *vcpu); bool vmx_nmi_blocked(struct kvm_vcpu *vcpu); bool vmx_interrupt_blocked(struct kvm_vcpu *vcpu); @@ -339,8 +389,12 @@ void vmx_set_virtual_apic_mode(struct kvm_vcpu *vcpu); struct vmx_uret_msr *vmx_find_uret_msr(struct vcpu_vmx *vmx, u32 msr); void pt_update_intercept_for_msr(struct kvm_vcpu *vcpu); void vmx_update_host_rsp(struct vcpu_vmx *vmx, unsigned long host_rsp); +bool __vmx_vcpu_run(struct vcpu_vmx *vmx, unsigned long *regs, bool launched); int vmx_find_loadstore_msr_slot(struct vmx_msrs *m, u32 msr); void vmx_ept_load_pdptrs(struct kvm_vcpu *vcpu); +void vmx_set_intercept_for_msr(struct kvm_vcpu *vcpu, + u32 msr, int type, bool value); +void vmx_update_cpu_dirty_logging(struct kvm_vcpu *vcpu); static inline u8 vmx_get_rvi(void) { diff --git a/arch/x86/kvm/x86.c b/arch/x86/kvm/x86.c index 1b404e4d7dd8..fe806e894212 100644 --- a/arch/x86/kvm/x86.c +++ b/arch/x86/kvm/x86.c @@ -29,6 +29,7 @@ #include "pmu.h" #include "hyperv.h" #include "lapic.h" +#include "xen.h" #include <linux/clocksource.h> #include <linux/interrupt.h> @@ -114,11 +115,21 @@ static int sync_regs(struct kvm_vcpu *vcpu); struct kvm_x86_ops kvm_x86_ops __read_mostly; EXPORT_SYMBOL_GPL(kvm_x86_ops); +#define KVM_X86_OP(func) \ + DEFINE_STATIC_CALL_NULL(kvm_x86_##func, \ + *(((struct kvm_x86_ops *)0)->func)); +#define KVM_X86_OP_NULL KVM_X86_OP +#include <asm/kvm-x86-ops.h> +EXPORT_STATIC_CALL_GPL(kvm_x86_get_cs_db_l_bits); +EXPORT_STATIC_CALL_GPL(kvm_x86_cache_reg); +EXPORT_STATIC_CALL_GPL(kvm_x86_tlb_flush_current); + static bool __read_mostly ignore_msrs = 0; module_param(ignore_msrs, bool, S_IRUGO | S_IWUSR); -static bool __read_mostly report_ignored_msrs = true; +bool __read_mostly report_ignored_msrs = true; module_param(report_ignored_msrs, bool, S_IRUGO | S_IWUSR); +EXPORT_SYMBOL_GPL(report_ignored_msrs); unsigned int min_timer_period_us = 200; module_param(min_timer_period_us, uint, S_IRUGO | S_IWUSR); @@ -136,6 +147,8 @@ u64 __read_mostly kvm_max_tsc_scaling_ratio; EXPORT_SYMBOL_GPL(kvm_max_tsc_scaling_ratio); u64 __read_mostly kvm_default_tsc_scaling_ratio; EXPORT_SYMBOL_GPL(kvm_default_tsc_scaling_ratio); +bool __read_mostly kvm_has_bus_lock_exit; +EXPORT_SYMBOL_GPL(kvm_has_bus_lock_exit); /* tsc tolerance in parts per million - default to 1/2 of the NTP threshold */ static u32 __read_mostly tsc_tolerance_ppm = 250; @@ -234,7 +247,6 @@ struct kvm_stats_debugfs_item debugfs_entries[] = { VCPU_STAT("halt_poll_fail_ns", halt_poll_fail_ns), VM_STAT("mmu_shadow_zapped", mmu_shadow_zapped), VM_STAT("mmu_pte_write", mmu_pte_write), - VM_STAT("mmu_pte_updated", mmu_pte_updated), VM_STAT("mmu_pde_zapped", mmu_pde_zapped), VM_STAT("mmu_flooded", mmu_flooded), VM_STAT("mmu_recycled", mmu_recycled), @@ -395,7 +407,7 @@ int kvm_set_apic_base(struct kvm_vcpu *vcpu, struct msr_data *msr_info) { enum lapic_mode old_mode = kvm_get_apic_mode(vcpu); enum lapic_mode new_mode = kvm_apic_mode(msr_info->data); - u64 reserved_bits = ((~0ULL) << cpuid_maxphyaddr(vcpu)) | 0x2ff | + u64 reserved_bits = kvm_vcpu_reserved_gpa_bits_raw(vcpu) | 0x2ff | (guest_cpuid_has(vcpu, X86_FEATURE_X2APIC) ? 0 : X2APIC_ENABLE); if ((msr_info->data & reserved_bits) != 0 || new_mode == LAPIC_MODE_INVALID) @@ -484,19 +496,24 @@ void kvm_deliver_exception_payload(struct kvm_vcpu *vcpu) */ vcpu->arch.dr6 &= ~DR_TRAP_BITS; /* - * DR6.RTM is set by all #DB exceptions that don't clear it. + * In order to reflect the #DB exception payload in guest + * dr6, three components need to be considered: active low + * bit, FIXED_1 bits and active high bits (e.g. DR6_BD, + * DR6_BS and DR6_BT) + * DR6_ACTIVE_LOW contains the FIXED_1 and active low bits. + * In the target guest dr6: + * FIXED_1 bits should always be set. + * Active low bits should be cleared if 1-setting in payload. + * Active high bits should be set if 1-setting in payload. + * + * Note, the payload is compatible with the pending debug + * exceptions/exit qualification under VMX, that active_low bits + * are active high in payload. + * So they need to be flipped for DR6. */ - vcpu->arch.dr6 |= DR6_RTM; + vcpu->arch.dr6 |= DR6_ACTIVE_LOW; vcpu->arch.dr6 |= payload; - /* - * Bit 16 should be set in the payload whenever the #DB - * exception should clear DR6.RTM. This makes the payload - * compatible with the pending debug exceptions under VMX. - * Though not currently documented in the SDM, this also - * makes the payload compatible with the exit qualification - * for #DB exceptions under VMX. - */ - vcpu->arch.dr6 ^= payload & DR6_RTM; + vcpu->arch.dr6 ^= payload & DR6_ACTIVE_LOW; /* * The #DB payload is defined as compatible with the 'pending @@ -692,7 +709,7 @@ EXPORT_SYMBOL_GPL(kvm_requeue_exception_e); */ bool kvm_require_cpl(struct kvm_vcpu *vcpu, int required_cpl) { - if (kvm_x86_ops.get_cpl(vcpu) <= required_cpl) + if (static_call(kvm_x86_get_cpl)(vcpu) <= required_cpl) return true; kvm_queue_exception_e(vcpu, GP_VECTOR, 0); return false; @@ -742,8 +759,7 @@ static int kvm_read_nested_guest_page(struct kvm_vcpu *vcpu, gfn_t gfn, static inline u64 pdptr_rsvd_bits(struct kvm_vcpu *vcpu) { - return rsvd_bits(cpuid_maxphyaddr(vcpu), 63) | rsvd_bits(5, 8) | - rsvd_bits(1, 2); + return vcpu->arch.reserved_gpa_bits | rsvd_bits(5, 8) | rsvd_bits(1, 2); } /* @@ -852,7 +868,7 @@ int kvm_set_cr0(struct kvm_vcpu *vcpu, unsigned long cr0) if (!is_pae(vcpu)) return 1; - kvm_x86_ops.get_cs_db_l_bits(vcpu, &cs_db, &cs_l); + static_call(kvm_x86_get_cs_db_l_bits)(vcpu, &cs_db, &cs_l); if (cs_l) return 1; } @@ -865,7 +881,7 @@ int kvm_set_cr0(struct kvm_vcpu *vcpu, unsigned long cr0) if (!(cr0 & X86_CR0_PG) && kvm_read_cr4_bits(vcpu, X86_CR4_PCIDE)) return 1; - kvm_x86_ops.set_cr0(vcpu, cr0); + static_call(kvm_x86_set_cr0)(vcpu, cr0); kvm_post_set_cr0(vcpu, old_cr0, cr0); @@ -970,12 +986,10 @@ static int __kvm_set_xcr(struct kvm_vcpu *vcpu, u32 index, u64 xcr) int kvm_set_xcr(struct kvm_vcpu *vcpu, u32 index, u64 xcr) { - if (kvm_x86_ops.get_cpl(vcpu) != 0 || - __kvm_set_xcr(vcpu, index, xcr)) { - kvm_inject_gp(vcpu, 0); - return 1; - } - return 0; + if (static_call(kvm_x86_get_cpl)(vcpu) == 0) + return __kvm_set_xcr(vcpu, index, xcr); + + return 1; } EXPORT_SYMBOL_GPL(kvm_set_xcr); @@ -987,7 +1001,7 @@ bool kvm_is_valid_cr4(struct kvm_vcpu *vcpu, unsigned long cr4) if (cr4 & vcpu->arch.cr4_guest_rsvd_bits) return false; - return kvm_x86_ops.is_valid_cr4(vcpu, cr4); + return static_call(kvm_x86_is_valid_cr4)(vcpu, cr4); } EXPORT_SYMBOL_GPL(kvm_is_valid_cr4); @@ -1031,7 +1045,7 @@ int kvm_set_cr4(struct kvm_vcpu *vcpu, unsigned long cr4) return 1; } - kvm_x86_ops.set_cr4(vcpu, cr4); + static_call(kvm_x86_set_cr4)(vcpu, cr4); kvm_post_set_cr4(vcpu, old_cr4, cr4); @@ -1059,8 +1073,7 @@ int kvm_set_cr3(struct kvm_vcpu *vcpu, unsigned long cr3) return 0; } - if (is_long_mode(vcpu) && - (cr3 & vcpu->arch.cr3_lm_rsvd_bits)) + if (is_long_mode(vcpu) && kvm_vcpu_is_illegal_gpa(vcpu, cr3)) return 1; else if (is_pae_paging(vcpu) && !load_pdptrs(vcpu, vcpu->arch.walk_mmu, cr3)) @@ -1114,7 +1127,7 @@ void kvm_update_dr7(struct kvm_vcpu *vcpu) dr7 = vcpu->arch.guest_debug_dr7; else dr7 = vcpu->arch.dr7; - kvm_x86_ops.set_dr7(vcpu, dr7); + static_call(kvm_x86_set_dr7)(vcpu, dr7); vcpu->arch.switch_db_regs &= ~KVM_DEBUGREG_BP_ENABLED; if (dr7 & DR7_BP_EN_MASK) vcpu->arch.switch_db_regs |= KVM_DEBUGREG_BP_ENABLED; @@ -1130,7 +1143,7 @@ static u64 kvm_dr6_fixed(struct kvm_vcpu *vcpu) return fixed; } -static int __kvm_set_dr(struct kvm_vcpu *vcpu, int dr, unsigned long val) +int kvm_set_dr(struct kvm_vcpu *vcpu, int dr, unsigned long val) { size_t size = ARRAY_SIZE(vcpu->arch.db); @@ -1143,13 +1156,13 @@ static int __kvm_set_dr(struct kvm_vcpu *vcpu, int dr, unsigned long val) case 4: case 6: if (!kvm_dr6_valid(val)) - return -1; /* #GP */ + return 1; /* #GP */ vcpu->arch.dr6 = (val & DR6_VOLATILE) | kvm_dr6_fixed(vcpu); break; case 5: default: /* 7 */ if (!kvm_dr7_valid(val)) - return -1; /* #GP */ + return 1; /* #GP */ vcpu->arch.dr7 = (val & DR7_VOLATILE) | DR7_FIXED_1; kvm_update_dr7(vcpu); break; @@ -1157,18 +1170,9 @@ static int __kvm_set_dr(struct kvm_vcpu *vcpu, int dr, unsigned long val) return 0; } - -int kvm_set_dr(struct kvm_vcpu *vcpu, int dr, unsigned long val) -{ - if (__kvm_set_dr(vcpu, dr, val)) { - kvm_inject_gp(vcpu, 0); - return 1; - } - return 0; -} EXPORT_SYMBOL_GPL(kvm_set_dr); -int kvm_get_dr(struct kvm_vcpu *vcpu, int dr, unsigned long *val) +void kvm_get_dr(struct kvm_vcpu *vcpu, int dr, unsigned long *val) { size_t size = ARRAY_SIZE(vcpu->arch.db); @@ -1185,7 +1189,6 @@ int kvm_get_dr(struct kvm_vcpu *vcpu, int dr, unsigned long *val) *val = vcpu->arch.dr7; break; } - return 0; } EXPORT_SYMBOL_GPL(kvm_get_dr); @@ -1426,7 +1429,7 @@ static int kvm_get_msr_feature(struct kvm_msr_entry *msr) rdmsrl_safe(msr->index, &msr->data); break; default: - return kvm_x86_ops.get_msr_feature(msr); + return static_call(kvm_x86_get_msr_feature)(msr); } return 0; } @@ -1502,7 +1505,7 @@ static int set_efer(struct kvm_vcpu *vcpu, struct msr_data *msr_info) efer &= ~EFER_LMA; efer |= vcpu->arch.efer & EFER_LMA; - r = kvm_x86_ops.set_efer(vcpu, efer); + r = static_call(kvm_x86_set_efer)(vcpu, efer); if (r) { WARN_ON(r > 0); return r; @@ -1523,35 +1526,44 @@ EXPORT_SYMBOL_GPL(kvm_enable_efer_bits); bool kvm_msr_allowed(struct kvm_vcpu *vcpu, u32 index, u32 type) { + struct kvm_x86_msr_filter *msr_filter; + struct msr_bitmap_range *ranges; struct kvm *kvm = vcpu->kvm; - struct msr_bitmap_range *ranges = kvm->arch.msr_filter.ranges; - u32 count = kvm->arch.msr_filter.count; - u32 i; - bool r = kvm->arch.msr_filter.default_allow; + bool allowed; int idx; + u32 i; - /* MSR filtering not set up or x2APIC enabled, allow everything */ - if (!count || (index >= 0x800 && index <= 0x8ff)) + /* x2APIC MSRs do not support filtering. */ + if (index >= 0x800 && index <= 0x8ff) return true; - /* Prevent collision with set_msr_filter */ idx = srcu_read_lock(&kvm->srcu); - for (i = 0; i < count; i++) { + msr_filter = srcu_dereference(kvm->arch.msr_filter, &kvm->srcu); + if (!msr_filter) { + allowed = true; + goto out; + } + + allowed = msr_filter->default_allow; + ranges = msr_filter->ranges; + + for (i = 0; i < msr_filter->count; i++) { u32 start = ranges[i].base; u32 end = start + ranges[i].nmsrs; u32 flags = ranges[i].flags; unsigned long *bitmap = ranges[i].bitmap; if ((index >= start) && (index < end) && (flags & type)) { - r = !!test_bit(index - start, bitmap); + allowed = !!test_bit(index - start, bitmap); break; } } +out: srcu_read_unlock(&kvm->srcu, idx); - return r; + return allowed; } EXPORT_SYMBOL_GPL(kvm_msr_allowed); @@ -1599,7 +1611,7 @@ static int __kvm_set_msr(struct kvm_vcpu *vcpu, u32 index, u64 data, msr.index = index; msr.host_initiated = host_initiated; - return kvm_x86_ops.set_msr(vcpu, &msr); + return static_call(kvm_x86_set_msr)(vcpu, &msr); } static int kvm_set_msr_ignored_check(struct kvm_vcpu *vcpu, @@ -1632,7 +1644,7 @@ int __kvm_get_msr(struct kvm_vcpu *vcpu, u32 index, u64 *data, msr.index = index; msr.host_initiated = host_initiated; - ret = kvm_x86_ops.get_msr(vcpu, &msr); + ret = static_call(kvm_x86_get_msr)(vcpu, &msr); if (!ret) *data = msr.data; return ret; @@ -1673,12 +1685,12 @@ static int complete_emulated_rdmsr(struct kvm_vcpu *vcpu) kvm_rdx_write(vcpu, vcpu->run->msr.data >> 32); } - return kvm_x86_ops.complete_emulated_msr(vcpu, err); + return static_call(kvm_x86_complete_emulated_msr)(vcpu, err); } static int complete_emulated_wrmsr(struct kvm_vcpu *vcpu) { - return kvm_x86_ops.complete_emulated_msr(vcpu, vcpu->run->msr.error); + return static_call(kvm_x86_complete_emulated_msr)(vcpu, vcpu->run->msr.error); } static u64 kvm_msr_reason(int r) @@ -1750,7 +1762,7 @@ int kvm_emulate_rdmsr(struct kvm_vcpu *vcpu) trace_kvm_msr_read_ex(ecx); } - return kvm_x86_ops.complete_emulated_msr(vcpu, r); + return static_call(kvm_x86_complete_emulated_msr)(vcpu, r); } EXPORT_SYMBOL_GPL(kvm_emulate_rdmsr); @@ -1776,16 +1788,16 @@ int kvm_emulate_wrmsr(struct kvm_vcpu *vcpu) else trace_kvm_msr_write_ex(ecx, data); - return kvm_x86_ops.complete_emulated_msr(vcpu, r); + return static_call(kvm_x86_complete_emulated_msr)(vcpu, r); } EXPORT_SYMBOL_GPL(kvm_emulate_wrmsr); -bool kvm_vcpu_exit_request(struct kvm_vcpu *vcpu) +static inline bool kvm_vcpu_exit_request(struct kvm_vcpu *vcpu) { + xfer_to_guest_mode_prepare(); return vcpu->mode == EXITING_GUEST_MODE || kvm_request_pending(vcpu) || xfer_to_guest_mode_work_pending(); } -EXPORT_SYMBOL_GPL(kvm_vcpu_exit_request); /* * The fast path for frequent and performance sensitive wrmsr emulation, @@ -1935,15 +1947,14 @@ static s64 get_kvmclock_base_ns(void) } #endif -static void kvm_write_wall_clock(struct kvm *kvm, gpa_t wall_clock) +void kvm_write_wall_clock(struct kvm *kvm, gpa_t wall_clock, int sec_hi_ofs) { int version; int r; struct pvclock_wall_clock wc; + u32 wc_sec_hi; u64 wall_nsec; - kvm->arch.wall_clock = wall_clock; - if (!wall_clock) return; @@ -1972,6 +1983,12 @@ static void kvm_write_wall_clock(struct kvm *kvm, gpa_t wall_clock) kvm_write_guest(kvm, wall_clock, &wc, sizeof(wc)); + if (sec_hi_ofs) { + wc_sec_hi = wall_nsec >> 32; + kvm_write_guest(kvm, wall_clock + sec_hi_ofs, + &wc_sec_hi, sizeof(wc_sec_hi)); + } + version++; kvm_write_guest(kvm, wall_clock, &version, sizeof(version)); } @@ -2208,7 +2225,7 @@ EXPORT_SYMBOL_GPL(kvm_read_l1_tsc); static void kvm_vcpu_write_tsc_offset(struct kvm_vcpu *vcpu, u64 offset) { vcpu->arch.l1_tsc_offset = offset; - vcpu->arch.tsc_offset = kvm_x86_ops.write_l1_tsc_offset(vcpu, offset); + vcpu->arch.tsc_offset = static_call(kvm_x86_write_l1_tsc_offset)(vcpu, offset); } static inline bool kvm_check_tsc_unstable(void) @@ -2543,6 +2560,8 @@ static void kvm_gen_update_masterclock(struct kvm *kvm) struct kvm_vcpu *vcpu; struct kvm_arch *ka = &kvm->arch; + kvm_hv_invalidate_tsc_page(kvm); + spin_lock(&ka->pvclock_gtod_sync_lock); kvm_make_mclock_inprogress_request(kvm); /* no guest entries from this point */ @@ -2591,13 +2610,15 @@ u64 get_kvmclock_ns(struct kvm *kvm) return ret; } -static void kvm_setup_pvclock_page(struct kvm_vcpu *v) +static void kvm_setup_pvclock_page(struct kvm_vcpu *v, + struct gfn_to_hva_cache *cache, + unsigned int offset) { struct kvm_vcpu_arch *vcpu = &v->arch; struct pvclock_vcpu_time_info guest_hv_clock; - if (unlikely(kvm_read_guest_cached(v->kvm, &vcpu->pv_time, - &guest_hv_clock, sizeof(guest_hv_clock)))) + if (unlikely(kvm_read_guest_offset_cached(v->kvm, cache, + &guest_hv_clock, offset, sizeof(guest_hv_clock)))) return; /* This VCPU is paused, but it's legal for a guest to read another @@ -2620,9 +2641,9 @@ static void kvm_setup_pvclock_page(struct kvm_vcpu *v) ++guest_hv_clock.version; /* first time write, random junk */ vcpu->hv_clock.version = guest_hv_clock.version + 1; - kvm_write_guest_cached(v->kvm, &vcpu->pv_time, - &vcpu->hv_clock, - sizeof(vcpu->hv_clock.version)); + kvm_write_guest_offset_cached(v->kvm, cache, + &vcpu->hv_clock, offset, + sizeof(vcpu->hv_clock.version)); smp_wmb(); @@ -2636,16 +2657,16 @@ static void kvm_setup_pvclock_page(struct kvm_vcpu *v) trace_kvm_pvclock_update(v->vcpu_id, &vcpu->hv_clock); - kvm_write_guest_cached(v->kvm, &vcpu->pv_time, - &vcpu->hv_clock, - sizeof(vcpu->hv_clock)); + kvm_write_guest_offset_cached(v->kvm, cache, + &vcpu->hv_clock, offset, + sizeof(vcpu->hv_clock)); smp_wmb(); vcpu->hv_clock.version++; - kvm_write_guest_cached(v->kvm, &vcpu->pv_time, - &vcpu->hv_clock, - sizeof(vcpu->hv_clock.version)); + kvm_write_guest_offset_cached(v->kvm, cache, + &vcpu->hv_clock, offset, + sizeof(vcpu->hv_clock.version)); } static int kvm_guest_time_update(struct kvm_vcpu *v) @@ -2732,7 +2753,12 @@ static int kvm_guest_time_update(struct kvm_vcpu *v) vcpu->hv_clock.flags = pvclock_flags; if (vcpu->pv_time_enabled) - kvm_setup_pvclock_page(v); + kvm_setup_pvclock_page(v, &vcpu->pv_time, 0); + if (vcpu->xen.vcpu_info_set) + kvm_setup_pvclock_page(v, &vcpu->xen.vcpu_info_cache, + offsetof(struct compat_vcpu_info, time)); + if (vcpu->xen.vcpu_time_info_set) + kvm_setup_pvclock_page(v, &vcpu->xen.vcpu_time_info_cache, 0); if (v == kvm_get_vcpu(v->kvm, 0)) kvm_hv_setup_tsc_page(v->kvm, &vcpu->hv_clock); return 0; @@ -2857,32 +2883,6 @@ static int set_msr_mce(struct kvm_vcpu *vcpu, struct msr_data *msr_info) return 0; } -static int xen_hvm_config(struct kvm_vcpu *vcpu, u64 data) -{ - struct kvm *kvm = vcpu->kvm; - int lm = is_long_mode(vcpu); - u8 *blob_addr = lm ? (u8 *)(long)kvm->arch.xen_hvm_config.blob_addr_64 - : (u8 *)(long)kvm->arch.xen_hvm_config.blob_addr_32; - u8 blob_size = lm ? kvm->arch.xen_hvm_config.blob_size_64 - : kvm->arch.xen_hvm_config.blob_size_32; - u32 page_num = data & ~PAGE_MASK; - u64 page_addr = data & PAGE_MASK; - u8 *page; - - if (page_num >= blob_size) - return 1; - - page = memdup_user(blob_addr + (page_num * PAGE_SIZE), PAGE_SIZE); - if (IS_ERR(page)) - return PTR_ERR(page); - - if (kvm_vcpu_write_guest(vcpu, page_addr, page, PAGE_SIZE)) { - kfree(page); - return 1; - } - return 0; -} - static inline bool kvm_pv_async_pf_enabled(struct kvm_vcpu *vcpu) { u64 mask = KVM_ASYNC_PF_ENABLED | KVM_ASYNC_PF_DELIVERY_AS_INT; @@ -2954,13 +2954,13 @@ static void kvmclock_reset(struct kvm_vcpu *vcpu) static void kvm_vcpu_flush_tlb_all(struct kvm_vcpu *vcpu) { ++vcpu->stat.tlb_flush; - kvm_x86_ops.tlb_flush_all(vcpu); + static_call(kvm_x86_tlb_flush_all)(vcpu); } static void kvm_vcpu_flush_tlb_guest(struct kvm_vcpu *vcpu) { ++vcpu->stat.tlb_flush; - kvm_x86_ops.tlb_flush_guest(vcpu); + static_call(kvm_x86_tlb_flush_guest)(vcpu); } static void record_steal_time(struct kvm_vcpu *vcpu) @@ -2968,6 +2968,11 @@ static void record_steal_time(struct kvm_vcpu *vcpu) struct kvm_host_map map; struct kvm_steal_time *st; + if (kvm_xen_msr_enabled(vcpu->kvm)) { + kvm_xen_runstate_set_running(vcpu); + return; + } + if (!(vcpu->arch.st.msr_val & KVM_MSR_ENABLED)) return; @@ -3016,6 +3021,9 @@ int kvm_set_msr_common(struct kvm_vcpu *vcpu, struct msr_data *msr_info) u32 msr = msr_info->index; u64 data = msr_info->data; + if (msr && msr == vcpu->kvm->arch.xen_hvm_config.msr) + return kvm_xen_write_hypercall_page(vcpu, data); + switch (msr) { case MSR_AMD64_NB_CFG: case MSR_IA32_UCODE_WRITE: @@ -3072,18 +3080,6 @@ int kvm_set_msr_common(struct kvm_vcpu *vcpu, struct msr_data *msr_info) return 1; } break; - case MSR_IA32_DEBUGCTLMSR: - if (!data) { - /* We support the non-activated case already */ - break; - } else if (data & ~(DEBUGCTLMSR_LBR | DEBUGCTLMSR_BTF)) { - /* Values other than LBR and BTF are vendor-specific, - thus reserved and should throw a #GP */ - return 1; - } else if (report_ignored_msrs) - vcpu_unimpl(vcpu, "%s: MSR_IA32_DEBUGCTLMSR 0x%llx, nop\n", - __func__, data); - break; case 0x200 ... 0x2ff: return kvm_mtrr_set_msr(vcpu, msr, data); case MSR_IA32_APICBASE: @@ -3152,13 +3148,15 @@ int kvm_set_msr_common(struct kvm_vcpu *vcpu, struct msr_data *msr_info) if (!guest_pv_has(vcpu, KVM_FEATURE_CLOCKSOURCE2)) return 1; - kvm_write_wall_clock(vcpu->kvm, data); + vcpu->kvm->arch.wall_clock = data; + kvm_write_wall_clock(vcpu->kvm, data, 0); break; case MSR_KVM_WALL_CLOCK: if (!guest_pv_has(vcpu, KVM_FEATURE_CLOCKSOURCE)) return 1; - kvm_write_wall_clock(vcpu->kvm, data); + vcpu->kvm->arch.wall_clock = data; + kvm_write_wall_clock(vcpu->kvm, data, 0); break; case MSR_KVM_SYSTEM_TIME_NEW: if (!guest_pv_has(vcpu, KVM_FEATURE_CLOCKSOURCE2)) @@ -3303,8 +3301,6 @@ int kvm_set_msr_common(struct kvm_vcpu *vcpu, struct msr_data *msr_info) vcpu->arch.msr_misc_features_enables = data; break; default: - if (msr && (msr == vcpu->kvm->arch.xen_hvm_config.msr)) - return xen_hvm_config(vcpu, data); if (kvm_pmu_is_valid_msr(vcpu, msr)) return kvm_pmu_set_msr(vcpu, msr_info); return KVM_MSR_RET_INVALID; @@ -3356,7 +3352,6 @@ int kvm_get_msr_common(struct kvm_vcpu *vcpu, struct msr_data *msr_info) switch (msr_info->index) { case MSR_IA32_PLATFORM_ID: case MSR_IA32_EBL_CR_POWERON: - case MSR_IA32_DEBUGCTLMSR: case MSR_IA32_LASTBRANCHFROMIP: case MSR_IA32_LASTBRANCHTOIP: case MSR_IA32_LASTINTFROMIP: @@ -3738,7 +3733,6 @@ int kvm_vm_ioctl_check_extension(struct kvm *kvm, long ext) case KVM_CAP_PIT2: case KVM_CAP_PIT_STATE2: case KVM_CAP_SET_IDENTITY_MAP_ADDR: - case KVM_CAP_XEN_HVM: case KVM_CAP_VCPU_EVENTS: case KVM_CAP_HYPERV: case KVM_CAP_HYPERV_VAPIC: @@ -3778,6 +3772,15 @@ int kvm_vm_ioctl_check_extension(struct kvm *kvm, long ext) case KVM_CAP_ENFORCE_PV_FEATURE_CPUID: r = 1; break; +#ifdef CONFIG_KVM_XEN + case KVM_CAP_XEN_HVM: + r = KVM_XEN_HVM_CONFIG_HYPERCALL_MSR | + KVM_XEN_HVM_CONFIG_INTERCEPT_HCALL | + KVM_XEN_HVM_CONFIG_SHARED_INFO; + if (sched_info_on()) + r |= KVM_XEN_HVM_CONFIG_RUNSTATE; + break; +#endif case KVM_CAP_SYNC_REGS: r = KVM_SYNC_X86_VALID_FIELDS; break; @@ -3799,10 +3802,10 @@ int kvm_vm_ioctl_check_extension(struct kvm *kvm, long ext) * fringe case that is not enabled except via specific settings * of the module parameters. */ - r = kvm_x86_ops.has_emulated_msr(kvm, MSR_IA32_SMBASE); + r = static_call(kvm_x86_has_emulated_msr)(kvm, MSR_IA32_SMBASE); break; case KVM_CAP_VAPIC: - r = !kvm_x86_ops.cpu_has_accelerated_tpr(); + r = !static_call(kvm_x86_cpu_has_accelerated_tpr)(); break; case KVM_CAP_NR_VCPUS: r = KVM_SOFT_MAX_VCPUS; @@ -3844,6 +3847,13 @@ int kvm_vm_ioctl_check_extension(struct kvm *kvm, long ext) case KVM_CAP_STEAL_TIME: r = sched_info_on(); break; + case KVM_CAP_X86_BUS_LOCK_EXIT: + if (kvm_has_bus_lock_exit) + r = KVM_BUS_LOCK_DETECTION_OFF | + KVM_BUS_LOCK_DETECTION_EXIT; + else + r = 0; + break; default: break; } @@ -3961,14 +3971,14 @@ void kvm_arch_vcpu_load(struct kvm_vcpu *vcpu, int cpu) { /* Address WBINVD may be executed by guest */ if (need_emulate_wbinvd(vcpu)) { - if (kvm_x86_ops.has_wbinvd_exit()) + if (static_call(kvm_x86_has_wbinvd_exit)()) cpumask_set_cpu(cpu, vcpu->arch.wbinvd_dirty_mask); else if (vcpu->cpu != -1 && vcpu->cpu != cpu) smp_call_function_single(vcpu->cpu, wbinvd_ipi, NULL, 1); } - kvm_x86_ops.vcpu_load(vcpu, cpu); + static_call(kvm_x86_vcpu_load)(vcpu, cpu); /* Save host pkru register if supported */ vcpu->arch.host_pkru = read_pkru(); @@ -4014,6 +4024,7 @@ static void kvm_steal_time_set_preempted(struct kvm_vcpu *vcpu) { struct kvm_host_map map; struct kvm_steal_time *st; + int idx; if (!(vcpu->arch.st.msr_val & KVM_MSR_ENABLED)) return; @@ -4021,9 +4032,15 @@ static void kvm_steal_time_set_preempted(struct kvm_vcpu *vcpu) if (vcpu->arch.st.preempted) return; + /* + * Take the srcu lock as memslots will be accessed to check the gfn + * cache generation against the memslots generation. + */ + idx = srcu_read_lock(&vcpu->kvm->srcu); + if (kvm_map_gfn(vcpu, vcpu->arch.st.msr_val >> PAGE_SHIFT, &map, &vcpu->arch.st.cache, true)) - return; + goto out; st = map.hva + offset_in_page(vcpu->arch.st.msr_val & KVM_STEAL_VALID_BITS); @@ -4031,33 +4048,22 @@ static void kvm_steal_time_set_preempted(struct kvm_vcpu *vcpu) st->preempted = vcpu->arch.st.preempted = KVM_VCPU_PREEMPTED; kvm_unmap_gfn(vcpu, &map, &vcpu->arch.st.cache, true, true); + +out: + srcu_read_unlock(&vcpu->kvm->srcu, idx); } void kvm_arch_vcpu_put(struct kvm_vcpu *vcpu) { - int idx; - if (vcpu->preempted && !vcpu->arch.guest_state_protected) - vcpu->arch.preempted_in_kernel = !kvm_x86_ops.get_cpl(vcpu); + vcpu->arch.preempted_in_kernel = !static_call(kvm_x86_get_cpl)(vcpu); - /* - * Disable page faults because we're in atomic context here. - * kvm_write_guest_offset_cached() would call might_fault() - * that relies on pagefault_disable() to tell if there's a - * bug. NOTE: the write to guest memory may not go through if - * during postcopy live migration or if there's heavy guest - * paging. - */ - pagefault_disable(); - /* - * kvm_memslots() will be called by - * kvm_write_guest_offset_cached() so take the srcu lock. - */ - idx = srcu_read_lock(&vcpu->kvm->srcu); - kvm_steal_time_set_preempted(vcpu); - srcu_read_unlock(&vcpu->kvm->srcu, idx); - pagefault_enable(); - kvm_x86_ops.vcpu_put(vcpu); + if (kvm_xen_msr_enabled(vcpu->kvm)) + kvm_xen_runstate_set_preempted(vcpu); + else + kvm_steal_time_set_preempted(vcpu); + + static_call(kvm_x86_vcpu_put)(vcpu); vcpu->arch.last_host_tsc = rdtsc(); /* * If userspace has set any breakpoints or watchpoints, dr6 is restored @@ -4071,7 +4077,7 @@ static int kvm_vcpu_ioctl_get_lapic(struct kvm_vcpu *vcpu, struct kvm_lapic_state *s) { if (vcpu->arch.apicv_active) - kvm_x86_ops.sync_pir_to_irr(vcpu); + static_call(kvm_x86_sync_pir_to_irr)(vcpu); return kvm_apic_get_state(vcpu, s); } @@ -4181,7 +4187,7 @@ static int kvm_vcpu_ioctl_x86_setup_mce(struct kvm_vcpu *vcpu, for (bank = 0; bank < bank_num; bank++) vcpu->arch.mce_banks[bank*4] = ~(u64)0; - kvm_x86_ops.setup_mce(vcpu); + static_call(kvm_x86_setup_mce)(vcpu); out: return r; } @@ -4288,11 +4294,11 @@ static void kvm_vcpu_ioctl_x86_get_vcpu_events(struct kvm_vcpu *vcpu, vcpu->arch.interrupt.injected && !vcpu->arch.interrupt.soft; events->interrupt.nr = vcpu->arch.interrupt.nr; events->interrupt.soft = 0; - events->interrupt.shadow = kvm_x86_ops.get_interrupt_shadow(vcpu); + events->interrupt.shadow = static_call(kvm_x86_get_interrupt_shadow)(vcpu); events->nmi.injected = vcpu->arch.nmi_injected; events->nmi.pending = vcpu->arch.nmi_pending != 0; - events->nmi.masked = kvm_x86_ops.get_nmi_mask(vcpu); + events->nmi.masked = static_call(kvm_x86_get_nmi_mask)(vcpu); events->nmi.pad = 0; events->sipi_vector = 0; /* never valid when reporting to user space */ @@ -4359,13 +4365,13 @@ static int kvm_vcpu_ioctl_x86_set_vcpu_events(struct kvm_vcpu *vcpu, vcpu->arch.interrupt.nr = events->interrupt.nr; vcpu->arch.interrupt.soft = events->interrupt.soft; if (events->flags & KVM_VCPUEVENT_VALID_SHADOW) - kvm_x86_ops.set_interrupt_shadow(vcpu, - events->interrupt.shadow); + static_call(kvm_x86_set_interrupt_shadow)(vcpu, + events->interrupt.shadow); vcpu->arch.nmi_injected = events->nmi.injected; if (events->flags & KVM_VCPUEVENT_VALID_NMI_PENDING) vcpu->arch.nmi_pending = events->nmi.pending; - kvm_x86_ops.set_nmi_mask(vcpu, events->nmi.masked); + static_call(kvm_x86_set_nmi_mask)(vcpu, events->nmi.masked); if (events->flags & KVM_VCPUEVENT_VALID_SIPI_VECTOR && lapic_in_kernel(vcpu)) @@ -4421,9 +4427,9 @@ static int kvm_vcpu_ioctl_x86_set_debugregs(struct kvm_vcpu *vcpu, if (dbgregs->flags) return -EINVAL; - if (dbgregs->dr6 & ~0xffffffffull) + if (!kvm_dr6_valid(dbgregs->dr6)) return -EINVAL; - if (dbgregs->dr7 & ~0xffffffffull) + if (!kvm_dr7_valid(dbgregs->dr7)) return -EINVAL; memcpy(vcpu->arch.db, dbgregs->db, sizeof(vcpu->arch.db)); @@ -4660,7 +4666,7 @@ static int kvm_vcpu_ioctl_enable_cap(struct kvm_vcpu *vcpu, if (!kvm_x86_ops.enable_direct_tlbflush) return -ENOTTY; - return kvm_x86_ops.enable_direct_tlbflush(vcpu); + return static_call(kvm_x86_enable_direct_tlbflush)(vcpu); case KVM_CAP_ENFORCE_PV_FEATURE_CPUID: vcpu->arch.pv_cpuid.enforce = cap->args[0]; @@ -5031,6 +5037,28 @@ long kvm_arch_vcpu_ioctl(struct file *filp, case KVM_GET_SUPPORTED_HV_CPUID: r = kvm_ioctl_get_supported_hv_cpuid(vcpu, argp); break; +#ifdef CONFIG_KVM_XEN + case KVM_XEN_VCPU_GET_ATTR: { + struct kvm_xen_vcpu_attr xva; + + r = -EFAULT; + if (copy_from_user(&xva, argp, sizeof(xva))) + goto out; + r = kvm_xen_vcpu_get_attr(vcpu, &xva); + if (!r && copy_to_user(argp, &xva, sizeof(xva))) + r = -EFAULT; + break; + } + case KVM_XEN_VCPU_SET_ATTR: { + struct kvm_xen_vcpu_attr xva; + + r = -EFAULT; + if (copy_from_user(&xva, argp, sizeof(xva))) + goto out; + r = kvm_xen_vcpu_set_attr(vcpu, &xva); + break; + } +#endif default: r = -EINVAL; } @@ -5052,14 +5080,14 @@ static int kvm_vm_ioctl_set_tss_addr(struct kvm *kvm, unsigned long addr) if (addr > (unsigned int)(-3 * PAGE_SIZE)) return -EINVAL; - ret = kvm_x86_ops.set_tss_addr(kvm, addr); + ret = static_call(kvm_x86_set_tss_addr)(kvm, addr); return ret; } static int kvm_vm_ioctl_set_identity_map_addr(struct kvm *kvm, u64 ident_addr) { - return kvm_x86_ops.set_identity_map_addr(kvm, ident_addr); + return static_call(kvm_x86_set_identity_map_addr)(kvm, ident_addr); } static int kvm_vm_ioctl_set_nr_mmu_pages(struct kvm *kvm, @@ -5213,11 +5241,18 @@ static int kvm_vm_ioctl_reinject(struct kvm *kvm, void kvm_arch_sync_dirty_log(struct kvm *kvm, struct kvm_memory_slot *memslot) { + /* - * Flush potentially hardware-cached dirty pages to dirty_bitmap. + * Flush all CPUs' dirty log buffers to the dirty_bitmap. Called + * before reporting dirty_bitmap to userspace. KVM flushes the buffers + * on all VM-Exits, thus we only need to kick running vCPUs to force a + * VM-Exit. */ - if (kvm_x86_ops.flush_log_dirty) - kvm_x86_ops.flush_log_dirty(kvm); + struct kvm_vcpu *vcpu; + int i; + + kvm_for_each_vcpu(i, vcpu, kvm) + kvm_vcpu_kick(vcpu); } int kvm_vm_ioctl_irq_line(struct kvm *kvm, struct kvm_irq_level *irq_event, @@ -5307,6 +5342,20 @@ split_irqchip_unlock: kvm->arch.user_space_msr_mask = cap->args[0]; r = 0; break; + case KVM_CAP_X86_BUS_LOCK_EXIT: + r = -EINVAL; + if (cap->args[0] & ~KVM_BUS_LOCK_DETECTION_VALID_MODE) + break; + + if ((cap->args[0] & KVM_BUS_LOCK_DETECTION_OFF) && + (cap->args[0] & KVM_BUS_LOCK_DETECTION_EXIT)) + break; + + if (kvm_has_bus_lock_exit && + cap->args[0] & KVM_BUS_LOCK_DETECTION_EXIT) + kvm->arch.bus_lock_detection_enabled = true; + r = 0; + break; default: r = -EINVAL; break; @@ -5314,25 +5363,34 @@ split_irqchip_unlock: return r; } -static void kvm_clear_msr_filter(struct kvm *kvm) +static struct kvm_x86_msr_filter *kvm_alloc_msr_filter(bool default_allow) +{ + struct kvm_x86_msr_filter *msr_filter; + + msr_filter = kzalloc(sizeof(*msr_filter), GFP_KERNEL_ACCOUNT); + if (!msr_filter) + return NULL; + + msr_filter->default_allow = default_allow; + return msr_filter; +} + +static void kvm_free_msr_filter(struct kvm_x86_msr_filter *msr_filter) { u32 i; - u32 count = kvm->arch.msr_filter.count; - struct msr_bitmap_range ranges[16]; - mutex_lock(&kvm->lock); - kvm->arch.msr_filter.count = 0; - memcpy(ranges, kvm->arch.msr_filter.ranges, count * sizeof(ranges[0])); - mutex_unlock(&kvm->lock); - synchronize_srcu(&kvm->srcu); + if (!msr_filter) + return; + + for (i = 0; i < msr_filter->count; i++) + kfree(msr_filter->ranges[i].bitmap); - for (i = 0; i < count; i++) - kfree(ranges[i].bitmap); + kfree(msr_filter); } -static int kvm_add_msr_filter(struct kvm *kvm, struct kvm_msr_filter_range *user_range) +static int kvm_add_msr_filter(struct kvm_x86_msr_filter *msr_filter, + struct kvm_msr_filter_range *user_range) { - struct msr_bitmap_range *ranges = kvm->arch.msr_filter.ranges; struct msr_bitmap_range range; unsigned long *bitmap = NULL; size_t bitmap_size; @@ -5366,11 +5424,9 @@ static int kvm_add_msr_filter(struct kvm *kvm, struct kvm_msr_filter_range *user goto err; } - /* Everything ok, add this range identifier to our global pool */ - ranges[kvm->arch.msr_filter.count] = range; - /* Make sure we filled the array before we tell anyone to walk it */ - smp_wmb(); - kvm->arch.msr_filter.count++; + /* Everything ok, add this range identifier. */ + msr_filter->ranges[msr_filter->count] = range; + msr_filter->count++; return 0; err: @@ -5381,10 +5437,11 @@ err: static int kvm_vm_ioctl_set_msr_filter(struct kvm *kvm, void __user *argp) { struct kvm_msr_filter __user *user_msr_filter = argp; + struct kvm_x86_msr_filter *new_filter, *old_filter; struct kvm_msr_filter filter; bool default_allow; - int r = 0; bool empty = true; + int r = 0; u32 i; if (copy_from_user(&filter, user_msr_filter, sizeof(filter))) @@ -5397,25 +5454,32 @@ static int kvm_vm_ioctl_set_msr_filter(struct kvm *kvm, void __user *argp) if (empty && !default_allow) return -EINVAL; - kvm_clear_msr_filter(kvm); + new_filter = kvm_alloc_msr_filter(default_allow); + if (!new_filter) + return -ENOMEM; - kvm->arch.msr_filter.default_allow = default_allow; - - /* - * Protect from concurrent calls to this function that could trigger - * a TOCTOU violation on kvm->arch.msr_filter.count. - */ - mutex_lock(&kvm->lock); for (i = 0; i < ARRAY_SIZE(filter.ranges); i++) { - r = kvm_add_msr_filter(kvm, &filter.ranges[i]); - if (r) - break; + r = kvm_add_msr_filter(new_filter, &filter.ranges[i]); + if (r) { + kvm_free_msr_filter(new_filter); + return r; + } } + mutex_lock(&kvm->lock); + + /* The per-VM filter is protected by kvm->lock... */ + old_filter = srcu_dereference_check(kvm->arch.msr_filter, &kvm->srcu, 1); + + rcu_assign_pointer(kvm->arch.msr_filter, new_filter); + synchronize_srcu(&kvm->srcu); + + kvm_free_msr_filter(old_filter); + kvm_make_all_cpus_request(kvm, KVM_REQ_MSR_FILTER_CHANGED); mutex_unlock(&kvm->lock); - return r; + return 0; } long kvm_arch_vm_ioctl(struct file *filp, @@ -5631,18 +5695,36 @@ set_pit2_out: kvm->arch.bsp_vcpu_id = arg; mutex_unlock(&kvm->lock); break; +#ifdef CONFIG_KVM_XEN case KVM_XEN_HVM_CONFIG: { struct kvm_xen_hvm_config xhc; r = -EFAULT; if (copy_from_user(&xhc, argp, sizeof(xhc))) goto out; - r = -EINVAL; - if (xhc.flags) + r = kvm_xen_hvm_config(kvm, &xhc); + break; + } + case KVM_XEN_HVM_GET_ATTR: { + struct kvm_xen_hvm_attr xha; + + r = -EFAULT; + if (copy_from_user(&xha, argp, sizeof(xha))) goto out; - memcpy(&kvm->arch.xen_hvm_config, &xhc, sizeof(xhc)); - r = 0; + r = kvm_xen_hvm_get_attr(kvm, &xha); + if (!r && copy_to_user(argp, &xha, sizeof(xha))) + r = -EFAULT; + break; + } + case KVM_XEN_HVM_SET_ATTR: { + struct kvm_xen_hvm_attr xha; + + r = -EFAULT; + if (copy_from_user(&xha, argp, sizeof(xha))) + goto out; + r = kvm_xen_hvm_set_attr(kvm, &xha); break; } +#endif case KVM_SET_CLOCK: { struct kvm_clock_data user_ns; u64 now_ns; @@ -5685,7 +5767,7 @@ set_pit2_out: case KVM_MEMORY_ENCRYPT_OP: { r = -ENOTTY; if (kvm_x86_ops.mem_enc_op) - r = kvm_x86_ops.mem_enc_op(kvm, argp); + r = static_call(kvm_x86_mem_enc_op)(kvm, argp); break; } case KVM_MEMORY_ENCRYPT_REG_REGION: { @@ -5697,7 +5779,7 @@ set_pit2_out: r = -ENOTTY; if (kvm_x86_ops.mem_enc_reg_region) - r = kvm_x86_ops.mem_enc_reg_region(kvm, ®ion); + r = static_call(kvm_x86_mem_enc_reg_region)(kvm, ®ion); break; } case KVM_MEMORY_ENCRYPT_UNREG_REGION: { @@ -5709,7 +5791,7 @@ set_pit2_out: r = -ENOTTY; if (kvm_x86_ops.mem_enc_unreg_region) - r = kvm_x86_ops.mem_enc_unreg_region(kvm, ®ion); + r = static_call(kvm_x86_mem_enc_unreg_region)(kvm, ®ion); break; } case KVM_HYPERV_EVENTFD: { @@ -5811,7 +5893,7 @@ static void kvm_init_msr_list(void) } for (i = 0; i < ARRAY_SIZE(emulated_msrs_all); i++) { - if (!kvm_x86_ops.has_emulated_msr(NULL, emulated_msrs_all[i])) + if (!static_call(kvm_x86_has_emulated_msr)(NULL, emulated_msrs_all[i])) continue; emulated_msrs[num_emulated_msrs++] = emulated_msrs_all[i]; @@ -5874,13 +5956,13 @@ static int vcpu_mmio_read(struct kvm_vcpu *vcpu, gpa_t addr, int len, void *v) static void kvm_set_segment(struct kvm_vcpu *vcpu, struct kvm_segment *var, int seg) { - kvm_x86_ops.set_segment(vcpu, var, seg); + static_call(kvm_x86_set_segment)(vcpu, var, seg); } void kvm_get_segment(struct kvm_vcpu *vcpu, struct kvm_segment *var, int seg) { - kvm_x86_ops.get_segment(vcpu, var, seg); + static_call(kvm_x86_get_segment)(vcpu, var, seg); } gpa_t translate_nested_gpa(struct kvm_vcpu *vcpu, gpa_t gpa, u32 access, @@ -5900,14 +5982,14 @@ gpa_t translate_nested_gpa(struct kvm_vcpu *vcpu, gpa_t gpa, u32 access, gpa_t kvm_mmu_gva_to_gpa_read(struct kvm_vcpu *vcpu, gva_t gva, struct x86_exception *exception) { - u32 access = (kvm_x86_ops.get_cpl(vcpu) == 3) ? PFERR_USER_MASK : 0; + u32 access = (static_call(kvm_x86_get_cpl)(vcpu) == 3) ? PFERR_USER_MASK : 0; return vcpu->arch.walk_mmu->gva_to_gpa(vcpu, gva, access, exception); } gpa_t kvm_mmu_gva_to_gpa_fetch(struct kvm_vcpu *vcpu, gva_t gva, struct x86_exception *exception) { - u32 access = (kvm_x86_ops.get_cpl(vcpu) == 3) ? PFERR_USER_MASK : 0; + u32 access = (static_call(kvm_x86_get_cpl)(vcpu) == 3) ? PFERR_USER_MASK : 0; access |= PFERR_FETCH_MASK; return vcpu->arch.walk_mmu->gva_to_gpa(vcpu, gva, access, exception); } @@ -5915,7 +5997,7 @@ gpa_t kvm_mmu_gva_to_gpa_read(struct kvm_vcpu *vcpu, gva_t gva, gpa_t kvm_mmu_gva_to_gpa_write(struct kvm_vcpu *vcpu, gva_t gva, struct x86_exception *exception) { - u32 access = (kvm_x86_ops.get_cpl(vcpu) == 3) ? PFERR_USER_MASK : 0; + u32 access = (static_call(kvm_x86_get_cpl)(vcpu) == 3) ? PFERR_USER_MASK : 0; access |= PFERR_WRITE_MASK; return vcpu->arch.walk_mmu->gva_to_gpa(vcpu, gva, access, exception); } @@ -5964,7 +6046,7 @@ static int kvm_fetch_guest_virt(struct x86_emulate_ctxt *ctxt, struct x86_exception *exception) { struct kvm_vcpu *vcpu = emul_to_vcpu(ctxt); - u32 access = (kvm_x86_ops.get_cpl(vcpu) == 3) ? PFERR_USER_MASK : 0; + u32 access = (static_call(kvm_x86_get_cpl)(vcpu) == 3) ? PFERR_USER_MASK : 0; unsigned offset; int ret; @@ -5989,7 +6071,7 @@ int kvm_read_guest_virt(struct kvm_vcpu *vcpu, gva_t addr, void *val, unsigned int bytes, struct x86_exception *exception) { - u32 access = (kvm_x86_ops.get_cpl(vcpu) == 3) ? PFERR_USER_MASK : 0; + u32 access = (static_call(kvm_x86_get_cpl)(vcpu) == 3) ? PFERR_USER_MASK : 0; /* * FIXME: this should call handle_emulation_failure if X86EMUL_IO_NEEDED @@ -6010,7 +6092,7 @@ static int emulator_read_std(struct x86_emulate_ctxt *ctxt, struct kvm_vcpu *vcpu = emul_to_vcpu(ctxt); u32 access = 0; - if (!system && kvm_x86_ops.get_cpl(vcpu) == 3) + if (!system && static_call(kvm_x86_get_cpl)(vcpu) == 3) access |= PFERR_USER_MASK; return kvm_read_guest_virt_helper(addr, val, bytes, vcpu, access, exception); @@ -6063,7 +6145,7 @@ static int emulator_write_std(struct x86_emulate_ctxt *ctxt, gva_t addr, void *v struct kvm_vcpu *vcpu = emul_to_vcpu(ctxt); u32 access = PFERR_WRITE_MASK; - if (!system && kvm_x86_ops.get_cpl(vcpu) == 3) + if (!system && static_call(kvm_x86_get_cpl)(vcpu) == 3) access |= PFERR_USER_MASK; return kvm_write_guest_virt_helper(addr, val, bytes, vcpu, @@ -6088,7 +6170,7 @@ int handle_ud(struct kvm_vcpu *vcpu) char sig[5]; /* ud2; .ascii "kvm" */ struct x86_exception e; - if (unlikely(!kvm_x86_ops.can_emulate_instruction(vcpu, NULL, 0))) + if (unlikely(!static_call(kvm_x86_can_emulate_instruction)(vcpu, NULL, 0))) return 1; if (force_emulation_prefix && @@ -6122,7 +6204,7 @@ static int vcpu_mmio_gva_to_gpa(struct kvm_vcpu *vcpu, unsigned long gva, gpa_t *gpa, struct x86_exception *exception, bool write) { - u32 access = ((kvm_x86_ops.get_cpl(vcpu) == 3) ? PFERR_USER_MASK : 0) + u32 access = ((static_call(kvm_x86_get_cpl)(vcpu) == 3) ? PFERR_USER_MASK : 0) | (write ? PFERR_WRITE_MASK : 0); /* @@ -6530,7 +6612,7 @@ static int emulator_pio_out_emulated(struct x86_emulate_ctxt *ctxt, static unsigned long get_segment_base(struct kvm_vcpu *vcpu, int seg) { - return kvm_x86_ops.get_segment_base(vcpu, seg); + return static_call(kvm_x86_get_segment_base)(vcpu, seg); } static void emulator_invlpg(struct x86_emulate_ctxt *ctxt, ulong address) @@ -6543,11 +6625,11 @@ static int kvm_emulate_wbinvd_noskip(struct kvm_vcpu *vcpu) if (!need_emulate_wbinvd(vcpu)) return X86EMUL_CONTINUE; - if (kvm_x86_ops.has_wbinvd_exit()) { + if (static_call(kvm_x86_has_wbinvd_exit)()) { int cpu = get_cpu(); cpumask_set_cpu(cpu, vcpu->arch.wbinvd_dirty_mask); - smp_call_function_many(vcpu->arch.wbinvd_dirty_mask, + on_each_cpu_mask(vcpu->arch.wbinvd_dirty_mask, wbinvd_ipi, NULL, 1); put_cpu(); cpumask_clear(vcpu->arch.wbinvd_dirty_mask); @@ -6570,17 +6652,17 @@ static void emulator_wbinvd(struct x86_emulate_ctxt *ctxt) kvm_emulate_wbinvd_noskip(emul_to_vcpu(ctxt)); } -static int emulator_get_dr(struct x86_emulate_ctxt *ctxt, int dr, - unsigned long *dest) +static void emulator_get_dr(struct x86_emulate_ctxt *ctxt, int dr, + unsigned long *dest) { - return kvm_get_dr(emul_to_vcpu(ctxt), dr, dest); + kvm_get_dr(emul_to_vcpu(ctxt), dr, dest); } static int emulator_set_dr(struct x86_emulate_ctxt *ctxt, int dr, unsigned long value) { - return __kvm_set_dr(emul_to_vcpu(ctxt), dr, value); + return kvm_set_dr(emul_to_vcpu(ctxt), dr, value); } static u64 mk_cr_64(u64 curr_cr, u32 new_val) @@ -6648,27 +6730,27 @@ static int emulator_set_cr(struct x86_emulate_ctxt *ctxt, int cr, ulong val) static int emulator_get_cpl(struct x86_emulate_ctxt *ctxt) { - return kvm_x86_ops.get_cpl(emul_to_vcpu(ctxt)); + return static_call(kvm_x86_get_cpl)(emul_to_vcpu(ctxt)); } static void emulator_get_gdt(struct x86_emulate_ctxt *ctxt, struct desc_ptr *dt) { - kvm_x86_ops.get_gdt(emul_to_vcpu(ctxt), dt); + static_call(kvm_x86_get_gdt)(emul_to_vcpu(ctxt), dt); } static void emulator_get_idt(struct x86_emulate_ctxt *ctxt, struct desc_ptr *dt) { - kvm_x86_ops.get_idt(emul_to_vcpu(ctxt), dt); + static_call(kvm_x86_get_idt)(emul_to_vcpu(ctxt), dt); } static void emulator_set_gdt(struct x86_emulate_ctxt *ctxt, struct desc_ptr *dt) { - kvm_x86_ops.set_gdt(emul_to_vcpu(ctxt), dt); + static_call(kvm_x86_set_gdt)(emul_to_vcpu(ctxt), dt); } static void emulator_set_idt(struct x86_emulate_ctxt *ctxt, struct desc_ptr *dt) { - kvm_x86_ops.set_idt(emul_to_vcpu(ctxt), dt); + static_call(kvm_x86_set_idt)(emul_to_vcpu(ctxt), dt); } static unsigned long emulator_get_cached_segment_base( @@ -6810,7 +6892,7 @@ static int emulator_intercept(struct x86_emulate_ctxt *ctxt, struct x86_instruction_info *info, enum x86_intercept_stage stage) { - return kvm_x86_ops.check_intercept(emul_to_vcpu(ctxt), info, stage, + return static_call(kvm_x86_check_intercept)(emul_to_vcpu(ctxt), info, stage, &ctxt->exception); } @@ -6848,7 +6930,7 @@ static void emulator_write_gpr(struct x86_emulate_ctxt *ctxt, unsigned reg, ulon static void emulator_set_nmi_mask(struct x86_emulate_ctxt *ctxt, bool masked) { - kvm_x86_ops.set_nmi_mask(emul_to_vcpu(ctxt), masked); + static_call(kvm_x86_set_nmi_mask)(emul_to_vcpu(ctxt), masked); } static unsigned emulator_get_hflags(struct x86_emulate_ctxt *ctxt) @@ -6864,7 +6946,7 @@ static void emulator_set_hflags(struct x86_emulate_ctxt *ctxt, unsigned emul_fla static int emulator_pre_leave_smm(struct x86_emulate_ctxt *ctxt, const char *smstate) { - return kvm_x86_ops.pre_leave_smm(emul_to_vcpu(ctxt), smstate); + return static_call(kvm_x86_pre_leave_smm)(emul_to_vcpu(ctxt), smstate); } static void emulator_post_leave_smm(struct x86_emulate_ctxt *ctxt) @@ -6926,7 +7008,7 @@ static const struct x86_emulate_ops emulate_ops = { static void toggle_interruptibility(struct kvm_vcpu *vcpu, u32 mask) { - u32 int_shadow = kvm_x86_ops.get_interrupt_shadow(vcpu); + u32 int_shadow = static_call(kvm_x86_get_interrupt_shadow)(vcpu); /* * an sti; sti; sequence only disable interrupts for the first * instruction. So, if the last instruction, be it emulated or @@ -6937,7 +7019,7 @@ static void toggle_interruptibility(struct kvm_vcpu *vcpu, u32 mask) if (int_shadow & mask) mask = 0; if (unlikely(int_shadow || mask)) { - kvm_x86_ops.set_interrupt_shadow(vcpu, mask); + static_call(kvm_x86_set_interrupt_shadow)(vcpu, mask); if (!mask) kvm_make_request(KVM_REQ_EVENT, vcpu); } @@ -6979,7 +7061,7 @@ static void init_emulate_ctxt(struct kvm_vcpu *vcpu) struct x86_emulate_ctxt *ctxt = vcpu->arch.emulate_ctxt; int cs_db, cs_l; - kvm_x86_ops.get_cs_db_l_bits(vcpu, &cs_db, &cs_l); + static_call(kvm_x86_get_cs_db_l_bits)(vcpu, &cs_db, &cs_l); ctxt->gpa_available = false; ctxt->eflags = kvm_get_rflags(vcpu); @@ -7040,7 +7122,7 @@ static int handle_emulation_failure(struct kvm_vcpu *vcpu, int emulation_type) kvm_queue_exception(vcpu, UD_VECTOR); - if (!is_guest_mode(vcpu) && kvm_x86_ops.get_cpl(vcpu) == 0) { + if (!is_guest_mode(vcpu) && static_call(kvm_x86_get_cpl)(vcpu) == 0) { vcpu->run->exit_reason = KVM_EXIT_INTERNAL_ERROR; vcpu->run->internal.suberror = KVM_INTERNAL_ERROR_EMULATION; vcpu->run->internal.ndata = 0; @@ -7100,9 +7182,9 @@ static bool reexecute_instruction(struct kvm_vcpu *vcpu, gpa_t cr2_or_gpa, if (vcpu->arch.mmu->direct_map) { unsigned int indirect_shadow_pages; - spin_lock(&vcpu->kvm->mmu_lock); + write_lock(&vcpu->kvm->mmu_lock); indirect_shadow_pages = vcpu->kvm->arch.indirect_shadow_pages; - spin_unlock(&vcpu->kvm->mmu_lock); + write_unlock(&vcpu->kvm->mmu_lock); if (indirect_shadow_pages) kvm_mmu_unprotect_page(vcpu->kvm, gpa_to_gfn(gpa)); @@ -7209,7 +7291,7 @@ static int kvm_vcpu_do_singlestep(struct kvm_vcpu *vcpu) struct kvm_run *kvm_run = vcpu->run; if (vcpu->guest_debug & KVM_GUESTDBG_SINGLESTEP) { - kvm_run->debug.arch.dr6 = DR6_BS | DR6_FIXED_1 | DR6_RTM; + kvm_run->debug.arch.dr6 = DR6_BS | DR6_ACTIVE_LOW; kvm_run->debug.arch.pc = kvm_get_linear_rip(vcpu); kvm_run->debug.arch.exception = DB_VECTOR; kvm_run->exit_reason = KVM_EXIT_DEBUG; @@ -7221,10 +7303,10 @@ static int kvm_vcpu_do_singlestep(struct kvm_vcpu *vcpu) int kvm_skip_emulated_instruction(struct kvm_vcpu *vcpu) { - unsigned long rflags = kvm_x86_ops.get_rflags(vcpu); + unsigned long rflags = static_call(kvm_x86_get_rflags)(vcpu); int r; - r = kvm_x86_ops.skip_emulated_instruction(vcpu); + r = static_call(kvm_x86_skip_emulated_instruction)(vcpu); if (unlikely(!r)) return 0; @@ -7253,7 +7335,7 @@ static bool kvm_vcpu_check_breakpoint(struct kvm_vcpu *vcpu, int *r) vcpu->arch.eff_db); if (dr6 != 0) { - kvm_run->debug.arch.dr6 = dr6 | DR6_FIXED_1 | DR6_RTM; + kvm_run->debug.arch.dr6 = dr6 | DR6_ACTIVE_LOW; kvm_run->debug.arch.pc = eip; kvm_run->debug.arch.exception = DB_VECTOR; kvm_run->exit_reason = KVM_EXIT_DEBUG; @@ -7310,6 +7392,42 @@ static bool is_vmware_backdoor_opcode(struct x86_emulate_ctxt *ctxt) return false; } +/* + * Decode to be emulated instruction. Return EMULATION_OK if success. + */ +int x86_decode_emulated_instruction(struct kvm_vcpu *vcpu, int emulation_type, + void *insn, int insn_len) +{ + int r = EMULATION_OK; + struct x86_emulate_ctxt *ctxt = vcpu->arch.emulate_ctxt; + + init_emulate_ctxt(vcpu); + + /* + * We will reenter on the same instruction since we do not set + * complete_userspace_io. This does not handle watchpoints yet, + * those would be handled in the emulate_ops. + */ + if (!(emulation_type & EMULTYPE_SKIP) && + kvm_vcpu_check_breakpoint(vcpu, &r)) + return r; + + ctxt->interruptibility = 0; + ctxt->have_exception = false; + ctxt->exception.vector = -1; + ctxt->perm_ok = false; + + ctxt->ud = emulation_type & EMULTYPE_TRAP_UD; + + r = x86_decode_insn(ctxt, insn, insn_len); + + trace_kvm_emulate_insn_start(vcpu); + ++vcpu->stat.insn_emulation; + + return r; +} +EXPORT_SYMBOL_GPL(x86_decode_emulated_instruction); + int x86_emulate_instruction(struct kvm_vcpu *vcpu, gpa_t cr2_or_gpa, int emulation_type, void *insn, int insn_len) { @@ -7318,7 +7436,7 @@ int x86_emulate_instruction(struct kvm_vcpu *vcpu, gpa_t cr2_or_gpa, bool writeback = true; bool write_fault_to_spt; - if (unlikely(!kvm_x86_ops.can_emulate_instruction(vcpu, insn, insn_len))) + if (unlikely(!static_call(kvm_x86_can_emulate_instruction)(vcpu, insn, insn_len))) return 1; vcpu->arch.l1tf_flush_l1d = true; @@ -7329,32 +7447,12 @@ int x86_emulate_instruction(struct kvm_vcpu *vcpu, gpa_t cr2_or_gpa, */ write_fault_to_spt = vcpu->arch.write_fault_to_shadow_pgtable; vcpu->arch.write_fault_to_shadow_pgtable = false; - kvm_clear_exception_queue(vcpu); if (!(emulation_type & EMULTYPE_NO_DECODE)) { - init_emulate_ctxt(vcpu); - - /* - * We will reenter on the same instruction since - * we do not set complete_userspace_io. This does not - * handle watchpoints yet, those would be handled in - * the emulate_ops. - */ - if (!(emulation_type & EMULTYPE_SKIP) && - kvm_vcpu_check_breakpoint(vcpu, &r)) - return r; - - ctxt->interruptibility = 0; - ctxt->have_exception = false; - ctxt->exception.vector = -1; - ctxt->perm_ok = false; - - ctxt->ud = emulation_type & EMULTYPE_TRAP_UD; + kvm_clear_exception_queue(vcpu); - r = x86_decode_insn(ctxt, insn, insn_len); - - trace_kvm_emulate_insn_start(vcpu); - ++vcpu->stat.insn_emulation; + r = x86_decode_emulated_instruction(vcpu, emulation_type, + insn, insn_len); if (r != EMULATION_OK) { if ((emulation_type & EMULTYPE_TRAP_UD) || (emulation_type & EMULTYPE_TRAP_UD_FORCED)) { @@ -7461,7 +7559,7 @@ restart: r = 1; if (writeback) { - unsigned long rflags = kvm_x86_ops.get_rflags(vcpu); + unsigned long rflags = static_call(kvm_x86_get_rflags)(vcpu); toggle_interruptibility(vcpu, ctxt->interruptibility); vcpu->arch.emulate_regs_need_sync_to_vcpu = false; if (!ctxt->have_exception || @@ -7470,7 +7568,7 @@ restart: if (r && (ctxt->tf || (vcpu->guest_debug & KVM_GUESTDBG_SINGLESTEP))) r = kvm_vcpu_do_singlestep(vcpu); if (kvm_x86_ops.update_emulated_instruction) - kvm_x86_ops.update_emulated_instruction(vcpu); + static_call(kvm_x86_update_emulated_instruction)(vcpu); __kvm_set_rflags(vcpu, ctxt->eflags); } @@ -7799,7 +7897,7 @@ static int kvm_is_user_mode(void) int user_mode = 3; if (__this_cpu_read(current_vcpu)) - user_mode = kvm_x86_ops.get_cpl(__this_cpu_read(current_vcpu)); + user_mode = static_call(kvm_x86_get_cpl)(__this_cpu_read(current_vcpu)); return user_mode != 0; } @@ -7944,7 +8042,6 @@ int kvm_arch_init(void *opaque) supported_xcr0 = host_xcr0 & KVM_SUPPORTED_XCR0; } - kvm_lapic_init(); if (pi_inject_timer == -1) pi_inject_timer = housekeeping_enabled(HK_FLAG_TIMER); #ifdef CONFIG_X86_64 @@ -7986,6 +8083,10 @@ void kvm_arch_exit(void) kvm_mmu_module_exit(); free_percpu(user_return_msrs); kmem_cache_destroy(x86_fpu_cache); +#ifdef CONFIG_KVM_XEN + static_key_deferred_flush(&kvm_xen_enabled); + WARN_ON(static_branch_unlikely(&kvm_xen_enabled.key)); +#endif } static int __kvm_vcpu_halt(struct kvm_vcpu *vcpu, int state, int reason) @@ -8037,7 +8138,7 @@ static int kvm_pv_clock_pairing(struct kvm_vcpu *vcpu, gpa_t paddr, if (clock_type != KVM_CLOCK_PAIRING_WALLCLOCK) return -KVM_EOPNOTSUPP; - if (kvm_get_walltime_and_clockread(&ts, &cycle) == false) + if (!kvm_get_walltime_and_clockread(&ts, &cycle)) return -KVM_EOPNOTSUPP; clock_pairing.sec = ts.tv_sec; @@ -8113,7 +8214,10 @@ int kvm_emulate_hypercall(struct kvm_vcpu *vcpu) unsigned long nr, a0, a1, a2, a3, ret; int op_64_bit; - if (kvm_hv_hypercall_enabled(vcpu->kvm)) + if (kvm_xen_hypercall_enabled(vcpu->kvm)) + return kvm_xen_hypercall(vcpu); + + if (kvm_hv_hypercall_enabled(vcpu)) return kvm_hv_hypercall(vcpu); nr = kvm_rax_read(vcpu); @@ -8133,7 +8237,7 @@ int kvm_emulate_hypercall(struct kvm_vcpu *vcpu) a3 &= 0xFFFFFFFF; } - if (kvm_x86_ops.get_cpl(vcpu) != 0) { + if (static_call(kvm_x86_get_cpl)(vcpu) != 0) { ret = -KVM_EPERM; goto out; } @@ -8190,7 +8294,7 @@ static int emulator_fix_hypercall(struct x86_emulate_ctxt *ctxt) char instruction[3]; unsigned long rip = kvm_rip_read(vcpu); - kvm_x86_ops.patch_hypercall(vcpu, instruction); + static_call(kvm_x86_patch_hypercall)(vcpu, instruction); return emulator_write_emulated(ctxt, rip, instruction, 3, &ctxt->exception); @@ -8214,12 +8318,14 @@ static void post_kvm_run_save(struct kvm_vcpu *vcpu) kvm_run->if_flag = !vcpu->arch.guest_state_protected && (kvm_get_rflags(vcpu) & X86_EFLAGS_IF) != 0; - kvm_run->flags = is_smm(vcpu) ? KVM_RUN_X86_SMM : 0; kvm_run->cr8 = kvm_get_cr8(vcpu); kvm_run->apic_base = kvm_get_apic_base(vcpu); kvm_run->ready_for_interrupt_injection = pic_in_kernel(vcpu->kvm) || kvm_vcpu_ready_for_interrupt_injection(vcpu); + + if (is_smm(vcpu)) + kvm_run->flags |= KVM_RUN_X86_SMM; } static void update_cr8_intercept(struct kvm_vcpu *vcpu) @@ -8245,7 +8351,7 @@ static void update_cr8_intercept(struct kvm_vcpu *vcpu) tpr = kvm_lapic_get_cr8(vcpu); - kvm_x86_ops.update_cr8_intercept(vcpu, tpr, max_irr); + static_call(kvm_x86_update_cr8_intercept)(vcpu, tpr, max_irr); } static void inject_pending_event(struct kvm_vcpu *vcpu, bool *req_immediate_exit) @@ -8256,7 +8362,7 @@ static void inject_pending_event(struct kvm_vcpu *vcpu, bool *req_immediate_exit /* try to reinject previous events if any */ if (vcpu->arch.exception.injected) { - kvm_x86_ops.queue_exception(vcpu); + static_call(kvm_x86_queue_exception)(vcpu); can_inject = false; } /* @@ -8275,10 +8381,10 @@ static void inject_pending_event(struct kvm_vcpu *vcpu, bool *req_immediate_exit */ else if (!vcpu->arch.exception.pending) { if (vcpu->arch.nmi_injected) { - kvm_x86_ops.set_nmi(vcpu); + static_call(kvm_x86_set_nmi)(vcpu); can_inject = false; } else if (vcpu->arch.interrupt.injected) { - kvm_x86_ops.set_irq(vcpu); + static_call(kvm_x86_set_irq)(vcpu); can_inject = false; } } @@ -8319,7 +8425,7 @@ static void inject_pending_event(struct kvm_vcpu *vcpu, bool *req_immediate_exit } } - kvm_x86_ops.queue_exception(vcpu); + static_call(kvm_x86_queue_exception)(vcpu); can_inject = false; } @@ -8335,7 +8441,7 @@ static void inject_pending_event(struct kvm_vcpu *vcpu, bool *req_immediate_exit * The kvm_x86_ops hooks communicate this by returning -EBUSY. */ if (vcpu->arch.smi_pending) { - r = can_inject ? kvm_x86_ops.smi_allowed(vcpu, true) : -EBUSY; + r = can_inject ? static_call(kvm_x86_smi_allowed)(vcpu, true) : -EBUSY; if (r < 0) goto busy; if (r) { @@ -8344,35 +8450,35 @@ static void inject_pending_event(struct kvm_vcpu *vcpu, bool *req_immediate_exit enter_smm(vcpu); can_inject = false; } else - kvm_x86_ops.enable_smi_window(vcpu); + static_call(kvm_x86_enable_smi_window)(vcpu); } if (vcpu->arch.nmi_pending) { - r = can_inject ? kvm_x86_ops.nmi_allowed(vcpu, true) : -EBUSY; + r = can_inject ? static_call(kvm_x86_nmi_allowed)(vcpu, true) : -EBUSY; if (r < 0) goto busy; if (r) { --vcpu->arch.nmi_pending; vcpu->arch.nmi_injected = true; - kvm_x86_ops.set_nmi(vcpu); + static_call(kvm_x86_set_nmi)(vcpu); can_inject = false; - WARN_ON(kvm_x86_ops.nmi_allowed(vcpu, true) < 0); + WARN_ON(static_call(kvm_x86_nmi_allowed)(vcpu, true) < 0); } if (vcpu->arch.nmi_pending) - kvm_x86_ops.enable_nmi_window(vcpu); + static_call(kvm_x86_enable_nmi_window)(vcpu); } if (kvm_cpu_has_injectable_intr(vcpu)) { - r = can_inject ? kvm_x86_ops.interrupt_allowed(vcpu, true) : -EBUSY; + r = can_inject ? static_call(kvm_x86_interrupt_allowed)(vcpu, true) : -EBUSY; if (r < 0) goto busy; if (r) { kvm_queue_interrupt(vcpu, kvm_cpu_get_interrupt(vcpu), false); - kvm_x86_ops.set_irq(vcpu); - WARN_ON(kvm_x86_ops.interrupt_allowed(vcpu, true) < 0); + static_call(kvm_x86_set_irq)(vcpu); + WARN_ON(static_call(kvm_x86_interrupt_allowed)(vcpu, true) < 0); } if (kvm_cpu_has_injectable_intr(vcpu)) - kvm_x86_ops.enable_irq_window(vcpu); + static_call(kvm_x86_enable_irq_window)(vcpu); } if (is_guest_mode(vcpu) && @@ -8397,7 +8503,7 @@ static void process_nmi(struct kvm_vcpu *vcpu) * If an NMI is already in progress, limit further NMIs to just one. * Otherwise, allow two (and we'll inject the first one immediately). */ - if (kvm_x86_ops.get_nmi_mask(vcpu) || vcpu->arch.nmi_injected) + if (static_call(kvm_x86_get_nmi_mask)(vcpu) || vcpu->arch.nmi_injected) limit = 1; vcpu->arch.nmi_pending += atomic_xchg(&vcpu->arch.nmi_queued, 0); @@ -8487,11 +8593,11 @@ static void enter_smm_save_state_32(struct kvm_vcpu *vcpu, char *buf) put_smstate(u32, buf, 0x7f7c, seg.limit); put_smstate(u32, buf, 0x7f78, enter_smm_get_segment_flags(&seg)); - kvm_x86_ops.get_gdt(vcpu, &dt); + static_call(kvm_x86_get_gdt)(vcpu, &dt); put_smstate(u32, buf, 0x7f74, dt.address); put_smstate(u32, buf, 0x7f70, dt.size); - kvm_x86_ops.get_idt(vcpu, &dt); + static_call(kvm_x86_get_idt)(vcpu, &dt); put_smstate(u32, buf, 0x7f58, dt.address); put_smstate(u32, buf, 0x7f54, dt.size); @@ -8541,7 +8647,7 @@ static void enter_smm_save_state_64(struct kvm_vcpu *vcpu, char *buf) put_smstate(u32, buf, 0x7e94, seg.limit); put_smstate(u64, buf, 0x7e98, seg.base); - kvm_x86_ops.get_idt(vcpu, &dt); + static_call(kvm_x86_get_idt)(vcpu, &dt); put_smstate(u32, buf, 0x7e84, dt.size); put_smstate(u64, buf, 0x7e88, dt.address); @@ -8551,7 +8657,7 @@ static void enter_smm_save_state_64(struct kvm_vcpu *vcpu, char *buf) put_smstate(u32, buf, 0x7e74, seg.limit); put_smstate(u64, buf, 0x7e78, seg.base); - kvm_x86_ops.get_gdt(vcpu, &dt); + static_call(kvm_x86_get_gdt)(vcpu, &dt); put_smstate(u32, buf, 0x7e64, dt.size); put_smstate(u64, buf, 0x7e68, dt.address); @@ -8581,30 +8687,30 @@ static void enter_smm(struct kvm_vcpu *vcpu) * vCPU state (e.g. leave guest mode) after we've saved the state into * the SMM state-save area. */ - kvm_x86_ops.pre_enter_smm(vcpu, buf); + static_call(kvm_x86_pre_enter_smm)(vcpu, buf); vcpu->arch.hflags |= HF_SMM_MASK; kvm_vcpu_write_guest(vcpu, vcpu->arch.smbase + 0xfe00, buf, sizeof(buf)); - if (kvm_x86_ops.get_nmi_mask(vcpu)) + if (static_call(kvm_x86_get_nmi_mask)(vcpu)) vcpu->arch.hflags |= HF_SMM_INSIDE_NMI_MASK; else - kvm_x86_ops.set_nmi_mask(vcpu, true); + static_call(kvm_x86_set_nmi_mask)(vcpu, true); kvm_set_rflags(vcpu, X86_EFLAGS_FIXED); kvm_rip_write(vcpu, 0x8000); cr0 = vcpu->arch.cr0 & ~(X86_CR0_PE | X86_CR0_EM | X86_CR0_TS | X86_CR0_PG); - kvm_x86_ops.set_cr0(vcpu, cr0); + static_call(kvm_x86_set_cr0)(vcpu, cr0); vcpu->arch.cr0 = cr0; - kvm_x86_ops.set_cr4(vcpu, 0); + static_call(kvm_x86_set_cr4)(vcpu, 0); /* Undocumented: IDT limit is set to zero on entry to SMM. */ dt.address = dt.size = 0; - kvm_x86_ops.set_idt(vcpu, &dt); + static_call(kvm_x86_set_idt)(vcpu, &dt); - __kvm_set_dr(vcpu, 7, DR7_FIXED_1); + kvm_set_dr(vcpu, 7, DR7_FIXED_1); cs.selector = (vcpu->arch.smbase >> 4) & 0xffff; cs.base = vcpu->arch.smbase; @@ -8633,7 +8739,7 @@ static void enter_smm(struct kvm_vcpu *vcpu) #ifdef CONFIG_X86_64 if (guest_cpuid_has(vcpu, X86_FEATURE_LM)) - kvm_x86_ops.set_efer(vcpu, 0); + static_call(kvm_x86_set_efer)(vcpu, 0); #endif kvm_update_cpuid_runtime(vcpu); @@ -8671,7 +8777,7 @@ void kvm_vcpu_update_apicv(struct kvm_vcpu *vcpu) vcpu->arch.apicv_active = kvm_apicv_activated(vcpu->kvm); kvm_apic_update_apicv(vcpu); - kvm_x86_ops.refresh_apicv_exec_ctrl(vcpu); + static_call(kvm_x86_refresh_apicv_exec_ctrl)(vcpu); } EXPORT_SYMBOL_GPL(kvm_vcpu_update_apicv); @@ -8688,7 +8794,7 @@ void kvm_request_apicv_update(struct kvm *kvm, bool activate, ulong bit) unsigned long old, new, expected; if (!kvm_x86_ops.check_apicv_inhibit_reasons || - !kvm_x86_ops.check_apicv_inhibit_reasons(bit)) + !static_call(kvm_x86_check_apicv_inhibit_reasons)(bit)) return; old = READ_ONCE(kvm->arch.apicv_inhibit_reasons); @@ -8708,7 +8814,7 @@ void kvm_request_apicv_update(struct kvm *kvm, bool activate, ulong bit) trace_kvm_apicv_update_request(activate, bit); if (kvm_x86_ops.pre_update_apicv_exec_ctrl) - kvm_x86_ops.pre_update_apicv_exec_ctrl(kvm, activate); + static_call(kvm_x86_pre_update_apicv_exec_ctrl)(kvm, activate); /* * Sending request to update APICV for all other vcpus, @@ -8734,7 +8840,7 @@ static void vcpu_scan_ioapic(struct kvm_vcpu *vcpu) kvm_scan_ioapic_routes(vcpu, vcpu->arch.ioapic_handled_vectors); else { if (vcpu->arch.apicv_active) - kvm_x86_ops.sync_pir_to_irr(vcpu); + static_call(kvm_x86_sync_pir_to_irr)(vcpu); if (ioapic_in_kernel(vcpu->kvm)) kvm_ioapic_scan_entry(vcpu, vcpu->arch.ioapic_handled_vectors); } @@ -8752,9 +8858,12 @@ static void vcpu_load_eoi_exitmap(struct kvm_vcpu *vcpu) if (!kvm_apic_hw_enabled(vcpu->arch.apic)) return; - bitmap_or((ulong *)eoi_exit_bitmap, vcpu->arch.ioapic_handled_vectors, - vcpu_to_synic(vcpu)->vec_bitmap, 256); - kvm_x86_ops.load_eoi_exitmap(vcpu, eoi_exit_bitmap); + if (to_hv_vcpu(vcpu)) + bitmap_or((ulong *)eoi_exit_bitmap, + vcpu->arch.ioapic_handled_vectors, + to_hv_synic(vcpu)->vec_bitmap, 256); + + static_call(kvm_x86_load_eoi_exitmap)(vcpu, eoi_exit_bitmap); } void kvm_arch_mmu_notifier_invalidate_range(struct kvm *kvm, @@ -8779,7 +8888,7 @@ void kvm_vcpu_reload_apic_access_page(struct kvm_vcpu *vcpu) if (!kvm_x86_ops.set_apic_access_page_addr) return; - kvm_x86_ops.set_apic_access_page_addr(vcpu); + static_call(kvm_x86_set_apic_access_page_addr)(vcpu); } void __kvm_request_immediate_exit(struct kvm_vcpu *vcpu) @@ -8904,8 +9013,10 @@ static int vcpu_enter_guest(struct kvm_vcpu *vcpu) goto out; } if (kvm_check_request(KVM_REQ_HV_EXIT, vcpu)) { + struct kvm_vcpu_hv *hv_vcpu = to_hv_vcpu(vcpu); + vcpu->run->exit_reason = KVM_EXIT_HYPERV; - vcpu->run->hyperv = vcpu->arch.hyperv.exit; + vcpu->run->hyperv = hv_vcpu->exit; r = 0; goto out; } @@ -8922,10 +9033,14 @@ static int vcpu_enter_guest(struct kvm_vcpu *vcpu) if (kvm_check_request(KVM_REQ_APF_READY, vcpu)) kvm_check_async_pf_completion(vcpu); if (kvm_check_request(KVM_REQ_MSR_FILTER_CHANGED, vcpu)) - kvm_x86_ops.msr_filter_changed(vcpu); + static_call(kvm_x86_msr_filter_changed)(vcpu); + + if (kvm_check_request(KVM_REQ_UPDATE_CPU_DIRTY_LOGGING, vcpu)) + static_call(kvm_x86_update_cpu_dirty_logging)(vcpu); } - if (kvm_check_request(KVM_REQ_EVENT, vcpu) || req_int_win) { + if (kvm_check_request(KVM_REQ_EVENT, vcpu) || req_int_win || + kvm_xen_has_interrupt(vcpu)) { ++vcpu->stat.req_event; kvm_apic_accept_events(vcpu); if (vcpu->arch.mp_state == KVM_MP_STATE_INIT_RECEIVED) { @@ -8935,7 +9050,7 @@ static int vcpu_enter_guest(struct kvm_vcpu *vcpu) inject_pending_event(vcpu, &req_immediate_exit); if (req_int_win) - kvm_x86_ops.enable_irq_window(vcpu); + static_call(kvm_x86_enable_irq_window)(vcpu); if (kvm_lapic_enabled(vcpu)) { update_cr8_intercept(vcpu); @@ -8950,7 +9065,7 @@ static int vcpu_enter_guest(struct kvm_vcpu *vcpu) preempt_disable(); - kvm_x86_ops.prepare_guest_switch(vcpu); + static_call(kvm_x86_prepare_guest_switch)(vcpu); /* * Disable IRQs before setting IN_GUEST_MODE. Posted interrupt @@ -8981,7 +9096,7 @@ static int vcpu_enter_guest(struct kvm_vcpu *vcpu) * notified with kvm_vcpu_kick. */ if (kvm_lapic_enabled(vcpu) && vcpu->arch.apicv_active) - kvm_x86_ops.sync_pir_to_irr(vcpu); + static_call(kvm_x86_sync_pir_to_irr)(vcpu); if (kvm_vcpu_exit_request(vcpu)) { vcpu->mode = OUTSIDE_GUEST_MODE; @@ -8995,7 +9110,7 @@ static int vcpu_enter_guest(struct kvm_vcpu *vcpu) if (req_immediate_exit) { kvm_make_request(KVM_REQ_EVENT, vcpu); - kvm_x86_ops.request_immediate_exit(vcpu); + static_call(kvm_x86_request_immediate_exit)(vcpu); } fpregs_assert_state_consistent(); @@ -9012,7 +9127,19 @@ static int vcpu_enter_guest(struct kvm_vcpu *vcpu) vcpu->arch.switch_db_regs &= ~KVM_DEBUGREG_RELOAD; } - exit_fastpath = kvm_x86_ops.run(vcpu); + for (;;) { + exit_fastpath = static_call(kvm_x86_run)(vcpu); + if (likely(exit_fastpath != EXIT_FASTPATH_REENTER_GUEST)) + break; + + if (unlikely(kvm_vcpu_exit_request(vcpu))) { + exit_fastpath = EXIT_FASTPATH_EXIT_HANDLED; + break; + } + + if (vcpu->arch.apicv_active) + static_call(kvm_x86_sync_pir_to_irr)(vcpu); + } /* * Do this here before restoring debug registers on the host. And @@ -9022,7 +9149,7 @@ static int vcpu_enter_guest(struct kvm_vcpu *vcpu) */ if (unlikely(vcpu->arch.switch_db_regs & KVM_DEBUGREG_WONT_EXIT)) { WARN_ON(vcpu->guest_debug & KVM_GUESTDBG_USE_HW_BP); - kvm_x86_ops.sync_dirty_debug_regs(vcpu); + static_call(kvm_x86_sync_dirty_debug_regs)(vcpu); kvm_update_dr0123(vcpu); kvm_update_dr7(vcpu); vcpu->arch.switch_db_regs &= ~KVM_DEBUGREG_RELOAD; @@ -9044,7 +9171,7 @@ static int vcpu_enter_guest(struct kvm_vcpu *vcpu) vcpu->mode = OUTSIDE_GUEST_MODE; smp_wmb(); - kvm_x86_ops.handle_exit_irqoff(vcpu); + static_call(kvm_x86_handle_exit_irqoff)(vcpu); /* * Consume any pending interrupts, including the possible source of @@ -9086,13 +9213,13 @@ static int vcpu_enter_guest(struct kvm_vcpu *vcpu) if (vcpu->arch.apic_attention) kvm_lapic_sync_from_vapic(vcpu); - r = kvm_x86_ops.handle_exit(vcpu, exit_fastpath); + r = static_call(kvm_x86_handle_exit)(vcpu, exit_fastpath); return r; cancel_injection: if (req_immediate_exit) kvm_make_request(KVM_REQ_EVENT, vcpu); - kvm_x86_ops.cancel_injection(vcpu); + static_call(kvm_x86_cancel_injection)(vcpu); if (unlikely(vcpu->arch.apic_attention)) kvm_lapic_sync_from_vapic(vcpu); out: @@ -9102,13 +9229,13 @@ out: static inline int vcpu_block(struct kvm *kvm, struct kvm_vcpu *vcpu) { if (!kvm_arch_vcpu_runnable(vcpu) && - (!kvm_x86_ops.pre_block || kvm_x86_ops.pre_block(vcpu) == 0)) { + (!kvm_x86_ops.pre_block || static_call(kvm_x86_pre_block)(vcpu) == 0)) { srcu_read_unlock(&kvm->srcu, vcpu->srcu_idx); kvm_vcpu_block(vcpu); vcpu->srcu_idx = srcu_read_lock(&kvm->srcu); if (kvm_x86_ops.post_block) - kvm_x86_ops.post_block(vcpu); + static_call(kvm_x86_post_block)(vcpu); if (!kvm_check_request(KVM_REQ_UNHALT, vcpu)) return 1; @@ -9329,6 +9456,7 @@ int kvm_arch_vcpu_ioctl_run(struct kvm_vcpu *vcpu) vcpu_load(vcpu); kvm_sigset_activate(vcpu); + kvm_run->flags = 0; kvm_load_guest_fpu(vcpu); if (unlikely(vcpu->arch.mp_state == KVM_MP_STATE_UNINITIALIZED)) { @@ -9503,10 +9631,10 @@ static void __get_sregs(struct kvm_vcpu *vcpu, struct kvm_sregs *sregs) kvm_get_segment(vcpu, &sregs->tr, VCPU_SREG_TR); kvm_get_segment(vcpu, &sregs->ldt, VCPU_SREG_LDTR); - kvm_x86_ops.get_idt(vcpu, &dt); + static_call(kvm_x86_get_idt)(vcpu, &dt); sregs->idt.limit = dt.size; sregs->idt.base = dt.address; - kvm_x86_ops.get_gdt(vcpu, &dt); + static_call(kvm_x86_get_gdt)(vcpu, &dt); sregs->gdt.limit = dt.size; sregs->gdt.base = dt.address; @@ -9624,7 +9752,7 @@ static bool kvm_is_valid_sregs(struct kvm_vcpu *vcpu, struct kvm_sregs *sregs) */ if (!(sregs->cr4 & X86_CR4_PAE) || !(sregs->efer & EFER_LMA)) return false; - if (sregs->cr3 & vcpu->arch.cr3_lm_rsvd_bits) + if (kvm_vcpu_is_illegal_gpa(vcpu, sregs->cr3)) return false; } else { /* @@ -9659,10 +9787,10 @@ static int __set_sregs(struct kvm_vcpu *vcpu, struct kvm_sregs *sregs) dt.size = sregs->idt.limit; dt.address = sregs->idt.base; - kvm_x86_ops.set_idt(vcpu, &dt); + static_call(kvm_x86_set_idt)(vcpu, &dt); dt.size = sregs->gdt.limit; dt.address = sregs->gdt.base; - kvm_x86_ops.set_gdt(vcpu, &dt); + static_call(kvm_x86_set_gdt)(vcpu, &dt); vcpu->arch.cr2 = sregs->cr2; mmu_reset_needed |= kvm_read_cr3(vcpu) != sregs->cr3; @@ -9672,14 +9800,14 @@ static int __set_sregs(struct kvm_vcpu *vcpu, struct kvm_sregs *sregs) kvm_set_cr8(vcpu, sregs->cr8); mmu_reset_needed |= vcpu->arch.efer != sregs->efer; - kvm_x86_ops.set_efer(vcpu, sregs->efer); + static_call(kvm_x86_set_efer)(vcpu, sregs->efer); mmu_reset_needed |= kvm_read_cr0(vcpu) != sregs->cr0; - kvm_x86_ops.set_cr0(vcpu, sregs->cr0); + static_call(kvm_x86_set_cr0)(vcpu, sregs->cr0); vcpu->arch.cr0 = sregs->cr0; mmu_reset_needed |= kvm_read_cr4(vcpu) != sregs->cr4; - kvm_x86_ops.set_cr4(vcpu, sregs->cr4); + static_call(kvm_x86_set_cr4)(vcpu, sregs->cr4); idx = srcu_read_lock(&vcpu->kvm->srcu); if (is_pae_paging(vcpu)) { @@ -9787,7 +9915,7 @@ int kvm_arch_vcpu_ioctl_set_guest_debug(struct kvm_vcpu *vcpu, */ kvm_set_rflags(vcpu, rflags); - kvm_x86_ops.update_exception_bitmap(vcpu); + static_call(kvm_x86_update_exception_bitmap)(vcpu); r = 0; @@ -9965,7 +10093,7 @@ int kvm_arch_vcpu_create(struct kvm_vcpu *vcpu) if (kvm_apicv_activated(vcpu->kvm)) vcpu->arch.apicv_active = true; } else - static_key_slow_inc(&kvm_no_apic_vcpu); + static_branch_inc(&kvm_has_noapic_vcpu); r = -ENOMEM; @@ -10003,7 +10131,7 @@ int kvm_arch_vcpu_create(struct kvm_vcpu *vcpu) fx_init(vcpu); vcpu->arch.maxphyaddr = cpuid_query_maxphyaddr(vcpu); - vcpu->arch.cr3_lm_rsvd_bits = rsvd_bits(cpuid_maxphyaddr(vcpu), 63); + vcpu->arch.reserved_gpa_bits = kvm_vcpu_reserved_gpa_bits_raw(vcpu); vcpu->arch.pat = MSR_IA32_CR_PAT_DEFAULT; @@ -10013,9 +10141,7 @@ int kvm_arch_vcpu_create(struct kvm_vcpu *vcpu) vcpu->arch.pending_external_vector = -1; vcpu->arch.preempted_in_kernel = false; - kvm_hv_vcpu_init(vcpu); - - r = kvm_x86_ops.vcpu_create(vcpu); + r = static_call(kvm_x86_vcpu_create)(vcpu); if (r) goto free_guest_fpu; @@ -10051,8 +10177,6 @@ void kvm_arch_vcpu_postcreate(struct kvm_vcpu *vcpu) { struct kvm *kvm = vcpu->kvm; - kvm_hv_vcpu_postcreate(vcpu); - if (mutex_lock_killable(&vcpu->mutex)) return; vcpu_load(vcpu); @@ -10078,7 +10202,7 @@ void kvm_arch_vcpu_destroy(struct kvm_vcpu *vcpu) kvmclock_reset(vcpu); - kvm_x86_ops.vcpu_free(vcpu); + static_call(kvm_x86_vcpu_free)(vcpu); kmem_cache_free(x86_emulator_cache, vcpu->arch.emulate_ctxt); free_cpumask_var(vcpu->arch.wbinvd_dirty_mask); @@ -10095,7 +10219,7 @@ void kvm_arch_vcpu_destroy(struct kvm_vcpu *vcpu) free_page((unsigned long)vcpu->arch.pio_data); kvfree(vcpu->arch.cpuid_entries); if (!lapic_in_kernel(vcpu)) - static_key_slow_dec(&kvm_no_apic_vcpu); + static_branch_dec(&kvm_has_noapic_vcpu); } void kvm_vcpu_reset(struct kvm_vcpu *vcpu, bool init_event) @@ -10114,7 +10238,7 @@ void kvm_vcpu_reset(struct kvm_vcpu *vcpu, bool init_event) memset(vcpu->arch.db, 0, sizeof(vcpu->arch.db)); kvm_update_dr0123(vcpu); - vcpu->arch.dr6 = DR6_INIT; + vcpu->arch.dr6 = DR6_ACTIVE_LOW; vcpu->arch.dr7 = DR7_FIXED_1; kvm_update_dr7(vcpu); @@ -10167,7 +10291,7 @@ void kvm_vcpu_reset(struct kvm_vcpu *vcpu, bool init_event) vcpu->arch.ia32_xss = 0; - kvm_x86_ops.vcpu_reset(vcpu, init_event); + static_call(kvm_x86_vcpu_reset)(vcpu, init_event); } void kvm_vcpu_deliver_sipi_vector(struct kvm_vcpu *vcpu, u8 vector) @@ -10193,7 +10317,7 @@ int kvm_arch_hardware_enable(void) bool stable, backwards_tsc = false; kvm_user_return_msr_cpu_online(); - ret = kvm_x86_ops.hardware_enable(); + ret = static_call(kvm_x86_hardware_enable)(); if (ret != 0) return ret; @@ -10275,7 +10399,7 @@ int kvm_arch_hardware_enable(void) void kvm_arch_hardware_disable(void) { - kvm_x86_ops.hardware_disable(); + static_call(kvm_x86_hardware_disable)(); drop_user_return_notifiers(); } @@ -10294,6 +10418,7 @@ int kvm_arch_hardware_setup(void *opaque) return r; memcpy(&kvm_x86_ops, ops->runtime_ops, sizeof(kvm_x86_ops)); + kvm_ops_static_call_update(); if (!kvm_cpu_cap_has(X86_FEATURE_XSAVES)) supported_xss = 0; @@ -10322,7 +10447,7 @@ int kvm_arch_hardware_setup(void *opaque) void kvm_arch_hardware_unsetup(void) { - kvm_x86_ops.hardware_unsetup(); + static_call(kvm_x86_hardware_unsetup)(); } int kvm_arch_check_processor_compat(void *opaque) @@ -10350,8 +10475,8 @@ bool kvm_vcpu_is_bsp(struct kvm_vcpu *vcpu) return (vcpu->arch.apic_base & MSR_IA32_APICBASE_BSP) != 0; } -struct static_key kvm_no_apic_vcpu __read_mostly; -EXPORT_SYMBOL_GPL(kvm_no_apic_vcpu); +__read_mostly DEFINE_STATIC_KEY_FALSE(kvm_has_noapic_vcpu); +EXPORT_SYMBOL_GPL(kvm_has_noapic_vcpu); void kvm_arch_sched_in(struct kvm_vcpu *vcpu, int cpu) { @@ -10362,12 +10487,12 @@ void kvm_arch_sched_in(struct kvm_vcpu *vcpu, int cpu) pmu->need_cleanup = true; kvm_make_request(KVM_REQ_PMU, vcpu); } - kvm_x86_ops.sched_in(vcpu, cpu); + static_call(kvm_x86_sched_in)(vcpu, cpu); } void kvm_arch_free_vm(struct kvm *kvm) { - kfree(kvm->arch.hyperv.hv_pa_pg); + kfree(to_kvm_hv(kvm)->hv_pa_pg); vfree(kvm); } @@ -10406,7 +10531,7 @@ int kvm_arch_init_vm(struct kvm *kvm, unsigned long type) kvm_page_track_init(kvm); kvm_mmu_init_vm(kvm); - return kvm_x86_ops.vm_init(kvm); + return static_call(kvm_x86_vm_init)(kvm); } int kvm_arch_post_init_vm(struct kvm *kvm) @@ -10502,7 +10627,7 @@ void __user * __x86_set_memory_region(struct kvm *kvm, int id, gpa_t gpa, return (void __user *)hva; } else { if (!slot || !slot->npages) - return 0; + return NULL; old_npages = slot->npages; hva = slot->userspace_addr; @@ -10535,8 +10660,6 @@ void kvm_arch_pre_destroy_vm(struct kvm *kvm) void kvm_arch_destroy_vm(struct kvm *kvm) { - u32 i; - if (current->mm == kvm->mm) { /* * Free memory regions allocated on behalf of userspace, @@ -10551,10 +10674,8 @@ void kvm_arch_destroy_vm(struct kvm *kvm) __x86_set_memory_region(kvm, TSS_PRIVATE_MEMSLOT, 0, 0); mutex_unlock(&kvm->slots_lock); } - if (kvm_x86_ops.vm_destroy) - kvm_x86_ops.vm_destroy(kvm); - for (i = 0; i < kvm->arch.msr_filter.count; i++) - kfree(kvm->arch.msr_filter.ranges[i].bitmap); + static_call_cond(kvm_x86_vm_destroy)(kvm); + kvm_free_msr_filter(srcu_dereference_check(kvm->arch.msr_filter, &kvm->srcu, 1)); kvm_pic_destroy(kvm); kvm_ioapic_destroy(kvm); kvm_free_vcpus(kvm); @@ -10562,6 +10683,7 @@ void kvm_arch_destroy_vm(struct kvm *kvm) kfree(srcu_dereference_check(kvm->arch.pmu_event_filter, &kvm->srcu, 1)); kvm_mmu_uninit_vm(kvm); kvm_page_track_cleanup(kvm); + kvm_xen_destroy_vm(kvm); kvm_hv_destroy_vm(kvm); } @@ -10680,75 +10802,96 @@ int kvm_arch_prepare_memory_region(struct kvm *kvm, return 0; } + +static void kvm_mmu_update_cpu_dirty_logging(struct kvm *kvm, bool enable) +{ + struct kvm_arch *ka = &kvm->arch; + + if (!kvm_x86_ops.cpu_dirty_log_size) + return; + + if ((enable && ++ka->cpu_dirty_logging_count == 1) || + (!enable && --ka->cpu_dirty_logging_count == 0)) + kvm_make_all_cpus_request(kvm, KVM_REQ_UPDATE_CPU_DIRTY_LOGGING); + + WARN_ON_ONCE(ka->cpu_dirty_logging_count < 0); +} + static void kvm_mmu_slot_apply_flags(struct kvm *kvm, struct kvm_memory_slot *old, struct kvm_memory_slot *new, enum kvm_mr_change change) { + bool log_dirty_pages = new->flags & KVM_MEM_LOG_DIRTY_PAGES; + /* - * Nothing to do for RO slots or CREATE/MOVE/DELETE of a slot. - * See comments below. + * Update CPU dirty logging if dirty logging is being toggled. This + * applies to all operations. */ - if ((change != KVM_MR_FLAGS_ONLY) || (new->flags & KVM_MEM_READONLY)) - return; + if ((old->flags ^ new->flags) & KVM_MEM_LOG_DIRTY_PAGES) + kvm_mmu_update_cpu_dirty_logging(kvm, log_dirty_pages); /* - * Dirty logging tracks sptes in 4k granularity, meaning that large - * sptes have to be split. If live migration is successful, the guest - * in the source machine will be destroyed and large sptes will be - * created in the destination. However, if the guest continues to run - * in the source machine (for example if live migration fails), small - * sptes will remain around and cause bad performance. - * - * Scan sptes if dirty logging has been stopped, dropping those - * which can be collapsed into a single large-page spte. Later - * page faults will create the large-page sptes. + * Nothing more to do for RO slots (which can't be dirtied and can't be + * made writable) or CREATE/MOVE/DELETE of a slot. * - * There is no need to do this in any of the following cases: + * For a memslot with dirty logging disabled: * CREATE: No dirty mappings will already exist. * MOVE/DELETE: The old mappings will already have been cleaned up by * kvm_arch_flush_shadow_memslot() + * + * For a memslot with dirty logging enabled: + * CREATE: No shadow pages exist, thus nothing to write-protect + * and no dirty bits to clear. + * MOVE/DELETE: The old mappings will already have been cleaned up by + * kvm_arch_flush_shadow_memslot(). */ - if ((old->flags & KVM_MEM_LOG_DIRTY_PAGES) && - !(new->flags & KVM_MEM_LOG_DIRTY_PAGES)) - kvm_mmu_zap_collapsible_sptes(kvm, new); + if ((change != KVM_MR_FLAGS_ONLY) || (new->flags & KVM_MEM_READONLY)) + return; /* - * Enable or disable dirty logging for the slot. - * - * For KVM_MR_DELETE and KVM_MR_MOVE, the shadow pages of the old - * slot have been zapped so no dirty logging updates are needed for - * the old slot. - * For KVM_MR_CREATE and KVM_MR_MOVE, once the new slot is visible - * any mappings that might be created in it will consume the - * properties of the new slot and do not need to be updated here. - * - * When PML is enabled, the kvm_x86_ops dirty logging hooks are - * called to enable/disable dirty logging. - * - * When disabling dirty logging with PML enabled, the D-bit is set - * for sptes in the slot in order to prevent unnecessary GPA - * logging in the PML buffer (and potential PML buffer full VMEXIT). - * This guarantees leaving PML enabled for the guest's lifetime - * won't have any additional overhead from PML when the guest is - * running with dirty logging disabled. - * - * When enabling dirty logging, large sptes are write-protected - * so they can be split on first write. New large sptes cannot - * be created for this slot until the end of the logging. - * See the comments in fast_page_fault(). - * For small sptes, nothing is done if the dirty log is in the - * initial-all-set state. Otherwise, depending on whether pml - * is enabled the D-bit or the W-bit will be cleared. + * READONLY and non-flags changes were filtered out above, and the only + * other flag is LOG_DIRTY_PAGES, i.e. something is wrong if dirty + * logging isn't being toggled on or off. */ - if (new->flags & KVM_MEM_LOG_DIRTY_PAGES) { - if (kvm_x86_ops.slot_enable_log_dirty) { - kvm_x86_ops.slot_enable_log_dirty(kvm, new); - } else { - int level = - kvm_dirty_log_manual_protect_and_init_set(kvm) ? - PG_LEVEL_2M : PG_LEVEL_4K; + if (WARN_ON_ONCE(!((old->flags ^ new->flags) & KVM_MEM_LOG_DIRTY_PAGES))) + return; + + if (!log_dirty_pages) { + /* + * Dirty logging tracks sptes in 4k granularity, meaning that + * large sptes have to be split. If live migration succeeds, + * the guest in the source machine will be destroyed and large + * sptes will be created in the destination. However, if the + * guest continues to run in the source machine (for example if + * live migration fails), small sptes will remain around and + * cause bad performance. + * + * Scan sptes if dirty logging has been stopped, dropping those + * which can be collapsed into a single large-page spte. Later + * page faults will create the large-page sptes. + */ + kvm_mmu_zap_collapsible_sptes(kvm, new); + } else { + /* By default, write-protect everything to log writes. */ + int level = PG_LEVEL_4K; + if (kvm_x86_ops.cpu_dirty_log_size) { + /* + * Clear all dirty bits, unless pages are treated as + * dirty from the get-go. + */ + if (!kvm_dirty_log_manual_protect_and_init_set(kvm)) + kvm_mmu_slot_leaf_clear_dirty(kvm, new); + + /* + * Write-protect large pages on write so that dirty + * logging happens at 4k granularity. No need to + * write-protect small SPTEs since write accesses are + * logged by the CPU via dirty bits. + */ + level = PG_LEVEL_2M; + } else if (kvm_dirty_log_manual_protect_and_init_set(kvm)) { /* * If we're with initial-all-set, we don't need * to write protect any small page because @@ -10757,11 +10900,9 @@ static void kvm_mmu_slot_apply_flags(struct kvm *kvm, * so that the page split can happen lazily on * the first write to the huge page. */ - kvm_mmu_slot_remove_write_access(kvm, new, level); + level = PG_LEVEL_2M; } - } else { - if (kvm_x86_ops.slot_disable_log_dirty) - kvm_x86_ops.slot_disable_log_dirty(kvm, new); + kvm_mmu_slot_remove_write_access(kvm, new, level); } } @@ -10800,7 +10941,7 @@ static inline bool kvm_guest_apic_has_interrupt(struct kvm_vcpu *vcpu) { return (is_guest_mode(vcpu) && kvm_x86_ops.guest_apic_has_interrupt && - kvm_x86_ops.guest_apic_has_interrupt(vcpu)); + static_call(kvm_x86_guest_apic_has_interrupt)(vcpu)); } static inline bool kvm_vcpu_has_events(struct kvm_vcpu *vcpu) @@ -10819,12 +10960,12 @@ static inline bool kvm_vcpu_has_events(struct kvm_vcpu *vcpu) if (kvm_test_request(KVM_REQ_NMI, vcpu) || (vcpu->arch.nmi_pending && - kvm_x86_ops.nmi_allowed(vcpu, false))) + static_call(kvm_x86_nmi_allowed)(vcpu, false))) return true; if (kvm_test_request(KVM_REQ_SMI, vcpu) || (vcpu->arch.smi_pending && - kvm_x86_ops.smi_allowed(vcpu, false))) + static_call(kvm_x86_smi_allowed)(vcpu, false))) return true; if (kvm_arch_interrupt_allowed(vcpu) && @@ -10858,7 +10999,7 @@ bool kvm_arch_dy_runnable(struct kvm_vcpu *vcpu) kvm_test_request(KVM_REQ_EVENT, vcpu)) return true; - if (vcpu->arch.apicv_active && kvm_x86_ops.dy_apicv_has_pending_interrupt(vcpu)) + if (vcpu->arch.apicv_active && static_call(kvm_x86_dy_apicv_has_pending_interrupt)(vcpu)) return true; return false; @@ -10876,7 +11017,7 @@ int kvm_arch_vcpu_should_kick(struct kvm_vcpu *vcpu) int kvm_arch_interrupt_allowed(struct kvm_vcpu *vcpu) { - return kvm_x86_ops.interrupt_allowed(vcpu, false); + return static_call(kvm_x86_interrupt_allowed)(vcpu, false); } unsigned long kvm_get_linear_rip(struct kvm_vcpu *vcpu) @@ -10902,7 +11043,7 @@ unsigned long kvm_get_rflags(struct kvm_vcpu *vcpu) { unsigned long rflags; - rflags = kvm_x86_ops.get_rflags(vcpu); + rflags = static_call(kvm_x86_get_rflags)(vcpu); if (vcpu->guest_debug & KVM_GUESTDBG_SINGLESTEP) rflags &= ~X86_EFLAGS_TF; return rflags; @@ -10914,7 +11055,7 @@ static void __kvm_set_rflags(struct kvm_vcpu *vcpu, unsigned long rflags) if (vcpu->guest_debug & KVM_GUESTDBG_SINGLESTEP && kvm_is_linear_rip(vcpu, vcpu->arch.singlestep_rip)) rflags |= X86_EFLAGS_TF; - kvm_x86_ops.set_rflags(vcpu, rflags); + static_call(kvm_x86_set_rflags)(vcpu, rflags); } void kvm_set_rflags(struct kvm_vcpu *vcpu, unsigned long rflags) @@ -11044,7 +11185,7 @@ static bool kvm_can_deliver_async_pf(struct kvm_vcpu *vcpu) return false; if (!kvm_pv_async_pf_enabled(vcpu) || - (vcpu->arch.apf.send_user_only && kvm_x86_ops.get_cpl(vcpu) == 0)) + (vcpu->arch.apf.send_user_only && static_call(kvm_x86_get_cpl)(vcpu) == 0)) return false; return true; @@ -11189,7 +11330,7 @@ int kvm_arch_irq_bypass_add_producer(struct irq_bypass_consumer *cons, irqfd->producer = prod; kvm_arch_start_assignment(irqfd->kvm); - ret = kvm_x86_ops.update_pi_irte(irqfd->kvm, + ret = static_call(kvm_x86_update_pi_irte)(irqfd->kvm, prod->irq, irqfd->gsi, 1); if (ret) @@ -11214,7 +11355,7 @@ void kvm_arch_irq_bypass_del_producer(struct irq_bypass_consumer *cons, * when the irq is masked/disabled or the consumer side (KVM * int this case doesn't want to receive the interrupts. */ - ret = kvm_x86_ops.update_pi_irte(irqfd->kvm, prod->irq, irqfd->gsi, 0); + ret = static_call(kvm_x86_update_pi_irte)(irqfd->kvm, prod->irq, irqfd->gsi, 0); if (ret) printk(KERN_INFO "irq bypass consumer (token %p) unregistration" " fails: %d\n", irqfd->consumer.token, ret); @@ -11225,7 +11366,7 @@ void kvm_arch_irq_bypass_del_producer(struct irq_bypass_consumer *cons, int kvm_arch_update_irqfd_routing(struct kvm *kvm, unsigned int host_irq, uint32_t guest_irq, bool set) { - return kvm_x86_ops.update_pi_irte(kvm, host_irq, guest_irq, set); + return static_call(kvm_x86_update_pi_irte)(kvm, host_irq, guest_irq, set); } bool kvm_vector_hashing_enabled(void) diff --git a/arch/x86/kvm/x86.h b/arch/x86/kvm/x86.h index 0f727b50bd3d..39eb04887141 100644 --- a/arch/x86/kvm/x86.h +++ b/arch/x86/kvm/x86.h @@ -98,7 +98,7 @@ static inline bool is_64_bit_mode(struct kvm_vcpu *vcpu) if (!is_long_mode(vcpu)) return false; - kvm_x86_ops.get_cs_db_l_bits(vcpu, &cs_db, &cs_l); + static_call(kvm_x86_get_cs_db_l_bits)(vcpu, &cs_db, &cs_l); return cs_l; } @@ -129,7 +129,7 @@ static inline bool mmu_is_nested(struct kvm_vcpu *vcpu) static inline void kvm_vcpu_flush_tlb_current(struct kvm_vcpu *vcpu) { ++vcpu->stat.tlb_flush; - kvm_x86_ops.tlb_flush_current(vcpu); + static_call(kvm_x86_tlb_flush_current)(vcpu); } static inline int is_pae(struct kvm_vcpu *vcpu) @@ -244,9 +244,10 @@ static inline bool kvm_check_has_quirk(struct kvm *kvm, u64 quirk) static inline bool kvm_vcpu_latch_init(struct kvm_vcpu *vcpu) { - return is_smm(vcpu) || kvm_x86_ops.apic_init_signal_blocked(vcpu); + return is_smm(vcpu) || static_call(kvm_x86_apic_init_signal_blocked)(vcpu); } +void kvm_write_wall_clock(struct kvm *kvm, gpa_t wall_clock, int sec_hi_ofs); void kvm_inject_realmode_interrupt(struct kvm_vcpu *vcpu, int irq, int inc_eip); void kvm_write_tsc(struct kvm_vcpu *vcpu, struct msr_data *msr); @@ -273,6 +274,8 @@ bool kvm_mtrr_check_gfn_range_consistency(struct kvm_vcpu *vcpu, gfn_t gfn, int page_num); bool kvm_vector_hashing_enabled(void); void kvm_fixup_and_inject_pf_error(struct kvm_vcpu *vcpu, gva_t gva, u16 error_code); +int x86_decode_emulated_instruction(struct kvm_vcpu *vcpu, int emulation_type, + void *insn, int insn_len); int x86_emulate_instruction(struct kvm_vcpu *vcpu, gpa_t cr2_or_gpa, int emulation_type, void *insn, int insn_len); fastpath_t handle_fastpath_set_msr_irqoff(struct kvm_vcpu *vcpu); @@ -296,6 +299,8 @@ extern int pi_inject_timer; extern struct static_key kvm_no_apic_vcpu; +extern bool report_ignored_msrs; + static inline u64 nsec_to_cycles(struct kvm_vcpu *vcpu, u64 nsec) { return pvclock_scale_delta(nsec, vcpu->arch.virtual_tsc_mult, @@ -391,7 +396,6 @@ void kvm_load_guest_xsave_state(struct kvm_vcpu *vcpu); void kvm_load_host_xsave_state(struct kvm_vcpu *vcpu); int kvm_spec_ctrl_test_value(u64 value); bool kvm_is_valid_cr4(struct kvm_vcpu *vcpu, unsigned long cr4); -bool kvm_vcpu_exit_request(struct kvm_vcpu *vcpu); int kvm_handle_memory_failure(struct kvm_vcpu *vcpu, int r, struct x86_exception *e); int kvm_handle_invpcid(struct kvm_vcpu *vcpu, unsigned long type, gva_t gva); diff --git a/arch/x86/kvm/xen.c b/arch/x86/kvm/xen.c new file mode 100644 index 000000000000..ae17250e1efe --- /dev/null +++ b/arch/x86/kvm/xen.c @@ -0,0 +1,721 @@ +// SPDX-License-Identifier: GPL-2.0 +/* + * Copyright © 2019 Oracle and/or its affiliates. All rights reserved. + * Copyright © 2020 Amazon.com, Inc. or its affiliates. All Rights Reserved. + * + * KVM Xen emulation + */ + +#include "x86.h" +#include "xen.h" +#include "hyperv.h" + +#include <linux/kvm_host.h> +#include <linux/sched/stat.h> + +#include <trace/events/kvm.h> +#include <xen/interface/xen.h> +#include <xen/interface/vcpu.h> + +#include "trace.h" + +DEFINE_STATIC_KEY_DEFERRED_FALSE(kvm_xen_enabled, HZ); + +static int kvm_xen_shared_info_init(struct kvm *kvm, gfn_t gfn) +{ + gpa_t gpa = gfn_to_gpa(gfn); + int wc_ofs, sec_hi_ofs; + int ret; + int idx = srcu_read_lock(&kvm->srcu); + + ret = kvm_gfn_to_hva_cache_init(kvm, &kvm->arch.xen.shinfo_cache, + gpa, PAGE_SIZE); + if (ret) + goto out; + + kvm->arch.xen.shinfo_set = true; + + /* Paranoia checks on the 32-bit struct layout */ + BUILD_BUG_ON(offsetof(struct compat_shared_info, wc) != 0x900); + BUILD_BUG_ON(offsetof(struct compat_shared_info, arch.wc_sec_hi) != 0x924); + BUILD_BUG_ON(offsetof(struct pvclock_vcpu_time_info, version) != 0); + + /* 32-bit location by default */ + wc_ofs = offsetof(struct compat_shared_info, wc); + sec_hi_ofs = offsetof(struct compat_shared_info, arch.wc_sec_hi); + +#ifdef CONFIG_X86_64 + /* Paranoia checks on the 64-bit struct layout */ + BUILD_BUG_ON(offsetof(struct shared_info, wc) != 0xc00); + BUILD_BUG_ON(offsetof(struct shared_info, wc_sec_hi) != 0xc0c); + + if (kvm->arch.xen.long_mode) { + wc_ofs = offsetof(struct shared_info, wc); + sec_hi_ofs = offsetof(struct shared_info, wc_sec_hi); + } +#endif + + kvm_write_wall_clock(kvm, gpa + wc_ofs, sec_hi_ofs - wc_ofs); + kvm_make_all_cpus_request(kvm, KVM_REQ_MASTERCLOCK_UPDATE); + +out: + srcu_read_unlock(&kvm->srcu, idx); + return ret; +} + +static void kvm_xen_update_runstate(struct kvm_vcpu *v, int state) +{ + struct kvm_vcpu_xen *vx = &v->arch.xen; + u64 now = get_kvmclock_ns(v->kvm); + u64 delta_ns = now - vx->runstate_entry_time; + u64 run_delay = current->sched_info.run_delay; + + if (unlikely(!vx->runstate_entry_time)) + vx->current_runstate = RUNSTATE_offline; + + /* + * Time waiting for the scheduler isn't "stolen" if the + * vCPU wasn't running anyway. + */ + if (vx->current_runstate == RUNSTATE_running) { + u64 steal_ns = run_delay - vx->last_steal; + + delta_ns -= steal_ns; + + vx->runstate_times[RUNSTATE_runnable] += steal_ns; + } + vx->last_steal = run_delay; + + vx->runstate_times[vx->current_runstate] += delta_ns; + vx->current_runstate = state; + vx->runstate_entry_time = now; +} + +void kvm_xen_update_runstate_guest(struct kvm_vcpu *v, int state) +{ + struct kvm_vcpu_xen *vx = &v->arch.xen; + uint64_t state_entry_time; + unsigned int offset; + + kvm_xen_update_runstate(v, state); + + if (!vx->runstate_set) + return; + + BUILD_BUG_ON(sizeof(struct compat_vcpu_runstate_info) != 0x2c); + + offset = offsetof(struct compat_vcpu_runstate_info, state_entry_time); +#ifdef CONFIG_X86_64 + /* + * The only difference is alignment of uint64_t in 32-bit. + * So the first field 'state' is accessed directly using + * offsetof() (where its offset happens to be zero), while the + * remaining fields which are all uint64_t, start at 'offset' + * which we tweak here by adding 4. + */ + BUILD_BUG_ON(offsetof(struct vcpu_runstate_info, state_entry_time) != + offsetof(struct compat_vcpu_runstate_info, state_entry_time) + 4); + BUILD_BUG_ON(offsetof(struct vcpu_runstate_info, time) != + offsetof(struct compat_vcpu_runstate_info, time) + 4); + + if (v->kvm->arch.xen.long_mode) + offset = offsetof(struct vcpu_runstate_info, state_entry_time); +#endif + /* + * First write the updated state_entry_time at the appropriate + * location determined by 'offset'. + */ + state_entry_time = vx->runstate_entry_time; + state_entry_time |= XEN_RUNSTATE_UPDATE; + + BUILD_BUG_ON(sizeof(((struct vcpu_runstate_info *)0)->state_entry_time) != + sizeof(state_entry_time)); + BUILD_BUG_ON(sizeof(((struct compat_vcpu_runstate_info *)0)->state_entry_time) != + sizeof(state_entry_time)); + + if (kvm_write_guest_offset_cached(v->kvm, &v->arch.xen.runstate_cache, + &state_entry_time, offset, + sizeof(state_entry_time))) + return; + smp_wmb(); + + /* + * Next, write the new runstate. This is in the *same* place + * for 32-bit and 64-bit guests, asserted here for paranoia. + */ + BUILD_BUG_ON(offsetof(struct vcpu_runstate_info, state) != + offsetof(struct compat_vcpu_runstate_info, state)); + BUILD_BUG_ON(sizeof(((struct vcpu_runstate_info *)0)->state) != + sizeof(vx->current_runstate)); + BUILD_BUG_ON(sizeof(((struct compat_vcpu_runstate_info *)0)->state) != + sizeof(vx->current_runstate)); + + if (kvm_write_guest_offset_cached(v->kvm, &v->arch.xen.runstate_cache, + &vx->current_runstate, + offsetof(struct vcpu_runstate_info, state), + sizeof(vx->current_runstate))) + return; + + /* + * Write the actual runstate times immediately after the + * runstate_entry_time. + */ + BUILD_BUG_ON(offsetof(struct vcpu_runstate_info, state_entry_time) != + offsetof(struct vcpu_runstate_info, time) - sizeof(u64)); + BUILD_BUG_ON(offsetof(struct compat_vcpu_runstate_info, state_entry_time) != + offsetof(struct compat_vcpu_runstate_info, time) - sizeof(u64)); + BUILD_BUG_ON(sizeof(((struct vcpu_runstate_info *)0)->time) != + sizeof(((struct compat_vcpu_runstate_info *)0)->time)); + BUILD_BUG_ON(sizeof(((struct vcpu_runstate_info *)0)->time) != + sizeof(vx->runstate_times)); + + if (kvm_write_guest_offset_cached(v->kvm, &v->arch.xen.runstate_cache, + &vx->runstate_times[0], + offset + sizeof(u64), + sizeof(vx->runstate_times))) + return; + + smp_wmb(); + + /* + * Finally, clear the XEN_RUNSTATE_UPDATE bit in the guest's + * runstate_entry_time field. + */ + + state_entry_time &= ~XEN_RUNSTATE_UPDATE; + if (kvm_write_guest_offset_cached(v->kvm, &v->arch.xen.runstate_cache, + &state_entry_time, offset, + sizeof(state_entry_time))) + return; +} + +int __kvm_xen_has_interrupt(struct kvm_vcpu *v) +{ + u8 rc = 0; + + /* + * If the global upcall vector (HVMIRQ_callback_vector) is set and + * the vCPU's evtchn_upcall_pending flag is set, the IRQ is pending. + */ + struct gfn_to_hva_cache *ghc = &v->arch.xen.vcpu_info_cache; + struct kvm_memslots *slots = kvm_memslots(v->kvm); + unsigned int offset = offsetof(struct vcpu_info, evtchn_upcall_pending); + + /* No need for compat handling here */ + BUILD_BUG_ON(offsetof(struct vcpu_info, evtchn_upcall_pending) != + offsetof(struct compat_vcpu_info, evtchn_upcall_pending)); + BUILD_BUG_ON(sizeof(rc) != + sizeof(((struct vcpu_info *)0)->evtchn_upcall_pending)); + BUILD_BUG_ON(sizeof(rc) != + sizeof(((struct compat_vcpu_info *)0)->evtchn_upcall_pending)); + + /* + * For efficiency, this mirrors the checks for using the valid + * cache in kvm_read_guest_offset_cached(), but just uses + * __get_user() instead. And falls back to the slow path. + */ + if (likely(slots->generation == ghc->generation && + !kvm_is_error_hva(ghc->hva) && ghc->memslot)) { + /* Fast path */ + __get_user(rc, (u8 __user *)ghc->hva + offset); + } else { + /* Slow path */ + kvm_read_guest_offset_cached(v->kvm, ghc, &rc, offset, + sizeof(rc)); + } + + return rc; +} + +int kvm_xen_hvm_set_attr(struct kvm *kvm, struct kvm_xen_hvm_attr *data) +{ + int r = -ENOENT; + + mutex_lock(&kvm->lock); + + switch (data->type) { + case KVM_XEN_ATTR_TYPE_LONG_MODE: + if (!IS_ENABLED(CONFIG_64BIT) && data->u.long_mode) { + r = -EINVAL; + } else { + kvm->arch.xen.long_mode = !!data->u.long_mode; + r = 0; + } + break; + + case KVM_XEN_ATTR_TYPE_SHARED_INFO: + if (data->u.shared_info.gfn == GPA_INVALID) { + kvm->arch.xen.shinfo_set = false; + r = 0; + break; + } + r = kvm_xen_shared_info_init(kvm, data->u.shared_info.gfn); + break; + + + case KVM_XEN_ATTR_TYPE_UPCALL_VECTOR: + if (data->u.vector && data->u.vector < 0x10) + r = -EINVAL; + else { + kvm->arch.xen.upcall_vector = data->u.vector; + r = 0; + } + break; + + default: + break; + } + + mutex_unlock(&kvm->lock); + return r; +} + +int kvm_xen_hvm_get_attr(struct kvm *kvm, struct kvm_xen_hvm_attr *data) +{ + int r = -ENOENT; + + mutex_lock(&kvm->lock); + + switch (data->type) { + case KVM_XEN_ATTR_TYPE_LONG_MODE: + data->u.long_mode = kvm->arch.xen.long_mode; + r = 0; + break; + + case KVM_XEN_ATTR_TYPE_SHARED_INFO: + if (kvm->arch.xen.shinfo_set) + data->u.shared_info.gfn = gpa_to_gfn(kvm->arch.xen.shinfo_cache.gpa); + else + data->u.shared_info.gfn = GPA_INVALID; + r = 0; + break; + + case KVM_XEN_ATTR_TYPE_UPCALL_VECTOR: + data->u.vector = kvm->arch.xen.upcall_vector; + r = 0; + break; + + default: + break; + } + + mutex_unlock(&kvm->lock); + return r; +} + +int kvm_xen_vcpu_set_attr(struct kvm_vcpu *vcpu, struct kvm_xen_vcpu_attr *data) +{ + int idx, r = -ENOENT; + + mutex_lock(&vcpu->kvm->lock); + idx = srcu_read_lock(&vcpu->kvm->srcu); + + switch (data->type) { + case KVM_XEN_VCPU_ATTR_TYPE_VCPU_INFO: + /* No compat necessary here. */ + BUILD_BUG_ON(sizeof(struct vcpu_info) != + sizeof(struct compat_vcpu_info)); + BUILD_BUG_ON(offsetof(struct vcpu_info, time) != + offsetof(struct compat_vcpu_info, time)); + + if (data->u.gpa == GPA_INVALID) { + vcpu->arch.xen.vcpu_info_set = false; + r = 0; + break; + } + + r = kvm_gfn_to_hva_cache_init(vcpu->kvm, + &vcpu->arch.xen.vcpu_info_cache, + data->u.gpa, + sizeof(struct vcpu_info)); + if (!r) { + vcpu->arch.xen.vcpu_info_set = true; + kvm_make_request(KVM_REQ_CLOCK_UPDATE, vcpu); + } + break; + + case KVM_XEN_VCPU_ATTR_TYPE_VCPU_TIME_INFO: + if (data->u.gpa == GPA_INVALID) { + vcpu->arch.xen.vcpu_time_info_set = false; + r = 0; + break; + } + + r = kvm_gfn_to_hva_cache_init(vcpu->kvm, + &vcpu->arch.xen.vcpu_time_info_cache, + data->u.gpa, + sizeof(struct pvclock_vcpu_time_info)); + if (!r) { + vcpu->arch.xen.vcpu_time_info_set = true; + kvm_make_request(KVM_REQ_CLOCK_UPDATE, vcpu); + } + break; + + case KVM_XEN_VCPU_ATTR_TYPE_RUNSTATE_ADDR: + if (!sched_info_on()) { + r = -EOPNOTSUPP; + break; + } + if (data->u.gpa == GPA_INVALID) { + vcpu->arch.xen.runstate_set = false; + r = 0; + break; + } + + r = kvm_gfn_to_hva_cache_init(vcpu->kvm, + &vcpu->arch.xen.runstate_cache, + data->u.gpa, + sizeof(struct vcpu_runstate_info)); + if (!r) { + vcpu->arch.xen.runstate_set = true; + } + break; + + case KVM_XEN_VCPU_ATTR_TYPE_RUNSTATE_CURRENT: + if (!sched_info_on()) { + r = -EOPNOTSUPP; + break; + } + if (data->u.runstate.state > RUNSTATE_offline) { + r = -EINVAL; + break; + } + + kvm_xen_update_runstate(vcpu, data->u.runstate.state); + r = 0; + break; + + case KVM_XEN_VCPU_ATTR_TYPE_RUNSTATE_DATA: + if (!sched_info_on()) { + r = -EOPNOTSUPP; + break; + } + if (data->u.runstate.state > RUNSTATE_offline) { + r = -EINVAL; + break; + } + if (data->u.runstate.state_entry_time != + (data->u.runstate.time_running + + data->u.runstate.time_runnable + + data->u.runstate.time_blocked + + data->u.runstate.time_offline)) { + r = -EINVAL; + break; + } + if (get_kvmclock_ns(vcpu->kvm) < + data->u.runstate.state_entry_time) { + r = -EINVAL; + break; + } + + vcpu->arch.xen.current_runstate = data->u.runstate.state; + vcpu->arch.xen.runstate_entry_time = + data->u.runstate.state_entry_time; + vcpu->arch.xen.runstate_times[RUNSTATE_running] = + data->u.runstate.time_running; + vcpu->arch.xen.runstate_times[RUNSTATE_runnable] = + data->u.runstate.time_runnable; + vcpu->arch.xen.runstate_times[RUNSTATE_blocked] = + data->u.runstate.time_blocked; + vcpu->arch.xen.runstate_times[RUNSTATE_offline] = + data->u.runstate.time_offline; + vcpu->arch.xen.last_steal = current->sched_info.run_delay; + r = 0; + break; + + case KVM_XEN_VCPU_ATTR_TYPE_RUNSTATE_ADJUST: + if (!sched_info_on()) { + r = -EOPNOTSUPP; + break; + } + if (data->u.runstate.state > RUNSTATE_offline && + data->u.runstate.state != (u64)-1) { + r = -EINVAL; + break; + } + /* The adjustment must add up */ + if (data->u.runstate.state_entry_time != + (data->u.runstate.time_running + + data->u.runstate.time_runnable + + data->u.runstate.time_blocked + + data->u.runstate.time_offline)) { + r = -EINVAL; + break; + } + + if (get_kvmclock_ns(vcpu->kvm) < + (vcpu->arch.xen.runstate_entry_time + + data->u.runstate.state_entry_time)) { + r = -EINVAL; + break; + } + + vcpu->arch.xen.runstate_entry_time += + data->u.runstate.state_entry_time; + vcpu->arch.xen.runstate_times[RUNSTATE_running] += + data->u.runstate.time_running; + vcpu->arch.xen.runstate_times[RUNSTATE_runnable] += + data->u.runstate.time_runnable; + vcpu->arch.xen.runstate_times[RUNSTATE_blocked] += + data->u.runstate.time_blocked; + vcpu->arch.xen.runstate_times[RUNSTATE_offline] += + data->u.runstate.time_offline; + + if (data->u.runstate.state <= RUNSTATE_offline) + kvm_xen_update_runstate(vcpu, data->u.runstate.state); + r = 0; + break; + + default: + break; + } + + srcu_read_unlock(&vcpu->kvm->srcu, idx); + mutex_unlock(&vcpu->kvm->lock); + return r; +} + +int kvm_xen_vcpu_get_attr(struct kvm_vcpu *vcpu, struct kvm_xen_vcpu_attr *data) +{ + int r = -ENOENT; + + mutex_lock(&vcpu->kvm->lock); + + switch (data->type) { + case KVM_XEN_VCPU_ATTR_TYPE_VCPU_INFO: + if (vcpu->arch.xen.vcpu_info_set) + data->u.gpa = vcpu->arch.xen.vcpu_info_cache.gpa; + else + data->u.gpa = GPA_INVALID; + r = 0; + break; + + case KVM_XEN_VCPU_ATTR_TYPE_VCPU_TIME_INFO: + if (vcpu->arch.xen.vcpu_time_info_set) + data->u.gpa = vcpu->arch.xen.vcpu_time_info_cache.gpa; + else + data->u.gpa = GPA_INVALID; + r = 0; + break; + + case KVM_XEN_VCPU_ATTR_TYPE_RUNSTATE_ADDR: + if (!sched_info_on()) { + r = -EOPNOTSUPP; + break; + } + if (vcpu->arch.xen.runstate_set) { + data->u.gpa = vcpu->arch.xen.runstate_cache.gpa; + r = 0; + } + break; + + case KVM_XEN_VCPU_ATTR_TYPE_RUNSTATE_CURRENT: + if (!sched_info_on()) { + r = -EOPNOTSUPP; + break; + } + data->u.runstate.state = vcpu->arch.xen.current_runstate; + r = 0; + break; + + case KVM_XEN_VCPU_ATTR_TYPE_RUNSTATE_DATA: + if (!sched_info_on()) { + r = -EOPNOTSUPP; + break; + } + data->u.runstate.state = vcpu->arch.xen.current_runstate; + data->u.runstate.state_entry_time = + vcpu->arch.xen.runstate_entry_time; + data->u.runstate.time_running = + vcpu->arch.xen.runstate_times[RUNSTATE_running]; + data->u.runstate.time_runnable = + vcpu->arch.xen.runstate_times[RUNSTATE_runnable]; + data->u.runstate.time_blocked = + vcpu->arch.xen.runstate_times[RUNSTATE_blocked]; + data->u.runstate.time_offline = + vcpu->arch.xen.runstate_times[RUNSTATE_offline]; + r = 0; + break; + + case KVM_XEN_VCPU_ATTR_TYPE_RUNSTATE_ADJUST: + r = -EINVAL; + break; + + default: + break; + } + + mutex_unlock(&vcpu->kvm->lock); + return r; +} + +int kvm_xen_write_hypercall_page(struct kvm_vcpu *vcpu, u64 data) +{ + struct kvm *kvm = vcpu->kvm; + u32 page_num = data & ~PAGE_MASK; + u64 page_addr = data & PAGE_MASK; + bool lm = is_long_mode(vcpu); + + /* Latch long_mode for shared_info pages etc. */ + vcpu->kvm->arch.xen.long_mode = lm; + + /* + * If Xen hypercall intercept is enabled, fill the hypercall + * page with VMCALL/VMMCALL instructions since that's what + * we catch. Else the VMM has provided the hypercall pages + * with instructions of its own choosing, so use those. + */ + if (kvm_xen_hypercall_enabled(kvm)) { + u8 instructions[32]; + int i; + + if (page_num) + return 1; + + /* mov imm32, %eax */ + instructions[0] = 0xb8; + + /* vmcall / vmmcall */ + kvm_x86_ops.patch_hypercall(vcpu, instructions + 5); + + /* ret */ + instructions[8] = 0xc3; + + /* int3 to pad */ + memset(instructions + 9, 0xcc, sizeof(instructions) - 9); + + for (i = 0; i < PAGE_SIZE / sizeof(instructions); i++) { + *(u32 *)&instructions[1] = i; + if (kvm_vcpu_write_guest(vcpu, + page_addr + (i * sizeof(instructions)), + instructions, sizeof(instructions))) + return 1; + } + } else { + /* + * Note, truncation is a non-issue as 'lm' is guaranteed to be + * false for a 32-bit kernel, i.e. when hva_t is only 4 bytes. + */ + hva_t blob_addr = lm ? kvm->arch.xen_hvm_config.blob_addr_64 + : kvm->arch.xen_hvm_config.blob_addr_32; + u8 blob_size = lm ? kvm->arch.xen_hvm_config.blob_size_64 + : kvm->arch.xen_hvm_config.blob_size_32; + u8 *page; + + if (page_num >= blob_size) + return 1; + + blob_addr += page_num * PAGE_SIZE; + + page = memdup_user((u8 __user *)blob_addr, PAGE_SIZE); + if (IS_ERR(page)) + return PTR_ERR(page); + + if (kvm_vcpu_write_guest(vcpu, page_addr, page, PAGE_SIZE)) { + kfree(page); + return 1; + } + } + return 0; +} + +int kvm_xen_hvm_config(struct kvm *kvm, struct kvm_xen_hvm_config *xhc) +{ + if (xhc->flags & ~KVM_XEN_HVM_CONFIG_INTERCEPT_HCALL) + return -EINVAL; + + /* + * With hypercall interception the kernel generates its own + * hypercall page so it must not be provided. + */ + if ((xhc->flags & KVM_XEN_HVM_CONFIG_INTERCEPT_HCALL) && + (xhc->blob_addr_32 || xhc->blob_addr_64 || + xhc->blob_size_32 || xhc->blob_size_64)) + return -EINVAL; + + mutex_lock(&kvm->lock); + + if (xhc->msr && !kvm->arch.xen_hvm_config.msr) + static_branch_inc(&kvm_xen_enabled.key); + else if (!xhc->msr && kvm->arch.xen_hvm_config.msr) + static_branch_slow_dec_deferred(&kvm_xen_enabled); + + memcpy(&kvm->arch.xen_hvm_config, xhc, sizeof(*xhc)); + + mutex_unlock(&kvm->lock); + return 0; +} + +void kvm_xen_destroy_vm(struct kvm *kvm) +{ + if (kvm->arch.xen_hvm_config.msr) + static_branch_slow_dec_deferred(&kvm_xen_enabled); +} + +static int kvm_xen_hypercall_set_result(struct kvm_vcpu *vcpu, u64 result) +{ + kvm_rax_write(vcpu, result); + return kvm_skip_emulated_instruction(vcpu); +} + +static int kvm_xen_hypercall_complete_userspace(struct kvm_vcpu *vcpu) +{ + struct kvm_run *run = vcpu->run; + + if (unlikely(!kvm_is_linear_rip(vcpu, vcpu->arch.xen.hypercall_rip))) + return 1; + + return kvm_xen_hypercall_set_result(vcpu, run->xen.u.hcall.result); +} + +int kvm_xen_hypercall(struct kvm_vcpu *vcpu) +{ + bool longmode; + u64 input, params[6]; + + input = (u64)kvm_register_read(vcpu, VCPU_REGS_RAX); + + /* Hyper-V hypercalls get bit 31 set in EAX */ + if ((input & 0x80000000) && + kvm_hv_hypercall_enabled(vcpu)) + return kvm_hv_hypercall(vcpu); + + longmode = is_64_bit_mode(vcpu); + if (!longmode) { + params[0] = (u32)kvm_rbx_read(vcpu); + params[1] = (u32)kvm_rcx_read(vcpu); + params[2] = (u32)kvm_rdx_read(vcpu); + params[3] = (u32)kvm_rsi_read(vcpu); + params[4] = (u32)kvm_rdi_read(vcpu); + params[5] = (u32)kvm_rbp_read(vcpu); + } +#ifdef CONFIG_X86_64 + else { + params[0] = (u64)kvm_rdi_read(vcpu); + params[1] = (u64)kvm_rsi_read(vcpu); + params[2] = (u64)kvm_rdx_read(vcpu); + params[3] = (u64)kvm_r10_read(vcpu); + params[4] = (u64)kvm_r8_read(vcpu); + params[5] = (u64)kvm_r9_read(vcpu); + } +#endif + trace_kvm_xen_hypercall(input, params[0], params[1], params[2], + params[3], params[4], params[5]); + + vcpu->run->exit_reason = KVM_EXIT_XEN; + vcpu->run->xen.type = KVM_EXIT_XEN_HCALL; + vcpu->run->xen.u.hcall.longmode = longmode; + vcpu->run->xen.u.hcall.cpl = kvm_x86_ops.get_cpl(vcpu); + vcpu->run->xen.u.hcall.input = input; + vcpu->run->xen.u.hcall.params[0] = params[0]; + vcpu->run->xen.u.hcall.params[1] = params[1]; + vcpu->run->xen.u.hcall.params[2] = params[2]; + vcpu->run->xen.u.hcall.params[3] = params[3]; + vcpu->run->xen.u.hcall.params[4] = params[4]; + vcpu->run->xen.u.hcall.params[5] = params[5]; + vcpu->arch.xen.hypercall_rip = kvm_get_linear_rip(vcpu); + vcpu->arch.complete_userspace_io = + kvm_xen_hypercall_complete_userspace; + + return 0; +} diff --git a/arch/x86/kvm/xen.h b/arch/x86/kvm/xen.h new file mode 100644 index 000000000000..463a7844a8ca --- /dev/null +++ b/arch/x86/kvm/xen.h @@ -0,0 +1,138 @@ +// SPDX-License-Identifier: GPL-2.0 +/* + * Copyright © 2019 Oracle and/or its affiliates. All rights reserved. + * Copyright © 2020 Amazon.com, Inc. or its affiliates. All Rights Reserved. + * + * KVM Xen emulation + */ + +#ifndef __ARCH_X86_KVM_XEN_H__ +#define __ARCH_X86_KVM_XEN_H__ + +#ifdef CONFIG_KVM_XEN +#include <linux/jump_label_ratelimit.h> + +extern struct static_key_false_deferred kvm_xen_enabled; + +int __kvm_xen_has_interrupt(struct kvm_vcpu *vcpu); +int kvm_xen_vcpu_set_attr(struct kvm_vcpu *vcpu, struct kvm_xen_vcpu_attr *data); +int kvm_xen_vcpu_get_attr(struct kvm_vcpu *vcpu, struct kvm_xen_vcpu_attr *data); +int kvm_xen_hvm_set_attr(struct kvm *kvm, struct kvm_xen_hvm_attr *data); +int kvm_xen_hvm_get_attr(struct kvm *kvm, struct kvm_xen_hvm_attr *data); +int kvm_xen_write_hypercall_page(struct kvm_vcpu *vcpu, u64 data); +int kvm_xen_hvm_config(struct kvm *kvm, struct kvm_xen_hvm_config *xhc); +void kvm_xen_destroy_vm(struct kvm *kvm); + +static inline bool kvm_xen_msr_enabled(struct kvm *kvm) +{ + return static_branch_unlikely(&kvm_xen_enabled.key) && + kvm->arch.xen_hvm_config.msr; +} + +static inline bool kvm_xen_hypercall_enabled(struct kvm *kvm) +{ + return static_branch_unlikely(&kvm_xen_enabled.key) && + (kvm->arch.xen_hvm_config.flags & + KVM_XEN_HVM_CONFIG_INTERCEPT_HCALL); +} + +static inline int kvm_xen_has_interrupt(struct kvm_vcpu *vcpu) +{ + if (static_branch_unlikely(&kvm_xen_enabled.key) && + vcpu->arch.xen.vcpu_info_set && vcpu->kvm->arch.xen.upcall_vector) + return __kvm_xen_has_interrupt(vcpu); + + return 0; +} +#else +static inline int kvm_xen_write_hypercall_page(struct kvm_vcpu *vcpu, u64 data) +{ + return 1; +} + +static inline void kvm_xen_destroy_vm(struct kvm *kvm) +{ +} + +static inline bool kvm_xen_msr_enabled(struct kvm *kvm) +{ + return false; +} + +static inline bool kvm_xen_hypercall_enabled(struct kvm *kvm) +{ + return false; +} + +static inline int kvm_xen_has_interrupt(struct kvm_vcpu *vcpu) +{ + return 0; +} +#endif + +int kvm_xen_hypercall(struct kvm_vcpu *vcpu); + +#include <asm/pvclock-abi.h> +#include <asm/xen/interface.h> +#include <xen/interface/vcpu.h> + +void kvm_xen_update_runstate_guest(struct kvm_vcpu *vcpu, int state); + +static inline void kvm_xen_runstate_set_running(struct kvm_vcpu *vcpu) +{ + kvm_xen_update_runstate_guest(vcpu, RUNSTATE_running); +} + +static inline void kvm_xen_runstate_set_preempted(struct kvm_vcpu *vcpu) +{ + /* + * If the vCPU wasn't preempted but took a normal exit for + * some reason (hypercalls, I/O, etc.), that is accounted as + * still RUNSTATE_running, as the VMM is still operating on + * behalf of the vCPU. Only if the VMM does actually block + * does it need to enter RUNSTATE_blocked. + */ + if (vcpu->preempted) + kvm_xen_update_runstate_guest(vcpu, RUNSTATE_runnable); +} + +/* 32-bit compatibility definitions, also used natively in 32-bit build */ +struct compat_arch_vcpu_info { + unsigned int cr2; + unsigned int pad[5]; +}; + +struct compat_vcpu_info { + uint8_t evtchn_upcall_pending; + uint8_t evtchn_upcall_mask; + uint16_t pad; + uint32_t evtchn_pending_sel; + struct compat_arch_vcpu_info arch; + struct pvclock_vcpu_time_info time; +}; /* 64 bytes (x86) */ + +struct compat_arch_shared_info { + unsigned int max_pfn; + unsigned int pfn_to_mfn_frame_list_list; + unsigned int nmi_reason; + unsigned int p2m_cr3; + unsigned int p2m_vaddr; + unsigned int p2m_generation; + uint32_t wc_sec_hi; +}; + +struct compat_shared_info { + struct compat_vcpu_info vcpu_info[MAX_VIRT_CPUS]; + uint32_t evtchn_pending[32]; + uint32_t evtchn_mask[32]; + struct pvclock_wall_clock wc; + struct compat_arch_shared_info arch; +}; + +struct compat_vcpu_runstate_info { + int state; + uint64_t state_entry_time; + uint64_t time[4]; +} __attribute__((packed)); + +#endif /* __ARCH_X86_KVM_XEN_H__ */ diff --git a/arch/x86/lib/insn-eval.c b/arch/x86/lib/insn-eval.c index 4229950a5d78..bb0b3fe1e0a0 100644 --- a/arch/x86/lib/insn-eval.c +++ b/arch/x86/lib/insn-eval.c @@ -1415,6 +1415,25 @@ void __user *insn_get_addr_ref(struct insn *insn, struct pt_regs *regs) } } +static unsigned long insn_get_effective_ip(struct pt_regs *regs) +{ + unsigned long seg_base = 0; + + /* + * If not in user-space long mode, a custom code segment could be in + * use. This is true in protected mode (if the process defined a local + * descriptor table), or virtual-8086 mode. In most of the cases + * seg_base will be zero as in USER_CS. + */ + if (!user_64bit_mode(regs)) { + seg_base = insn_get_seg_base(regs, INAT_SEG_REG_CS); + if (seg_base == -1L) + return 0; + } + + return seg_base + regs->ip; +} + /** * insn_fetch_from_user() - Copy instruction bytes from user-space memory * @regs: Structure with register values as seen when entering kernel mode @@ -1431,24 +1450,43 @@ void __user *insn_get_addr_ref(struct insn *insn, struct pt_regs *regs) */ int insn_fetch_from_user(struct pt_regs *regs, unsigned char buf[MAX_INSN_SIZE]) { - unsigned long seg_base = 0; + unsigned long ip; int not_copied; - /* - * If not in user-space long mode, a custom code segment could be in - * use. This is true in protected mode (if the process defined a local - * descriptor table), or virtual-8086 mode. In most of the cases - * seg_base will be zero as in USER_CS. - */ - if (!user_64bit_mode(regs)) { - seg_base = insn_get_seg_base(regs, INAT_SEG_REG_CS); - if (seg_base == -1L) - return 0; - } + ip = insn_get_effective_ip(regs); + if (!ip) + return 0; + + not_copied = copy_from_user(buf, (void __user *)ip, MAX_INSN_SIZE); + return MAX_INSN_SIZE - not_copied; +} + +/** + * insn_fetch_from_user_inatomic() - Copy instruction bytes from user-space memory + * while in atomic code + * @regs: Structure with register values as seen when entering kernel mode + * @buf: Array to store the fetched instruction + * + * Gets the linear address of the instruction and copies the instruction bytes + * to the buf. This function must be used in atomic context. + * + * Returns: + * + * Number of instruction bytes copied. + * + * 0 if nothing was copied. + */ +int insn_fetch_from_user_inatomic(struct pt_regs *regs, unsigned char buf[MAX_INSN_SIZE]) +{ + unsigned long ip; + int not_copied; + + ip = insn_get_effective_ip(regs); + if (!ip) + return 0; - not_copied = copy_from_user(buf, (void __user *)(seg_base + regs->ip), - MAX_INSN_SIZE); + not_copied = __copy_from_user_inatomic(buf, (void __user *)ip, MAX_INSN_SIZE); return MAX_INSN_SIZE - not_copied; } diff --git a/arch/x86/lib/insn.c b/arch/x86/lib/insn.c index 404279563891..435630a6ec97 100644 --- a/arch/x86/lib/insn.c +++ b/arch/x86/lib/insn.c @@ -5,6 +5,7 @@ * Copyright (C) IBM Corporation, 2002, 2004, 2009 */ +#include <linux/kernel.h> #ifdef __KERNEL__ #include <linux/string.h> #else @@ -15,15 +16,28 @@ #include <asm/emulate_prefix.h> +#define leXX_to_cpu(t, r) \ +({ \ + __typeof__(t) v; \ + switch (sizeof(t)) { \ + case 4: v = le32_to_cpu(r); break; \ + case 2: v = le16_to_cpu(r); break; \ + case 1: v = r; break; \ + default: \ + BUILD_BUG(); break; \ + } \ + v; \ +}) + /* Verify next sizeof(t) bytes can be on the same instruction */ #define validate_next(t, insn, n) \ ((insn)->next_byte + sizeof(t) + n <= (insn)->end_kaddr) #define __get_next(t, insn) \ - ({ t r = *(t*)insn->next_byte; insn->next_byte += sizeof(t); r; }) + ({ t r = *(t*)insn->next_byte; insn->next_byte += sizeof(t); leXX_to_cpu(t, r); }) #define __peek_nbyte_next(t, insn, n) \ - ({ t r = *(t*)((insn)->next_byte + n); r; }) + ({ t r = *(t*)((insn)->next_byte + n); leXX_to_cpu(t, r); }) #define get_next(t, insn) \ ({ if (unlikely(!validate_next(t, insn, 0))) goto err_out; __get_next(t, insn); }) @@ -147,9 +161,9 @@ found: b = insn->prefixes.bytes[3]; for (i = 0; i < nb; i++) if (prefixes->bytes[i] == lb) - prefixes->bytes[i] = b; + insn_set_byte(prefixes, i, b); } - insn->prefixes.bytes[3] = lb; + insn_set_byte(&insn->prefixes, 3, lb); } /* Decode REX prefix */ @@ -157,8 +171,7 @@ found: b = peek_next(insn_byte_t, insn); attr = inat_get_opcode_attribute(b); if (inat_is_rex_prefix(attr)) { - insn->rex_prefix.value = b; - insn->rex_prefix.nbytes = 1; + insn_field_set(&insn->rex_prefix, b, 1); insn->next_byte++; if (X86_REX_W(b)) /* REX.W overrides opnd_size */ @@ -181,13 +194,13 @@ found: if (X86_MODRM_MOD(b2) != 3) goto vex_end; } - insn->vex_prefix.bytes[0] = b; - insn->vex_prefix.bytes[1] = b2; + insn_set_byte(&insn->vex_prefix, 0, b); + insn_set_byte(&insn->vex_prefix, 1, b2); if (inat_is_evex_prefix(attr)) { b2 = peek_nbyte_next(insn_byte_t, insn, 2); - insn->vex_prefix.bytes[2] = b2; + insn_set_byte(&insn->vex_prefix, 2, b2); b2 = peek_nbyte_next(insn_byte_t, insn, 3); - insn->vex_prefix.bytes[3] = b2; + insn_set_byte(&insn->vex_prefix, 3, b2); insn->vex_prefix.nbytes = 4; insn->next_byte += 4; if (insn->x86_64 && X86_VEX_W(b2)) @@ -195,7 +208,7 @@ found: insn->opnd_bytes = 8; } else if (inat_is_vex3_prefix(attr)) { b2 = peek_nbyte_next(insn_byte_t, insn, 2); - insn->vex_prefix.bytes[2] = b2; + insn_set_byte(&insn->vex_prefix, 2, b2); insn->vex_prefix.nbytes = 3; insn->next_byte += 3; if (insn->x86_64 && X86_VEX_W(b2)) @@ -207,7 +220,7 @@ found: * Makes it easier to decode vex.W, vex.vvvv, * vex.L and vex.pp. Masking with 0x7f sets vex.W == 0. */ - insn->vex_prefix.bytes[2] = b2 & 0x7f; + insn_set_byte(&insn->vex_prefix, 2, b2 & 0x7f); insn->vex_prefix.nbytes = 2; insn->next_byte += 2; } @@ -243,7 +256,7 @@ void insn_get_opcode(struct insn *insn) /* Get first opcode */ op = get_next(insn_byte_t, insn); - opcode->bytes[0] = op; + insn_set_byte(opcode, 0, op); opcode->nbytes = 1; /* Check if there is VEX prefix or not */ @@ -295,8 +308,7 @@ void insn_get_modrm(struct insn *insn) if (inat_has_modrm(insn->attr)) { mod = get_next(insn_byte_t, insn); - modrm->value = mod; - modrm->nbytes = 1; + insn_field_set(modrm, mod, 1); if (inat_is_group(insn->attr)) { pfx_id = insn_last_prefix_id(insn); insn->attr = inat_get_group_attribute(mod, pfx_id, @@ -334,7 +346,7 @@ int insn_rip_relative(struct insn *insn) * For rip-relative instructions, the mod field (top 2 bits) * is zero and the r/m field (bottom 3 bits) is 0x5. */ - return (modrm->nbytes && (modrm->value & 0xc7) == 0x5); + return (modrm->nbytes && (modrm->bytes[0] & 0xc7) == 0x5); } /** @@ -353,11 +365,11 @@ void insn_get_sib(struct insn *insn) if (!insn->modrm.got) insn_get_modrm(insn); if (insn->modrm.nbytes) { - modrm = (insn_byte_t)insn->modrm.value; + modrm = insn->modrm.bytes[0]; if (insn->addr_bytes != 2 && X86_MODRM_MOD(modrm) != 3 && X86_MODRM_RM(modrm) == 4) { - insn->sib.value = get_next(insn_byte_t, insn); - insn->sib.nbytes = 1; + insn_field_set(&insn->sib, + get_next(insn_byte_t, insn), 1); } } insn->sib.got = 1; @@ -407,19 +419,18 @@ void insn_get_displacement(struct insn *insn) if (mod == 3) goto out; if (mod == 1) { - insn->displacement.value = get_next(signed char, insn); - insn->displacement.nbytes = 1; + insn_field_set(&insn->displacement, + get_next(signed char, insn), 1); } else if (insn->addr_bytes == 2) { if ((mod == 0 && rm == 6) || mod == 2) { - insn->displacement.value = - get_next(short, insn); - insn->displacement.nbytes = 2; + insn_field_set(&insn->displacement, + get_next(short, insn), 2); } } else { if ((mod == 0 && rm == 5) || mod == 2 || (mod == 0 && base == 5)) { - insn->displacement.value = get_next(int, insn); - insn->displacement.nbytes = 4; + insn_field_set(&insn->displacement, + get_next(int, insn), 4); } } } @@ -435,18 +446,14 @@ static int __get_moffset(struct insn *insn) { switch (insn->addr_bytes) { case 2: - insn->moffset1.value = get_next(short, insn); - insn->moffset1.nbytes = 2; + insn_field_set(&insn->moffset1, get_next(short, insn), 2); break; case 4: - insn->moffset1.value = get_next(int, insn); - insn->moffset1.nbytes = 4; + insn_field_set(&insn->moffset1, get_next(int, insn), 4); break; case 8: - insn->moffset1.value = get_next(int, insn); - insn->moffset1.nbytes = 4; - insn->moffset2.value = get_next(int, insn); - insn->moffset2.nbytes = 4; + insn_field_set(&insn->moffset1, get_next(int, insn), 4); + insn_field_set(&insn->moffset2, get_next(int, insn), 4); break; default: /* opnd_bytes must be modified manually */ goto err_out; @@ -464,13 +471,11 @@ static int __get_immv32(struct insn *insn) { switch (insn->opnd_bytes) { case 2: - insn->immediate.value = get_next(short, insn); - insn->immediate.nbytes = 2; + insn_field_set(&insn->immediate, get_next(short, insn), 2); break; case 4: case 8: - insn->immediate.value = get_next(int, insn); - insn->immediate.nbytes = 4; + insn_field_set(&insn->immediate, get_next(int, insn), 4); break; default: /* opnd_bytes must be modified manually */ goto err_out; @@ -487,18 +492,15 @@ static int __get_immv(struct insn *insn) { switch (insn->opnd_bytes) { case 2: - insn->immediate1.value = get_next(short, insn); - insn->immediate1.nbytes = 2; + insn_field_set(&insn->immediate1, get_next(short, insn), 2); break; case 4: - insn->immediate1.value = get_next(int, insn); + insn_field_set(&insn->immediate1, get_next(int, insn), 4); insn->immediate1.nbytes = 4; break; case 8: - insn->immediate1.value = get_next(int, insn); - insn->immediate1.nbytes = 4; - insn->immediate2.value = get_next(int, insn); - insn->immediate2.nbytes = 4; + insn_field_set(&insn->immediate1, get_next(int, insn), 4); + insn_field_set(&insn->immediate2, get_next(int, insn), 4); break; default: /* opnd_bytes must be modified manually */ goto err_out; @@ -515,12 +517,10 @@ static int __get_immptr(struct insn *insn) { switch (insn->opnd_bytes) { case 2: - insn->immediate1.value = get_next(short, insn); - insn->immediate1.nbytes = 2; + insn_field_set(&insn->immediate1, get_next(short, insn), 2); break; case 4: - insn->immediate1.value = get_next(int, insn); - insn->immediate1.nbytes = 4; + insn_field_set(&insn->immediate1, get_next(int, insn), 4); break; case 8: /* ptr16:64 is not exist (no segment) */ @@ -528,8 +528,7 @@ static int __get_immptr(struct insn *insn) default: /* opnd_bytes must be modified manually */ goto err_out; } - insn->immediate2.value = get_next(unsigned short, insn); - insn->immediate2.nbytes = 2; + insn_field_set(&insn->immediate2, get_next(unsigned short, insn), 2); insn->immediate1.got = insn->immediate2.got = 1; return 1; @@ -565,22 +564,17 @@ void insn_get_immediate(struct insn *insn) switch (inat_immediate_size(insn->attr)) { case INAT_IMM_BYTE: - insn->immediate.value = get_next(signed char, insn); - insn->immediate.nbytes = 1; + insn_field_set(&insn->immediate, get_next(signed char, insn), 1); break; case INAT_IMM_WORD: - insn->immediate.value = get_next(short, insn); - insn->immediate.nbytes = 2; + insn_field_set(&insn->immediate, get_next(short, insn), 2); break; case INAT_IMM_DWORD: - insn->immediate.value = get_next(int, insn); - insn->immediate.nbytes = 4; + insn_field_set(&insn->immediate, get_next(int, insn), 4); break; case INAT_IMM_QWORD: - insn->immediate1.value = get_next(int, insn); - insn->immediate1.nbytes = 4; - insn->immediate2.value = get_next(int, insn); - insn->immediate2.nbytes = 4; + insn_field_set(&insn->immediate1, get_next(int, insn), 4); + insn_field_set(&insn->immediate2, get_next(int, insn), 4); break; case INAT_IMM_PTR: if (!__get_immptr(insn)) @@ -599,8 +593,7 @@ void insn_get_immediate(struct insn *insn) goto err_out; } if (inat_has_second_immediate(insn->attr)) { - insn->immediate2.value = get_next(signed char, insn); - insn->immediate2.nbytes = 1; + insn_field_set(&insn->immediate2, get_next(signed char, insn), 1); } done: insn->immediate.got = 1; diff --git a/arch/x86/lib/retpoline.S b/arch/x86/lib/retpoline.S index b4c43a9b1483..f6fb1d218dcc 100644 --- a/arch/x86/lib/retpoline.S +++ b/arch/x86/lib/retpoline.S @@ -28,7 +28,7 @@ SYM_FUNC_START_NOALIGN(__x86_retpoline_\reg) jmp .Lspec_trap_\@ .Ldo_rop_\@: mov %\reg, (%_ASM_SP) - UNWIND_HINT_RET_OFFSET + UNWIND_HINT_FUNC ret SYM_FUNC_END(__x86_retpoline_\reg) diff --git a/arch/x86/mm/fault.c b/arch/x86/mm/fault.c index f1f1b5a0956a..a73347e2cdfc 100644 --- a/arch/x86/mm/fault.c +++ b/arch/x86/mm/fault.c @@ -9,6 +9,7 @@ #include <linux/kdebug.h> /* oops_begin/end, ... */ #include <linux/extable.h> /* search_exception_tables */ #include <linux/memblock.h> /* max_low_pfn */ +#include <linux/kfence.h> /* kfence_handle_page_fault */ #include <linux/kprobes.h> /* NOKPROBE_SYMBOL, ... */ #include <linux/mmiotrace.h> /* kmmio_handler, ... */ #include <linux/perf_event.h> /* perf_sw_event */ @@ -16,7 +17,7 @@ #include <linux/prefetch.h> /* prefetchw */ #include <linux/context_tracking.h> /* exception_enter(), ... */ #include <linux/uaccess.h> /* faulthandler_disabled() */ -#include <linux/efi.h> /* efi_recover_from_page_fault()*/ +#include <linux/efi.h> /* efi_crash_gracefully_on_page_fault()*/ #include <linux/mm_types.h> #include <asm/cpufeature.h> /* boot_cpu_has, ... */ @@ -25,7 +26,7 @@ #include <asm/vsyscall.h> /* emulate_vsyscall */ #include <asm/vm86.h> /* struct vm86 */ #include <asm/mmu_context.h> /* vma_pkey() */ -#include <asm/efi.h> /* efi_recover_from_page_fault()*/ +#include <asm/efi.h> /* efi_crash_gracefully_on_page_fault()*/ #include <asm/desc.h> /* store_idt(), ... */ #include <asm/cpu_entry_area.h> /* exception stack */ #include <asm/pgtable_areas.h> /* VMALLOC_START, ... */ @@ -54,7 +55,7 @@ kmmio_fault(struct pt_regs *regs, unsigned long addr) * 32-bit mode: * * Sometimes AMD Athlon/Opteron CPUs report invalid exceptions on prefetch. - * Check that here and ignore it. + * Check that here and ignore it. This is AMD erratum #91. * * 64-bit mode: * @@ -83,11 +84,7 @@ check_prefetch_opcode(struct pt_regs *regs, unsigned char *instr, #ifdef CONFIG_X86_64 case 0x40: /* - * In AMD64 long mode 0x40..0x4F are valid REX prefixes - * Need to figure out under what instruction mode the - * instruction was issued. Could check the LDT for lm, - * but for now it's good enough to assume that long - * mode only uses well known segments or kernel. + * In 64-bit mode 0x40..0x4F are valid REX prefixes */ return (!user_mode(regs) || user_64bit_mode(regs)); #endif @@ -110,6 +107,15 @@ check_prefetch_opcode(struct pt_regs *regs, unsigned char *instr, } } +static bool is_amd_k8_pre_npt(void) +{ + struct cpuinfo_x86 *c = &boot_cpu_data; + + return unlikely(IS_ENABLED(CONFIG_CPU_SUP_AMD) && + c->x86_vendor == X86_VENDOR_AMD && + c->x86 == 0xf && c->x86_model < 0x40); +} + static int is_prefetch(struct pt_regs *regs, unsigned long error_code, unsigned long addr) { @@ -117,6 +123,10 @@ is_prefetch(struct pt_regs *regs, unsigned long error_code, unsigned long addr) unsigned char *instr; int prefetch = 0; + /* Erratum #91 affects AMD K8, pre-NPT CPUs */ + if (!is_amd_k8_pre_npt()) + return 0; + /* * If it was a exec (instruction fetch) fault on NX page, then * do not ignore the fault: @@ -127,20 +137,31 @@ is_prefetch(struct pt_regs *regs, unsigned long error_code, unsigned long addr) instr = (void *)convert_ip_to_linear(current, regs); max_instr = instr + 15; - if (user_mode(regs) && instr >= (unsigned char *)TASK_SIZE_MAX) - return 0; + /* + * This code has historically always bailed out if IP points to a + * not-present page (e.g. due to a race). No one has ever + * complained about this. + */ + pagefault_disable(); while (instr < max_instr) { unsigned char opcode; - if (get_kernel_nofault(opcode, instr)) - break; + if (user_mode(regs)) { + if (get_user(opcode, instr)) + break; + } else { + if (get_kernel_nofault(opcode, instr)) + break; + } instr++; if (!check_prefetch_opcode(regs, instr, opcode, &prefetch)) break; } + + pagefault_enable(); return prefetch; } @@ -262,25 +283,6 @@ void arch_sync_kernel_mappings(unsigned long start, unsigned long end) } } -/* - * Did it hit the DOS screen memory VA from vm86 mode? - */ -static inline void -check_v8086_mode(struct pt_regs *regs, unsigned long address, - struct task_struct *tsk) -{ -#ifdef CONFIG_VM86 - unsigned long bit; - - if (!v8086_mode(regs) || !tsk->thread.vm86) - return; - - bit = (address - 0xA0000) >> PAGE_SHIFT; - if (bit < 32) - tsk->thread.vm86->screen_bitmap |= 1 << bit; -#endif -} - static bool low_pfn(unsigned long pfn) { return pfn < max_low_pfn; @@ -335,15 +337,6 @@ KERN_ERR "******* Disabling USB legacy in the BIOS may also help.\n"; #endif -/* - * No vm86 mode in 64-bit mode: - */ -static inline void -check_v8086_mode(struct pt_regs *regs, unsigned long address, - struct task_struct *tsk) -{ -} - static int bad_address(void *p) { unsigned long dummy; @@ -427,6 +420,9 @@ static int is_errata93(struct pt_regs *regs, unsigned long address) || boot_cpu_data.x86 != 0xf) return 0; + if (user_mode(regs)) + return 0; + if (address != regs->ip) return 0; @@ -462,10 +458,12 @@ static int is_errata100(struct pt_regs *regs, unsigned long address) } /* Pentium F0 0F C7 C8 bug workaround: */ -static int is_f00f_bug(struct pt_regs *regs, unsigned long address) +static int is_f00f_bug(struct pt_regs *regs, unsigned long error_code, + unsigned long address) { #ifdef CONFIG_X86_F00F_BUG - if (boot_cpu_has_bug(X86_BUG_F00F) && idt_is_f00f_address(address)) { + if (boot_cpu_has_bug(X86_BUG_F00F) && !(error_code & X86_PF_USER) && + idt_is_f00f_address(address)) { handle_invalid_op(regs); return 1; } @@ -630,53 +628,20 @@ static void set_signal_archinfo(unsigned long address, } static noinline void -no_context(struct pt_regs *regs, unsigned long error_code, - unsigned long address, int signal, int si_code) +page_fault_oops(struct pt_regs *regs, unsigned long error_code, + unsigned long address) { - struct task_struct *tsk = current; unsigned long flags; int sig; if (user_mode(regs)) { /* - * This is an implicit supervisor-mode access from user - * mode. Bypass all the kernel-mode recovery code and just - * OOPS. + * Implicit kernel access from user mode? Skip the stack + * overflow and EFI special cases. */ goto oops; } - /* Are we prepared to handle this kernel fault? */ - if (fixup_exception(regs, X86_TRAP_PF, error_code, address)) { - /* - * Any interrupt that takes a fault gets the fixup. This makes - * the below recursive fault logic only apply to a faults from - * task context. - */ - if (in_interrupt()) - return; - - /* - * Per the above we're !in_interrupt(), aka. task context. - * - * In this case we need to make sure we're not recursively - * faulting through the emulate_vsyscall() logic. - */ - if (current->thread.sig_on_uaccess_err && signal) { - sanitize_error_code(address, &error_code); - - set_signal_archinfo(address, error_code); - - /* XXX: hwpoison faults will set the wrong code. */ - force_sig_fault(signal, si_code, (void __user *)address); - } - - /* - * Barring that, we can do the fixup and be happy. - */ - return; - } - #ifdef CONFIG_VMAP_STACK /* * Stack overflow? During boot, we can fault near the initial @@ -684,8 +649,8 @@ no_context(struct pt_regs *regs, unsigned long error_code, * that we're in vmalloc space to avoid this. */ if (is_vmalloc_addr((void *)address) && - (((unsigned long)tsk->stack - 1 - address < PAGE_SIZE) || - address - ((unsigned long)tsk->stack + THREAD_SIZE) < PAGE_SIZE)) { + (((unsigned long)current->stack - 1 - address < PAGE_SIZE) || + address - ((unsigned long)current->stack + THREAD_SIZE) < PAGE_SIZE)) { unsigned long stack = __this_cpu_ist_top_va(DF) - sizeof(void *); /* * We're likely to be running with very little stack space @@ -709,29 +674,18 @@ no_context(struct pt_regs *regs, unsigned long error_code, #endif /* - * 32-bit: - * - * Valid to do another page fault here, because if this fault - * had been triggered by is_prefetch fixup_exception would have - * handled it. - * - * 64-bit: - * - * Hall of shame of CPU/BIOS bugs. + * Buggy firmware could access regions which might page fault. If + * this happens, EFI has a special OOPS path that will try to + * avoid hanging the system. */ - if (is_prefetch(regs, error_code, address)) - return; + if (IS_ENABLED(CONFIG_EFI)) + efi_crash_gracefully_on_page_fault(address); - if (is_errata93(regs, address)) + /* Only not-present faults should be handled by KFENCE. */ + if (!(error_code & X86_PF_PROT) && + kfence_handle_page_fault(address, error_code & X86_PF_WRITE, regs)) return; - /* - * Buggy firmware could access regions which might page fault, try to - * recover from such faults. - */ - if (IS_ENABLED(CONFIG_EFI)) - efi_recover_from_page_fault(address); - oops: /* * Oops. The kernel tried to access some bad page. We'll have to @@ -741,7 +695,7 @@ oops: show_fault_oops(regs, error_code, address); - if (task_stack_end_corrupted(tsk)) + if (task_stack_end_corrupted(current)) printk(KERN_EMERG "Thread overran stack, or stack corrupted\n"); sig = SIGKILL; @@ -754,6 +708,53 @@ oops: oops_end(flags, regs, sig); } +static noinline void +kernelmode_fixup_or_oops(struct pt_regs *regs, unsigned long error_code, + unsigned long address, int signal, int si_code) +{ + WARN_ON_ONCE(user_mode(regs)); + + /* Are we prepared to handle this kernel fault? */ + if (fixup_exception(regs, X86_TRAP_PF, error_code, address)) { + /* + * Any interrupt that takes a fault gets the fixup. This makes + * the below recursive fault logic only apply to a faults from + * task context. + */ + if (in_interrupt()) + return; + + /* + * Per the above we're !in_interrupt(), aka. task context. + * + * In this case we need to make sure we're not recursively + * faulting through the emulate_vsyscall() logic. + */ + if (current->thread.sig_on_uaccess_err && signal) { + sanitize_error_code(address, &error_code); + + set_signal_archinfo(address, error_code); + + /* XXX: hwpoison faults will set the wrong code. */ + force_sig_fault(signal, si_code, (void __user *)address); + } + + /* + * Barring that, we can do the fixup and be happy. + */ + return; + } + + /* + * AMD erratum #91 manifests as a spurious page fault on a PREFETCH + * instruction. + */ + if (is_prefetch(regs, error_code, address)) + return; + + page_fault_oops(regs, error_code, address); +} + /* * Print out info about fatal segfaults, if the show_unhandled_signals * sysctl is set: @@ -796,47 +797,49 @@ __bad_area_nosemaphore(struct pt_regs *regs, unsigned long error_code, { struct task_struct *tsk = current; - /* User mode accesses just cause a SIGSEGV */ - if (user_mode(regs) && (error_code & X86_PF_USER)) { - /* - * It's possible to have interrupts off here: - */ - local_irq_enable(); - - /* - * Valid to do another page fault here because this one came - * from user space: - */ - if (is_prefetch(regs, error_code, address)) - return; + if (!user_mode(regs)) { + kernelmode_fixup_or_oops(regs, error_code, address, pkey, si_code); + return; + } - if (is_errata100(regs, address)) - return; + if (!(error_code & X86_PF_USER)) { + /* Implicit user access to kernel memory -- just oops */ + page_fault_oops(regs, error_code, address); + return; + } - sanitize_error_code(address, &error_code); + /* + * User mode accesses just cause a SIGSEGV. + * It's possible to have interrupts off here: + */ + local_irq_enable(); - if (fixup_vdso_exception(regs, X86_TRAP_PF, error_code, address)) - return; + /* + * Valid to do another page fault here because this one came + * from user space: + */ + if (is_prefetch(regs, error_code, address)) + return; - if (likely(show_unhandled_signals)) - show_signal_msg(regs, error_code, address, tsk); + if (is_errata100(regs, address)) + return; - set_signal_archinfo(address, error_code); + sanitize_error_code(address, &error_code); - if (si_code == SEGV_PKUERR) - force_sig_pkuerr((void __user *)address, pkey); + if (fixup_vdso_exception(regs, X86_TRAP_PF, error_code, address)) + return; - force_sig_fault(SIGSEGV, si_code, (void __user *)address); + if (likely(show_unhandled_signals)) + show_signal_msg(regs, error_code, address, tsk); - local_irq_disable(); + set_signal_archinfo(address, error_code); - return; - } + if (si_code == SEGV_PKUERR) + force_sig_pkuerr((void __user *)address, pkey); - if (is_f00f_bug(regs, address)) - return; + force_sig_fault(SIGSEGV, si_code, (void __user *)address); - no_context(regs, error_code, address, SIGSEGV, si_code); + local_irq_disable(); } static noinline void @@ -926,8 +929,8 @@ do_sigbus(struct pt_regs *regs, unsigned long error_code, unsigned long address, vm_fault_t fault) { /* Kernel mode? Handle exceptions or die: */ - if (!(error_code & X86_PF_USER)) { - no_context(regs, error_code, address, SIGBUS, BUS_ADRERR); + if (!user_mode(regs)) { + kernelmode_fixup_or_oops(regs, error_code, address, SIGBUS, BUS_ADRERR); return; } @@ -961,40 +964,6 @@ do_sigbus(struct pt_regs *regs, unsigned long error_code, unsigned long address, force_sig_fault(SIGBUS, BUS_ADRERR, (void __user *)address); } -static noinline void -mm_fault_error(struct pt_regs *regs, unsigned long error_code, - unsigned long address, vm_fault_t fault) -{ - if (fatal_signal_pending(current) && !(error_code & X86_PF_USER)) { - no_context(regs, error_code, address, 0, 0); - return; - } - - if (fault & VM_FAULT_OOM) { - /* Kernel mode? Handle exceptions or die: */ - if (!(error_code & X86_PF_USER)) { - no_context(regs, error_code, address, - SIGSEGV, SEGV_MAPERR); - return; - } - - /* - * We ran out of memory, call the OOM killer, and return the - * userspace (which will retry the fault, or kill us if we got - * oom-killed): - */ - pagefault_out_of_memory(); - } else { - if (fault & (VM_FAULT_SIGBUS|VM_FAULT_HWPOISON| - VM_FAULT_HWPOISON_LARGE)) - do_sigbus(regs, error_code, address, fault); - else if (fault & VM_FAULT_SIGSEGV) - bad_area_nosemaphore(regs, error_code, address); - else - BUG(); - } -} - static int spurious_kernel_fault_check(unsigned long error_code, pte_t *pte) { if ((error_code & X86_PF_WRITE) && !pte_write(*pte)) @@ -1209,6 +1178,9 @@ do_kern_addr_fault(struct pt_regs *regs, unsigned long hw_error_code, } #endif + if (is_f00f_bug(regs, hw_error_code, address)) + return; + /* Was the fault spurious, caused by lazy TLB invalidation? */ if (spurious_kernel_fault(hw_error_code, address)) return; @@ -1229,10 +1201,17 @@ do_kern_addr_fault(struct pt_regs *regs, unsigned long hw_error_code, } NOKPROBE_SYMBOL(do_kern_addr_fault); -/* Handle faults in the user portion of the address space */ +/* + * Handle faults in the user portion of the address space. Nothing in here + * should check X86_PF_USER without a specific justification: for almost + * all purposes, we should treat a normal kernel access to user memory + * (e.g. get_user(), put_user(), etc.) the same as the WRUSS instruction. + * The one exception is AC flag handling, which is, per the x86 + * architecture, special for WRUSS. + */ static inline void do_user_addr_fault(struct pt_regs *regs, - unsigned long hw_error_code, + unsigned long error_code, unsigned long address) { struct vm_area_struct *vma; @@ -1244,6 +1223,21 @@ void do_user_addr_fault(struct pt_regs *regs, tsk = current; mm = tsk->mm; + if (unlikely((error_code & (X86_PF_USER | X86_PF_INSTR)) == X86_PF_INSTR)) { + /* + * Whoops, this is kernel mode code trying to execute from + * user memory. Unless this is AMD erratum #93, which + * corrupts RIP such that it looks like a user address, + * this is unrecoverable. Don't even try to look up the + * VMA or look for extable entries. + */ + if (is_errata93(regs, address)) + return; + + page_fault_oops(regs, error_code, address); + return; + } + /* kprobes don't want to hook the spurious faults: */ if (unlikely(kprobe_page_fault(regs, X86_TRAP_PF))) return; @@ -1252,8 +1246,8 @@ void do_user_addr_fault(struct pt_regs *regs, * Reserved bits are never expected to be set on * entries in the user portion of the page tables. */ - if (unlikely(hw_error_code & X86_PF_RSVD)) - pgtable_bad(regs, hw_error_code, address); + if (unlikely(error_code & X86_PF_RSVD)) + pgtable_bad(regs, error_code, address); /* * If SMAP is on, check for invalid kernel (supervisor) access to user @@ -1263,10 +1257,13 @@ void do_user_addr_fault(struct pt_regs *regs, * enforcement appears to be consistent with the USER bit. */ if (unlikely(cpu_feature_enabled(X86_FEATURE_SMAP) && - !(hw_error_code & X86_PF_USER) && - !(regs->flags & X86_EFLAGS_AC))) - { - bad_area_nosemaphore(regs, hw_error_code, address); + !(error_code & X86_PF_USER) && + !(regs->flags & X86_EFLAGS_AC))) { + /* + * No extable entry here. This was a kernel access to an + * invalid pointer. get_kernel_nofault() will not get here. + */ + page_fault_oops(regs, error_code, address); return; } @@ -1275,7 +1272,7 @@ void do_user_addr_fault(struct pt_regs *regs, * in a region with pagefaults disabled then we must not take the fault */ if (unlikely(faulthandler_disabled() || !mm)) { - bad_area_nosemaphore(regs, hw_error_code, address); + bad_area_nosemaphore(regs, error_code, address); return; } @@ -1296,9 +1293,9 @@ void do_user_addr_fault(struct pt_regs *regs, perf_sw_event(PERF_COUNT_SW_PAGE_FAULTS, 1, regs, address); - if (hw_error_code & X86_PF_WRITE) + if (error_code & X86_PF_WRITE) flags |= FAULT_FLAG_WRITE; - if (hw_error_code & X86_PF_INSTR) + if (error_code & X86_PF_INSTR) flags |= FAULT_FLAG_INSTRUCTION; #ifdef CONFIG_X86_64 @@ -1314,7 +1311,7 @@ void do_user_addr_fault(struct pt_regs *regs, * to consider the PF_PK bit. */ if (is_vsyscall_vaddr(address)) { - if (emulate_vsyscall(hw_error_code, regs, address)) + if (emulate_vsyscall(error_code, regs, address)) return; } #endif @@ -1337,7 +1334,7 @@ void do_user_addr_fault(struct pt_regs *regs, * Fault from code in kernel from * which we do not expect faults. */ - bad_area_nosemaphore(regs, hw_error_code, address); + bad_area_nosemaphore(regs, error_code, address); return; } retry: @@ -1353,17 +1350,17 @@ retry: vma = find_vma(mm, address); if (unlikely(!vma)) { - bad_area(regs, hw_error_code, address); + bad_area(regs, error_code, address); return; } if (likely(vma->vm_start <= address)) goto good_area; if (unlikely(!(vma->vm_flags & VM_GROWSDOWN))) { - bad_area(regs, hw_error_code, address); + bad_area(regs, error_code, address); return; } if (unlikely(expand_stack(vma, address))) { - bad_area(regs, hw_error_code, address); + bad_area(regs, error_code, address); return; } @@ -1372,8 +1369,8 @@ retry: * we can handle it.. */ good_area: - if (unlikely(access_error(hw_error_code, vma))) { - bad_area_access_error(regs, hw_error_code, address, vma); + if (unlikely(access_error(error_code, vma))) { + bad_area_access_error(regs, error_code, address, vma); return; } @@ -1392,11 +1389,14 @@ good_area: */ fault = handle_mm_fault(vma, address, flags, regs); - /* Quick path to respond to signals */ if (fault_signal_pending(fault, regs)) { + /* + * Quick path to respond to signals. The core mm code + * has unlocked the mm for us if we get here. + */ if (!user_mode(regs)) - no_context(regs, hw_error_code, address, SIGBUS, - BUS_ADRERR); + kernelmode_fixup_or_oops(regs, error_code, address, + SIGBUS, BUS_ADRERR); return; } @@ -1412,12 +1412,37 @@ good_area: } mmap_read_unlock(mm); - if (unlikely(fault & VM_FAULT_ERROR)) { - mm_fault_error(regs, hw_error_code, address, fault); + if (likely(!(fault & VM_FAULT_ERROR))) + return; + + if (fatal_signal_pending(current) && !user_mode(regs)) { + kernelmode_fixup_or_oops(regs, error_code, address, 0, 0); return; } - check_v8086_mode(regs, address, tsk); + if (fault & VM_FAULT_OOM) { + /* Kernel mode? Handle exceptions or die: */ + if (!user_mode(regs)) { + kernelmode_fixup_or_oops(regs, error_code, address, + SIGSEGV, SEGV_MAPERR); + return; + } + + /* + * We ran out of memory, call the OOM killer, and return the + * userspace (which will retry the fault, or kill us if we got + * oom-killed): + */ + pagefault_out_of_memory(); + } else { + if (fault & (VM_FAULT_SIGBUS|VM_FAULT_HWPOISON| + VM_FAULT_HWPOISON_LARGE)) + do_sigbus(regs, error_code, address, fault); + else if (fault & VM_FAULT_SIGSEGV) + bad_area_nosemaphore(regs, error_code, address); + else + BUG(); + } } NOKPROBE_SYMBOL(do_user_addr_fault); diff --git a/arch/x86/mm/init.c b/arch/x86/mm/init.c index e26f5c5c6565..dd694fb93916 100644 --- a/arch/x86/mm/init.c +++ b/arch/x86/mm/init.c @@ -157,16 +157,25 @@ __ref void *alloc_low_pages(unsigned int num) } /* - * By default need 3 4k for initial PMD_SIZE, 3 4k for 0-ISA_END_ADDRESS. - * With KASLR memory randomization, depending on the machine e820 memory - * and the PUD alignment. We may need twice more pages when KASLR memory + * By default need to be able to allocate page tables below PGD firstly for + * the 0-ISA_END_ADDRESS range and secondly for the initial PMD_SIZE mapping. + * With KASLR memory randomization, depending on the machine e820 memory and the + * PUD alignment, twice that many pages may be needed when KASLR memory * randomization is enabled. */ + +#ifndef CONFIG_X86_5LEVEL +#define INIT_PGD_PAGE_TABLES 3 +#else +#define INIT_PGD_PAGE_TABLES 4 +#endif + #ifndef CONFIG_RANDOMIZE_MEMORY -#define INIT_PGD_PAGE_COUNT 6 +#define INIT_PGD_PAGE_COUNT (2 * INIT_PGD_PAGE_TABLES) #else -#define INIT_PGD_PAGE_COUNT 12 +#define INIT_PGD_PAGE_COUNT (4 * INIT_PGD_PAGE_TABLES) #endif + #define INIT_PGT_BUF_SIZE (INIT_PGD_PAGE_COUNT * PAGE_SIZE) RESERVE_BRK(early_pgt_alloc, INIT_PGT_BUF_SIZE); void __init early_alloc_pgt_buf(void) diff --git a/arch/x86/mm/mem_encrypt.c b/arch/x86/mm/mem_encrypt.c index c3d5f0236f35..4b01f7dbaf30 100644 --- a/arch/x86/mm/mem_encrypt.c +++ b/arch/x86/mm/mem_encrypt.c @@ -475,9 +475,10 @@ void __init mem_encrypt_init(void) swiotlb_update_mem_attributes(); /* - * With SEV, we need to unroll the rep string I/O instructions. + * With SEV, we need to unroll the rep string I/O instructions, + * but SEV-ES supports them through the #VC handler. */ - if (sev_active()) + if (sev_active() && !sev_es_active()) static_branch_enable(&sev_enable_key); print_mem_encrypt_feature_info(); diff --git a/arch/x86/mm/mmio-mod.c b/arch/x86/mm/mmio-mod.c index bd7aff5c51f7..cd768dafca9e 100644 --- a/arch/x86/mm/mmio-mod.c +++ b/arch/x86/mm/mmio-mod.c @@ -10,8 +10,6 @@ #define pr_fmt(fmt) "mmiotrace: " fmt -#define DEBUG 1 - #include <linux/moduleparam.h> #include <linux/debugfs.h> #include <linux/slab.h> diff --git a/arch/x86/mm/pat/memtype.c b/arch/x86/mm/pat/memtype.c index 8f665c352bf0..ca311aaa67b8 100644 --- a/arch/x86/mm/pat/memtype.c +++ b/arch/x86/mm/pat/memtype.c @@ -1164,12 +1164,14 @@ static void *memtype_seq_start(struct seq_file *seq, loff_t *pos) static void *memtype_seq_next(struct seq_file *seq, void *v, loff_t *pos) { + kfree(v); ++*pos; return memtype_get_idx(*pos); } static void memtype_seq_stop(struct seq_file *seq, void *v) { + kfree(v); } static int memtype_seq_show(struct seq_file *seq, void *v) @@ -1181,8 +1183,6 @@ static int memtype_seq_show(struct seq_file *seq, void *v) entry_print->end, cattr_name(entry_print->type)); - kfree(entry_print); - return 0; } diff --git a/arch/x86/net/bpf_jit_comp.c b/arch/x86/net/bpf_jit_comp.c index 796506dcfc42..6926d0ca6c71 100644 --- a/arch/x86/net/bpf_jit_comp.c +++ b/arch/x86/net/bpf_jit_comp.c @@ -205,6 +205,18 @@ static u8 add_2reg(u8 byte, u32 dst_reg, u32 src_reg) return byte + reg2hex[dst_reg] + (reg2hex[src_reg] << 3); } +/* Some 1-byte opcodes for binary ALU operations */ +static u8 simple_alu_opcodes[] = { + [BPF_ADD] = 0x01, + [BPF_SUB] = 0x29, + [BPF_AND] = 0x21, + [BPF_OR] = 0x09, + [BPF_XOR] = 0x31, + [BPF_LSH] = 0xE0, + [BPF_RSH] = 0xE8, + [BPF_ARSH] = 0xF8, +}; + static void jit_fill_hole(void *area, unsigned int size) { /* Fill whole space with INT3 instructions */ @@ -681,6 +693,42 @@ static void emit_mov_reg(u8 **pprog, bool is64, u32 dst_reg, u32 src_reg) *pprog = prog; } +/* Emit the suffix (ModR/M etc) for addressing *(ptr_reg + off) and val_reg */ +static void emit_insn_suffix(u8 **pprog, u32 ptr_reg, u32 val_reg, int off) +{ + u8 *prog = *pprog; + int cnt = 0; + + if (is_imm8(off)) { + /* 1-byte signed displacement. + * + * If off == 0 we could skip this and save one extra byte, but + * special case of x86 R13 which always needs an offset is not + * worth the hassle + */ + EMIT2(add_2reg(0x40, ptr_reg, val_reg), off); + } else { + /* 4-byte signed displacement */ + EMIT1_off32(add_2reg(0x80, ptr_reg, val_reg), off); + } + *pprog = prog; +} + +/* + * Emit a REX byte if it will be necessary to address these registers + */ +static void maybe_emit_mod(u8 **pprog, u32 dst_reg, u32 src_reg, bool is64) +{ + u8 *prog = *pprog; + int cnt = 0; + + if (is64) + EMIT1(add_2mod(0x48, dst_reg, src_reg)); + else if (is_ereg(dst_reg) || is_ereg(src_reg)) + EMIT1(add_2mod(0x40, dst_reg, src_reg)); + *pprog = prog; +} + /* LDX: dst_reg = *(u8*)(src_reg + off) */ static void emit_ldx(u8 **pprog, u32 size, u32 dst_reg, u32 src_reg, int off) { @@ -708,15 +756,7 @@ static void emit_ldx(u8 **pprog, u32 size, u32 dst_reg, u32 src_reg, int off) EMIT2(add_2mod(0x48, src_reg, dst_reg), 0x8B); break; } - /* - * If insn->off == 0 we can save one extra byte, but - * special case of x86 R13 which always needs an offset - * is not worth the hassle - */ - if (is_imm8(off)) - EMIT2(add_2reg(0x40, src_reg, dst_reg), off); - else - EMIT1_off32(add_2reg(0x80, src_reg, dst_reg), off); + emit_insn_suffix(&prog, src_reg, dst_reg, off); *pprog = prog; } @@ -751,11 +791,51 @@ static void emit_stx(u8 **pprog, u32 size, u32 dst_reg, u32 src_reg, int off) EMIT2(add_2mod(0x48, dst_reg, src_reg), 0x89); break; } - if (is_imm8(off)) - EMIT2(add_2reg(0x40, dst_reg, src_reg), off); - else - EMIT1_off32(add_2reg(0x80, dst_reg, src_reg), off); + emit_insn_suffix(&prog, dst_reg, src_reg, off); + *pprog = prog; +} + +static int emit_atomic(u8 **pprog, u8 atomic_op, + u32 dst_reg, u32 src_reg, s16 off, u8 bpf_size) +{ + u8 *prog = *pprog; + int cnt = 0; + + EMIT1(0xF0); /* lock prefix */ + + maybe_emit_mod(&prog, dst_reg, src_reg, bpf_size == BPF_DW); + + /* emit opcode */ + switch (atomic_op) { + case BPF_ADD: + case BPF_SUB: + case BPF_AND: + case BPF_OR: + case BPF_XOR: + /* lock *(u32/u64*)(dst_reg + off) <op>= src_reg */ + EMIT1(simple_alu_opcodes[atomic_op]); + break; + case BPF_ADD | BPF_FETCH: + /* src_reg = atomic_fetch_add(dst_reg + off, src_reg); */ + EMIT2(0x0F, 0xC1); + break; + case BPF_XCHG: + /* src_reg = atomic_xchg(dst_reg + off, src_reg); */ + EMIT1(0x87); + break; + case BPF_CMPXCHG: + /* r0 = atomic_cmpxchg(dst_reg + off, r0, src_reg); */ + EMIT2(0x0F, 0xB1); + break; + default: + pr_err("bpf_jit: unknown atomic opcode %02x\n", atomic_op); + return -EFAULT; + } + + emit_insn_suffix(&prog, dst_reg, src_reg, off); + *pprog = prog; + return 0; } static bool ex_handler_bpf(const struct exception_table_entry *x, @@ -789,8 +869,31 @@ static void detect_reg_usage(struct bpf_insn *insn, int insn_cnt, } } +static int emit_nops(u8 **pprog, int len) +{ + u8 *prog = *pprog; + int i, noplen, cnt = 0; + + while (len > 0) { + noplen = len; + + if (noplen > ASM_NOP_MAX) + noplen = ASM_NOP_MAX; + + for (i = 0; i < noplen; i++) + EMIT1(ideal_nops[noplen][i]); + len -= noplen; + } + + *pprog = prog; + + return cnt; +} + +#define INSN_SZ_DIFF (((addrs[i] - addrs[i - 1]) - (prog - temp))) + static int do_jit(struct bpf_prog *bpf_prog, int *addrs, u8 *image, - int oldproglen, struct jit_context *ctx) + int oldproglen, struct jit_context *ctx, bool jmp_padding) { bool tail_call_reachable = bpf_prog->aux->tail_call_reachable; struct bpf_insn *insn = bpf_prog->insnsi; @@ -800,8 +903,9 @@ static int do_jit(struct bpf_prog *bpf_prog, int *addrs, u8 *image, bool seen_exit = false; u8 temp[BPF_MAX_INSN_SIZE + BPF_INSN_SAFETY]; int i, cnt = 0, excnt = 0; - int proglen = 0; + int ilen, proglen = 0; u8 *prog = temp; + int err; detect_reg_usage(insn, insn_cnt, callee_regs_used, &tail_call_seen); @@ -813,17 +917,24 @@ static int do_jit(struct bpf_prog *bpf_prog, int *addrs, u8 *image, bpf_prog_was_classic(bpf_prog), tail_call_reachable, bpf_prog->aux->func_idx != 0); push_callee_regs(&prog, callee_regs_used); - addrs[0] = prog - temp; + + ilen = prog - temp; + if (image) + memcpy(image + proglen, temp, ilen); + proglen += ilen; + addrs[0] = proglen; + prog = temp; for (i = 1; i <= insn_cnt; i++, insn++) { const s32 imm32 = insn->imm; u32 dst_reg = insn->dst_reg; u32 src_reg = insn->src_reg; u8 b2 = 0, b3 = 0; + u8 *start_of_ldx; s64 jmp_offset; u8 jmp_cond; - int ilen; u8 *func; + int nops; switch (insn->code) { /* ALU */ @@ -837,17 +948,9 @@ static int do_jit(struct bpf_prog *bpf_prog, int *addrs, u8 *image, case BPF_ALU64 | BPF_AND | BPF_X: case BPF_ALU64 | BPF_OR | BPF_X: case BPF_ALU64 | BPF_XOR | BPF_X: - switch (BPF_OP(insn->code)) { - case BPF_ADD: b2 = 0x01; break; - case BPF_SUB: b2 = 0x29; break; - case BPF_AND: b2 = 0x21; break; - case BPF_OR: b2 = 0x09; break; - case BPF_XOR: b2 = 0x31; break; - } - if (BPF_CLASS(insn->code) == BPF_ALU64) - EMIT1(add_2mod(0x48, dst_reg, src_reg)); - else if (is_ereg(dst_reg) || is_ereg(src_reg)) - EMIT1(add_2mod(0x40, dst_reg, src_reg)); + maybe_emit_mod(&prog, dst_reg, src_reg, + BPF_CLASS(insn->code) == BPF_ALU64); + b2 = simple_alu_opcodes[BPF_OP(insn->code)]; EMIT2(b2, add_2reg(0xC0, dst_reg, src_reg)); break; @@ -1027,12 +1130,7 @@ static int do_jit(struct bpf_prog *bpf_prog, int *addrs, u8 *image, else if (is_ereg(dst_reg)) EMIT1(add_1mod(0x40, dst_reg)); - switch (BPF_OP(insn->code)) { - case BPF_LSH: b3 = 0xE0; break; - case BPF_RSH: b3 = 0xE8; break; - case BPF_ARSH: b3 = 0xF8; break; - } - + b3 = simple_alu_opcodes[BPF_OP(insn->code)]; if (imm32 == 1) EMIT2(0xD1, add_1reg(b3, dst_reg)); else @@ -1066,11 +1164,7 @@ static int do_jit(struct bpf_prog *bpf_prog, int *addrs, u8 *image, else if (is_ereg(dst_reg)) EMIT1(add_1mod(0x40, dst_reg)); - switch (BPF_OP(insn->code)) { - case BPF_LSH: b3 = 0xE0; break; - case BPF_RSH: b3 = 0xE8; break; - case BPF_ARSH: b3 = 0xF8; break; - } + b3 = simple_alu_opcodes[BPF_OP(insn->code)]; EMIT2(0xD3, add_1reg(b3, dst_reg)); if (src_reg != BPF_REG_4) @@ -1185,12 +1279,30 @@ st: if (is_imm8(insn->off)) case BPF_LDX | BPF_PROBE_MEM | BPF_W: case BPF_LDX | BPF_MEM | BPF_DW: case BPF_LDX | BPF_PROBE_MEM | BPF_DW: + if (BPF_MODE(insn->code) == BPF_PROBE_MEM) { + /* test src_reg, src_reg */ + maybe_emit_mod(&prog, src_reg, src_reg, true); /* always 1 byte */ + EMIT2(0x85, add_2reg(0xC0, src_reg, src_reg)); + /* jne start_of_ldx */ + EMIT2(X86_JNE, 0); + /* xor dst_reg, dst_reg */ + emit_mov_imm32(&prog, false, dst_reg, 0); + /* jmp byte_after_ldx */ + EMIT2(0xEB, 0); + + /* populate jmp_offset for JNE above */ + temp[4] = prog - temp - 5 /* sizeof(test + jne) */; + start_of_ldx = prog; + } emit_ldx(&prog, BPF_SIZE(insn->code), dst_reg, src_reg, insn->off); if (BPF_MODE(insn->code) == BPF_PROBE_MEM) { struct exception_table_entry *ex; u8 *_insn = image + proglen; s64 delta; + /* populate jmp_offset for JMP above */ + start_of_ldx[-1] = prog - start_of_ldx; + if (!bpf_prog->aux->extable) break; @@ -1230,21 +1342,60 @@ st: if (is_imm8(insn->off)) } break; - /* STX XADD: lock *(u32*)(dst_reg + off) += src_reg */ - case BPF_STX | BPF_XADD | BPF_W: - /* Emit 'lock add dword ptr [rax + off], eax' */ - if (is_ereg(dst_reg) || is_ereg(src_reg)) - EMIT3(0xF0, add_2mod(0x40, dst_reg, src_reg), 0x01); - else - EMIT2(0xF0, 0x01); - goto xadd; - case BPF_STX | BPF_XADD | BPF_DW: - EMIT3(0xF0, add_2mod(0x48, dst_reg, src_reg), 0x01); -xadd: if (is_imm8(insn->off)) - EMIT2(add_2reg(0x40, dst_reg, src_reg), insn->off); - else - EMIT1_off32(add_2reg(0x80, dst_reg, src_reg), - insn->off); + case BPF_STX | BPF_ATOMIC | BPF_W: + case BPF_STX | BPF_ATOMIC | BPF_DW: + if (insn->imm == (BPF_AND | BPF_FETCH) || + insn->imm == (BPF_OR | BPF_FETCH) || + insn->imm == (BPF_XOR | BPF_FETCH)) { + u8 *branch_target; + bool is64 = BPF_SIZE(insn->code) == BPF_DW; + u32 real_src_reg = src_reg; + + /* + * Can't be implemented with a single x86 insn. + * Need to do a CMPXCHG loop. + */ + + /* Will need RAX as a CMPXCHG operand so save R0 */ + emit_mov_reg(&prog, true, BPF_REG_AX, BPF_REG_0); + if (src_reg == BPF_REG_0) + real_src_reg = BPF_REG_AX; + + branch_target = prog; + /* Load old value */ + emit_ldx(&prog, BPF_SIZE(insn->code), + BPF_REG_0, dst_reg, insn->off); + /* + * Perform the (commutative) operation locally, + * put the result in the AUX_REG. + */ + emit_mov_reg(&prog, is64, AUX_REG, BPF_REG_0); + maybe_emit_mod(&prog, AUX_REG, real_src_reg, is64); + EMIT2(simple_alu_opcodes[BPF_OP(insn->imm)], + add_2reg(0xC0, AUX_REG, real_src_reg)); + /* Attempt to swap in new value */ + err = emit_atomic(&prog, BPF_CMPXCHG, + dst_reg, AUX_REG, insn->off, + BPF_SIZE(insn->code)); + if (WARN_ON(err)) + return err; + /* + * ZF tells us whether we won the race. If it's + * cleared we need to try again. + */ + EMIT2(X86_JNE, -(prog - branch_target) - 2); + /* Return the pre-modification value */ + emit_mov_reg(&prog, is64, real_src_reg, BPF_REG_0); + /* Restore R0 after clobbering RAX */ + emit_mov_reg(&prog, true, BPF_REG_0, BPF_REG_AX); + break; + + } + + err = emit_atomic(&prog, insn->imm, dst_reg, src_reg, + insn->off, BPF_SIZE(insn->code)); + if (err) + return err; break; /* call */ @@ -1295,20 +1446,16 @@ xadd: if (is_imm8(insn->off)) case BPF_JMP32 | BPF_JSGE | BPF_X: case BPF_JMP32 | BPF_JSLE | BPF_X: /* cmp dst_reg, src_reg */ - if (BPF_CLASS(insn->code) == BPF_JMP) - EMIT1(add_2mod(0x48, dst_reg, src_reg)); - else if (is_ereg(dst_reg) || is_ereg(src_reg)) - EMIT1(add_2mod(0x40, dst_reg, src_reg)); + maybe_emit_mod(&prog, dst_reg, src_reg, + BPF_CLASS(insn->code) == BPF_JMP); EMIT2(0x39, add_2reg(0xC0, dst_reg, src_reg)); goto emit_cond_jmp; case BPF_JMP | BPF_JSET | BPF_X: case BPF_JMP32 | BPF_JSET | BPF_X: /* test dst_reg, src_reg */ - if (BPF_CLASS(insn->code) == BPF_JMP) - EMIT1(add_2mod(0x48, dst_reg, src_reg)); - else if (is_ereg(dst_reg) || is_ereg(src_reg)) - EMIT1(add_2mod(0x40, dst_reg, src_reg)); + maybe_emit_mod(&prog, dst_reg, src_reg, + BPF_CLASS(insn->code) == BPF_JMP); EMIT2(0x85, add_2reg(0xC0, dst_reg, src_reg)); goto emit_cond_jmp; @@ -1344,10 +1491,8 @@ xadd: if (is_imm8(insn->off)) case BPF_JMP32 | BPF_JSLE | BPF_K: /* test dst_reg, dst_reg to save one extra byte */ if (imm32 == 0) { - if (BPF_CLASS(insn->code) == BPF_JMP) - EMIT1(add_2mod(0x48, dst_reg, dst_reg)); - else if (is_ereg(dst_reg)) - EMIT1(add_2mod(0x40, dst_reg, dst_reg)); + maybe_emit_mod(&prog, dst_reg, dst_reg, + BPF_CLASS(insn->code) == BPF_JMP); EMIT2(0x85, add_2reg(0xC0, dst_reg, dst_reg)); goto emit_cond_jmp; } @@ -1409,6 +1554,30 @@ emit_cond_jmp: /* Convert BPF opcode to x86 */ } jmp_offset = addrs[i + insn->off] - addrs[i]; if (is_imm8(jmp_offset)) { + if (jmp_padding) { + /* To keep the jmp_offset valid, the extra bytes are + * padded before the jump insn, so we substract the + * 2 bytes of jmp_cond insn from INSN_SZ_DIFF. + * + * If the previous pass already emits an imm8 + * jmp_cond, then this BPF insn won't shrink, so + * "nops" is 0. + * + * On the other hand, if the previous pass emits an + * imm32 jmp_cond, the extra 4 bytes(*) is padded to + * keep the image from shrinking further. + * + * (*) imm32 jmp_cond is 6 bytes, and imm8 jmp_cond + * is 2 bytes, so the size difference is 4 bytes. + */ + nops = INSN_SZ_DIFF - 2; + if (nops != 0 && nops != 4) { + pr_err("unexpected jmp_cond padding: %d bytes\n", + nops); + return -EFAULT; + } + cnt += emit_nops(&prog, nops); + } EMIT2(jmp_cond, jmp_offset); } else if (is_simm32(jmp_offset)) { EMIT2_off32(0x0F, jmp_cond + 0x10, jmp_offset); @@ -1431,11 +1600,55 @@ emit_cond_jmp: /* Convert BPF opcode to x86 */ else jmp_offset = addrs[i + insn->off] - addrs[i]; - if (!jmp_offset) - /* Optimize out nop jumps */ + if (!jmp_offset) { + /* + * If jmp_padding is enabled, the extra nops will + * be inserted. Otherwise, optimize out nop jumps. + */ + if (jmp_padding) { + /* There are 3 possible conditions. + * (1) This BPF_JA is already optimized out in + * the previous run, so there is no need + * to pad any extra byte (0 byte). + * (2) The previous pass emits an imm8 jmp, + * so we pad 2 bytes to match the previous + * insn size. + * (3) Similarly, the previous pass emits an + * imm32 jmp, and 5 bytes is padded. + */ + nops = INSN_SZ_DIFF; + if (nops != 0 && nops != 2 && nops != 5) { + pr_err("unexpected nop jump padding: %d bytes\n", + nops); + return -EFAULT; + } + cnt += emit_nops(&prog, nops); + } break; + } emit_jmp: if (is_imm8(jmp_offset)) { + if (jmp_padding) { + /* To avoid breaking jmp_offset, the extra bytes + * are padded before the actual jmp insn, so + * 2 bytes is substracted from INSN_SZ_DIFF. + * + * If the previous pass already emits an imm8 + * jmp, there is nothing to pad (0 byte). + * + * If it emits an imm32 jmp (5 bytes) previously + * and now an imm8 jmp (2 bytes), then we pad + * (5 - 2 = 3) bytes to stop the image from + * shrinking further. + */ + nops = INSN_SZ_DIFF - 2; + if (nops != 0 && nops != 3) { + pr_err("unexpected jump padding: %d bytes\n", + nops); + return -EFAULT; + } + cnt += emit_nops(&prog, INSN_SZ_DIFF - 2); + } EMIT2(0xEB, jmp_offset); } else if (is_simm32(jmp_offset)) { EMIT1_off32(0xE9, jmp_offset); @@ -1531,17 +1744,25 @@ static int invoke_bpf_prog(const struct btf_func_model *m, u8 **pprog, struct bpf_prog *p, int stack_size, bool mod_ret) { u8 *prog = *pprog; + u8 *jmp_insn; int cnt = 0; - if (p->aux->sleepable) { - if (emit_call(&prog, __bpf_prog_enter_sleepable, prog)) + /* arg1: mov rdi, progs[i] */ + emit_mov_imm64(&prog, BPF_REG_1, (long) p >> 32, (u32) (long) p); + if (emit_call(&prog, + p->aux->sleepable ? __bpf_prog_enter_sleepable : + __bpf_prog_enter, prog)) return -EINVAL; - } else { - if (emit_call(&prog, __bpf_prog_enter, prog)) - return -EINVAL; - /* remember prog start time returned by __bpf_prog_enter */ - emit_mov_reg(&prog, true, BPF_REG_6, BPF_REG_0); - } + /* remember prog start time returned by __bpf_prog_enter */ + emit_mov_reg(&prog, true, BPF_REG_6, BPF_REG_0); + + /* if (__bpf_prog_enter*(prog) == 0) + * goto skip_exec_of_prog; + */ + EMIT3(0x48, 0x85, 0xC0); /* test rax,rax */ + /* emit 2 nops that will be replaced with JE insn */ + jmp_insn = prog; + emit_nops(&prog, 2); /* arg1: lea rdi, [rbp - stack_size] */ EMIT4(0x48, 0x8D, 0x7D, -stack_size); @@ -1561,43 +1782,23 @@ static int invoke_bpf_prog(const struct btf_func_model *m, u8 **pprog, if (mod_ret) emit_stx(&prog, BPF_DW, BPF_REG_FP, BPF_REG_0, -8); - if (p->aux->sleepable) { - if (emit_call(&prog, __bpf_prog_exit_sleepable, prog)) - return -EINVAL; - } else { - /* arg1: mov rdi, progs[i] */ - emit_mov_imm64(&prog, BPF_REG_1, (long) p >> 32, - (u32) (long) p); - /* arg2: mov rsi, rbx <- start time in nsec */ - emit_mov_reg(&prog, true, BPF_REG_2, BPF_REG_6); - if (emit_call(&prog, __bpf_prog_exit, prog)) + /* replace 2 nops with JE insn, since jmp target is known */ + jmp_insn[0] = X86_JE; + jmp_insn[1] = prog - jmp_insn - 2; + + /* arg1: mov rdi, progs[i] */ + emit_mov_imm64(&prog, BPF_REG_1, (long) p >> 32, (u32) (long) p); + /* arg2: mov rsi, rbx <- start time in nsec */ + emit_mov_reg(&prog, true, BPF_REG_2, BPF_REG_6); + if (emit_call(&prog, + p->aux->sleepable ? __bpf_prog_exit_sleepable : + __bpf_prog_exit, prog)) return -EINVAL; - } *pprog = prog; return 0; } -static void emit_nops(u8 **pprog, unsigned int len) -{ - unsigned int i, noplen; - u8 *prog = *pprog; - int cnt = 0; - - while (len > 0) { - noplen = len; - - if (noplen > ASM_NOP_MAX) - noplen = ASM_NOP_MAX; - - for (i = 0; i < noplen; i++) - EMIT1(ideal_nops[noplen][i]); - len -= noplen; - } - - *pprog = prog; -} - static void emit_align(u8 **pprog, u32 align) { u8 *target, *prog = *pprog; @@ -1972,6 +2173,9 @@ struct x64_jit_data { struct jit_context ctx; }; +#define MAX_PASSES 20 +#define PADDING_PASSES (MAX_PASSES - 5) + struct bpf_prog *bpf_int_jit_compile(struct bpf_prog *prog) { struct bpf_binary_header *header = NULL; @@ -1981,6 +2185,7 @@ struct bpf_prog *bpf_int_jit_compile(struct bpf_prog *prog) struct jit_context ctx = {}; bool tmp_blinded = false; bool extra_pass = false; + bool padding = false; u8 *image = NULL; int *addrs; int pass; @@ -2017,6 +2222,7 @@ struct bpf_prog *bpf_int_jit_compile(struct bpf_prog *prog) image = jit_data->image; header = jit_data->header; extra_pass = true; + padding = true; goto skip_init_addrs; } addrs = kmalloc_array(prog->len + 1, sizeof(*addrs), GFP_KERNEL); @@ -2042,8 +2248,10 @@ skip_init_addrs: * may converge on the last pass. In such case do one more * pass to emit the final image. */ - for (pass = 0; pass < 20 || image; pass++) { - proglen = do_jit(prog, addrs, image, oldproglen, &ctx); + for (pass = 0; pass < MAX_PASSES || image; pass++) { + if (!padding && pass >= PADDING_PASSES) + padding = true; + proglen = do_jit(prog, addrs, image, oldproglen, &ctx, padding); if (proglen <= 0) { out_image: image = NULL; diff --git a/arch/x86/net/bpf_jit_comp32.c b/arch/x86/net/bpf_jit_comp32.c index 96fde03aa987..d17b67c69f89 100644 --- a/arch/x86/net/bpf_jit_comp32.c +++ b/arch/x86/net/bpf_jit_comp32.c @@ -2243,10 +2243,8 @@ emit_jmp: return -EFAULT; } break; - /* STX XADD: lock *(u32 *)(dst + off) += src */ - case BPF_STX | BPF_XADD | BPF_W: - /* STX XADD: lock *(u64 *)(dst + off) += src */ - case BPF_STX | BPF_XADD | BPF_DW: + case BPF_STX | BPF_ATOMIC | BPF_W: + case BPF_STX | BPF_ATOMIC | BPF_DW: goto notyet; case BPF_JMP | BPF_EXIT: if (seen_exit) { diff --git a/arch/x86/oprofile/Makefile b/arch/x86/oprofile/Makefile deleted file mode 100644 index 4d49b5a27025..000000000000 --- a/arch/x86/oprofile/Makefile +++ /dev/null @@ -1,12 +0,0 @@ -# SPDX-License-Identifier: GPL-2.0 -obj-$(CONFIG_OPROFILE) += oprofile.o - -DRIVER_OBJS = $(addprefix ../../../drivers/oprofile/, \ - oprof.o cpu_buffer.o buffer_sync.o \ - event_buffer.o oprofile_files.o \ - oprofilefs.o oprofile_stats.o \ - timer_int.o nmi_timer_int.o ) - -oprofile-y := $(DRIVER_OBJS) init.o backtrace.o -oprofile-$(CONFIG_X86_LOCAL_APIC) += nmi_int.o op_model_amd.o \ - op_model_ppro.o op_model_p4.o diff --git a/arch/x86/oprofile/backtrace.c b/arch/x86/oprofile/backtrace.c deleted file mode 100644 index 1d8391fcca68..000000000000 --- a/arch/x86/oprofile/backtrace.c +++ /dev/null @@ -1,127 +0,0 @@ -/** - * @file backtrace.c - * - * @remark Copyright 2002 OProfile authors - * @remark Read the file COPYING - * - * @author John Levon - * @author David Smith - */ - -#include <linux/oprofile.h> -#include <linux/sched.h> -#include <linux/mm.h> -#include <linux/compat.h> -#include <linux/uaccess.h> - -#include <asm/ptrace.h> -#include <asm/stacktrace.h> -#include <asm/unwind.h> - -#ifdef CONFIG_COMPAT -static struct stack_frame_ia32 * -dump_user_backtrace_32(struct stack_frame_ia32 *head) -{ - /* Also check accessibility of one struct frame_head beyond: */ - struct stack_frame_ia32 bufhead[2]; - struct stack_frame_ia32 *fp; - unsigned long bytes; - - bytes = copy_from_user_nmi(bufhead, head, sizeof(bufhead)); - if (bytes != 0) - return NULL; - - fp = (struct stack_frame_ia32 *) compat_ptr(bufhead[0].next_frame); - - oprofile_add_trace(bufhead[0].return_address); - - /* frame pointers should strictly progress back up the stack - * (towards higher addresses) */ - if (head >= fp) - return NULL; - - return fp; -} - -static inline int -x86_backtrace_32(struct pt_regs * const regs, unsigned int depth) -{ - struct stack_frame_ia32 *head; - - /* User process is IA32 */ - if (!current || user_64bit_mode(regs)) - return 0; - - head = (struct stack_frame_ia32 *) regs->bp; - while (depth-- && head) - head = dump_user_backtrace_32(head); - - return 1; -} - -#else -static inline int -x86_backtrace_32(struct pt_regs * const regs, unsigned int depth) -{ - return 0; -} -#endif /* CONFIG_COMPAT */ - -static struct stack_frame *dump_user_backtrace(struct stack_frame *head) -{ - /* Also check accessibility of one struct frame_head beyond: */ - struct stack_frame bufhead[2]; - unsigned long bytes; - - bytes = copy_from_user_nmi(bufhead, head, sizeof(bufhead)); - if (bytes != 0) - return NULL; - - oprofile_add_trace(bufhead[0].return_address); - - /* frame pointers should strictly progress back up the stack - * (towards higher addresses) */ - if (head >= bufhead[0].next_frame) - return NULL; - - return bufhead[0].next_frame; -} - -void -x86_backtrace(struct pt_regs * const regs, unsigned int depth) -{ - struct stack_frame *head = (struct stack_frame *)frame_pointer(regs); - - if (!user_mode(regs)) { - struct unwind_state state; - unsigned long addr; - - if (!depth) - return; - - oprofile_add_trace(regs->ip); - - if (!--depth) - return; - - for (unwind_start(&state, current, regs, NULL); - !unwind_done(&state); unwind_next_frame(&state)) { - addr = unwind_get_return_address(&state); - if (!addr) - break; - - oprofile_add_trace(addr); - - if (!--depth) - break; - } - - return; - } - - if (x86_backtrace_32(regs, depth)) - return; - - while (depth-- && head) - head = dump_user_backtrace(head); -} diff --git a/arch/x86/oprofile/init.c b/arch/x86/oprofile/init.c deleted file mode 100644 index 9e138d00ad36..000000000000 --- a/arch/x86/oprofile/init.c +++ /dev/null @@ -1,38 +0,0 @@ -/** - * @file init.c - * - * @remark Copyright 2002 OProfile authors - * @remark Read the file COPYING - * - * @author John Levon <levon@movementarian.org> - */ - -#include <linux/oprofile.h> -#include <linux/init.h> -#include <linux/errno.h> - -/* - * We support CPUs that have performance counters like the Pentium Pro - * with the NMI mode driver. - */ - -#ifdef CONFIG_X86_LOCAL_APIC -extern int op_nmi_init(struct oprofile_operations *ops); -extern void op_nmi_exit(void); -#else -static int op_nmi_init(struct oprofile_operations *ops) { return -ENODEV; } -static void op_nmi_exit(void) { } -#endif - -extern void x86_backtrace(struct pt_regs * const regs, unsigned int depth); - -int __init oprofile_arch_init(struct oprofile_operations *ops) -{ - ops->backtrace = x86_backtrace; - return op_nmi_init(ops); -} - -void oprofile_arch_exit(void) -{ - op_nmi_exit(); -} diff --git a/arch/x86/oprofile/nmi_int.c b/arch/x86/oprofile/nmi_int.c deleted file mode 100644 index a7a7677265b6..000000000000 --- a/arch/x86/oprofile/nmi_int.c +++ /dev/null @@ -1,780 +0,0 @@ -/** - * @file nmi_int.c - * - * @remark Copyright 2002-2009 OProfile authors - * @remark Read the file COPYING - * - * @author John Levon <levon@movementarian.org> - * @author Robert Richter <robert.richter@amd.com> - * @author Barry Kasindorf <barry.kasindorf@amd.com> - * @author Jason Yeh <jason.yeh@amd.com> - * @author Suravee Suthikulpanit <suravee.suthikulpanit@amd.com> - */ - -#include <linux/init.h> -#include <linux/notifier.h> -#include <linux/smp.h> -#include <linux/oprofile.h> -#include <linux/syscore_ops.h> -#include <linux/slab.h> -#include <linux/moduleparam.h> -#include <linux/kdebug.h> -#include <linux/cpu.h> -#include <asm/nmi.h> -#include <asm/msr.h> -#include <asm/apic.h> - -#include "op_counter.h" -#include "op_x86_model.h" - -static struct op_x86_model_spec *model; -static DEFINE_PER_CPU(struct op_msrs, cpu_msrs); -static DEFINE_PER_CPU(unsigned long, saved_lvtpc); - -/* must be protected with get_online_cpus()/put_online_cpus(): */ -static int nmi_enabled; -static int ctr_running; - -struct op_counter_config counter_config[OP_MAX_COUNTER]; - -/* common functions */ - -u64 op_x86_get_ctrl(struct op_x86_model_spec const *model, - struct op_counter_config *counter_config) -{ - u64 val = 0; - u16 event = (u16)counter_config->event; - - val |= ARCH_PERFMON_EVENTSEL_INT; - val |= counter_config->user ? ARCH_PERFMON_EVENTSEL_USR : 0; - val |= counter_config->kernel ? ARCH_PERFMON_EVENTSEL_OS : 0; - val |= (counter_config->unit_mask & 0xFF) << 8; - counter_config->extra &= (ARCH_PERFMON_EVENTSEL_INV | - ARCH_PERFMON_EVENTSEL_EDGE | - ARCH_PERFMON_EVENTSEL_CMASK); - val |= counter_config->extra; - event &= model->event_mask ? model->event_mask : 0xFF; - val |= event & 0xFF; - val |= (u64)(event & 0x0F00) << 24; - - return val; -} - - -static int profile_exceptions_notify(unsigned int val, struct pt_regs *regs) -{ - if (ctr_running) - model->check_ctrs(regs, this_cpu_ptr(&cpu_msrs)); - else if (!nmi_enabled) - return NMI_DONE; - else - model->stop(this_cpu_ptr(&cpu_msrs)); - return NMI_HANDLED; -} - -static void nmi_cpu_save_registers(struct op_msrs *msrs) -{ - struct op_msr *counters = msrs->counters; - struct op_msr *controls = msrs->controls; - unsigned int i; - - for (i = 0; i < model->num_counters; ++i) { - if (counters[i].addr) - rdmsrl(counters[i].addr, counters[i].saved); - } - - for (i = 0; i < model->num_controls; ++i) { - if (controls[i].addr) - rdmsrl(controls[i].addr, controls[i].saved); - } -} - -static void nmi_cpu_start(void *dummy) -{ - struct op_msrs const *msrs = this_cpu_ptr(&cpu_msrs); - if (!msrs->controls) - WARN_ON_ONCE(1); - else - model->start(msrs); -} - -static int nmi_start(void) -{ - get_online_cpus(); - ctr_running = 1; - /* make ctr_running visible to the nmi handler: */ - smp_mb(); - on_each_cpu(nmi_cpu_start, NULL, 1); - put_online_cpus(); - return 0; -} - -static void nmi_cpu_stop(void *dummy) -{ - struct op_msrs const *msrs = this_cpu_ptr(&cpu_msrs); - if (!msrs->controls) - WARN_ON_ONCE(1); - else - model->stop(msrs); -} - -static void nmi_stop(void) -{ - get_online_cpus(); - on_each_cpu(nmi_cpu_stop, NULL, 1); - ctr_running = 0; - put_online_cpus(); -} - -#ifdef CONFIG_OPROFILE_EVENT_MULTIPLEX - -static DEFINE_PER_CPU(int, switch_index); - -static inline int has_mux(void) -{ - return !!model->switch_ctrl; -} - -inline int op_x86_phys_to_virt(int phys) -{ - return __this_cpu_read(switch_index) + phys; -} - -inline int op_x86_virt_to_phys(int virt) -{ - return virt % model->num_counters; -} - -static void nmi_shutdown_mux(void) -{ - int i; - - if (!has_mux()) - return; - - for_each_possible_cpu(i) { - kfree(per_cpu(cpu_msrs, i).multiplex); - per_cpu(cpu_msrs, i).multiplex = NULL; - per_cpu(switch_index, i) = 0; - } -} - -static int nmi_setup_mux(void) -{ - size_t multiplex_size = - sizeof(struct op_msr) * model->num_virt_counters; - int i; - - if (!has_mux()) - return 1; - - for_each_possible_cpu(i) { - per_cpu(cpu_msrs, i).multiplex = - kzalloc(multiplex_size, GFP_KERNEL); - if (!per_cpu(cpu_msrs, i).multiplex) - return 0; - } - - return 1; -} - -static void nmi_cpu_setup_mux(int cpu, struct op_msrs const * const msrs) -{ - int i; - struct op_msr *multiplex = msrs->multiplex; - - if (!has_mux()) - return; - - for (i = 0; i < model->num_virt_counters; ++i) { - if (counter_config[i].enabled) { - multiplex[i].saved = -(u64)counter_config[i].count; - } else { - multiplex[i].saved = 0; - } - } - - per_cpu(switch_index, cpu) = 0; -} - -static void nmi_cpu_save_mpx_registers(struct op_msrs *msrs) -{ - struct op_msr *counters = msrs->counters; - struct op_msr *multiplex = msrs->multiplex; - int i; - - for (i = 0; i < model->num_counters; ++i) { - int virt = op_x86_phys_to_virt(i); - if (counters[i].addr) - rdmsrl(counters[i].addr, multiplex[virt].saved); - } -} - -static void nmi_cpu_restore_mpx_registers(struct op_msrs *msrs) -{ - struct op_msr *counters = msrs->counters; - struct op_msr *multiplex = msrs->multiplex; - int i; - - for (i = 0; i < model->num_counters; ++i) { - int virt = op_x86_phys_to_virt(i); - if (counters[i].addr) - wrmsrl(counters[i].addr, multiplex[virt].saved); - } -} - -static void nmi_cpu_switch(void *dummy) -{ - int cpu = smp_processor_id(); - int si = per_cpu(switch_index, cpu); - struct op_msrs *msrs = &per_cpu(cpu_msrs, cpu); - - nmi_cpu_stop(NULL); - nmi_cpu_save_mpx_registers(msrs); - - /* move to next set */ - si += model->num_counters; - if ((si >= model->num_virt_counters) || (counter_config[si].count == 0)) - per_cpu(switch_index, cpu) = 0; - else - per_cpu(switch_index, cpu) = si; - - model->switch_ctrl(model, msrs); - nmi_cpu_restore_mpx_registers(msrs); - - nmi_cpu_start(NULL); -} - - -/* - * Quick check to see if multiplexing is necessary. - * The check should be sufficient since counters are used - * in ordre. - */ -static int nmi_multiplex_on(void) -{ - return counter_config[model->num_counters].count ? 0 : -EINVAL; -} - -static int nmi_switch_event(void) -{ - if (!has_mux()) - return -ENOSYS; /* not implemented */ - if (nmi_multiplex_on() < 0) - return -EINVAL; /* not necessary */ - - get_online_cpus(); - if (ctr_running) - on_each_cpu(nmi_cpu_switch, NULL, 1); - put_online_cpus(); - - return 0; -} - -static inline void mux_init(struct oprofile_operations *ops) -{ - if (has_mux()) - ops->switch_events = nmi_switch_event; -} - -static void mux_clone(int cpu) -{ - if (!has_mux()) - return; - - memcpy(per_cpu(cpu_msrs, cpu).multiplex, - per_cpu(cpu_msrs, 0).multiplex, - sizeof(struct op_msr) * model->num_virt_counters); -} - -#else - -inline int op_x86_phys_to_virt(int phys) { return phys; } -inline int op_x86_virt_to_phys(int virt) { return virt; } -static inline void nmi_shutdown_mux(void) { } -static inline int nmi_setup_mux(void) { return 1; } -static inline void -nmi_cpu_setup_mux(int cpu, struct op_msrs const * const msrs) { } -static inline void mux_init(struct oprofile_operations *ops) { } -static void mux_clone(int cpu) { } - -#endif - -static void free_msrs(void) -{ - int i; - for_each_possible_cpu(i) { - kfree(per_cpu(cpu_msrs, i).counters); - per_cpu(cpu_msrs, i).counters = NULL; - kfree(per_cpu(cpu_msrs, i).controls); - per_cpu(cpu_msrs, i).controls = NULL; - } - nmi_shutdown_mux(); -} - -static int allocate_msrs(void) -{ - size_t controls_size = sizeof(struct op_msr) * model->num_controls; - size_t counters_size = sizeof(struct op_msr) * model->num_counters; - - int i; - for_each_possible_cpu(i) { - per_cpu(cpu_msrs, i).counters = kzalloc(counters_size, - GFP_KERNEL); - if (!per_cpu(cpu_msrs, i).counters) - goto fail; - per_cpu(cpu_msrs, i).controls = kzalloc(controls_size, - GFP_KERNEL); - if (!per_cpu(cpu_msrs, i).controls) - goto fail; - } - - if (!nmi_setup_mux()) - goto fail; - - return 1; - -fail: - free_msrs(); - return 0; -} - -static void nmi_cpu_setup(void) -{ - int cpu = smp_processor_id(); - struct op_msrs *msrs = &per_cpu(cpu_msrs, cpu); - - nmi_cpu_save_registers(msrs); - raw_spin_lock(&oprofilefs_lock); - model->setup_ctrs(model, msrs); - nmi_cpu_setup_mux(cpu, msrs); - raw_spin_unlock(&oprofilefs_lock); - per_cpu(saved_lvtpc, cpu) = apic_read(APIC_LVTPC); - apic_write(APIC_LVTPC, APIC_DM_NMI); -} - -static void nmi_cpu_restore_registers(struct op_msrs *msrs) -{ - struct op_msr *counters = msrs->counters; - struct op_msr *controls = msrs->controls; - unsigned int i; - - for (i = 0; i < model->num_controls; ++i) { - if (controls[i].addr) - wrmsrl(controls[i].addr, controls[i].saved); - } - - for (i = 0; i < model->num_counters; ++i) { - if (counters[i].addr) - wrmsrl(counters[i].addr, counters[i].saved); - } -} - -static void nmi_cpu_shutdown(void) -{ - unsigned int v; - int cpu = smp_processor_id(); - struct op_msrs *msrs = &per_cpu(cpu_msrs, cpu); - - /* restoring APIC_LVTPC can trigger an apic error because the delivery - * mode and vector nr combination can be illegal. That's by design: on - * power on apic lvt contain a zero vector nr which are legal only for - * NMI delivery mode. So inhibit apic err before restoring lvtpc - */ - v = apic_read(APIC_LVTERR); - apic_write(APIC_LVTERR, v | APIC_LVT_MASKED); - apic_write(APIC_LVTPC, per_cpu(saved_lvtpc, cpu)); - apic_write(APIC_LVTERR, v); - nmi_cpu_restore_registers(msrs); -} - -static int nmi_cpu_online(unsigned int cpu) -{ - local_irq_disable(); - if (nmi_enabled) - nmi_cpu_setup(); - if (ctr_running) - nmi_cpu_start(NULL); - local_irq_enable(); - return 0; -} - -static int nmi_cpu_down_prep(unsigned int cpu) -{ - local_irq_disable(); - if (ctr_running) - nmi_cpu_stop(NULL); - if (nmi_enabled) - nmi_cpu_shutdown(); - local_irq_enable(); - return 0; -} - -static int nmi_create_files(struct dentry *root) -{ - unsigned int i; - - for (i = 0; i < model->num_virt_counters; ++i) { - struct dentry *dir; - char buf[4]; - - /* quick little hack to _not_ expose a counter if it is not - * available for use. This should protect userspace app. - * NOTE: assumes 1:1 mapping here (that counters are organized - * sequentially in their struct assignment). - */ - if (!avail_to_resrv_perfctr_nmi_bit(op_x86_virt_to_phys(i))) - continue; - - snprintf(buf, sizeof(buf), "%d", i); - dir = oprofilefs_mkdir(root, buf); - oprofilefs_create_ulong(dir, "enabled", &counter_config[i].enabled); - oprofilefs_create_ulong(dir, "event", &counter_config[i].event); - oprofilefs_create_ulong(dir, "count", &counter_config[i].count); - oprofilefs_create_ulong(dir, "unit_mask", &counter_config[i].unit_mask); - oprofilefs_create_ulong(dir, "kernel", &counter_config[i].kernel); - oprofilefs_create_ulong(dir, "user", &counter_config[i].user); - oprofilefs_create_ulong(dir, "extra", &counter_config[i].extra); - } - - return 0; -} - -static enum cpuhp_state cpuhp_nmi_online; - -static int nmi_setup(void) -{ - int err = 0; - int cpu; - - if (!allocate_msrs()) - return -ENOMEM; - - /* We need to serialize save and setup for HT because the subset - * of msrs are distinct for save and setup operations - */ - - /* Assume saved/restored counters are the same on all CPUs */ - err = model->fill_in_addresses(&per_cpu(cpu_msrs, 0)); - if (err) - goto fail; - - for_each_possible_cpu(cpu) { - if (!IS_ENABLED(CONFIG_SMP) || !cpu) - continue; - - memcpy(per_cpu(cpu_msrs, cpu).counters, - per_cpu(cpu_msrs, 0).counters, - sizeof(struct op_msr) * model->num_counters); - - memcpy(per_cpu(cpu_msrs, cpu).controls, - per_cpu(cpu_msrs, 0).controls, - sizeof(struct op_msr) * model->num_controls); - - mux_clone(cpu); - } - - nmi_enabled = 0; - ctr_running = 0; - /* make variables visible to the nmi handler: */ - smp_mb(); - err = register_nmi_handler(NMI_LOCAL, profile_exceptions_notify, - 0, "oprofile"); - if (err) - goto fail; - - nmi_enabled = 1; - /* make nmi_enabled visible to the nmi handler: */ - smp_mb(); - err = cpuhp_setup_state(CPUHP_AP_ONLINE_DYN, "x86/oprofile:online", - nmi_cpu_online, nmi_cpu_down_prep); - if (err < 0) - goto fail_nmi; - cpuhp_nmi_online = err; - return 0; -fail_nmi: - unregister_nmi_handler(NMI_LOCAL, "oprofile"); -fail: - free_msrs(); - return err; -} - -static void nmi_shutdown(void) -{ - struct op_msrs *msrs; - - cpuhp_remove_state(cpuhp_nmi_online); - nmi_enabled = 0; - ctr_running = 0; - - /* make variables visible to the nmi handler: */ - smp_mb(); - unregister_nmi_handler(NMI_LOCAL, "oprofile"); - msrs = &get_cpu_var(cpu_msrs); - model->shutdown(msrs); - free_msrs(); - put_cpu_var(cpu_msrs); -} - -#ifdef CONFIG_PM - -static int nmi_suspend(void) -{ - /* Only one CPU left, just stop that one */ - if (nmi_enabled == 1) - nmi_cpu_stop(NULL); - return 0; -} - -static void nmi_resume(void) -{ - if (nmi_enabled == 1) - nmi_cpu_start(NULL); -} - -static struct syscore_ops oprofile_syscore_ops = { - .resume = nmi_resume, - .suspend = nmi_suspend, -}; - -static void __init init_suspend_resume(void) -{ - register_syscore_ops(&oprofile_syscore_ops); -} - -static void exit_suspend_resume(void) -{ - unregister_syscore_ops(&oprofile_syscore_ops); -} - -#else - -static inline void init_suspend_resume(void) { } -static inline void exit_suspend_resume(void) { } - -#endif /* CONFIG_PM */ - -static int __init p4_init(char **cpu_type) -{ - __u8 cpu_model = boot_cpu_data.x86_model; - - if (cpu_model > 6 || cpu_model == 5) - return 0; - -#ifndef CONFIG_SMP - *cpu_type = "i386/p4"; - model = &op_p4_spec; - return 1; -#else - switch (smp_num_siblings) { - case 1: - *cpu_type = "i386/p4"; - model = &op_p4_spec; - return 1; - - case 2: - *cpu_type = "i386/p4-ht"; - model = &op_p4_ht2_spec; - return 1; - } -#endif - - printk(KERN_INFO "oprofile: P4 HyperThreading detected with > 2 threads\n"); - printk(KERN_INFO "oprofile: Reverting to timer mode.\n"); - return 0; -} - -enum __force_cpu_type { - reserved = 0, /* do not force */ - timer, - arch_perfmon, -}; - -static int force_cpu_type; - -static int set_cpu_type(const char *str, const struct kernel_param *kp) -{ - if (!strcmp(str, "timer")) { - force_cpu_type = timer; - printk(KERN_INFO "oprofile: forcing NMI timer mode\n"); - } else if (!strcmp(str, "arch_perfmon")) { - force_cpu_type = arch_perfmon; - printk(KERN_INFO "oprofile: forcing architectural perfmon\n"); - } else { - force_cpu_type = 0; - } - - return 0; -} -module_param_call(cpu_type, set_cpu_type, NULL, NULL, 0); - -static int __init ppro_init(char **cpu_type) -{ - __u8 cpu_model = boot_cpu_data.x86_model; - struct op_x86_model_spec *spec = &op_ppro_spec; /* default */ - - if (force_cpu_type == arch_perfmon && boot_cpu_has(X86_FEATURE_ARCH_PERFMON)) - return 0; - - /* - * Documentation on identifying Intel processors by CPU family - * and model can be found in the Intel Software Developer's - * Manuals (SDM): - * - * http://www.intel.com/products/processor/manuals/ - * - * As of May 2010 the documentation for this was in the: - * "Intel 64 and IA-32 Architectures Software Developer's - * Manual Volume 3B: System Programming Guide", "Table B-1 - * CPUID Signature Values of DisplayFamily_DisplayModel". - */ - switch (cpu_model) { - case 0 ... 2: - *cpu_type = "i386/ppro"; - break; - case 3 ... 5: - *cpu_type = "i386/pii"; - break; - case 6 ... 8: - case 10 ... 11: - *cpu_type = "i386/piii"; - break; - case 9: - case 13: - *cpu_type = "i386/p6_mobile"; - break; - case 14: - *cpu_type = "i386/core"; - break; - case 0x0f: - case 0x16: - case 0x17: - case 0x1d: - *cpu_type = "i386/core_2"; - break; - case 0x1a: - case 0x1e: - case 0x2e: - spec = &op_arch_perfmon_spec; - *cpu_type = "i386/core_i7"; - break; - case 0x1c: - *cpu_type = "i386/atom"; - break; - default: - /* Unknown */ - return 0; - } - - model = spec; - return 1; -} - -int __init op_nmi_init(struct oprofile_operations *ops) -{ - __u8 vendor = boot_cpu_data.x86_vendor; - __u8 family = boot_cpu_data.x86; - char *cpu_type = NULL; - int ret = 0; - - if (!boot_cpu_has(X86_FEATURE_APIC)) - return -ENODEV; - - if (force_cpu_type == timer) - return -ENODEV; - - switch (vendor) { - case X86_VENDOR_AMD: - /* Needs to be at least an Athlon (or hammer in 32bit mode) */ - - switch (family) { - case 6: - cpu_type = "i386/athlon"; - break; - case 0xf: - /* - * Actually it could be i386/hammer too, but - * give user space an consistent name. - */ - cpu_type = "x86-64/hammer"; - break; - case 0x10: - cpu_type = "x86-64/family10"; - break; - case 0x11: - cpu_type = "x86-64/family11h"; - break; - case 0x12: - cpu_type = "x86-64/family12h"; - break; - case 0x14: - cpu_type = "x86-64/family14h"; - break; - case 0x15: - cpu_type = "x86-64/family15h"; - break; - default: - return -ENODEV; - } - model = &op_amd_spec; - break; - - case X86_VENDOR_INTEL: - switch (family) { - /* Pentium IV */ - case 0xf: - p4_init(&cpu_type); - break; - - /* A P6-class processor */ - case 6: - ppro_init(&cpu_type); - break; - - default: - break; - } - - if (cpu_type) - break; - - if (!boot_cpu_has(X86_FEATURE_ARCH_PERFMON)) - return -ENODEV; - - /* use arch perfmon as fallback */ - cpu_type = "i386/arch_perfmon"; - model = &op_arch_perfmon_spec; - break; - - default: - return -ENODEV; - } - - /* default values, can be overwritten by model */ - ops->create_files = nmi_create_files; - ops->setup = nmi_setup; - ops->shutdown = nmi_shutdown; - ops->start = nmi_start; - ops->stop = nmi_stop; - ops->cpu_type = cpu_type; - - if (model->init) - ret = model->init(ops); - if (ret) - return ret; - - if (!model->num_virt_counters) - model->num_virt_counters = model->num_counters; - - mux_init(ops); - - init_suspend_resume(); - - printk(KERN_INFO "oprofile: using NMI interrupt.\n"); - return 0; -} - -void op_nmi_exit(void) -{ - exit_suspend_resume(); -} diff --git a/arch/x86/oprofile/op_counter.h b/arch/x86/oprofile/op_counter.h deleted file mode 100644 index 0b7b7b179cbe..000000000000 --- a/arch/x86/oprofile/op_counter.h +++ /dev/null @@ -1,30 +0,0 @@ -/** - * @file op_counter.h - * - * @remark Copyright 2002 OProfile authors - * @remark Read the file COPYING - * - * @author John Levon - */ - -#ifndef OP_COUNTER_H -#define OP_COUNTER_H - -#define OP_MAX_COUNTER 32 - -/* Per-perfctr configuration as set via - * oprofilefs. - */ -struct op_counter_config { - unsigned long count; - unsigned long enabled; - unsigned long event; - unsigned long kernel; - unsigned long user; - unsigned long unit_mask; - unsigned long extra; -}; - -extern struct op_counter_config counter_config[]; - -#endif /* OP_COUNTER_H */ diff --git a/arch/x86/oprofile/op_model_amd.c b/arch/x86/oprofile/op_model_amd.c deleted file mode 100644 index 660a83c8287b..000000000000 --- a/arch/x86/oprofile/op_model_amd.c +++ /dev/null @@ -1,542 +0,0 @@ -/* - * @file op_model_amd.c - * athlon / K7 / K8 / Family 10h model-specific MSR operations - * - * @remark Copyright 2002-2009 OProfile authors - * @remark Read the file COPYING - * - * @author John Levon - * @author Philippe Elie - * @author Graydon Hoare - * @author Robert Richter <robert.richter@amd.com> - * @author Barry Kasindorf <barry.kasindorf@amd.com> - * @author Jason Yeh <jason.yeh@amd.com> - * @author Suravee Suthikulpanit <suravee.suthikulpanit@amd.com> - */ - -#include <linux/oprofile.h> -#include <linux/device.h> -#include <linux/pci.h> -#include <linux/percpu.h> - -#include <asm/ptrace.h> -#include <asm/msr.h> -#include <asm/nmi.h> -#include <asm/apic.h> -#include <asm/processor.h> - -#include "op_x86_model.h" -#include "op_counter.h" - -#ifdef CONFIG_OPROFILE_EVENT_MULTIPLEX -#define NUM_VIRT_COUNTERS 32 -#else -#define NUM_VIRT_COUNTERS 0 -#endif - -#define OP_EVENT_MASK 0x0FFF -#define OP_CTR_OVERFLOW (1ULL<<31) - -#define MSR_AMD_EVENTSEL_RESERVED ((0xFFFFFCF0ULL<<32)|(1ULL<<21)) - -static int num_counters; -static unsigned long reset_value[OP_MAX_COUNTER]; - -#define IBS_FETCH_SIZE 6 -#define IBS_OP_SIZE 12 - -static u32 ibs_caps; - -struct ibs_config { - unsigned long op_enabled; - unsigned long fetch_enabled; - unsigned long max_cnt_fetch; - unsigned long max_cnt_op; - unsigned long rand_en; - unsigned long dispatched_ops; - unsigned long branch_target; -}; - -struct ibs_state { - u64 ibs_op_ctl; - int branch_target; - unsigned long sample_size; -}; - -static struct ibs_config ibs_config; -static struct ibs_state ibs_state; - -/* - * IBS randomization macros - */ -#define IBS_RANDOM_BITS 12 -#define IBS_RANDOM_MASK ((1ULL << IBS_RANDOM_BITS) - 1) -#define IBS_RANDOM_MAXCNT_OFFSET (1ULL << (IBS_RANDOM_BITS - 5)) - -/* - * 16-bit Linear Feedback Shift Register (LFSR) - * - * 16 14 13 11 - * Feedback polynomial = X + X + X + X + 1 - */ -static unsigned int lfsr_random(void) -{ - static unsigned int lfsr_value = 0xF00D; - unsigned int bit; - - /* Compute next bit to shift in */ - bit = ((lfsr_value >> 0) ^ - (lfsr_value >> 2) ^ - (lfsr_value >> 3) ^ - (lfsr_value >> 5)) & 0x0001; - - /* Advance to next register value */ - lfsr_value = (lfsr_value >> 1) | (bit << 15); - - return lfsr_value; -} - -/* - * IBS software randomization - * - * The IBS periodic op counter is randomized in software. The lower 12 - * bits of the 20 bit counter are randomized. IbsOpCurCnt is - * initialized with a 12 bit random value. - */ -static inline u64 op_amd_randomize_ibs_op(u64 val) -{ - unsigned int random = lfsr_random(); - - if (!(ibs_caps & IBS_CAPS_RDWROPCNT)) - /* - * Work around if the hw can not write to IbsOpCurCnt - * - * Randomize the lower 8 bits of the 16 bit - * IbsOpMaxCnt [15:0] value in the range of -128 to - * +127 by adding/subtracting an offset to the - * maximum count (IbsOpMaxCnt). - * - * To avoid over or underflows and protect upper bits - * starting at bit 16, the initial value for - * IbsOpMaxCnt must fit in the range from 0x0081 to - * 0xff80. - */ - val += (s8)(random >> 4); - else - val |= (u64)(random & IBS_RANDOM_MASK) << 32; - - return val; -} - -static inline void -op_amd_handle_ibs(struct pt_regs * const regs, - struct op_msrs const * const msrs) -{ - u64 val, ctl; - struct op_entry entry; - - if (!ibs_caps) - return; - - if (ibs_config.fetch_enabled) { - rdmsrl(MSR_AMD64_IBSFETCHCTL, ctl); - if (ctl & IBS_FETCH_VAL) { - rdmsrl(MSR_AMD64_IBSFETCHLINAD, val); - oprofile_write_reserve(&entry, regs, val, - IBS_FETCH_CODE, IBS_FETCH_SIZE); - oprofile_add_data64(&entry, val); - oprofile_add_data64(&entry, ctl); - rdmsrl(MSR_AMD64_IBSFETCHPHYSAD, val); - oprofile_add_data64(&entry, val); - oprofile_write_commit(&entry); - - /* reenable the IRQ */ - ctl &= ~(IBS_FETCH_VAL | IBS_FETCH_CNT); - ctl |= IBS_FETCH_ENABLE; - wrmsrl(MSR_AMD64_IBSFETCHCTL, ctl); - } - } - - if (ibs_config.op_enabled) { - rdmsrl(MSR_AMD64_IBSOPCTL, ctl); - if (ctl & IBS_OP_VAL) { - rdmsrl(MSR_AMD64_IBSOPRIP, val); - oprofile_write_reserve(&entry, regs, val, IBS_OP_CODE, - ibs_state.sample_size); - oprofile_add_data64(&entry, val); - rdmsrl(MSR_AMD64_IBSOPDATA, val); - oprofile_add_data64(&entry, val); - rdmsrl(MSR_AMD64_IBSOPDATA2, val); - oprofile_add_data64(&entry, val); - rdmsrl(MSR_AMD64_IBSOPDATA3, val); - oprofile_add_data64(&entry, val); - rdmsrl(MSR_AMD64_IBSDCLINAD, val); - oprofile_add_data64(&entry, val); - rdmsrl(MSR_AMD64_IBSDCPHYSAD, val); - oprofile_add_data64(&entry, val); - if (ibs_state.branch_target) { - rdmsrl(MSR_AMD64_IBSBRTARGET, val); - oprofile_add_data(&entry, (unsigned long)val); - } - oprofile_write_commit(&entry); - - /* reenable the IRQ */ - ctl = op_amd_randomize_ibs_op(ibs_state.ibs_op_ctl); - wrmsrl(MSR_AMD64_IBSOPCTL, ctl); - } - } -} - -static inline void op_amd_start_ibs(void) -{ - u64 val; - - if (!ibs_caps) - return; - - memset(&ibs_state, 0, sizeof(ibs_state)); - - /* - * Note: Since the max count settings may out of range we - * write back the actual used values so that userland can read - * it. - */ - - if (ibs_config.fetch_enabled) { - val = ibs_config.max_cnt_fetch >> 4; - val = min(val, IBS_FETCH_MAX_CNT); - ibs_config.max_cnt_fetch = val << 4; - val |= ibs_config.rand_en ? IBS_FETCH_RAND_EN : 0; - val |= IBS_FETCH_ENABLE; - wrmsrl(MSR_AMD64_IBSFETCHCTL, val); - } - - if (ibs_config.op_enabled) { - val = ibs_config.max_cnt_op >> 4; - if (!(ibs_caps & IBS_CAPS_RDWROPCNT)) { - /* - * IbsOpCurCnt not supported. See - * op_amd_randomize_ibs_op() for details. - */ - val = clamp(val, 0x0081ULL, 0xFF80ULL); - ibs_config.max_cnt_op = val << 4; - } else { - /* - * The start value is randomized with a - * positive offset, we need to compensate it - * with the half of the randomized range. Also - * avoid underflows. - */ - val += IBS_RANDOM_MAXCNT_OFFSET; - if (ibs_caps & IBS_CAPS_OPCNTEXT) - val = min(val, IBS_OP_MAX_CNT_EXT); - else - val = min(val, IBS_OP_MAX_CNT); - ibs_config.max_cnt_op = - (val - IBS_RANDOM_MAXCNT_OFFSET) << 4; - } - val = ((val & ~IBS_OP_MAX_CNT) << 4) | (val & IBS_OP_MAX_CNT); - val |= ibs_config.dispatched_ops ? IBS_OP_CNT_CTL : 0; - val |= IBS_OP_ENABLE; - ibs_state.ibs_op_ctl = val; - ibs_state.sample_size = IBS_OP_SIZE; - if (ibs_config.branch_target) { - ibs_state.branch_target = 1; - ibs_state.sample_size++; - } - val = op_amd_randomize_ibs_op(ibs_state.ibs_op_ctl); - wrmsrl(MSR_AMD64_IBSOPCTL, val); - } -} - -static void op_amd_stop_ibs(void) -{ - if (!ibs_caps) - return; - - if (ibs_config.fetch_enabled) - /* clear max count and enable */ - wrmsrl(MSR_AMD64_IBSFETCHCTL, 0); - - if (ibs_config.op_enabled) - /* clear max count and enable */ - wrmsrl(MSR_AMD64_IBSOPCTL, 0); -} - -#ifdef CONFIG_OPROFILE_EVENT_MULTIPLEX - -static void op_mux_switch_ctrl(struct op_x86_model_spec const *model, - struct op_msrs const * const msrs) -{ - u64 val; - int i; - - /* enable active counters */ - for (i = 0; i < num_counters; ++i) { - int virt = op_x86_phys_to_virt(i); - if (!reset_value[virt]) - continue; - rdmsrl(msrs->controls[i].addr, val); - val &= model->reserved; - val |= op_x86_get_ctrl(model, &counter_config[virt]); - wrmsrl(msrs->controls[i].addr, val); - } -} - -#endif - -/* functions for op_amd_spec */ - -static void op_amd_shutdown(struct op_msrs const * const msrs) -{ - int i; - - for (i = 0; i < num_counters; ++i) { - if (!msrs->counters[i].addr) - continue; - release_perfctr_nmi(MSR_K7_PERFCTR0 + i); - release_evntsel_nmi(MSR_K7_EVNTSEL0 + i); - } -} - -static int op_amd_fill_in_addresses(struct op_msrs * const msrs) -{ - int i; - - for (i = 0; i < num_counters; i++) { - if (!reserve_perfctr_nmi(MSR_K7_PERFCTR0 + i)) - goto fail; - if (!reserve_evntsel_nmi(MSR_K7_EVNTSEL0 + i)) { - release_perfctr_nmi(MSR_K7_PERFCTR0 + i); - goto fail; - } - /* both registers must be reserved */ - if (num_counters == AMD64_NUM_COUNTERS_CORE) { - msrs->counters[i].addr = MSR_F15H_PERF_CTR + (i << 1); - msrs->controls[i].addr = MSR_F15H_PERF_CTL + (i << 1); - } else { - msrs->controls[i].addr = MSR_K7_EVNTSEL0 + i; - msrs->counters[i].addr = MSR_K7_PERFCTR0 + i; - } - continue; - fail: - if (!counter_config[i].enabled) - continue; - op_x86_warn_reserved(i); - op_amd_shutdown(msrs); - return -EBUSY; - } - - return 0; -} - -static void op_amd_setup_ctrs(struct op_x86_model_spec const *model, - struct op_msrs const * const msrs) -{ - u64 val; - int i; - - /* setup reset_value */ - for (i = 0; i < OP_MAX_COUNTER; ++i) { - if (counter_config[i].enabled - && msrs->counters[op_x86_virt_to_phys(i)].addr) - reset_value[i] = counter_config[i].count; - else - reset_value[i] = 0; - } - - /* clear all counters */ - for (i = 0; i < num_counters; ++i) { - if (!msrs->controls[i].addr) - continue; - rdmsrl(msrs->controls[i].addr, val); - if (val & ARCH_PERFMON_EVENTSEL_ENABLE) - op_x86_warn_in_use(i); - val &= model->reserved; - wrmsrl(msrs->controls[i].addr, val); - /* - * avoid a false detection of ctr overflows in NMI - * handler - */ - wrmsrl(msrs->counters[i].addr, -1LL); - } - - /* enable active counters */ - for (i = 0; i < num_counters; ++i) { - int virt = op_x86_phys_to_virt(i); - if (!reset_value[virt]) - continue; - - /* setup counter registers */ - wrmsrl(msrs->counters[i].addr, -(u64)reset_value[virt]); - - /* setup control registers */ - rdmsrl(msrs->controls[i].addr, val); - val &= model->reserved; - val |= op_x86_get_ctrl(model, &counter_config[virt]); - wrmsrl(msrs->controls[i].addr, val); - } -} - -static int op_amd_check_ctrs(struct pt_regs * const regs, - struct op_msrs const * const msrs) -{ - u64 val; - int i; - - for (i = 0; i < num_counters; ++i) { - int virt = op_x86_phys_to_virt(i); - if (!reset_value[virt]) - continue; - rdmsrl(msrs->counters[i].addr, val); - /* bit is clear if overflowed: */ - if (val & OP_CTR_OVERFLOW) - continue; - oprofile_add_sample(regs, virt); - wrmsrl(msrs->counters[i].addr, -(u64)reset_value[virt]); - } - - op_amd_handle_ibs(regs, msrs); - - /* See op_model_ppro.c */ - return 1; -} - -static void op_amd_start(struct op_msrs const * const msrs) -{ - u64 val; - int i; - - for (i = 0; i < num_counters; ++i) { - if (!reset_value[op_x86_phys_to_virt(i)]) - continue; - rdmsrl(msrs->controls[i].addr, val); - val |= ARCH_PERFMON_EVENTSEL_ENABLE; - wrmsrl(msrs->controls[i].addr, val); - } - - op_amd_start_ibs(); -} - -static void op_amd_stop(struct op_msrs const * const msrs) -{ - u64 val; - int i; - - /* - * Subtle: stop on all counters to avoid race with setting our - * pm callback - */ - for (i = 0; i < num_counters; ++i) { - if (!reset_value[op_x86_phys_to_virt(i)]) - continue; - rdmsrl(msrs->controls[i].addr, val); - val &= ~ARCH_PERFMON_EVENTSEL_ENABLE; - wrmsrl(msrs->controls[i].addr, val); - } - - op_amd_stop_ibs(); -} - -/* - * check and reserve APIC extended interrupt LVT offset for IBS if - * available - */ - -static void init_ibs(void) -{ - ibs_caps = get_ibs_caps(); - - if (!ibs_caps) - return; - - printk(KERN_INFO "oprofile: AMD IBS detected (0x%08x)\n", ibs_caps); -} - -static int (*create_arch_files)(struct dentry *root); - -static int setup_ibs_files(struct dentry *root) -{ - struct dentry *dir; - int ret = 0; - - /* architecture specific files */ - if (create_arch_files) - ret = create_arch_files(root); - - if (ret) - return ret; - - if (!ibs_caps) - return ret; - - /* model specific files */ - - /* setup some reasonable defaults */ - memset(&ibs_config, 0, sizeof(ibs_config)); - ibs_config.max_cnt_fetch = 250000; - ibs_config.max_cnt_op = 250000; - - if (ibs_caps & IBS_CAPS_FETCHSAM) { - dir = oprofilefs_mkdir(root, "ibs_fetch"); - oprofilefs_create_ulong(dir, "enable", - &ibs_config.fetch_enabled); - oprofilefs_create_ulong(dir, "max_count", - &ibs_config.max_cnt_fetch); - oprofilefs_create_ulong(dir, "rand_enable", - &ibs_config.rand_en); - } - - if (ibs_caps & IBS_CAPS_OPSAM) { - dir = oprofilefs_mkdir(root, "ibs_op"); - oprofilefs_create_ulong(dir, "enable", - &ibs_config.op_enabled); - oprofilefs_create_ulong(dir, "max_count", - &ibs_config.max_cnt_op); - if (ibs_caps & IBS_CAPS_OPCNT) - oprofilefs_create_ulong(dir, "dispatched_ops", - &ibs_config.dispatched_ops); - if (ibs_caps & IBS_CAPS_BRNTRGT) - oprofilefs_create_ulong(dir, "branch_target", - &ibs_config.branch_target); - } - - return 0; -} - -struct op_x86_model_spec op_amd_spec; - -static int op_amd_init(struct oprofile_operations *ops) -{ - init_ibs(); - create_arch_files = ops->create_files; - ops->create_files = setup_ibs_files; - - if (boot_cpu_data.x86 == 0x15) { - num_counters = AMD64_NUM_COUNTERS_CORE; - } else { - num_counters = AMD64_NUM_COUNTERS; - } - - op_amd_spec.num_counters = num_counters; - op_amd_spec.num_controls = num_counters; - op_amd_spec.num_virt_counters = max(num_counters, NUM_VIRT_COUNTERS); - - return 0; -} - -struct op_x86_model_spec op_amd_spec = { - /* num_counters/num_controls filled in at runtime */ - .reserved = MSR_AMD_EVENTSEL_RESERVED, - .event_mask = OP_EVENT_MASK, - .init = op_amd_init, - .fill_in_addresses = &op_amd_fill_in_addresses, - .setup_ctrs = &op_amd_setup_ctrs, - .check_ctrs = &op_amd_check_ctrs, - .start = &op_amd_start, - .stop = &op_amd_stop, - .shutdown = &op_amd_shutdown, -#ifdef CONFIG_OPROFILE_EVENT_MULTIPLEX - .switch_ctrl = &op_mux_switch_ctrl, -#endif -}; diff --git a/arch/x86/oprofile/op_model_p4.c b/arch/x86/oprofile/op_model_p4.c deleted file mode 100644 index ad1d91f475ab..000000000000 --- a/arch/x86/oprofile/op_model_p4.c +++ /dev/null @@ -1,723 +0,0 @@ -/** - * @file op_model_p4.c - * P4 model-specific MSR operations - * - * @remark Copyright 2002 OProfile authors - * @remark Read the file COPYING - * - * @author Graydon Hoare - */ - -#include <linux/oprofile.h> -#include <linux/smp.h> -#include <linux/ptrace.h> -#include <asm/nmi.h> -#include <asm/msr.h> -#include <asm/fixmap.h> -#include <asm/apic.h> - - -#include "op_x86_model.h" -#include "op_counter.h" - -#define NUM_EVENTS 39 - -#define NUM_COUNTERS_NON_HT 8 -#define NUM_ESCRS_NON_HT 45 -#define NUM_CCCRS_NON_HT 18 -#define NUM_CONTROLS_NON_HT (NUM_ESCRS_NON_HT + NUM_CCCRS_NON_HT) - -#define NUM_COUNTERS_HT2 4 -#define NUM_ESCRS_HT2 23 -#define NUM_CCCRS_HT2 9 -#define NUM_CONTROLS_HT2 (NUM_ESCRS_HT2 + NUM_CCCRS_HT2) - -#define OP_CTR_OVERFLOW (1ULL<<31) - -static unsigned int num_counters = NUM_COUNTERS_NON_HT; -static unsigned int num_controls = NUM_CONTROLS_NON_HT; - -/* this has to be checked dynamically since the - hyper-threadedness of a chip is discovered at - kernel boot-time. */ -static inline void setup_num_counters(void) -{ -#ifdef CONFIG_SMP - if (smp_num_siblings == 2) { - num_counters = NUM_COUNTERS_HT2; - num_controls = NUM_CONTROLS_HT2; - } -#endif -} - -static inline int addr_increment(void) -{ -#ifdef CONFIG_SMP - return smp_num_siblings == 2 ? 2 : 1; -#else - return 1; -#endif -} - - -/* tables to simulate simplified hardware view of p4 registers */ -struct p4_counter_binding { - int virt_counter; - int counter_address; - int cccr_address; -}; - -struct p4_event_binding { - int escr_select; /* value to put in CCCR */ - int event_select; /* value to put in ESCR */ - struct { - int virt_counter; /* for this counter... */ - int escr_address; /* use this ESCR */ - } bindings[2]; -}; - -/* nb: these CTR_* defines are a duplicate of defines in - event/i386.p4*events. */ - - -#define CTR_BPU_0 (1 << 0) -#define CTR_MS_0 (1 << 1) -#define CTR_FLAME_0 (1 << 2) -#define CTR_IQ_4 (1 << 3) -#define CTR_BPU_2 (1 << 4) -#define CTR_MS_2 (1 << 5) -#define CTR_FLAME_2 (1 << 6) -#define CTR_IQ_5 (1 << 7) - -static struct p4_counter_binding p4_counters[NUM_COUNTERS_NON_HT] = { - { CTR_BPU_0, MSR_P4_BPU_PERFCTR0, MSR_P4_BPU_CCCR0 }, - { CTR_MS_0, MSR_P4_MS_PERFCTR0, MSR_P4_MS_CCCR0 }, - { CTR_FLAME_0, MSR_P4_FLAME_PERFCTR0, MSR_P4_FLAME_CCCR0 }, - { CTR_IQ_4, MSR_P4_IQ_PERFCTR4, MSR_P4_IQ_CCCR4 }, - { CTR_BPU_2, MSR_P4_BPU_PERFCTR2, MSR_P4_BPU_CCCR2 }, - { CTR_MS_2, MSR_P4_MS_PERFCTR2, MSR_P4_MS_CCCR2 }, - { CTR_FLAME_2, MSR_P4_FLAME_PERFCTR2, MSR_P4_FLAME_CCCR2 }, - { CTR_IQ_5, MSR_P4_IQ_PERFCTR5, MSR_P4_IQ_CCCR5 } -}; - -#define NUM_UNUSED_CCCRS (NUM_CCCRS_NON_HT - NUM_COUNTERS_NON_HT) - -/* p4 event codes in libop/op_event.h are indices into this table. */ - -static struct p4_event_binding p4_events[NUM_EVENTS] = { - - { /* BRANCH_RETIRED */ - 0x05, 0x06, - { {CTR_IQ_4, MSR_P4_CRU_ESCR2}, - {CTR_IQ_5, MSR_P4_CRU_ESCR3} } - }, - - { /* MISPRED_BRANCH_RETIRED */ - 0x04, 0x03, - { { CTR_IQ_4, MSR_P4_CRU_ESCR0}, - { CTR_IQ_5, MSR_P4_CRU_ESCR1} } - }, - - { /* TC_DELIVER_MODE */ - 0x01, 0x01, - { { CTR_MS_0, MSR_P4_TC_ESCR0}, - { CTR_MS_2, MSR_P4_TC_ESCR1} } - }, - - { /* BPU_FETCH_REQUEST */ - 0x00, 0x03, - { { CTR_BPU_0, MSR_P4_BPU_ESCR0}, - { CTR_BPU_2, MSR_P4_BPU_ESCR1} } - }, - - { /* ITLB_REFERENCE */ - 0x03, 0x18, - { { CTR_BPU_0, MSR_P4_ITLB_ESCR0}, - { CTR_BPU_2, MSR_P4_ITLB_ESCR1} } - }, - - { /* MEMORY_CANCEL */ - 0x05, 0x02, - { { CTR_FLAME_0, MSR_P4_DAC_ESCR0}, - { CTR_FLAME_2, MSR_P4_DAC_ESCR1} } - }, - - { /* MEMORY_COMPLETE */ - 0x02, 0x08, - { { CTR_FLAME_0, MSR_P4_SAAT_ESCR0}, - { CTR_FLAME_2, MSR_P4_SAAT_ESCR1} } - }, - - { /* LOAD_PORT_REPLAY */ - 0x02, 0x04, - { { CTR_FLAME_0, MSR_P4_SAAT_ESCR0}, - { CTR_FLAME_2, MSR_P4_SAAT_ESCR1} } - }, - - { /* STORE_PORT_REPLAY */ - 0x02, 0x05, - { { CTR_FLAME_0, MSR_P4_SAAT_ESCR0}, - { CTR_FLAME_2, MSR_P4_SAAT_ESCR1} } - }, - - { /* MOB_LOAD_REPLAY */ - 0x02, 0x03, - { { CTR_BPU_0, MSR_P4_MOB_ESCR0}, - { CTR_BPU_2, MSR_P4_MOB_ESCR1} } - }, - - { /* PAGE_WALK_TYPE */ - 0x04, 0x01, - { { CTR_BPU_0, MSR_P4_PMH_ESCR0}, - { CTR_BPU_2, MSR_P4_PMH_ESCR1} } - }, - - { /* BSQ_CACHE_REFERENCE */ - 0x07, 0x0c, - { { CTR_BPU_0, MSR_P4_BSU_ESCR0}, - { CTR_BPU_2, MSR_P4_BSU_ESCR1} } - }, - - { /* IOQ_ALLOCATION */ - 0x06, 0x03, - { { CTR_BPU_0, MSR_P4_FSB_ESCR0}, - { 0, 0 } } - }, - - { /* IOQ_ACTIVE_ENTRIES */ - 0x06, 0x1a, - { { CTR_BPU_2, MSR_P4_FSB_ESCR1}, - { 0, 0 } } - }, - - { /* FSB_DATA_ACTIVITY */ - 0x06, 0x17, - { { CTR_BPU_0, MSR_P4_FSB_ESCR0}, - { CTR_BPU_2, MSR_P4_FSB_ESCR1} } - }, - - { /* BSQ_ALLOCATION */ - 0x07, 0x05, - { { CTR_BPU_0, MSR_P4_BSU_ESCR0}, - { 0, 0 } } - }, - - { /* BSQ_ACTIVE_ENTRIES */ - 0x07, 0x06, - { { CTR_BPU_2, MSR_P4_BSU_ESCR1 /* guess */}, - { 0, 0 } } - }, - - { /* X87_ASSIST */ - 0x05, 0x03, - { { CTR_IQ_4, MSR_P4_CRU_ESCR2}, - { CTR_IQ_5, MSR_P4_CRU_ESCR3} } - }, - - { /* SSE_INPUT_ASSIST */ - 0x01, 0x34, - { { CTR_FLAME_0, MSR_P4_FIRM_ESCR0}, - { CTR_FLAME_2, MSR_P4_FIRM_ESCR1} } - }, - - { /* PACKED_SP_UOP */ - 0x01, 0x08, - { { CTR_FLAME_0, MSR_P4_FIRM_ESCR0}, - { CTR_FLAME_2, MSR_P4_FIRM_ESCR1} } - }, - - { /* PACKED_DP_UOP */ - 0x01, 0x0c, - { { CTR_FLAME_0, MSR_P4_FIRM_ESCR0}, - { CTR_FLAME_2, MSR_P4_FIRM_ESCR1} } - }, - - { /* SCALAR_SP_UOP */ - 0x01, 0x0a, - { { CTR_FLAME_0, MSR_P4_FIRM_ESCR0}, - { CTR_FLAME_2, MSR_P4_FIRM_ESCR1} } - }, - - { /* SCALAR_DP_UOP */ - 0x01, 0x0e, - { { CTR_FLAME_0, MSR_P4_FIRM_ESCR0}, - { CTR_FLAME_2, MSR_P4_FIRM_ESCR1} } - }, - - { /* 64BIT_MMX_UOP */ - 0x01, 0x02, - { { CTR_FLAME_0, MSR_P4_FIRM_ESCR0}, - { CTR_FLAME_2, MSR_P4_FIRM_ESCR1} } - }, - - { /* 128BIT_MMX_UOP */ - 0x01, 0x1a, - { { CTR_FLAME_0, MSR_P4_FIRM_ESCR0}, - { CTR_FLAME_2, MSR_P4_FIRM_ESCR1} } - }, - - { /* X87_FP_UOP */ - 0x01, 0x04, - { { CTR_FLAME_0, MSR_P4_FIRM_ESCR0}, - { CTR_FLAME_2, MSR_P4_FIRM_ESCR1} } - }, - - { /* X87_SIMD_MOVES_UOP */ - 0x01, 0x2e, - { { CTR_FLAME_0, MSR_P4_FIRM_ESCR0}, - { CTR_FLAME_2, MSR_P4_FIRM_ESCR1} } - }, - - { /* MACHINE_CLEAR */ - 0x05, 0x02, - { { CTR_IQ_4, MSR_P4_CRU_ESCR2}, - { CTR_IQ_5, MSR_P4_CRU_ESCR3} } - }, - - { /* GLOBAL_POWER_EVENTS */ - 0x06, 0x13 /* older manual says 0x05, newer 0x13 */, - { { CTR_BPU_0, MSR_P4_FSB_ESCR0}, - { CTR_BPU_2, MSR_P4_FSB_ESCR1} } - }, - - { /* TC_MS_XFER */ - 0x00, 0x05, - { { CTR_MS_0, MSR_P4_MS_ESCR0}, - { CTR_MS_2, MSR_P4_MS_ESCR1} } - }, - - { /* UOP_QUEUE_WRITES */ - 0x00, 0x09, - { { CTR_MS_0, MSR_P4_MS_ESCR0}, - { CTR_MS_2, MSR_P4_MS_ESCR1} } - }, - - { /* FRONT_END_EVENT */ - 0x05, 0x08, - { { CTR_IQ_4, MSR_P4_CRU_ESCR2}, - { CTR_IQ_5, MSR_P4_CRU_ESCR3} } - }, - - { /* EXECUTION_EVENT */ - 0x05, 0x0c, - { { CTR_IQ_4, MSR_P4_CRU_ESCR2}, - { CTR_IQ_5, MSR_P4_CRU_ESCR3} } - }, - - { /* REPLAY_EVENT */ - 0x05, 0x09, - { { CTR_IQ_4, MSR_P4_CRU_ESCR2}, - { CTR_IQ_5, MSR_P4_CRU_ESCR3} } - }, - - { /* INSTR_RETIRED */ - 0x04, 0x02, - { { CTR_IQ_4, MSR_P4_CRU_ESCR0}, - { CTR_IQ_5, MSR_P4_CRU_ESCR1} } - }, - - { /* UOPS_RETIRED */ - 0x04, 0x01, - { { CTR_IQ_4, MSR_P4_CRU_ESCR0}, - { CTR_IQ_5, MSR_P4_CRU_ESCR1} } - }, - - { /* UOP_TYPE */ - 0x02, 0x02, - { { CTR_IQ_4, MSR_P4_RAT_ESCR0}, - { CTR_IQ_5, MSR_P4_RAT_ESCR1} } - }, - - { /* RETIRED_MISPRED_BRANCH_TYPE */ - 0x02, 0x05, - { { CTR_MS_0, MSR_P4_TBPU_ESCR0}, - { CTR_MS_2, MSR_P4_TBPU_ESCR1} } - }, - - { /* RETIRED_BRANCH_TYPE */ - 0x02, 0x04, - { { CTR_MS_0, MSR_P4_TBPU_ESCR0}, - { CTR_MS_2, MSR_P4_TBPU_ESCR1} } - } -}; - - -#define MISC_PMC_ENABLED_P(x) ((x) & 1 << 7) - -#define ESCR_RESERVED_BITS 0x80000003 -#define ESCR_CLEAR(escr) ((escr) &= ESCR_RESERVED_BITS) -#define ESCR_SET_USR_0(escr, usr) ((escr) |= (((usr) & 1) << 2)) -#define ESCR_SET_OS_0(escr, os) ((escr) |= (((os) & 1) << 3)) -#define ESCR_SET_USR_1(escr, usr) ((escr) |= (((usr) & 1))) -#define ESCR_SET_OS_1(escr, os) ((escr) |= (((os) & 1) << 1)) -#define ESCR_SET_EVENT_SELECT(escr, sel) ((escr) |= (((sel) & 0x3f) << 25)) -#define ESCR_SET_EVENT_MASK(escr, mask) ((escr) |= (((mask) & 0xffff) << 9)) - -#define CCCR_RESERVED_BITS 0x38030FFF -#define CCCR_CLEAR(cccr) ((cccr) &= CCCR_RESERVED_BITS) -#define CCCR_SET_REQUIRED_BITS(cccr) ((cccr) |= 0x00030000) -#define CCCR_SET_ESCR_SELECT(cccr, sel) ((cccr) |= (((sel) & 0x07) << 13)) -#define CCCR_SET_PMI_OVF_0(cccr) ((cccr) |= (1<<26)) -#define CCCR_SET_PMI_OVF_1(cccr) ((cccr) |= (1<<27)) -#define CCCR_SET_ENABLE(cccr) ((cccr) |= (1<<12)) -#define CCCR_SET_DISABLE(cccr) ((cccr) &= ~(1<<12)) -#define CCCR_OVF_P(cccr) ((cccr) & (1U<<31)) -#define CCCR_CLEAR_OVF(cccr) ((cccr) &= (~(1U<<31))) - - -/* this assigns a "stagger" to the current CPU, which is used throughout - the code in this module as an extra array offset, to select the "even" - or "odd" part of all the divided resources. */ -static unsigned int get_stagger(void) -{ -#ifdef CONFIG_SMP - int cpu = smp_processor_id(); - return cpu != cpumask_first(this_cpu_cpumask_var_ptr(cpu_sibling_map)); -#endif - return 0; -} - - -/* finally, mediate access to a real hardware counter - by passing a "virtual" counter numer to this macro, - along with your stagger setting. */ -#define VIRT_CTR(stagger, i) ((i) + ((num_counters) * (stagger))) - -static unsigned long reset_value[NUM_COUNTERS_NON_HT]; - -static void p4_shutdown(struct op_msrs const * const msrs) -{ - int i; - - for (i = 0; i < num_counters; ++i) { - if (msrs->counters[i].addr) - release_perfctr_nmi(msrs->counters[i].addr); - } - /* - * some of the control registers are specially reserved in - * conjunction with the counter registers (hence the starting offset). - * This saves a few bits. - */ - for (i = num_counters; i < num_controls; ++i) { - if (msrs->controls[i].addr) - release_evntsel_nmi(msrs->controls[i].addr); - } -} - -static int p4_fill_in_addresses(struct op_msrs * const msrs) -{ - unsigned int i; - unsigned int addr, cccraddr, stag; - - setup_num_counters(); - stag = get_stagger(); - - /* the counter & cccr registers we pay attention to */ - for (i = 0; i < num_counters; ++i) { - addr = p4_counters[VIRT_CTR(stag, i)].counter_address; - cccraddr = p4_counters[VIRT_CTR(stag, i)].cccr_address; - if (reserve_perfctr_nmi(addr)) { - msrs->counters[i].addr = addr; - msrs->controls[i].addr = cccraddr; - } - } - - /* 43 ESCR registers in three or four discontiguous group */ - for (addr = MSR_P4_BSU_ESCR0 + stag; - addr < MSR_P4_IQ_ESCR0; ++i, addr += addr_increment()) { - if (reserve_evntsel_nmi(addr)) - msrs->controls[i].addr = addr; - } - - /* no IQ_ESCR0/1 on some models, we save a seconde time BSU_ESCR0/1 - * to avoid special case in nmi_{save|restore}_registers() */ - if (boot_cpu_data.x86_model >= 0x3) { - for (addr = MSR_P4_BSU_ESCR0 + stag; - addr <= MSR_P4_BSU_ESCR1; ++i, addr += addr_increment()) { - if (reserve_evntsel_nmi(addr)) - msrs->controls[i].addr = addr; - } - } else { - for (addr = MSR_P4_IQ_ESCR0 + stag; - addr <= MSR_P4_IQ_ESCR1; ++i, addr += addr_increment()) { - if (reserve_evntsel_nmi(addr)) - msrs->controls[i].addr = addr; - } - } - - for (addr = MSR_P4_RAT_ESCR0 + stag; - addr <= MSR_P4_SSU_ESCR0; ++i, addr += addr_increment()) { - if (reserve_evntsel_nmi(addr)) - msrs->controls[i].addr = addr; - } - - for (addr = MSR_P4_MS_ESCR0 + stag; - addr <= MSR_P4_TC_ESCR1; ++i, addr += addr_increment()) { - if (reserve_evntsel_nmi(addr)) - msrs->controls[i].addr = addr; - } - - for (addr = MSR_P4_IX_ESCR0 + stag; - addr <= MSR_P4_CRU_ESCR3; ++i, addr += addr_increment()) { - if (reserve_evntsel_nmi(addr)) - msrs->controls[i].addr = addr; - } - - /* there are 2 remaining non-contiguously located ESCRs */ - - if (num_counters == NUM_COUNTERS_NON_HT) { - /* standard non-HT CPUs handle both remaining ESCRs*/ - if (reserve_evntsel_nmi(MSR_P4_CRU_ESCR5)) - msrs->controls[i++].addr = MSR_P4_CRU_ESCR5; - if (reserve_evntsel_nmi(MSR_P4_CRU_ESCR4)) - msrs->controls[i++].addr = MSR_P4_CRU_ESCR4; - - } else if (stag == 0) { - /* HT CPUs give the first remainder to the even thread, as - the 32nd control register */ - if (reserve_evntsel_nmi(MSR_P4_CRU_ESCR4)) - msrs->controls[i++].addr = MSR_P4_CRU_ESCR4; - - } else { - /* and two copies of the second to the odd thread, - for the 22st and 23nd control registers */ - if (reserve_evntsel_nmi(MSR_P4_CRU_ESCR5)) { - msrs->controls[i++].addr = MSR_P4_CRU_ESCR5; - msrs->controls[i++].addr = MSR_P4_CRU_ESCR5; - } - } - - for (i = 0; i < num_counters; ++i) { - if (!counter_config[i].enabled) - continue; - if (msrs->controls[i].addr) - continue; - op_x86_warn_reserved(i); - p4_shutdown(msrs); - return -EBUSY; - } - - return 0; -} - - -static void pmc_setup_one_p4_counter(unsigned int ctr) -{ - int i; - int const maxbind = 2; - unsigned int cccr = 0; - unsigned int escr = 0; - unsigned int high = 0; - unsigned int counter_bit; - struct p4_event_binding *ev = NULL; - unsigned int stag; - - stag = get_stagger(); - - /* convert from counter *number* to counter *bit* */ - counter_bit = 1 << VIRT_CTR(stag, ctr); - - /* find our event binding structure. */ - if (counter_config[ctr].event <= 0 || counter_config[ctr].event > NUM_EVENTS) { - printk(KERN_ERR - "oprofile: P4 event code 0x%lx out of range\n", - counter_config[ctr].event); - return; - } - - ev = &(p4_events[counter_config[ctr].event - 1]); - - for (i = 0; i < maxbind; i++) { - if (ev->bindings[i].virt_counter & counter_bit) { - - /* modify ESCR */ - rdmsr(ev->bindings[i].escr_address, escr, high); - ESCR_CLEAR(escr); - if (stag == 0) { - ESCR_SET_USR_0(escr, counter_config[ctr].user); - ESCR_SET_OS_0(escr, counter_config[ctr].kernel); - } else { - ESCR_SET_USR_1(escr, counter_config[ctr].user); - ESCR_SET_OS_1(escr, counter_config[ctr].kernel); - } - ESCR_SET_EVENT_SELECT(escr, ev->event_select); - ESCR_SET_EVENT_MASK(escr, counter_config[ctr].unit_mask); - wrmsr(ev->bindings[i].escr_address, escr, high); - - /* modify CCCR */ - rdmsr(p4_counters[VIRT_CTR(stag, ctr)].cccr_address, - cccr, high); - CCCR_CLEAR(cccr); - CCCR_SET_REQUIRED_BITS(cccr); - CCCR_SET_ESCR_SELECT(cccr, ev->escr_select); - if (stag == 0) - CCCR_SET_PMI_OVF_0(cccr); - else - CCCR_SET_PMI_OVF_1(cccr); - wrmsr(p4_counters[VIRT_CTR(stag, ctr)].cccr_address, - cccr, high); - return; - } - } - - printk(KERN_ERR - "oprofile: P4 event code 0x%lx no binding, stag %d ctr %d\n", - counter_config[ctr].event, stag, ctr); -} - - -static void p4_setup_ctrs(struct op_x86_model_spec const *model, - struct op_msrs const * const msrs) -{ - unsigned int i; - unsigned int low, high; - unsigned int stag; - - stag = get_stagger(); - - rdmsr(MSR_IA32_MISC_ENABLE, low, high); - if (!MISC_PMC_ENABLED_P(low)) { - printk(KERN_ERR "oprofile: P4 PMC not available\n"); - return; - } - - /* clear the cccrs we will use */ - for (i = 0; i < num_counters; i++) { - if (unlikely(!msrs->controls[i].addr)) - continue; - rdmsr(p4_counters[VIRT_CTR(stag, i)].cccr_address, low, high); - CCCR_CLEAR(low); - CCCR_SET_REQUIRED_BITS(low); - wrmsr(p4_counters[VIRT_CTR(stag, i)].cccr_address, low, high); - } - - /* clear all escrs (including those outside our concern) */ - for (i = num_counters; i < num_controls; i++) { - if (unlikely(!msrs->controls[i].addr)) - continue; - wrmsr(msrs->controls[i].addr, 0, 0); - } - - /* setup all counters */ - for (i = 0; i < num_counters; ++i) { - if (counter_config[i].enabled && msrs->controls[i].addr) { - reset_value[i] = counter_config[i].count; - pmc_setup_one_p4_counter(i); - wrmsrl(p4_counters[VIRT_CTR(stag, i)].counter_address, - -(u64)counter_config[i].count); - } else { - reset_value[i] = 0; - } - } -} - - -static int p4_check_ctrs(struct pt_regs * const regs, - struct op_msrs const * const msrs) -{ - unsigned long ctr, low, high, stag, real; - int i; - - stag = get_stagger(); - - for (i = 0; i < num_counters; ++i) { - - if (!reset_value[i]) - continue; - - /* - * there is some eccentricity in the hardware which - * requires that we perform 2 extra corrections: - * - * - check both the CCCR:OVF flag for overflow and the - * counter high bit for un-flagged overflows. - * - * - write the counter back twice to ensure it gets - * updated properly. - * - * the former seems to be related to extra NMIs happening - * during the current NMI; the latter is reported as errata - * N15 in intel doc 249199-029, pentium 4 specification - * update, though their suggested work-around does not - * appear to solve the problem. - */ - - real = VIRT_CTR(stag, i); - - rdmsr(p4_counters[real].cccr_address, low, high); - rdmsr(p4_counters[real].counter_address, ctr, high); - if (CCCR_OVF_P(low) || !(ctr & OP_CTR_OVERFLOW)) { - oprofile_add_sample(regs, i); - wrmsrl(p4_counters[real].counter_address, - -(u64)reset_value[i]); - CCCR_CLEAR_OVF(low); - wrmsr(p4_counters[real].cccr_address, low, high); - wrmsrl(p4_counters[real].counter_address, - -(u64)reset_value[i]); - } - } - - /* P4 quirk: you have to re-unmask the apic vector */ - apic_write(APIC_LVTPC, apic_read(APIC_LVTPC) & ~APIC_LVT_MASKED); - - /* See op_model_ppro.c */ - return 1; -} - - -static void p4_start(struct op_msrs const * const msrs) -{ - unsigned int low, high, stag; - int i; - - stag = get_stagger(); - - for (i = 0; i < num_counters; ++i) { - if (!reset_value[i]) - continue; - rdmsr(p4_counters[VIRT_CTR(stag, i)].cccr_address, low, high); - CCCR_SET_ENABLE(low); - wrmsr(p4_counters[VIRT_CTR(stag, i)].cccr_address, low, high); - } -} - - -static void p4_stop(struct op_msrs const * const msrs) -{ - unsigned int low, high, stag; - int i; - - stag = get_stagger(); - - for (i = 0; i < num_counters; ++i) { - if (!reset_value[i]) - continue; - rdmsr(p4_counters[VIRT_CTR(stag, i)].cccr_address, low, high); - CCCR_SET_DISABLE(low); - wrmsr(p4_counters[VIRT_CTR(stag, i)].cccr_address, low, high); - } -} - -#ifdef CONFIG_SMP -struct op_x86_model_spec op_p4_ht2_spec = { - .num_counters = NUM_COUNTERS_HT2, - .num_controls = NUM_CONTROLS_HT2, - .fill_in_addresses = &p4_fill_in_addresses, - .setup_ctrs = &p4_setup_ctrs, - .check_ctrs = &p4_check_ctrs, - .start = &p4_start, - .stop = &p4_stop, - .shutdown = &p4_shutdown -}; -#endif - -struct op_x86_model_spec op_p4_spec = { - .num_counters = NUM_COUNTERS_NON_HT, - .num_controls = NUM_CONTROLS_NON_HT, - .fill_in_addresses = &p4_fill_in_addresses, - .setup_ctrs = &p4_setup_ctrs, - .check_ctrs = &p4_check_ctrs, - .start = &p4_start, - .stop = &p4_stop, - .shutdown = &p4_shutdown -}; diff --git a/arch/x86/oprofile/op_model_ppro.c b/arch/x86/oprofile/op_model_ppro.c deleted file mode 100644 index 7913b6921959..000000000000 --- a/arch/x86/oprofile/op_model_ppro.c +++ /dev/null @@ -1,245 +0,0 @@ -/* - * @file op_model_ppro.h - * Family 6 perfmon and architectural perfmon MSR operations - * - * @remark Copyright 2002 OProfile authors - * @remark Copyright 2008 Intel Corporation - * @remark Read the file COPYING - * - * @author John Levon - * @author Philippe Elie - * @author Graydon Hoare - * @author Andi Kleen - * @author Robert Richter <robert.richter@amd.com> - */ - -#include <linux/oprofile.h> -#include <linux/slab.h> -#include <asm/ptrace.h> -#include <asm/msr.h> -#include <asm/apic.h> -#include <asm/nmi.h> - -#include "op_x86_model.h" -#include "op_counter.h" - -static int num_counters = 2; -static int counter_width = 32; - -#define MSR_PPRO_EVENTSEL_RESERVED ((0xFFFFFFFFULL<<32)|(1ULL<<21)) - -static u64 reset_value[OP_MAX_COUNTER]; - -static void ppro_shutdown(struct op_msrs const * const msrs) -{ - int i; - - for (i = 0; i < num_counters; ++i) { - if (!msrs->counters[i].addr) - continue; - release_perfctr_nmi(MSR_P6_PERFCTR0 + i); - release_evntsel_nmi(MSR_P6_EVNTSEL0 + i); - } -} - -static int ppro_fill_in_addresses(struct op_msrs * const msrs) -{ - int i; - - for (i = 0; i < num_counters; i++) { - if (!reserve_perfctr_nmi(MSR_P6_PERFCTR0 + i)) - goto fail; - if (!reserve_evntsel_nmi(MSR_P6_EVNTSEL0 + i)) { - release_perfctr_nmi(MSR_P6_PERFCTR0 + i); - goto fail; - } - /* both registers must be reserved */ - msrs->counters[i].addr = MSR_P6_PERFCTR0 + i; - msrs->controls[i].addr = MSR_P6_EVNTSEL0 + i; - continue; - fail: - if (!counter_config[i].enabled) - continue; - op_x86_warn_reserved(i); - ppro_shutdown(msrs); - return -EBUSY; - } - - return 0; -} - - -static void ppro_setup_ctrs(struct op_x86_model_spec const *model, - struct op_msrs const * const msrs) -{ - u64 val; - int i; - - if (boot_cpu_has(X86_FEATURE_ARCH_PERFMON)) { - union cpuid10_eax eax; - eax.full = cpuid_eax(0xa); - - /* - * For Core2 (family 6, model 15), don't reset the - * counter width: - */ - if (!(eax.split.version_id == 0 && - __this_cpu_read(cpu_info.x86) == 6 && - __this_cpu_read(cpu_info.x86_model) == 15)) { - - if (counter_width < eax.split.bit_width) - counter_width = eax.split.bit_width; - } - } - - /* clear all counters */ - for (i = 0; i < num_counters; ++i) { - if (!msrs->controls[i].addr) - continue; - rdmsrl(msrs->controls[i].addr, val); - if (val & ARCH_PERFMON_EVENTSEL_ENABLE) - op_x86_warn_in_use(i); - val &= model->reserved; - wrmsrl(msrs->controls[i].addr, val); - /* - * avoid a false detection of ctr overflows in NMI * - * handler - */ - wrmsrl(msrs->counters[i].addr, -1LL); - } - - /* enable active counters */ - for (i = 0; i < num_counters; ++i) { - if (counter_config[i].enabled && msrs->counters[i].addr) { - reset_value[i] = counter_config[i].count; - wrmsrl(msrs->counters[i].addr, -reset_value[i]); - rdmsrl(msrs->controls[i].addr, val); - val &= model->reserved; - val |= op_x86_get_ctrl(model, &counter_config[i]); - wrmsrl(msrs->controls[i].addr, val); - } else { - reset_value[i] = 0; - } - } -} - - -static int ppro_check_ctrs(struct pt_regs * const regs, - struct op_msrs const * const msrs) -{ - u64 val; - int i; - - for (i = 0; i < num_counters; ++i) { - if (!reset_value[i]) - continue; - rdmsrl(msrs->counters[i].addr, val); - if (val & (1ULL << (counter_width - 1))) - continue; - oprofile_add_sample(regs, i); - wrmsrl(msrs->counters[i].addr, -reset_value[i]); - } - - /* Only P6 based Pentium M need to re-unmask the apic vector but it - * doesn't hurt other P6 variant */ - apic_write(APIC_LVTPC, apic_read(APIC_LVTPC) & ~APIC_LVT_MASKED); - - /* We can't work out if we really handled an interrupt. We - * might have caught a *second* counter just after overflowing - * the interrupt for this counter then arrives - * and we don't find a counter that's overflowed, so we - * would return 0 and get dazed + confused. Instead we always - * assume we found an overflow. This sucks. - */ - return 1; -} - - -static void ppro_start(struct op_msrs const * const msrs) -{ - u64 val; - int i; - - for (i = 0; i < num_counters; ++i) { - if (reset_value[i]) { - rdmsrl(msrs->controls[i].addr, val); - val |= ARCH_PERFMON_EVENTSEL_ENABLE; - wrmsrl(msrs->controls[i].addr, val); - } - } -} - - -static void ppro_stop(struct op_msrs const * const msrs) -{ - u64 val; - int i; - - for (i = 0; i < num_counters; ++i) { - if (!reset_value[i]) - continue; - rdmsrl(msrs->controls[i].addr, val); - val &= ~ARCH_PERFMON_EVENTSEL_ENABLE; - wrmsrl(msrs->controls[i].addr, val); - } -} - -struct op_x86_model_spec op_ppro_spec = { - .num_counters = 2, - .num_controls = 2, - .reserved = MSR_PPRO_EVENTSEL_RESERVED, - .fill_in_addresses = &ppro_fill_in_addresses, - .setup_ctrs = &ppro_setup_ctrs, - .check_ctrs = &ppro_check_ctrs, - .start = &ppro_start, - .stop = &ppro_stop, - .shutdown = &ppro_shutdown -}; - -/* - * Architectural performance monitoring. - * - * Newer Intel CPUs (Core1+) have support for architectural - * events described in CPUID 0xA. See the IA32 SDM Vol3b.18 for details. - * The advantage of this is that it can be done without knowing about - * the specific CPU. - */ - -static void arch_perfmon_setup_counters(void) -{ - union cpuid10_eax eax; - - eax.full = cpuid_eax(0xa); - - /* Workaround for BIOS bugs in 6/15. Taken from perfmon2 */ - if (eax.split.version_id == 0 && boot_cpu_data.x86 == 6 && - boot_cpu_data.x86_model == 15) { - eax.split.version_id = 2; - eax.split.num_counters = 2; - eax.split.bit_width = 40; - } - - num_counters = min((int)eax.split.num_counters, OP_MAX_COUNTER); - - op_arch_perfmon_spec.num_counters = num_counters; - op_arch_perfmon_spec.num_controls = num_counters; -} - -static int arch_perfmon_init(struct oprofile_operations *ignore) -{ - arch_perfmon_setup_counters(); - return 0; -} - -struct op_x86_model_spec op_arch_perfmon_spec = { - .reserved = MSR_PPRO_EVENTSEL_RESERVED, - .init = &arch_perfmon_init, - /* num_counters/num_controls filled in at runtime */ - .fill_in_addresses = &ppro_fill_in_addresses, - /* user space does the cpuid check for available events */ - .setup_ctrs = &ppro_setup_ctrs, - .check_ctrs = &ppro_check_ctrs, - .start = &ppro_start, - .stop = &ppro_stop, - .shutdown = &ppro_shutdown -}; diff --git a/arch/x86/oprofile/op_x86_model.h b/arch/x86/oprofile/op_x86_model.h deleted file mode 100644 index 276cf79b5d24..000000000000 --- a/arch/x86/oprofile/op_x86_model.h +++ /dev/null @@ -1,90 +0,0 @@ -/** - * @file op_x86_model.h - * interface to x86 model-specific MSR operations - * - * @remark Copyright 2002 OProfile authors - * @remark Read the file COPYING - * - * @author Graydon Hoare - * @author Robert Richter <robert.richter@amd.com> - */ - -#ifndef OP_X86_MODEL_H -#define OP_X86_MODEL_H - -#include <asm/types.h> -#include <asm/perf_event.h> - -struct op_msr { - unsigned long addr; - u64 saved; -}; - -struct op_msrs { - struct op_msr *counters; - struct op_msr *controls; - struct op_msr *multiplex; -}; - -struct pt_regs; - -struct oprofile_operations; - -/* The model vtable abstracts the differences between - * various x86 CPU models' perfctr support. - */ -struct op_x86_model_spec { - unsigned int num_counters; - unsigned int num_controls; - unsigned int num_virt_counters; - u64 reserved; - u16 event_mask; - int (*init)(struct oprofile_operations *ops); - int (*fill_in_addresses)(struct op_msrs * const msrs); - void (*setup_ctrs)(struct op_x86_model_spec const *model, - struct op_msrs const * const msrs); - int (*check_ctrs)(struct pt_regs * const regs, - struct op_msrs const * const msrs); - void (*start)(struct op_msrs const * const msrs); - void (*stop)(struct op_msrs const * const msrs); - void (*shutdown)(struct op_msrs const * const msrs); -#ifdef CONFIG_OPROFILE_EVENT_MULTIPLEX - void (*switch_ctrl)(struct op_x86_model_spec const *model, - struct op_msrs const * const msrs); -#endif -}; - -struct op_counter_config; - -static inline void op_x86_warn_in_use(int counter) -{ - /* - * The warning indicates an already running counter. If - * oprofile doesn't collect data, then try using a different - * performance counter on your platform to monitor the desired - * event. Delete counter #%d from the desired event by editing - * the /usr/share/oprofile/%s/<cpu>/events file. If the event - * cannot be monitored by any other counter, contact your - * hardware or BIOS vendor. - */ - pr_warn("oprofile: counter #%d on cpu #%d may already be used\n", - counter, smp_processor_id()); -} - -static inline void op_x86_warn_reserved(int counter) -{ - pr_warn("oprofile: counter #%d is already reserved\n", counter); -} - -extern u64 op_x86_get_ctrl(struct op_x86_model_spec const *model, - struct op_counter_config *counter_config); -extern int op_x86_phys_to_virt(int phys); -extern int op_x86_virt_to_phys(int virt); - -extern struct op_x86_model_spec op_ppro_spec; -extern struct op_x86_model_spec op_p4_spec; -extern struct op_x86_model_spec op_p4_ht2_spec; -extern struct op_x86_model_spec op_amd_spec; -extern struct op_x86_model_spec op_arch_perfmon_spec; - -#endif /* OP_X86_MODEL_H */ diff --git a/arch/x86/pci/intel_mid_pci.c b/arch/x86/pci/intel_mid_pci.c index 95e2e6bd8d8c..8edd62206604 100644 --- a/arch/x86/pci/intel_mid_pci.c +++ b/arch/x86/pci/intel_mid_pci.c @@ -28,10 +28,12 @@ #include <linux/io.h> #include <linux/smp.h> +#include <asm/cpu_device_id.h> #include <asm/segment.h> #include <asm/pci_x86.h> #include <asm/hw_irq.h> #include <asm/io_apic.h> +#include <asm/intel-family.h> #include <asm/intel-mid.h> #include <asm/acpi.h> @@ -140,6 +142,7 @@ static int pci_device_update_fixed(struct pci_bus *bus, unsigned int devfn, * type1_access_ok - check whether to use type 1 * @bus: bus number * @devfn: device & function in question + * @reg: configuration register offset * * If the bus is on a Lincroft chip and it exists, or is not on a Lincroft at * all, the we can go ahead with any reads & writes. If it's on a Lincroft, @@ -212,10 +215,17 @@ static int pci_write(struct pci_bus *bus, unsigned int devfn, int where, where, size, value); } +static const struct x86_cpu_id intel_mid_cpu_ids[] = { + X86_MATCH_INTEL_FAM6_MODEL(ATOM_SILVERMONT_MID, NULL), + {} +}; + static int intel_mid_pci_irq_enable(struct pci_dev *dev) { + const struct x86_cpu_id *id; struct irq_alloc_info info; bool polarity_low; + u16 model = 0; int ret; u8 gsi; @@ -228,8 +238,12 @@ static int intel_mid_pci_irq_enable(struct pci_dev *dev) return ret; } - switch (intel_mid_identify_cpu()) { - case INTEL_MID_CPU_CHIP_TANGIER: + id = x86_match_cpu(intel_mid_cpu_ids); + if (id) + model = id->model; + + switch (model) { + case INTEL_FAM6_ATOM_SILVERMONT_MID: polarity_low = false; /* Special treatment for IRQ0 */ diff --git a/arch/x86/pci/mmconfig-shared.c b/arch/x86/pci/mmconfig-shared.c index 234998f196d4..de6bf0e7e8f8 100644 --- a/arch/x86/pci/mmconfig-shared.c +++ b/arch/x86/pci/mmconfig-shared.c @@ -11,9 +11,9 @@ * themselves. */ +#include <linux/acpi.h> #include <linux/pci.h> #include <linux/init.h> -#include <linux/sfi_acpi.h> #include <linux/bitmap.h> #include <linux/dmi.h> #include <linux/slab.h> @@ -665,7 +665,7 @@ void __init pci_mmcfg_early_init(void) if (pci_mmcfg_check_hostbridge()) known_bridge = 1; else - acpi_sfi_table_parse(ACPI_SIG_MCFG, pci_parse_mcfg); + acpi_table_parse(ACPI_SIG_MCFG, pci_parse_mcfg); __pci_mmcfg_init(1); set_apei_filter(); @@ -683,7 +683,7 @@ void __init pci_mmcfg_late_init(void) /* MMCONFIG hasn't been enabled yet, try again */ if (pci_probe & PCI_PROBE_MASK & ~PCI_PROBE_MMCONF) { - acpi_sfi_table_parse(ACPI_SIG_MCFG, pci_parse_mcfg); + acpi_table_parse(ACPI_SIG_MCFG, pci_parse_mcfg); __pci_mmcfg_init(0); } } diff --git a/arch/x86/platform/Makefile b/arch/x86/platform/Makefile index d0e835470d01..3ed03a2552d0 100644 --- a/arch/x86/platform/Makefile +++ b/arch/x86/platform/Makefile @@ -4,13 +4,11 @@ obj-y += atom/ obj-y += ce4100/ obj-y += efi/ obj-y += geode/ -obj-y += goldfish/ obj-y += iris/ obj-y += intel/ obj-y += intel-mid/ obj-y += intel-quark/ obj-y += olpc/ obj-y += scx200/ -obj-y += sfi/ obj-y += ts5500/ obj-y += uv/ diff --git a/arch/x86/platform/efi/efi_64.c b/arch/x86/platform/efi/efi_64.c index 8efd003540ca..1b82d77019b1 100644 --- a/arch/x86/platform/efi/efi_64.c +++ b/arch/x86/platform/efi/efi_64.c @@ -54,10 +54,7 @@ * 0xffff_ffff_0000_0000 and limit EFI VA mapping space to 64G. */ static u64 efi_va = EFI_VA_START; - -struct efi_scratch efi_scratch; - -EXPORT_SYMBOL_GPL(efi_mm); +static struct mm_struct *efi_prev_mm; /* * We need our own copy of the higher levels of the page tables @@ -237,7 +234,7 @@ int __init efi_setup_page_tables(unsigned long pa_memmap, unsigned num_pages) return 1; } - efi_scratch.phys_stack = page_to_phys(page + 1); /* stack grows down */ + efi_mixed_mode_stack_pa = page_to_phys(page + 1); /* stack grows down */ npages = (_etext - _text) >> PAGE_SHIFT; text = __pa(_text); @@ -462,11 +459,17 @@ void __init efi_dump_pagetable(void) * can not change under us. * It should be ensured that there are no concurent calls to this function. */ -void efi_switch_mm(struct mm_struct *mm) +void efi_enter_mm(void) +{ + efi_prev_mm = current->active_mm; + current->active_mm = &efi_mm; + switch_mm(efi_prev_mm, &efi_mm, NULL); +} + +void efi_leave_mm(void) { - efi_scratch.prev_mm = current->active_mm; - current->active_mm = mm; - switch_mm(efi_scratch.prev_mm, mm, NULL); + current->active_mm = efi_prev_mm; + switch_mm(&efi_mm, efi_prev_mm, NULL); } static DEFINE_SPINLOCK(efi_runtime_lock); @@ -530,12 +533,12 @@ efi_thunk_set_virtual_address_map(unsigned long memory_map_size, efi_sync_low_kernel_mappings(); local_irq_save(flags); - efi_switch_mm(&efi_mm); + efi_enter_mm(); status = __efi_thunk(set_virtual_address_map, memory_map_size, descriptor_size, descriptor_version, virtual_map); - efi_switch_mm(efi_scratch.prev_mm); + efi_leave_mm(); local_irq_restore(flags); return status; @@ -829,9 +832,9 @@ efi_set_virtual_address_map(unsigned long memory_map_size, descriptor_size, descriptor_version, virtual_map); - efi_switch_mm(&efi_mm); + efi_enter_mm(); - kernel_fpu_begin(); + efi_fpu_begin(); /* Disable interrupts around EFI calls: */ local_irq_save(flags); @@ -840,12 +843,12 @@ efi_set_virtual_address_map(unsigned long memory_map_size, descriptor_version, virtual_map); local_irq_restore(flags); - kernel_fpu_end(); + efi_fpu_end(); /* grab the virtually remapped EFI runtime services table pointer */ efi.runtime = READ_ONCE(systab->runtime); - efi_switch_mm(efi_scratch.prev_mm); + efi_leave_mm(); return status; } diff --git a/arch/x86/platform/efi/efi_thunk_64.S b/arch/x86/platform/efi/efi_thunk_64.S index 26f0da238c1c..fd3dd1708eba 100644 --- a/arch/x86/platform/efi/efi_thunk_64.S +++ b/arch/x86/platform/efi/efi_thunk_64.S @@ -33,7 +33,7 @@ SYM_CODE_START(__efi64_thunk) * Switch to 1:1 mapped 32-bit stack pointer. */ movq %rsp, %rax - movq efi_scratch(%rip), %rsp + movq efi_mixed_mode_stack_pa(%rip), %rsp push %rax /* @@ -70,3 +70,7 @@ SYM_CODE_START(__efi64_thunk) pushl %ebp lret SYM_CODE_END(__efi64_thunk) + + .bss + .balign 8 +SYM_DATA(efi_mixed_mode_stack_pa, .quad 0) diff --git a/arch/x86/platform/efi/quirks.c b/arch/x86/platform/efi/quirks.c index 5a40fe411ebd..67d93a243c35 100644 --- a/arch/x86/platform/efi/quirks.c +++ b/arch/x86/platform/efi/quirks.c @@ -687,15 +687,25 @@ int efi_capsule_setup_info(struct capsule_info *cap_info, void *kbuff, * @return: Returns, if the page fault is not handled. This function * will never return if the page fault is handled successfully. */ -void efi_recover_from_page_fault(unsigned long phys_addr) +void efi_crash_gracefully_on_page_fault(unsigned long phys_addr) { if (!IS_ENABLED(CONFIG_X86_64)) return; /* + * If we get an interrupt/NMI while processing an EFI runtime service + * then this is a regular OOPS, not an EFI failure. + */ + if (in_interrupt()) + return; + + /* * Make sure that an efi runtime service caused the page fault. + * READ_ONCE() because we might be OOPSing in a different thread, + * and we don't want to trip KTSAN while trying to OOPS. */ - if (efi_rts_work.efi_rts_id == EFI_NONE) + if (READ_ONCE(efi_rts_work.efi_rts_id) == EFI_NONE || + current_work() != &efi_rts_work.work) return; /* @@ -747,6 +757,4 @@ void efi_recover_from_page_fault(unsigned long phys_addr) set_current_state(TASK_IDLE); schedule(); } - - return; } diff --git a/arch/x86/platform/geode/alix.c b/arch/x86/platform/geode/alix.c index c33f744b5388..b39bf3b5e108 100644 --- a/arch/x86/platform/geode/alix.c +++ b/arch/x86/platform/geode/alix.c @@ -22,6 +22,7 @@ #include <linux/platform_device.h> #include <linux/input.h> #include <linux/gpio_keys.h> +#include <linux/gpio/machine.h> #include <linux/dmi.h> #include <asm/geode.h> @@ -69,21 +70,15 @@ static struct platform_device alix_buttons_dev = { static struct gpio_led alix_leds[] = { { .name = "alix:1", - .gpio = 6, .default_trigger = "default-on", - .active_low = 1, }, { .name = "alix:2", - .gpio = 25, .default_trigger = "default-off", - .active_low = 1, }, { .name = "alix:3", - .gpio = 27, .default_trigger = "default-off", - .active_low = 1, }, }; @@ -92,6 +87,17 @@ static struct gpio_led_platform_data alix_leds_data = { .leds = alix_leds, }; +static struct gpiod_lookup_table alix_leds_gpio_table = { + .dev_id = "leds-gpio", + .table = { + /* The Geode GPIOs should be on the CS5535 companion chip */ + GPIO_LOOKUP_IDX("cs5535-gpio", 6, NULL, 0, GPIO_ACTIVE_LOW), + GPIO_LOOKUP_IDX("cs5535-gpio", 25, NULL, 1, GPIO_ACTIVE_LOW), + GPIO_LOOKUP_IDX("cs5535-gpio", 27, NULL, 2, GPIO_ACTIVE_LOW), + { } + }, +}; + static struct platform_device alix_leds_dev = { .name = "leds-gpio", .id = -1, @@ -106,6 +112,7 @@ static struct platform_device *alix_devs[] __initdata = { static void __init register_alix(void) { /* Setup LED control through leds-gpio driver */ + gpiod_add_lookup_table(&alix_leds_gpio_table); platform_add_devices(alix_devs, ARRAY_SIZE(alix_devs)); } diff --git a/arch/x86/platform/geode/geos.c b/arch/x86/platform/geode/geos.c index 73a3f49b4eb6..d263528c90bb 100644 --- a/arch/x86/platform/geode/geos.c +++ b/arch/x86/platform/geode/geos.c @@ -20,6 +20,7 @@ #include <linux/platform_device.h> #include <linux/input.h> #include <linux/gpio_keys.h> +#include <linux/gpio/machine.h> #include <linux/dmi.h> #include <asm/geode.h> @@ -53,21 +54,15 @@ static struct platform_device geos_buttons_dev = { 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, }, }; @@ -76,6 +71,17 @@ static struct gpio_led_platform_data geos_leds_data = { .leds = geos_leds, }; +static struct gpiod_lookup_table geos_leds_gpio_table = { + .dev_id = "leds-gpio", + .table = { + /* The Geode GPIOs should be on the CS5535 companion chip */ + GPIO_LOOKUP_IDX("cs5535-gpio", 6, NULL, 0, GPIO_ACTIVE_LOW), + GPIO_LOOKUP_IDX("cs5535-gpio", 25, NULL, 1, GPIO_ACTIVE_LOW), + GPIO_LOOKUP_IDX("cs5535-gpio", 27, NULL, 2, GPIO_ACTIVE_LOW), + { } + }, +}; + static struct platform_device geos_leds_dev = { .name = "leds-gpio", .id = -1, @@ -90,6 +96,7 @@ static struct platform_device *geos_devs[] __initdata = { static void __init register_geos(void) { /* Setup LED control through leds-gpio driver */ + gpiod_add_lookup_table(&geos_leds_gpio_table); platform_add_devices(geos_devs, ARRAY_SIZE(geos_devs)); } diff --git a/arch/x86/platform/geode/net5501.c b/arch/x86/platform/geode/net5501.c index 163e1b545517..558384acd777 100644 --- a/arch/x86/platform/geode/net5501.c +++ b/arch/x86/platform/geode/net5501.c @@ -20,6 +20,7 @@ #include <linux/platform_device.h> #include <linux/input.h> #include <linux/gpio_keys.h> +#include <linux/gpio/machine.h> #include <asm/geode.h> @@ -55,9 +56,7 @@ static struct platform_device net5501_buttons_dev = { static struct gpio_led net5501_leds[] = { { .name = "net5501:1", - .gpio = 6, .default_trigger = "default-on", - .active_low = 0, }, }; @@ -66,6 +65,15 @@ static struct gpio_led_platform_data net5501_leds_data = { .leds = net5501_leds, }; +static struct gpiod_lookup_table net5501_leds_gpio_table = { + .dev_id = "leds-gpio", + .table = { + /* The Geode GPIOs should be on the CS5535 companion chip */ + GPIO_LOOKUP_IDX("cs5535-gpio", 6, NULL, 0, GPIO_ACTIVE_HIGH), + { } + }, +}; + static struct platform_device net5501_leds_dev = { .name = "leds-gpio", .id = -1, @@ -80,6 +88,7 @@ static struct platform_device *net5501_devs[] __initdata = { static void __init register_net5501(void) { /* Setup LED control through leds-gpio driver */ + gpiod_add_lookup_table(&net5501_leds_gpio_table); platform_add_devices(net5501_devs, ARRAY_SIZE(net5501_devs)); } diff --git a/arch/x86/platform/goldfish/Makefile b/arch/x86/platform/goldfish/Makefile deleted file mode 100644 index 072c395379ac..000000000000 --- a/arch/x86/platform/goldfish/Makefile +++ /dev/null @@ -1,2 +0,0 @@ -# SPDX-License-Identifier: GPL-2.0-only -obj-$(CONFIG_GOLDFISH) += goldfish.o diff --git a/arch/x86/platform/goldfish/goldfish.c b/arch/x86/platform/goldfish/goldfish.c deleted file mode 100644 index 6b6f8b4360dd..000000000000 --- a/arch/x86/platform/goldfish/goldfish.c +++ /dev/null @@ -1,54 +0,0 @@ -// SPDX-License-Identifier: GPL-2.0-only -/* - * Copyright (C) 2007 Google, Inc. - * Copyright (C) 2011 Intel, Inc. - * Copyright (C) 2013 Intel, Inc. - */ - -#include <linux/kernel.h> -#include <linux/irq.h> -#include <linux/platform_device.h> - -/* - * Where in virtual device memory the IO devices (timers, system controllers - * and so on) - */ - -#define GOLDFISH_PDEV_BUS_BASE (0xff001000) -#define GOLDFISH_PDEV_BUS_END (0xff7fffff) -#define GOLDFISH_PDEV_BUS_IRQ (4) - -#define GOLDFISH_TTY_BASE (0x2000) - -static struct resource goldfish_pdev_bus_resources[] = { - { - .start = GOLDFISH_PDEV_BUS_BASE, - .end = GOLDFISH_PDEV_BUS_END, - .flags = IORESOURCE_MEM, - }, - { - .start = GOLDFISH_PDEV_BUS_IRQ, - .end = GOLDFISH_PDEV_BUS_IRQ, - .flags = IORESOURCE_IRQ, - } -}; - -static bool goldfish_enable __initdata; - -static int __init goldfish_setup(char *str) -{ - goldfish_enable = true; - return 0; -} -__setup("goldfish", goldfish_setup); - -static int __init goldfish_init(void) -{ - if (!goldfish_enable) - return -ENODEV; - - platform_device_register_simple("goldfish_pdev_bus", -1, - goldfish_pdev_bus_resources, 2); - return 0; -} -device_initcall(goldfish_init); diff --git a/arch/x86/platform/intel-mid/Makefile b/arch/x86/platform/intel-mid/Makefile index cc2549f0ccb1..ddfc08783fb8 100644 --- a/arch/x86/platform/intel-mid/Makefile +++ b/arch/x86/platform/intel-mid/Makefile @@ -1,7 +1,2 @@ # SPDX-License-Identifier: GPL-2.0-only -obj-$(CONFIG_X86_INTEL_MID) += intel-mid.o intel_mid_vrtc.o pwr.o - -# SFI specific code -ifdef CONFIG_X86_INTEL_MID -obj-$(CONFIG_SFI) += sfi.o device_libs/ -endif +obj-$(CONFIG_X86_INTEL_MID) += intel-mid.o pwr.o diff --git a/arch/x86/platform/intel-mid/device_libs/Makefile b/arch/x86/platform/intel-mid/device_libs/Makefile deleted file mode 100644 index 480fed21cc7d..000000000000 --- a/arch/x86/platform/intel-mid/device_libs/Makefile +++ /dev/null @@ -1,33 +0,0 @@ -# SPDX-License-Identifier: GPL-2.0 -# Family-Level Interface Shim (FLIS) -obj-$(subst m,y,$(CONFIG_PINCTRL_MERRIFIELD)) += platform_mrfld_pinctrl.o -# SDHCI Devices -obj-$(subst m,y,$(CONFIG_MMC_SDHCI_PCI)) += platform_mrfld_sd.o -# WiFi + BT -obj-$(subst m,y,$(CONFIG_BRCMFMAC_SDIO)) += platform_bcm43xx.o -obj-$(subst m,y,$(CONFIG_BT_HCIUART_BCM)) += platform_bt.o -# IPC Devices -obj-$(subst m,y,$(CONFIG_MFD_INTEL_MSIC)) += platform_msic.o -obj-$(subst m,y,$(CONFIG_SND_MFLD_MACHINE)) += platform_msic_audio.o -obj-$(subst m,y,$(CONFIG_GPIO_MSIC)) += platform_msic_gpio.o -obj-$(subst m,y,$(CONFIG_MFD_INTEL_MSIC)) += platform_msic_ocd.o -obj-$(subst m,y,$(CONFIG_MFD_INTEL_MSIC)) += platform_msic_battery.o -obj-$(subst m,y,$(CONFIG_INTEL_MID_POWER_BUTTON)) += platform_msic_power_btn.o -obj-$(subst m,y,$(CONFIG_INTEL_MFLD_THERMAL)) += platform_msic_thermal.o -# SPI Devices -obj-$(subst m,y,$(CONFIG_SPI_SPIDEV)) += platform_mrfld_spidev.o -# I2C Devices -obj-$(subst m,y,$(CONFIG_SENSORS_EMC1403)) += platform_emc1403.o -obj-$(subst m,y,$(CONFIG_SENSORS_LIS3LV02D)) += platform_lis331.o -obj-$(subst m,y,$(CONFIG_MPU3050_I2C)) += platform_mpu3050.o -obj-$(subst m,y,$(CONFIG_INPUT_BMA150)) += platform_bma023.o -obj-$(subst m,y,$(CONFIG_DRM_MEDFIELD)) += platform_tc35876x.o -# I2C GPIO Expanders -obj-$(subst m,y,$(CONFIG_GPIO_PCA953X)) += platform_max7315.o -obj-$(subst m,y,$(CONFIG_GPIO_PCA953X)) += platform_pcal9555a.o -obj-$(subst m,y,$(CONFIG_GPIO_PCA953X)) += platform_tca6416.o -# MISC Devices -obj-$(subst m,y,$(CONFIG_KEYBOARD_GPIO)) += platform_gpio_keys.o -obj-$(subst m,y,$(CONFIG_INTEL_MID_POWER_BUTTON)) += platform_mrfld_power_btn.o -obj-$(subst m,y,$(CONFIG_RTC_DRV_CMOS)) += platform_mrfld_rtc.o -obj-$(subst m,y,$(CONFIG_INTEL_MID_WATCHDOG)) += platform_mrfld_wdt.o diff --git a/arch/x86/platform/intel-mid/device_libs/platform_bcm43xx.c b/arch/x86/platform/intel-mid/device_libs/platform_bcm43xx.c deleted file mode 100644 index 564c47c53f3a..000000000000 --- a/arch/x86/platform/intel-mid/device_libs/platform_bcm43xx.c +++ /dev/null @@ -1,101 +0,0 @@ -// SPDX-License-Identifier: GPL-2.0-only -/* - * platform_bcm43xx.c: bcm43xx platform data initialization file - * - * (C) Copyright 2016 Intel Corporation - * Author: Andy Shevchenko <andriy.shevchenko@linux.intel.com> - */ - -#include <linux/gpio/machine.h> -#include <linux/platform_device.h> -#include <linux/regulator/machine.h> -#include <linux/regulator/fixed.h> -#include <linux/sfi.h> - -#include <asm/intel-mid.h> - -#define WLAN_SFI_GPIO_IRQ_NAME "WLAN-interrupt" -#define WLAN_SFI_GPIO_ENABLE_NAME "WLAN-enable" - -#define WLAN_DEV_NAME "0000:00:01.3" - -static struct regulator_consumer_supply bcm43xx_vmmc_supply = { - .dev_name = WLAN_DEV_NAME, - .supply = "vmmc", -}; - -static struct regulator_init_data bcm43xx_vmmc_data = { - .constraints = { - .valid_ops_mask = REGULATOR_CHANGE_STATUS, - }, - .num_consumer_supplies = 1, - .consumer_supplies = &bcm43xx_vmmc_supply, -}; - -static struct fixed_voltage_config bcm43xx_vmmc = { - .supply_name = "bcm43xx-vmmc-regulator", - /* - * Announce 2.0V here to be compatible with SDIO specification. The - * real voltage and signaling are still 1.8V. - */ - .microvolts = 2000000, /* 1.8V */ - .startup_delay = 250 * 1000, /* 250ms */ - .enabled_at_boot = 0, /* disabled at boot */ - .init_data = &bcm43xx_vmmc_data, -}; - -static struct platform_device bcm43xx_vmmc_regulator = { - .name = "reg-fixed-voltage", - .id = PLATFORM_DEVID_AUTO, - .dev = { - .platform_data = &bcm43xx_vmmc, - }, -}; - -static struct gpiod_lookup_table bcm43xx_vmmc_gpio_table = { - .dev_id = "reg-fixed-voltage.0", - .table = { - GPIO_LOOKUP("0000:00:0c.0", -1, NULL, GPIO_ACTIVE_LOW), - {} - }, -}; - -static int __init bcm43xx_regulator_register(void) -{ - struct gpiod_lookup_table *table = &bcm43xx_vmmc_gpio_table; - struct gpiod_lookup *lookup = table->table; - int ret; - - lookup[0].chip_hwnum = get_gpio_by_name(WLAN_SFI_GPIO_ENABLE_NAME); - gpiod_add_lookup_table(table); - - ret = platform_device_register(&bcm43xx_vmmc_regulator); - if (ret) { - pr_err("%s: vmmc regulator register failed\n", __func__); - return ret; - } - - return 0; -} - -static void __init *bcm43xx_platform_data(void *info) -{ - int ret; - - ret = bcm43xx_regulator_register(); - if (ret) - return NULL; - - pr_info("Using generic wifi platform data\n"); - - /* For now it's empty */ - return NULL; -} - -static const struct devs_id bcm43xx_clk_vmmc_dev_id __initconst = { - .name = "bcm43xx_clk_vmmc", - .type = SFI_DEV_TYPE_SD, - .get_platform_data = &bcm43xx_platform_data, -}; - -sfi_device(bcm43xx_clk_vmmc_dev_id); diff --git a/arch/x86/platform/intel-mid/device_libs/platform_bma023.c b/arch/x86/platform/intel-mid/device_libs/platform_bma023.c deleted file mode 100644 index 32912a17f68e..000000000000 --- a/arch/x86/platform/intel-mid/device_libs/platform_bma023.c +++ /dev/null @@ -1,16 +0,0 @@ -// SPDX-License-Identifier: GPL-2.0-only -/* - * platform_bma023.c: bma023 platform data initialization file - * - * (C) Copyright 2013 Intel Corporation - */ - -#include <asm/intel-mid.h> - -static const struct devs_id bma023_dev_id __initconst = { - .name = "bma023", - .type = SFI_DEV_TYPE_I2C, - .delay = 1, -}; - -sfi_device(bma023_dev_id); diff --git a/arch/x86/platform/intel-mid/device_libs/platform_bt.c b/arch/x86/platform/intel-mid/device_libs/platform_bt.c deleted file mode 100644 index 31dda18bb370..000000000000 --- a/arch/x86/platform/intel-mid/device_libs/platform_bt.c +++ /dev/null @@ -1,101 +0,0 @@ -// SPDX-License-Identifier: GPL-2.0-only -/* - * Bluetooth platform data initialization file - * - * (C) Copyright 2017 Intel Corporation - * Author: Andy Shevchenko <andriy.shevchenko@linux.intel.com> - */ - -#include <linux/gpio/machine.h> -#include <linux/pci.h> -#include <linux/platform_device.h> - -#include <asm/cpu_device_id.h> -#include <asm/intel-family.h> -#include <asm/intel-mid.h> - -struct bt_sfi_data { - struct device *dev; - const char *name; - int (*setup)(struct bt_sfi_data *ddata); -}; - -static struct gpiod_lookup_table tng_bt_sfi_gpio_table = { - .dev_id = "hci_bcm", - .table = { - GPIO_LOOKUP("0000:00:0c.0", -1, "device-wakeup", GPIO_ACTIVE_HIGH), - GPIO_LOOKUP("0000:00:0c.0", -1, "shutdown", GPIO_ACTIVE_HIGH), - GPIO_LOOKUP("0000:00:0c.0", -1, "host-wakeup", GPIO_ACTIVE_HIGH), - { }, - }, -}; - -#define TNG_BT_SFI_GPIO_DEVICE_WAKEUP "bt_wakeup" -#define TNG_BT_SFI_GPIO_SHUTDOWN "BT-reset" -#define TNG_BT_SFI_GPIO_HOST_WAKEUP "bt_uart_enable" - -static int __init tng_bt_sfi_setup(struct bt_sfi_data *ddata) -{ - struct gpiod_lookup_table *table = &tng_bt_sfi_gpio_table; - struct gpiod_lookup *lookup = table->table; - struct pci_dev *pdev; - - /* Connected to /dev/ttyS0 */ - pdev = pci_get_domain_bus_and_slot(0, 0, PCI_DEVFN(4, 1)); - if (!pdev) - return -ENODEV; - - ddata->dev = &pdev->dev; - ddata->name = table->dev_id; - - lookup[0].chip_hwnum = get_gpio_by_name(TNG_BT_SFI_GPIO_DEVICE_WAKEUP); - lookup[1].chip_hwnum = get_gpio_by_name(TNG_BT_SFI_GPIO_SHUTDOWN); - lookup[2].chip_hwnum = get_gpio_by_name(TNG_BT_SFI_GPIO_HOST_WAKEUP); - - gpiod_add_lookup_table(table); - return 0; -} - -static struct bt_sfi_data tng_bt_sfi_data __initdata = { - .setup = tng_bt_sfi_setup, -}; - -static const struct x86_cpu_id bt_sfi_cpu_ids[] = { - X86_MATCH_INTEL_FAM6_MODEL(ATOM_SILVERMONT_MID, &tng_bt_sfi_data), - {} -}; - -static int __init bt_sfi_init(void) -{ - struct platform_device_info info; - struct platform_device *pdev; - const struct x86_cpu_id *id; - struct bt_sfi_data *ddata; - int ret; - - id = x86_match_cpu(bt_sfi_cpu_ids); - if (!id) - return -ENODEV; - - ddata = (struct bt_sfi_data *)id->driver_data; - if (!ddata) - return -ENODEV; - - ret = ddata->setup(ddata); - if (ret) - return ret; - - memset(&info, 0, sizeof(info)); - info.fwnode = ddata->dev->fwnode; - info.parent = ddata->dev; - info.name = ddata->name, - info.id = PLATFORM_DEVID_NONE, - - pdev = platform_device_register_full(&info); - if (IS_ERR(pdev)) - return PTR_ERR(pdev); - - dev_info(ddata->dev, "Registered Bluetooth device: %s\n", ddata->name); - return 0; -} -device_initcall(bt_sfi_init); diff --git a/arch/x86/platform/intel-mid/device_libs/platform_emc1403.c b/arch/x86/platform/intel-mid/device_libs/platform_emc1403.c deleted file mode 100644 index a2508582a0b1..000000000000 --- a/arch/x86/platform/intel-mid/device_libs/platform_emc1403.c +++ /dev/null @@ -1,39 +0,0 @@ -// SPDX-License-Identifier: GPL-2.0-only -/* - * platform_emc1403.c: emc1403 platform data initialization file - * - * (C) Copyright 2013 Intel Corporation - * Author: Sathyanarayanan Kuppuswamy <sathyanarayanan.kuppuswamy@intel.com> - */ - -#include <linux/init.h> -#include <linux/gpio.h> -#include <linux/i2c.h> -#include <asm/intel-mid.h> - -static void __init *emc1403_platform_data(void *info) -{ - static short intr2nd_pdata; - struct i2c_board_info *i2c_info = info; - int intr = get_gpio_by_name("thermal_int"); - int intr2nd = get_gpio_by_name("thermal_alert"); - - if (intr < 0) - return NULL; - if (intr2nd < 0) - return NULL; - - i2c_info->irq = intr + INTEL_MID_IRQ_OFFSET; - intr2nd_pdata = intr2nd + INTEL_MID_IRQ_OFFSET; - - return &intr2nd_pdata; -} - -static const struct devs_id emc1403_dev_id __initconst = { - .name = "emc1403", - .type = SFI_DEV_TYPE_I2C, - .delay = 1, - .get_platform_data = &emc1403_platform_data, -}; - -sfi_device(emc1403_dev_id); diff --git a/arch/x86/platform/intel-mid/device_libs/platform_gpio_keys.c b/arch/x86/platform/intel-mid/device_libs/platform_gpio_keys.c deleted file mode 100644 index d9435d2196a4..000000000000 --- a/arch/x86/platform/intel-mid/device_libs/platform_gpio_keys.c +++ /dev/null @@ -1,81 +0,0 @@ -// SPDX-License-Identifier: GPL-2.0-only -/* - * platform_gpio_keys.c: gpio_keys platform data initialization file - * - * (C) Copyright 2013 Intel Corporation - * Author: Sathyanarayanan Kuppuswamy <sathyanarayanan.kuppuswamy@intel.com> - */ - -#include <linux/input.h> -#include <linux/init.h> -#include <linux/kernel.h> -#include <linux/gpio.h> -#include <linux/gpio_keys.h> -#include <linux/platform_device.h> -#include <asm/intel-mid.h> - -#define DEVICE_NAME "gpio-keys" - -/* - * we will search these buttons in SFI GPIO table (by name) - * and register them dynamically. Please add all possible - * buttons here, we will shrink them if no GPIO found. - */ -static struct gpio_keys_button gpio_button[] = { - {KEY_POWER, -1, 1, "power_btn", EV_KEY, 0, 3000}, - {KEY_PROG1, -1, 1, "prog_btn1", EV_KEY, 0, 20}, - {KEY_PROG2, -1, 1, "prog_btn2", EV_KEY, 0, 20}, - {SW_LID, -1, 1, "lid_switch", EV_SW, 0, 20}, - {KEY_VOLUMEUP, -1, 1, "vol_up", EV_KEY, 0, 20}, - {KEY_VOLUMEDOWN, -1, 1, "vol_down", EV_KEY, 0, 20}, - {KEY_MUTE, -1, 1, "mute_enable", EV_KEY, 0, 20}, - {KEY_VOLUMEUP, -1, 1, "volume_up", EV_KEY, 0, 20}, - {KEY_VOLUMEDOWN, -1, 1, "volume_down", EV_KEY, 0, 20}, - {KEY_CAMERA, -1, 1, "camera_full", EV_KEY, 0, 20}, - {KEY_CAMERA_FOCUS, -1, 1, "camera_half", EV_KEY, 0, 20}, - {SW_KEYPAD_SLIDE, -1, 1, "MagSw1", EV_SW, 0, 20}, - {SW_KEYPAD_SLIDE, -1, 1, "MagSw2", EV_SW, 0, 20}, -}; - -static struct gpio_keys_platform_data gpio_keys = { - .buttons = gpio_button, - .rep = 1, - .nbuttons = -1, /* will fill it after search */ -}; - -static struct platform_device pb_device = { - .name = DEVICE_NAME, - .id = -1, - .dev = { - .platform_data = &gpio_keys, - }, -}; - -/* - * Shrink the non-existent buttons, register the gpio button - * device if there is some - */ -static int __init pb_keys_init(void) -{ - struct gpio_keys_button *gb = gpio_button; - int i, good = 0; - - for (i = 0; i < ARRAY_SIZE(gpio_button); 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 < 0) - continue; - - if (i != good) - gb[good] = gb[i]; - good++; - } - - if (good) { - gpio_keys.nbuttons = good; - return platform_device_register(&pb_device); - } - return 0; -} -late_initcall(pb_keys_init); diff --git a/arch/x86/platform/intel-mid/device_libs/platform_lis331.c b/arch/x86/platform/intel-mid/device_libs/platform_lis331.c deleted file mode 100644 index a4485cd638c6..000000000000 --- a/arch/x86/platform/intel-mid/device_libs/platform_lis331.c +++ /dev/null @@ -1,37 +0,0 @@ -// SPDX-License-Identifier: GPL-2.0-only -/* - * platform_lis331.c: lis331 platform data initialization file - * - * (C) Copyright 2013 Intel Corporation - * Author: Sathyanarayanan Kuppuswamy <sathyanarayanan.kuppuswamy@intel.com> - */ - -#include <linux/i2c.h> -#include <linux/gpio.h> -#include <asm/intel-mid.h> - -static void __init *lis331dl_platform_data(void *info) -{ - static short intr2nd_pdata; - struct i2c_board_info *i2c_info = info; - int intr = get_gpio_by_name("accel_int"); - int intr2nd = get_gpio_by_name("accel_2"); - - if (intr < 0) - return NULL; - if (intr2nd < 0) - return NULL; - - i2c_info->irq = intr + INTEL_MID_IRQ_OFFSET; - intr2nd_pdata = intr2nd + INTEL_MID_IRQ_OFFSET; - - return &intr2nd_pdata; -} - -static const struct devs_id lis331dl_dev_id __initconst = { - .name = "i2c_accel", - .type = SFI_DEV_TYPE_I2C, - .get_platform_data = &lis331dl_platform_data, -}; - -sfi_device(lis331dl_dev_id); diff --git a/arch/x86/platform/intel-mid/device_libs/platform_max7315.c b/arch/x86/platform/intel-mid/device_libs/platform_max7315.c deleted file mode 100644 index e9287c3184da..000000000000 --- a/arch/x86/platform/intel-mid/device_libs/platform_max7315.c +++ /dev/null @@ -1,77 +0,0 @@ -// SPDX-License-Identifier: GPL-2.0-only -/* - * platform_max7315.c: max7315 platform data initialization file - * - * (C) Copyright 2013 Intel Corporation - * Author: Sathyanarayanan Kuppuswamy <sathyanarayanan.kuppuswamy@intel.com> - */ - -#include <linux/init.h> -#include <linux/gpio.h> -#include <linux/i2c.h> -#include <linux/platform_data/pca953x.h> -#include <asm/intel-mid.h> - -#define MAX7315_NUM 2 - -static void __init *max7315_platform_data(void *info) -{ - static struct pca953x_platform_data max7315_pdata[MAX7315_NUM]; - static int nr; - struct pca953x_platform_data *max7315 = &max7315_pdata[nr]; - struct i2c_board_info *i2c_info = info; - int gpio_base, intr; - char base_pin_name[SFI_NAME_LEN + 1]; - char intr_pin_name[SFI_NAME_LEN + 1]; - - if (nr == MAX7315_NUM) { - pr_err("too many max7315s, we only support %d\n", - MAX7315_NUM); - return NULL; - } - /* we have several max7315 on the board, we only need load several - * instances of the same pca953x driver to cover them - */ - strcpy(i2c_info->type, "max7315"); - if (nr++) { - snprintf(base_pin_name, sizeof(base_pin_name), - "max7315_%d_base", nr); - snprintf(intr_pin_name, sizeof(intr_pin_name), - "max7315_%d_int", nr); - } else { - strcpy(base_pin_name, "max7315_base"); - strcpy(intr_pin_name, "max7315_int"); - } - - gpio_base = get_gpio_by_name(base_pin_name); - intr = get_gpio_by_name(intr_pin_name); - - if (gpio_base < 0) - return NULL; - max7315->gpio_base = gpio_base; - if (intr != -1) { - i2c_info->irq = intr + INTEL_MID_IRQ_OFFSET; - max7315->irq_base = gpio_base + INTEL_MID_IRQ_OFFSET; - } else { - i2c_info->irq = -1; - max7315->irq_base = -1; - } - return max7315; -} - -static const struct devs_id max7315_dev_id __initconst = { - .name = "i2c_max7315", - .type = SFI_DEV_TYPE_I2C, - .delay = 1, - .get_platform_data = &max7315_platform_data, -}; - -static const struct devs_id max7315_2_dev_id __initconst = { - .name = "i2c_max7315_2", - .type = SFI_DEV_TYPE_I2C, - .delay = 1, - .get_platform_data = &max7315_platform_data, -}; - -sfi_device(max7315_dev_id); -sfi_device(max7315_2_dev_id); diff --git a/arch/x86/platform/intel-mid/device_libs/platform_mpu3050.c b/arch/x86/platform/intel-mid/device_libs/platform_mpu3050.c deleted file mode 100644 index 28a182713934..000000000000 --- a/arch/x86/platform/intel-mid/device_libs/platform_mpu3050.c +++ /dev/null @@ -1,32 +0,0 @@ -// SPDX-License-Identifier: GPL-2.0-only -/* - * platform_mpu3050.c: mpu3050 platform data initialization file - * - * (C) Copyright 2013 Intel Corporation - * Author: Sathyanarayanan Kuppuswamy <sathyanarayanan.kuppuswamy@intel.com> - */ - -#include <linux/gpio.h> -#include <linux/i2c.h> -#include <asm/intel-mid.h> - -static void *mpu3050_platform_data(void *info) -{ - struct i2c_board_info *i2c_info = info; - int intr = get_gpio_by_name("mpu3050_int"); - - if (intr < 0) - return NULL; - - i2c_info->irq = intr + INTEL_MID_IRQ_OFFSET; - return NULL; -} - -static const struct devs_id mpu3050_dev_id __initconst = { - .name = "mpu3050", - .type = SFI_DEV_TYPE_I2C, - .delay = 1, - .get_platform_data = &mpu3050_platform_data, -}; - -sfi_device(mpu3050_dev_id); diff --git a/arch/x86/platform/intel-mid/device_libs/platform_mrfld_pinctrl.c b/arch/x86/platform/intel-mid/device_libs/platform_mrfld_pinctrl.c deleted file mode 100644 index 605e1f94ad89..000000000000 --- a/arch/x86/platform/intel-mid/device_libs/platform_mrfld_pinctrl.c +++ /dev/null @@ -1,39 +0,0 @@ -// SPDX-License-Identifier: GPL-2.0-only -/* - * Intel Merrifield FLIS platform device initialization file - * - * Copyright (C) 2016, Intel Corporation - * - * Author: Andy Shevchenko <andriy.shevchenko@linux.intel.com> - */ - -#include <linux/init.h> -#include <linux/ioport.h> -#include <linux/platform_device.h> - -#include <asm/intel-mid.h> - -#define FLIS_BASE_ADDR 0xff0c0000 -#define FLIS_LENGTH 0x8000 - -static struct resource mrfld_pinctrl_mmio_resource = { - .start = FLIS_BASE_ADDR, - .end = FLIS_BASE_ADDR + FLIS_LENGTH - 1, - .flags = IORESOURCE_MEM, -}; - -static struct platform_device mrfld_pinctrl_device = { - .name = "pinctrl-merrifield", - .id = PLATFORM_DEVID_NONE, - .resource = &mrfld_pinctrl_mmio_resource, - .num_resources = 1, -}; - -static int __init mrfld_pinctrl_init(void) -{ - if (intel_mid_identify_cpu() == INTEL_MID_CPU_CHIP_TANGIER) - return platform_device_register(&mrfld_pinctrl_device); - - return -ENODEV; -} -arch_initcall(mrfld_pinctrl_init); diff --git a/arch/x86/platform/intel-mid/device_libs/platform_mrfld_power_btn.c b/arch/x86/platform/intel-mid/device_libs/platform_mrfld_power_btn.c deleted file mode 100644 index ec2afb41b34a..000000000000 --- a/arch/x86/platform/intel-mid/device_libs/platform_mrfld_power_btn.c +++ /dev/null @@ -1,78 +0,0 @@ -// SPDX-License-Identifier: GPL-2.0-only -/* - * Intel Merrifield power button support - * - * (C) Copyright 2017 Intel Corporation - * - * Author: Andy Shevchenko <andriy.shevchenko@linux.intel.com> - */ - -#include <linux/init.h> -#include <linux/ioport.h> -#include <linux/platform_device.h> -#include <linux/sfi.h> - -#include <asm/intel-mid.h> -#include <asm/intel_scu_ipc.h> - -static struct resource mrfld_power_btn_resources[] = { - { - .flags = IORESOURCE_IRQ, - }, -}; - -static struct platform_device mrfld_power_btn_dev = { - .name = "msic_power_btn", - .id = PLATFORM_DEVID_NONE, - .num_resources = ARRAY_SIZE(mrfld_power_btn_resources), - .resource = mrfld_power_btn_resources, -}; - -static int mrfld_power_btn_scu_status_change(struct notifier_block *nb, - unsigned long code, void *data) -{ - if (code == SCU_DOWN) { - platform_device_unregister(&mrfld_power_btn_dev); - return 0; - } - - return platform_device_register(&mrfld_power_btn_dev); -} - -static struct notifier_block mrfld_power_btn_scu_notifier = { - .notifier_call = mrfld_power_btn_scu_status_change, -}; - -static int __init register_mrfld_power_btn(void) -{ - if (intel_mid_identify_cpu() != INTEL_MID_CPU_CHIP_TANGIER) - return -ENODEV; - - /* - * We need to be sure that the SCU IPC is ready before - * PMIC power button device can be registered: - */ - intel_scu_notifier_add(&mrfld_power_btn_scu_notifier); - - return 0; -} -arch_initcall(register_mrfld_power_btn); - -static void __init *mrfld_power_btn_platform_data(void *info) -{ - struct resource *res = mrfld_power_btn_resources; - struct sfi_device_table_entry *pentry = info; - - res->start = res->end = pentry->irq; - return NULL; -} - -static const struct devs_id mrfld_power_btn_dev_id __initconst = { - .name = "bcove_power_btn", - .type = SFI_DEV_TYPE_IPC, - .delay = 1, - .msic = 1, - .get_platform_data = &mrfld_power_btn_platform_data, -}; - -sfi_device(mrfld_power_btn_dev_id); diff --git a/arch/x86/platform/intel-mid/device_libs/platform_mrfld_rtc.c b/arch/x86/platform/intel-mid/device_libs/platform_mrfld_rtc.c deleted file mode 100644 index 40e9808a9634..000000000000 --- a/arch/x86/platform/intel-mid/device_libs/platform_mrfld_rtc.c +++ /dev/null @@ -1,44 +0,0 @@ -// SPDX-License-Identifier: GPL-2.0-only -/* - * Intel Merrifield legacy RTC initialization file - * - * (C) Copyright 2017 Intel Corporation - * - * Author: Andy Shevchenko <andriy.shevchenko@linux.intel.com> - */ - -#include <linux/init.h> - -#include <asm/hw_irq.h> -#include <asm/intel-mid.h> -#include <asm/io_apic.h> -#include <asm/time.h> -#include <asm/x86_init.h> - -static int __init mrfld_legacy_rtc_alloc_irq(void) -{ - struct irq_alloc_info info; - int ret; - - if (!x86_platform.legacy.rtc) - return -ENODEV; - - ioapic_set_alloc_attr(&info, NUMA_NO_NODE, 1, 0); - ret = mp_map_gsi_to_irq(RTC_IRQ, IOAPIC_MAP_ALLOC, &info); - if (ret < 0) { - pr_info("Failed to allocate RTC interrupt. Disabling RTC\n"); - x86_platform.legacy.rtc = 0; - return ret; - } - - return 0; -} - -static int __init mrfld_legacy_rtc_init(void) -{ - if (intel_mid_identify_cpu() != INTEL_MID_CPU_CHIP_TANGIER) - return -ENODEV; - - return mrfld_legacy_rtc_alloc_irq(); -} -arch_initcall(mrfld_legacy_rtc_init); diff --git a/arch/x86/platform/intel-mid/device_libs/platform_mrfld_sd.c b/arch/x86/platform/intel-mid/device_libs/platform_mrfld_sd.c deleted file mode 100644 index fe3b7ff975f3..000000000000 --- a/arch/x86/platform/intel-mid/device_libs/platform_mrfld_sd.c +++ /dev/null @@ -1,43 +0,0 @@ -// SPDX-License-Identifier: GPL-2.0-only -/* - * SDHCI platform data initilisation file - * - * (C) Copyright 2016 Intel Corporation - * Author: Andy Shevchenko <andriy.shevchenko@linux.intel.com> - */ - -#include <linux/init.h> -#include <linux/pci.h> - -#include <linux/mmc/sdhci-pci-data.h> - -#include <asm/intel-mid.h> - -#define INTEL_MRFLD_SD 2 -#define INTEL_MRFLD_SD_CD_GPIO 77 - -static struct sdhci_pci_data mrfld_sdhci_pci_data = { - .rst_n_gpio = -EINVAL, - .cd_gpio = INTEL_MRFLD_SD_CD_GPIO, -}; - -static struct sdhci_pci_data * -mrfld_sdhci_pci_get_data(struct pci_dev *pdev, int slotno) -{ - unsigned int func = PCI_FUNC(pdev->devfn); - - if (func == INTEL_MRFLD_SD) - return &mrfld_sdhci_pci_data; - - return NULL; -} - -static int __init mrfld_sd_init(void) -{ - if (intel_mid_identify_cpu() != INTEL_MID_CPU_CHIP_TANGIER) - return -ENODEV; - - sdhci_pci_get_data = mrfld_sdhci_pci_get_data; - return 0; -} -arch_initcall(mrfld_sd_init); diff --git a/arch/x86/platform/intel-mid/device_libs/platform_mrfld_spidev.c b/arch/x86/platform/intel-mid/device_libs/platform_mrfld_spidev.c deleted file mode 100644 index b828f4fd40be..000000000000 --- a/arch/x86/platform/intel-mid/device_libs/platform_mrfld_spidev.c +++ /dev/null @@ -1,50 +0,0 @@ -// SPDX-License-Identifier: GPL-2.0-only -/* - * spidev platform data initialization file - * - * (C) Copyright 2014, 2016 Intel Corporation - * Authors: Andy Shevchenko <andriy.shevchenko@linux.intel.com> - * Dan O'Donovan <dan@emutex.com> - */ - -#include <linux/err.h> -#include <linux/init.h> -#include <linux/sfi.h> -#include <linux/spi/pxa2xx_spi.h> -#include <linux/spi/spi.h> - -#include <asm/intel-mid.h> - -#define MRFLD_SPI_DEFAULT_DMA_BURST 8 -#define MRFLD_SPI_DEFAULT_TIMEOUT 500 - -/* GPIO pin for spidev chipselect */ -#define MRFLD_SPIDEV_GPIO_CS 111 - -static struct pxa2xx_spi_chip spidev_spi_chip = { - .dma_burst_size = MRFLD_SPI_DEFAULT_DMA_BURST, - .timeout = MRFLD_SPI_DEFAULT_TIMEOUT, - .gpio_cs = MRFLD_SPIDEV_GPIO_CS, -}; - -static void __init *spidev_platform_data(void *info) -{ - struct spi_board_info *spi_info = info; - - if (intel_mid_identify_cpu() != INTEL_MID_CPU_CHIP_TANGIER) - return ERR_PTR(-ENODEV); - - spi_info->mode = SPI_MODE_0; - spi_info->controller_data = &spidev_spi_chip; - - return NULL; -} - -static const struct devs_id spidev_dev_id __initconst = { - .name = "spidev", - .type = SFI_DEV_TYPE_SPI, - .delay = 0, - .get_platform_data = &spidev_platform_data, -}; - -sfi_device(spidev_dev_id); diff --git a/arch/x86/platform/intel-mid/device_libs/platform_mrfld_wdt.c b/arch/x86/platform/intel-mid/device_libs/platform_mrfld_wdt.c deleted file mode 100644 index 227218a8f98e..000000000000 --- a/arch/x86/platform/intel-mid/device_libs/platform_mrfld_wdt.c +++ /dev/null @@ -1,82 +0,0 @@ -// SPDX-License-Identifier: GPL-2.0-only -/* - * Intel Merrifield watchdog platform device library file - * - * (C) Copyright 2014 Intel Corporation - * Author: David Cohen <david.a.cohen@linux.intel.com> - */ - -#include <linux/init.h> -#include <linux/interrupt.h> -#include <linux/platform_device.h> -#include <linux/platform_data/intel-mid_wdt.h> - -#include <asm/intel-mid.h> -#include <asm/intel_scu_ipc.h> -#include <asm/io_apic.h> -#include <asm/hw_irq.h> - -#define TANGIER_EXT_TIMER0_MSI 12 - -static struct platform_device wdt_dev = { - .name = "intel_mid_wdt", - .id = -1, -}; - -static int tangier_probe(struct platform_device *pdev) -{ - struct irq_alloc_info info; - struct intel_mid_wdt_pdata *pdata = pdev->dev.platform_data; - int gsi = TANGIER_EXT_TIMER0_MSI; - int irq; - - if (!pdata) - return -EINVAL; - - /* IOAPIC builds identity mapping between GSI and IRQ on MID */ - ioapic_set_alloc_attr(&info, cpu_to_node(0), 1, 0); - irq = mp_map_gsi_to_irq(gsi, IOAPIC_MAP_ALLOC, &info); - if (irq < 0) { - dev_warn(&pdev->dev, "cannot find interrupt %d in ioapic\n", gsi); - return irq; - } - - pdata->irq = irq; - return 0; -} - -static struct intel_mid_wdt_pdata tangier_pdata = { - .probe = tangier_probe, -}; - -static int wdt_scu_status_change(struct notifier_block *nb, - unsigned long code, void *data) -{ - if (code == SCU_DOWN) { - platform_device_unregister(&wdt_dev); - return 0; - } - - return platform_device_register(&wdt_dev); -} - -static struct notifier_block wdt_scu_notifier = { - .notifier_call = wdt_scu_status_change, -}; - -static int __init register_mid_wdt(void) -{ - if (intel_mid_identify_cpu() != INTEL_MID_CPU_CHIP_TANGIER) - return -ENODEV; - - wdt_dev.dev.platform_data = &tangier_pdata; - - /* - * We need to be sure that the SCU IPC is ready before watchdog device - * can be registered: - */ - intel_scu_notifier_add(&wdt_scu_notifier); - - return 0; -} -arch_initcall(register_mid_wdt); diff --git a/arch/x86/platform/intel-mid/device_libs/platform_msic.c b/arch/x86/platform/intel-mid/device_libs/platform_msic.c deleted file mode 100644 index b17783d0d4e7..000000000000 --- a/arch/x86/platform/intel-mid/device_libs/platform_msic.c +++ /dev/null @@ -1,83 +0,0 @@ -// SPDX-License-Identifier: GPL-2.0-only -/* - * platform_msic.c: MSIC platform data initialization file - * - * (C) Copyright 2013 Intel Corporation - * Author: Sathyanarayanan Kuppuswamy <sathyanarayanan.kuppuswamy@intel.com> - */ - -#include <linux/kernel.h> -#include <linux/interrupt.h> -#include <linux/scatterlist.h> -#include <linux/init.h> -#include <linux/sfi.h> -#include <linux/mfd/intel_msic.h> -#include <asm/intel_scu_ipc.h> -#include <asm/intel-mid.h> -#include "platform_msic.h" - -struct intel_msic_platform_data msic_pdata; - -static struct resource msic_resources[] = { - { - .start = INTEL_MSIC_IRQ_PHYS_BASE, - .end = INTEL_MSIC_IRQ_PHYS_BASE + 64 - 1, - .flags = IORESOURCE_MEM, - }, -}; - -static struct platform_device msic_device = { - .name = "intel_msic", - .id = -1, - .dev = { - .platform_data = &msic_pdata, - }, - .num_resources = ARRAY_SIZE(msic_resources), - .resource = msic_resources, -}; - -static int msic_scu_status_change(struct notifier_block *nb, - unsigned long code, void *data) -{ - if (code == SCU_DOWN) { - platform_device_unregister(&msic_device); - return 0; - } - - return platform_device_register(&msic_device); -} - -static int __init msic_init(void) -{ - static struct notifier_block msic_scu_notifier = { - .notifier_call = msic_scu_status_change, - }; - - /* - * We need to be sure that the SCU IPC is ready before MSIC device - * can be registered. - */ - if (intel_mid_has_msic()) - intel_scu_notifier_add(&msic_scu_notifier); - - return 0; -} -arch_initcall(msic_init); - -/* - * msic_generic_platform_data - sets generic platform data for the block - * @info: pointer to the SFI device table entry for this block - * @block: MSIC block - * - * Function sets IRQ number from the SFI table entry for given device to - * the MSIC platform data. - */ -void *msic_generic_platform_data(void *info, enum intel_msic_block block) -{ - struct sfi_device_table_entry *entry = info; - - BUG_ON(block < 0 || block >= INTEL_MSIC_BLOCK_LAST); - msic_pdata.irq[block] = entry->irq; - - return NULL; -} diff --git a/arch/x86/platform/intel-mid/device_libs/platform_msic.h b/arch/x86/platform/intel-mid/device_libs/platform_msic.h deleted file mode 100644 index 91deb2e65b0e..000000000000 --- a/arch/x86/platform/intel-mid/device_libs/platform_msic.h +++ /dev/null @@ -1,15 +0,0 @@ -/* SPDX-License-Identifier: GPL-2.0-only */ -/* - * platform_msic.h: MSIC platform data header file - * - * (C) Copyright 2013 Intel Corporation - * Author: Sathyanarayanan Kuppuswamy <sathyanarayanan.kuppuswamy@intel.com> - */ -#ifndef _PLATFORM_MSIC_H_ -#define _PLATFORM_MSIC_H_ - -extern struct intel_msic_platform_data msic_pdata; - -void *msic_generic_platform_data(void *info, enum intel_msic_block block); - -#endif diff --git a/arch/x86/platform/intel-mid/device_libs/platform_msic_audio.c b/arch/x86/platform/intel-mid/device_libs/platform_msic_audio.c deleted file mode 100644 index e765da78ad8c..000000000000 --- a/arch/x86/platform/intel-mid/device_libs/platform_msic_audio.c +++ /dev/null @@ -1,42 +0,0 @@ -// SPDX-License-Identifier: GPL-2.0-only -/* - * platform_msic_audio.c: MSIC audio platform data initialization file - * - * (C) Copyright 2013 Intel Corporation - * Author: Sathyanarayanan Kuppuswamy <sathyanarayanan.kuppuswamy@intel.com> - */ - -#include <linux/kernel.h> -#include <linux/interrupt.h> -#include <linux/scatterlist.h> -#include <linux/init.h> -#include <linux/sfi.h> -#include <linux/platform_device.h> -#include <linux/mfd/intel_msic.h> -#include <asm/intel-mid.h> - -#include "platform_msic.h" - -static void *msic_audio_platform_data(void *info) -{ - struct platform_device *pdev; - - pdev = platform_device_register_simple("sst-platform", -1, NULL, 0); - - if (IS_ERR(pdev)) { - pr_err("failed to create audio platform device\n"); - return NULL; - } - - return msic_generic_platform_data(info, INTEL_MSIC_BLOCK_AUDIO); -} - -static const struct devs_id msic_audio_dev_id __initconst = { - .name = "msic_audio", - .type = SFI_DEV_TYPE_IPC, - .delay = 1, - .msic = 1, - .get_platform_data = &msic_audio_platform_data, -}; - -sfi_device(msic_audio_dev_id); diff --git a/arch/x86/platform/intel-mid/device_libs/platform_msic_battery.c b/arch/x86/platform/intel-mid/device_libs/platform_msic_battery.c deleted file mode 100644 index f461f84903f8..000000000000 --- a/arch/x86/platform/intel-mid/device_libs/platform_msic_battery.c +++ /dev/null @@ -1,32 +0,0 @@ -// SPDX-License-Identifier: GPL-2.0-only -/* - * platform_msic_battery.c: MSIC battery platform data initialization file - * - * (C) Copyright 2013 Intel Corporation - * Author: Sathyanarayanan Kuppuswamy <sathyanarayanan.kuppuswamy@intel.com> - */ - -#include <linux/kernel.h> -#include <linux/interrupt.h> -#include <linux/scatterlist.h> -#include <linux/init.h> -#include <linux/sfi.h> -#include <linux/mfd/intel_msic.h> -#include <asm/intel-mid.h> - -#include "platform_msic.h" - -static void __init *msic_battery_platform_data(void *info) -{ - return msic_generic_platform_data(info, INTEL_MSIC_BLOCK_BATTERY); -} - -static const struct devs_id msic_battery_dev_id __initconst = { - .name = "msic_battery", - .type = SFI_DEV_TYPE_IPC, - .delay = 1, - .msic = 1, - .get_platform_data = &msic_battery_platform_data, -}; - -sfi_device(msic_battery_dev_id); diff --git a/arch/x86/platform/intel-mid/device_libs/platform_msic_gpio.c b/arch/x86/platform/intel-mid/device_libs/platform_msic_gpio.c deleted file mode 100644 index 71a7d6db3878..000000000000 --- a/arch/x86/platform/intel-mid/device_libs/platform_msic_gpio.c +++ /dev/null @@ -1,43 +0,0 @@ -// SPDX-License-Identifier: GPL-2.0-only -/* - * platform_msic_gpio.c: MSIC GPIO platform data initialization file - * - * (C) Copyright 2013 Intel Corporation - * Author: Sathyanarayanan Kuppuswamy <sathyanarayanan.kuppuswamy@intel.com> - */ - -#include <linux/kernel.h> -#include <linux/interrupt.h> -#include <linux/scatterlist.h> -#include <linux/sfi.h> -#include <linux/init.h> -#include <linux/gpio.h> -#include <linux/mfd/intel_msic.h> -#include <asm/intel-mid.h> - -#include "platform_msic.h" - -static void __init *msic_gpio_platform_data(void *info) -{ - static struct intel_msic_gpio_pdata msic_gpio_pdata; - - int gpio = get_gpio_by_name("msic_gpio_base"); - - if (gpio < 0) - return NULL; - - msic_gpio_pdata.gpio_base = gpio; - msic_pdata.gpio = &msic_gpio_pdata; - - return msic_generic_platform_data(info, INTEL_MSIC_BLOCK_GPIO); -} - -static const struct devs_id msic_gpio_dev_id __initconst = { - .name = "msic_gpio", - .type = SFI_DEV_TYPE_IPC, - .delay = 1, - .msic = 1, - .get_platform_data = &msic_gpio_platform_data, -}; - -sfi_device(msic_gpio_dev_id); diff --git a/arch/x86/platform/intel-mid/device_libs/platform_msic_ocd.c b/arch/x86/platform/intel-mid/device_libs/platform_msic_ocd.c deleted file mode 100644 index 558c0d974430..000000000000 --- a/arch/x86/platform/intel-mid/device_libs/platform_msic_ocd.c +++ /dev/null @@ -1,44 +0,0 @@ -// SPDX-License-Identifier: GPL-2.0-only -/* - * platform_msic_ocd.c: MSIC OCD platform data initialization file - * - * (C) Copyright 2013 Intel Corporation - * Author: Sathyanarayanan Kuppuswamy <sathyanarayanan.kuppuswamy@intel.com> - */ - -#include <linux/kernel.h> -#include <linux/interrupt.h> -#include <linux/scatterlist.h> -#include <linux/sfi.h> -#include <linux/init.h> -#include <linux/gpio.h> -#include <linux/mfd/intel_msic.h> -#include <asm/intel-mid.h> - -#include "platform_msic.h" - -static void __init *msic_ocd_platform_data(void *info) -{ - static struct intel_msic_ocd_pdata msic_ocd_pdata; - int gpio; - - gpio = get_gpio_by_name("ocd_gpio"); - - if (gpio < 0) - return NULL; - - msic_ocd_pdata.gpio = gpio; - msic_pdata.ocd = &msic_ocd_pdata; - - return msic_generic_platform_data(info, INTEL_MSIC_BLOCK_OCD); -} - -static const struct devs_id msic_ocd_dev_id __initconst = { - .name = "msic_ocd", - .type = SFI_DEV_TYPE_IPC, - .delay = 1, - .msic = 1, - .get_platform_data = &msic_ocd_platform_data, -}; - -sfi_device(msic_ocd_dev_id); diff --git a/arch/x86/platform/intel-mid/device_libs/platform_msic_power_btn.c b/arch/x86/platform/intel-mid/device_libs/platform_msic_power_btn.c deleted file mode 100644 index 3d3de2d59726..000000000000 --- a/arch/x86/platform/intel-mid/device_libs/platform_msic_power_btn.c +++ /dev/null @@ -1,31 +0,0 @@ -// SPDX-License-Identifier: GPL-2.0-only -/* - * platform_msic_power_btn.c: MSIC power btn platform data initialization file - * - * (C) Copyright 2013 Intel Corporation - * Author: Sathyanarayanan Kuppuswamy <sathyanarayanan.kuppuswamy@intel.com> - */ -#include <linux/kernel.h> -#include <linux/interrupt.h> -#include <linux/scatterlist.h> -#include <linux/sfi.h> -#include <linux/init.h> -#include <linux/mfd/intel_msic.h> -#include <asm/intel-mid.h> - -#include "platform_msic.h" - -static void __init *msic_power_btn_platform_data(void *info) -{ - return msic_generic_platform_data(info, INTEL_MSIC_BLOCK_POWER_BTN); -} - -static const struct devs_id msic_power_btn_dev_id __initconst = { - .name = "msic_power_btn", - .type = SFI_DEV_TYPE_IPC, - .delay = 1, - .msic = 1, - .get_platform_data = &msic_power_btn_platform_data, -}; - -sfi_device(msic_power_btn_dev_id); diff --git a/arch/x86/platform/intel-mid/device_libs/platform_msic_thermal.c b/arch/x86/platform/intel-mid/device_libs/platform_msic_thermal.c deleted file mode 100644 index 4858da1d78c6..000000000000 --- a/arch/x86/platform/intel-mid/device_libs/platform_msic_thermal.c +++ /dev/null @@ -1,32 +0,0 @@ -// SPDX-License-Identifier: GPL-2.0-only -/* - * platform_msic_thermal.c: msic_thermal platform data initialization file - * - * (C) Copyright 2013 Intel Corporation - * Author: Sathyanarayanan Kuppuswamy <sathyanarayanan.kuppuswamy@intel.com> - */ - -#include <linux/input.h> -#include <linux/init.h> -#include <linux/kernel.h> -#include <linux/gpio.h> -#include <linux/platform_device.h> -#include <linux/mfd/intel_msic.h> -#include <asm/intel-mid.h> - -#include "platform_msic.h" - -static void __init *msic_thermal_platform_data(void *info) -{ - return msic_generic_platform_data(info, INTEL_MSIC_BLOCK_THERMAL); -} - -static const struct devs_id msic_thermal_dev_id __initconst = { - .name = "msic_thermal", - .type = SFI_DEV_TYPE_IPC, - .delay = 1, - .msic = 1, - .get_platform_data = &msic_thermal_platform_data, -}; - -sfi_device(msic_thermal_dev_id); diff --git a/arch/x86/platform/intel-mid/device_libs/platform_pcal9555a.c b/arch/x86/platform/intel-mid/device_libs/platform_pcal9555a.c deleted file mode 100644 index 5609d8da3978..000000000000 --- a/arch/x86/platform/intel-mid/device_libs/platform_pcal9555a.c +++ /dev/null @@ -1,95 +0,0 @@ -// SPDX-License-Identifier: GPL-2.0-only -/* - * PCAL9555a platform data initialization file - * - * Copyright (C) 2016, Intel Corporation - * - * Authors: Andy Shevchenko <andriy.shevchenko@linux.intel.com> - * Dan O'Donovan <dan@emutex.com> - */ - -#include <linux/gpio.h> -#include <linux/init.h> -#include <linux/i2c.h> -#include <linux/platform_data/pca953x.h> -#include <linux/sfi.h> - -#include <asm/intel-mid.h> - -#define PCAL9555A_NUM 4 - -static struct pca953x_platform_data pcal9555a_pdata[PCAL9555A_NUM]; -static int nr; - -static void __init *pcal9555a_platform_data(void *info) -{ - struct i2c_board_info *i2c_info = info; - char *type = i2c_info->type; - struct pca953x_platform_data *pcal9555a; - char base_pin_name[SFI_NAME_LEN + 1]; - char intr_pin_name[SFI_NAME_LEN + 1]; - int gpio_base, intr; - - snprintf(base_pin_name, sizeof(base_pin_name), "%s_base", type); - snprintf(intr_pin_name, sizeof(intr_pin_name), "%s_int", type); - - gpio_base = get_gpio_by_name(base_pin_name); - intr = get_gpio_by_name(intr_pin_name); - - /* Check if the SFI record valid */ - if (gpio_base == -1) - return NULL; - - if (nr >= PCAL9555A_NUM) { - pr_err("%s: Too many instances, only %d supported\n", __func__, - PCAL9555A_NUM); - return NULL; - } - - pcal9555a = &pcal9555a_pdata[nr++]; - pcal9555a->gpio_base = gpio_base; - - if (intr >= 0) { - i2c_info->irq = intr + INTEL_MID_IRQ_OFFSET; - pcal9555a->irq_base = gpio_base + INTEL_MID_IRQ_OFFSET; - } else { - i2c_info->irq = -1; - pcal9555a->irq_base = -1; - } - - strcpy(type, "pcal9555a"); - return pcal9555a; -} - -static const struct devs_id pcal9555a_1_dev_id __initconst = { - .name = "pcal9555a-1", - .type = SFI_DEV_TYPE_I2C, - .delay = 1, - .get_platform_data = &pcal9555a_platform_data, -}; - -static const struct devs_id pcal9555a_2_dev_id __initconst = { - .name = "pcal9555a-2", - .type = SFI_DEV_TYPE_I2C, - .delay = 1, - .get_platform_data = &pcal9555a_platform_data, -}; - -static const struct devs_id pcal9555a_3_dev_id __initconst = { - .name = "pcal9555a-3", - .type = SFI_DEV_TYPE_I2C, - .delay = 1, - .get_platform_data = &pcal9555a_platform_data, -}; - -static const struct devs_id pcal9555a_4_dev_id __initconst = { - .name = "pcal9555a-4", - .type = SFI_DEV_TYPE_I2C, - .delay = 1, - .get_platform_data = &pcal9555a_platform_data, -}; - -sfi_device(pcal9555a_1_dev_id); -sfi_device(pcal9555a_2_dev_id); -sfi_device(pcal9555a_3_dev_id); -sfi_device(pcal9555a_4_dev_id); diff --git a/arch/x86/platform/intel-mid/device_libs/platform_tc35876x.c b/arch/x86/platform/intel-mid/device_libs/platform_tc35876x.c deleted file mode 100644 index 139738bbdd36..000000000000 --- a/arch/x86/platform/intel-mid/device_libs/platform_tc35876x.c +++ /dev/null @@ -1,42 +0,0 @@ -// SPDX-License-Identifier: GPL-2.0-only -/* - * platform_tc35876x.c: tc35876x platform data initialization file - * - * (C) Copyright 2013 Intel Corporation - * Author: Sathyanarayanan Kuppuswamy <sathyanarayanan.kuppuswamy@intel.com> - */ - -#include <linux/gpio/machine.h> -#include <asm/intel-mid.h> - -static struct gpiod_lookup_table tc35876x_gpio_table = { - .dev_id = "i2c_disp_brig", - .table = { - GPIO_LOOKUP("0000:00:0c.0", -1, "bridge-reset", GPIO_ACTIVE_HIGH), - GPIO_LOOKUP("0000:00:0c.0", -1, "bl-en", GPIO_ACTIVE_HIGH), - GPIO_LOOKUP("0000:00:0c.0", -1, "vadd", GPIO_ACTIVE_HIGH), - { }, - }, -}; - -/*tc35876x DSI_LVDS bridge chip and panel platform data*/ -static void *tc35876x_platform_data(void *data) -{ - struct gpiod_lookup_table *table = &tc35876x_gpio_table; - struct gpiod_lookup *lookup = table->table; - - lookup[0].chip_hwnum = get_gpio_by_name("LCMB_RXEN"); - lookup[1].chip_hwnum = get_gpio_by_name("6S6P_BL_EN"); - lookup[2].chip_hwnum = get_gpio_by_name("EN_VREG_LCD_V3P3"); - gpiod_add_lookup_table(table); - - return NULL; -} - -static const struct devs_id tc35876x_dev_id __initconst = { - .name = "i2c_disp_brig", - .type = SFI_DEV_TYPE_I2C, - .get_platform_data = &tc35876x_platform_data, -}; - -sfi_device(tc35876x_dev_id); diff --git a/arch/x86/platform/intel-mid/device_libs/platform_tca6416.c b/arch/x86/platform/intel-mid/device_libs/platform_tca6416.c deleted file mode 100644 index e689d8f61059..000000000000 --- a/arch/x86/platform/intel-mid/device_libs/platform_tca6416.c +++ /dev/null @@ -1,53 +0,0 @@ -// SPDX-License-Identifier: GPL-2.0-only -/* - * platform_tca6416.c: tca6416 platform data initialization file - * - * (C) Copyright 2013 Intel Corporation - * Author: Sathyanarayanan Kuppuswamy <sathyanarayanan.kuppuswamy@intel.com> - */ - -#include <linux/platform_data/pca953x.h> -#include <linux/i2c.h> -#include <linux/gpio.h> -#include <asm/intel-mid.h> - -#define TCA6416_NAME "tca6416" -#define TCA6416_BASE "tca6416_base" -#define TCA6416_INTR "tca6416_int" - -static void *tca6416_platform_data(void *info) -{ - static struct pca953x_platform_data tca6416; - struct i2c_board_info *i2c_info = info; - int gpio_base, intr; - char base_pin_name[SFI_NAME_LEN + 1]; - char intr_pin_name[SFI_NAME_LEN + 1]; - - strcpy(i2c_info->type, TCA6416_NAME); - strcpy(base_pin_name, TCA6416_BASE); - strcpy(intr_pin_name, TCA6416_INTR); - - gpio_base = get_gpio_by_name(base_pin_name); - intr = get_gpio_by_name(intr_pin_name); - - if (gpio_base < 0) - return NULL; - tca6416.gpio_base = gpio_base; - if (intr >= 0) { - i2c_info->irq = intr + INTEL_MID_IRQ_OFFSET; - tca6416.irq_base = gpio_base + INTEL_MID_IRQ_OFFSET; - } else { - i2c_info->irq = -1; - tca6416.irq_base = -1; - } - return &tca6416; -} - -static const struct devs_id tca6416_dev_id __initconst = { - .name = "tca6416", - .type = SFI_DEV_TYPE_I2C, - .delay = 1, - .get_platform_data = &tca6416_platform_data, -}; - -sfi_device(tca6416_dev_id); diff --git a/arch/x86/platform/intel-mid/intel-mid.c b/arch/x86/platform/intel-mid/intel-mid.c index 780728161f7d..f4592dc7a1c1 100644 --- a/arch/x86/platform/intel-mid/intel-mid.c +++ b/arch/x86/platform/intel-mid/intel-mid.c @@ -1,8 +1,8 @@ // SPDX-License-Identifier: GPL-2.0-only /* - * intel-mid.c: Intel MID platform setup code + * Intel MID platform setup code * - * (C) Copyright 2008, 2012 Intel Corporation + * (C) Copyright 2008, 2012, 2021 Intel Corporation * Author: Jacob Pan (jacob.jun.pan@intel.com) * Author: Sathyanarayanan Kuppuswamy <sathyanarayanan.kuppuswamy@intel.com> */ @@ -14,7 +14,6 @@ #include <linux/interrupt.h> #include <linux/regulator/machine.h> #include <linux/scatterlist.h> -#include <linux/sfi.h> #include <linux/irq.h> #include <linux/export.h> #include <linux/notifier.h> @@ -25,38 +24,13 @@ #include <asm/apic.h> #include <asm/io_apic.h> #include <asm/intel-mid.h> -#include <asm/intel_mid_vrtc.h> #include <asm/io.h> #include <asm/i8259.h> #include <asm/intel_scu_ipc.h> -#include <asm/apb_timer.h> #include <asm/reboot.h> -/* - * the clockevent devices on Moorestown/Medfield can be APBT or LAPIC clock, - * cmdline option x86_intel_mid_timer can be used to override the configuration - * to prefer one or the other. - * at runtime, there are basically three timer configurations: - * 1. per cpu apbt clock only - * 2. per cpu always-on lapic clocks only, this is Penwell/Medfield only - * 3. per cpu lapic clock (C3STOP) and one apbt clock, with broadcast. - * - * by default (without cmdline option), platform code first detects cpu type - * to see if we are on lincroft or penwell, then set up both lapic or apbt - * clocks accordingly. - * i.e. by default, medfield uses configuration #2, moorestown uses #1. - * config #3 is supported but not recommended on medfield. - * - * rating and feature summary: - * lapic (with C3STOP) --------- 100 - * apbt (always-on) ------------ 110 - * lapic (always-on,ARAT) ------ 150 - */ - -enum intel_mid_timer_options intel_mid_timer_options; - -enum intel_mid_cpu_type __intel_mid_cpu_chip; -EXPORT_SYMBOL_GPL(__intel_mid_cpu_chip); +#define IPCMSG_COLD_OFF 0x80 /* Only for Tangier */ +#define IPCMSG_COLD_RESET 0xF1 static void intel_mid_power_off(void) { @@ -64,69 +38,32 @@ static void intel_mid_power_off(void) intel_mid_pwr_power_off(); /* Only for Tangier, the rest will ignore this command */ - intel_scu_ipc_simple_command(IPCMSG_COLD_OFF, 1); + intel_scu_ipc_dev_simple_command(NULL, IPCMSG_COLD_OFF, 1); }; static void intel_mid_reboot(void) { - intel_scu_ipc_simple_command(IPCMSG_COLD_RESET, 0); -} - -static void __init intel_mid_setup_bp_timer(void) -{ - apbt_time_init(); - setup_boot_APIC_clock(); + intel_scu_ipc_dev_simple_command(NULL, IPCMSG_COLD_RESET, 0); } static void __init intel_mid_time_init(void) { - sfi_table_parse(SFI_SIG_MTMR, NULL, NULL, sfi_parse_mtmr); - - switch (intel_mid_timer_options) { - case INTEL_MID_TIMER_APBT_ONLY: - break; - case INTEL_MID_TIMER_LAPIC_APBT: - /* Use apbt and local apic */ - x86_init.timers.setup_percpu_clockev = intel_mid_setup_bp_timer; - x86_cpuinit.setup_percpu_clockev = setup_secondary_APIC_clock; - return; - default: - if (!boot_cpu_has(X86_FEATURE_ARAT)) - break; - /* Lapic only, no apbt */ - x86_init.timers.setup_percpu_clockev = setup_boot_APIC_clock; - x86_cpuinit.setup_percpu_clockev = setup_secondary_APIC_clock; - return; - } - - x86_init.timers.setup_percpu_clockev = apbt_time_init; + /* Lapic only, no apbt */ + x86_init.timers.setup_percpu_clockev = setup_boot_APIC_clock; + x86_cpuinit.setup_percpu_clockev = setup_secondary_APIC_clock; } static void intel_mid_arch_setup(void) { - if (boot_cpu_data.x86 != 6) { - pr_err("Unknown Intel MID CPU (%d:%d), default to Penwell\n", - boot_cpu_data.x86, boot_cpu_data.x86_model); - __intel_mid_cpu_chip = INTEL_MID_CPU_CHIP_PENWELL; - goto out; - } - switch (boot_cpu_data.x86_model) { - case 0x35: - __intel_mid_cpu_chip = INTEL_MID_CPU_CHIP_CLOVERVIEW; - break; case 0x3C: case 0x4A: - __intel_mid_cpu_chip = INTEL_MID_CPU_CHIP_TANGIER; x86_platform.legacy.rtc = 1; break; - case 0x27: default: - __intel_mid_cpu_chip = INTEL_MID_CPU_CHIP_PENWELL; break; } -out: /* * Intel MID platforms are using explicitly defined regulators. * @@ -159,14 +96,11 @@ void __init x86_intel_mid_early_setup(void) x86_init.timers.timer_init = intel_mid_time_init; x86_init.timers.setup_percpu_clockev = x86_init_noop; - x86_init.timers.wallclock_init = intel_mid_rtc_init; x86_init.irqs.pre_vector_init = x86_init_noop; x86_init.oem.arch_setup = intel_mid_arch_setup; - x86_cpuinit.setup_percpu_clockev = apbt_setup_secondary_clock; - x86_platform.get_nmi_reason = intel_mid_get_nmi_reason; x86_init.pci.arch_init = intel_mid_pci_init; @@ -188,25 +122,3 @@ void __init x86_intel_mid_early_setup(void) x86_init.mpparse.get_smp_config = x86_init_uint_noop; set_bit(MP_BUS_ISA, mp_bus_not_pci); } - -/* - * if user does not want to use per CPU apb timer, just give it a lower rating - * than local apic timer and skip the late per cpu timer init. - */ -static inline int __init setup_x86_intel_mid_timer(char *arg) -{ - if (!arg) - return -EINVAL; - - if (strcmp("apbt_only", arg) == 0) - intel_mid_timer_options = INTEL_MID_TIMER_APBT_ONLY; - else if (strcmp("lapic_and_apbt", arg) == 0) - intel_mid_timer_options = INTEL_MID_TIMER_LAPIC_APBT; - else { - pr_warn("X86 INTEL_MID timer option %s not recognised use x86_intel_mid_timer=apbt_only or lapic_and_apbt\n", - arg); - return -EINVAL; - } - return 0; -} -__setup("x86_intel_mid_timer=", setup_x86_intel_mid_timer); diff --git a/arch/x86/platform/intel-mid/intel_mid_vrtc.c b/arch/x86/platform/intel-mid/intel_mid_vrtc.c deleted file mode 100644 index 2226da4f437a..000000000000 --- a/arch/x86/platform/intel-mid/intel_mid_vrtc.c +++ /dev/null @@ -1,173 +0,0 @@ -// SPDX-License-Identifier: GPL-2.0-only -/* - * intel_mid_vrtc.c: Driver for virtual RTC device on Intel MID platform - * - * (C) Copyright 2009 Intel Corporation - * - * Note: - * VRTC is emulated by system controller firmware, the real HW - * RTC is located in the PMIC device. SCU FW shadows PMIC RTC - * in a memory mapped IO space that is visible to the host IA - * processor. - * - * This driver is based on RTC CMOS driver. - */ - -#include <linux/kernel.h> -#include <linux/export.h> -#include <linux/init.h> -#include <linux/sfi.h> -#include <linux/platform_device.h> -#include <linux/mc146818rtc.h> - -#include <asm/intel-mid.h> -#include <asm/intel_mid_vrtc.h> -#include <asm/time.h> -#include <asm/fixmap.h> - -static unsigned char __iomem *vrtc_virt_base; - -unsigned char vrtc_cmos_read(unsigned char reg) -{ - unsigned char retval; - - /* vRTC's registers range from 0x0 to 0xD */ - if (reg > 0xd || !vrtc_virt_base) - return 0xff; - - lock_cmos_prefix(reg); - retval = __raw_readb(vrtc_virt_base + (reg << 2)); - lock_cmos_suffix(reg); - return retval; -} -EXPORT_SYMBOL_GPL(vrtc_cmos_read); - -void vrtc_cmos_write(unsigned char val, unsigned char reg) -{ - if (reg > 0xd || !vrtc_virt_base) - return; - - lock_cmos_prefix(reg); - __raw_writeb(val, vrtc_virt_base + (reg << 2)); - lock_cmos_suffix(reg); -} -EXPORT_SYMBOL_GPL(vrtc_cmos_write); - -void vrtc_get_time(struct timespec64 *now) -{ - u8 sec, min, hour, mday, mon; - unsigned long flags; - u32 year; - - spin_lock_irqsave(&rtc_lock, flags); - - while ((vrtc_cmos_read(RTC_FREQ_SELECT) & RTC_UIP)) - cpu_relax(); - - sec = vrtc_cmos_read(RTC_SECONDS); - min = vrtc_cmos_read(RTC_MINUTES); - hour = vrtc_cmos_read(RTC_HOURS); - mday = vrtc_cmos_read(RTC_DAY_OF_MONTH); - mon = vrtc_cmos_read(RTC_MONTH); - year = vrtc_cmos_read(RTC_YEAR); - - spin_unlock_irqrestore(&rtc_lock, flags); - - /* vRTC YEAR reg contains the offset to 1972 */ - year += 1972; - - pr_info("vRTC: sec: %d min: %d hour: %d day: %d " - "mon: %d year: %d\n", sec, min, hour, mday, mon, year); - - now->tv_sec = mktime64(year, mon, mday, hour, min, sec); - now->tv_nsec = 0; -} - -int vrtc_set_mmss(const struct timespec64 *now) -{ - unsigned long flags; - struct rtc_time tm; - int year; - int retval = 0; - - rtc_time64_to_tm(now->tv_sec, &tm); - if (!rtc_valid_tm(&tm) && tm.tm_year >= 72) { - /* - * tm.year is the number of years since 1900, and the - * vrtc need the years since 1972. - */ - year = tm.tm_year - 72; - spin_lock_irqsave(&rtc_lock, flags); - vrtc_cmos_write(year, RTC_YEAR); - vrtc_cmos_write(tm.tm_mon, RTC_MONTH); - vrtc_cmos_write(tm.tm_mday, RTC_DAY_OF_MONTH); - vrtc_cmos_write(tm.tm_hour, RTC_HOURS); - vrtc_cmos_write(tm.tm_min, RTC_MINUTES); - vrtc_cmos_write(tm.tm_sec, RTC_SECONDS); - spin_unlock_irqrestore(&rtc_lock, flags); - } else { - pr_err("%s: Invalid vRTC value: write of %llx to vRTC failed\n", - __func__, (s64)now->tv_sec); - retval = -EINVAL; - } - return retval; -} - -void __init intel_mid_rtc_init(void) -{ - unsigned long vrtc_paddr; - - sfi_table_parse(SFI_SIG_MRTC, NULL, NULL, sfi_parse_mrtc); - - vrtc_paddr = sfi_mrtc_array[0].phys_addr; - if (!sfi_mrtc_num || !vrtc_paddr) - return; - - vrtc_virt_base = (void __iomem *)set_fixmap_offset_nocache(FIX_LNW_VRTC, - vrtc_paddr); - x86_platform.get_wallclock = vrtc_get_time; - x86_platform.set_wallclock = vrtc_set_mmss; -} - -/* - * The Moorestown platform has a memory mapped virtual RTC device that emulates - * the programming interface of the RTC. - */ - -static struct resource vrtc_resources[] = { - [0] = { - .flags = IORESOURCE_MEM, - }, - [1] = { - .flags = IORESOURCE_IRQ, - } -}; - -static struct platform_device vrtc_device = { - .name = "rtc_mrst", - .id = -1, - .resource = vrtc_resources, - .num_resources = ARRAY_SIZE(vrtc_resources), -}; - -/* Register the RTC device if appropriate */ -static int __init intel_mid_device_create(void) -{ - /* No Moorestown, no device */ - if (!intel_mid_identify_cpu()) - return -ENODEV; - /* No timer, no device */ - if (!sfi_mrtc_num) - return -ENODEV; - - /* iomem resource */ - vrtc_resources[0].start = sfi_mrtc_array[0].phys_addr; - vrtc_resources[0].end = sfi_mrtc_array[0].phys_addr + - MRST_VRTC_MAP_SZ; - /* irq resource */ - vrtc_resources[1].start = sfi_mrtc_array[0].irq; - vrtc_resources[1].end = sfi_mrtc_array[0].irq; - - return platform_device_register(&vrtc_device); -} -device_initcall(intel_mid_device_create); diff --git a/arch/x86/platform/intel-mid/sfi.c b/arch/x86/platform/intel-mid/sfi.c deleted file mode 100644 index 30bd5714a3d4..000000000000 --- a/arch/x86/platform/intel-mid/sfi.c +++ /dev/null @@ -1,543 +0,0 @@ -// SPDX-License-Identifier: GPL-2.0-only -/* - * intel_mid_sfi.c: Intel MID SFI initialization code - * - * (C) Copyright 2013 Intel Corporation - * Author: Sathyanarayanan Kuppuswamy <sathyanarayanan.kuppuswamy@intel.com> - */ - -#include <linux/init.h> -#include <linux/kernel.h> -#include <linux/interrupt.h> -#include <linux/scatterlist.h> -#include <linux/sfi.h> -#include <linux/spi/spi.h> -#include <linux/i2c.h> -#include <linux/skbuff.h> -#include <linux/gpio.h> -#include <linux/gpio_keys.h> -#include <linux/input.h> -#include <linux/platform_device.h> -#include <linux/irq.h> -#include <linux/export.h> -#include <linux/notifier.h> -#include <linux/mmc/core.h> -#include <linux/mmc/card.h> -#include <linux/blkdev.h> - -#include <asm/setup.h> -#include <asm/mpspec_def.h> -#include <asm/hw_irq.h> -#include <asm/apic.h> -#include <asm/io_apic.h> -#include <asm/intel-mid.h> -#include <asm/intel_mid_vrtc.h> -#include <asm/io.h> -#include <asm/i8259.h> -#include <asm/intel_scu_ipc.h> -#include <asm/apb_timer.h> -#include <asm/reboot.h> - -#define SFI_SIG_OEM0 "OEM0" -#define MAX_IPCDEVS 24 -#define MAX_SCU_SPI 24 -#define MAX_SCU_I2C 24 - -static struct platform_device *ipc_devs[MAX_IPCDEVS]; -static struct spi_board_info *spi_devs[MAX_SCU_SPI]; -static struct i2c_board_info *i2c_devs[MAX_SCU_I2C]; -static struct sfi_gpio_table_entry *gpio_table; -static struct sfi_timer_table_entry sfi_mtimer_array[SFI_MTMR_MAX_NUM]; -static int ipc_next_dev; -static int spi_next_dev; -static int i2c_next_dev; -static int i2c_bus[MAX_SCU_I2C]; -static int gpio_num_entry; -static u32 sfi_mtimer_usage[SFI_MTMR_MAX_NUM]; -int sfi_mrtc_num; -int sfi_mtimer_num; - -struct sfi_rtc_table_entry sfi_mrtc_array[SFI_MRTC_MAX]; -EXPORT_SYMBOL_GPL(sfi_mrtc_array); - -struct blocking_notifier_head intel_scu_notifier = - BLOCKING_NOTIFIER_INIT(intel_scu_notifier); -EXPORT_SYMBOL_GPL(intel_scu_notifier); - -#define intel_mid_sfi_get_pdata(dev, priv) \ - ((dev)->get_platform_data ? (dev)->get_platform_data(priv) : NULL) - -/* parse all the mtimer info to a static mtimer array */ -int __init sfi_parse_mtmr(struct sfi_table_header *table) -{ - struct sfi_table_simple *sb; - struct sfi_timer_table_entry *pentry; - struct mpc_intsrc mp_irq; - int totallen; - - sb = (struct sfi_table_simple *)table; - if (!sfi_mtimer_num) { - sfi_mtimer_num = SFI_GET_NUM_ENTRIES(sb, - struct sfi_timer_table_entry); - pentry = (struct sfi_timer_table_entry *) sb->pentry; - totallen = sfi_mtimer_num * sizeof(*pentry); - memcpy(sfi_mtimer_array, pentry, totallen); - } - - pr_debug("SFI MTIMER info (num = %d):\n", sfi_mtimer_num); - pentry = sfi_mtimer_array; - for (totallen = 0; totallen < sfi_mtimer_num; totallen++, pentry++) { - pr_debug("timer[%d]: paddr = 0x%08x, freq = %dHz, irq = %d\n", - totallen, (u32)pentry->phys_addr, - pentry->freq_hz, pentry->irq); - mp_irq.type = MP_INTSRC; - mp_irq.irqtype = mp_INT; - mp_irq.irqflag = MP_IRQTRIG_EDGE | MP_IRQPOL_ACTIVE_HIGH; - mp_irq.srcbus = MP_BUS_ISA; - mp_irq.srcbusirq = pentry->irq; /* IRQ */ - mp_irq.dstapic = MP_APIC_ALL; - mp_irq.dstirq = pentry->irq; - mp_save_irq(&mp_irq); - mp_map_gsi_to_irq(pentry->irq, IOAPIC_MAP_ALLOC, NULL); - } - - return 0; -} - -struct sfi_timer_table_entry *sfi_get_mtmr(int hint) -{ - int i; - if (hint < sfi_mtimer_num) { - if (!sfi_mtimer_usage[hint]) { - pr_debug("hint taken for timer %d irq %d\n", - hint, sfi_mtimer_array[hint].irq); - sfi_mtimer_usage[hint] = 1; - return &sfi_mtimer_array[hint]; - } - } - /* take the first timer available */ - for (i = 0; i < sfi_mtimer_num;) { - if (!sfi_mtimer_usage[i]) { - sfi_mtimer_usage[i] = 1; - return &sfi_mtimer_array[i]; - } - i++; - } - return NULL; -} - -void sfi_free_mtmr(struct sfi_timer_table_entry *mtmr) -{ - int i; - for (i = 0; i < sfi_mtimer_num;) { - if (mtmr->irq == sfi_mtimer_array[i].irq) { - sfi_mtimer_usage[i] = 0; - return; - } - i++; - } -} - -/* parse all the mrtc info to a global mrtc array */ -int __init sfi_parse_mrtc(struct sfi_table_header *table) -{ - struct sfi_table_simple *sb; - struct sfi_rtc_table_entry *pentry; - struct mpc_intsrc mp_irq; - - int totallen; - - sb = (struct sfi_table_simple *)table; - if (!sfi_mrtc_num) { - sfi_mrtc_num = SFI_GET_NUM_ENTRIES(sb, - struct sfi_rtc_table_entry); - pentry = (struct sfi_rtc_table_entry *)sb->pentry; - totallen = sfi_mrtc_num * sizeof(*pentry); - memcpy(sfi_mrtc_array, pentry, totallen); - } - - pr_debug("SFI RTC info (num = %d):\n", sfi_mrtc_num); - pentry = sfi_mrtc_array; - for (totallen = 0; totallen < sfi_mrtc_num; totallen++, pentry++) { - pr_debug("RTC[%d]: paddr = 0x%08x, irq = %d\n", - totallen, (u32)pentry->phys_addr, pentry->irq); - mp_irq.type = MP_INTSRC; - mp_irq.irqtype = mp_INT; - mp_irq.irqflag = MP_IRQTRIG_LEVEL | MP_IRQPOL_ACTIVE_LOW; - mp_irq.srcbus = MP_BUS_ISA; - mp_irq.srcbusirq = pentry->irq; /* IRQ */ - mp_irq.dstapic = MP_APIC_ALL; - mp_irq.dstirq = pentry->irq; - mp_save_irq(&mp_irq); - mp_map_gsi_to_irq(pentry->irq, IOAPIC_MAP_ALLOC, NULL); - } - return 0; -} - - -/* - * Parsing GPIO table first, since the DEVS table will need this table - * to map the pin name to the actual pin. - */ -static int __init sfi_parse_gpio(struct sfi_table_header *table) -{ - struct sfi_table_simple *sb; - struct sfi_gpio_table_entry *pentry; - int num, i; - - if (gpio_table) - return 0; - sb = (struct sfi_table_simple *)table; - num = SFI_GET_NUM_ENTRIES(sb, struct sfi_gpio_table_entry); - pentry = (struct sfi_gpio_table_entry *)sb->pentry; - - gpio_table = kmemdup(pentry, num * sizeof(*pentry), GFP_KERNEL); - if (!gpio_table) - return -1; - gpio_num_entry = num; - - pr_debug("GPIO pin info:\n"); - for (i = 0; i < num; i++, pentry++) - pr_debug("info[%2d]: controller = %16.16s, pin_name = %16.16s," - " pin = %d\n", i, - pentry->controller_name, - pentry->pin_name, - pentry->pin_no); - return 0; -} - -int get_gpio_by_name(const char *name) -{ - struct sfi_gpio_table_entry *pentry = gpio_table; - int i; - - if (!pentry) - return -1; - for (i = 0; i < gpio_num_entry; i++, pentry++) { - if (!strncmp(name, pentry->pin_name, SFI_NAME_LEN)) - return pentry->pin_no; - } - return -EINVAL; -} - -static void __init intel_scu_ipc_device_register(struct platform_device *pdev) -{ - if (ipc_next_dev == MAX_IPCDEVS) - pr_err("too many SCU IPC devices"); - else - ipc_devs[ipc_next_dev++] = pdev; -} - -static void __init intel_scu_spi_device_register(struct spi_board_info *sdev) -{ - struct spi_board_info *new_dev; - - if (spi_next_dev == MAX_SCU_SPI) { - pr_err("too many SCU SPI devices"); - return; - } - - new_dev = kzalloc(sizeof(*sdev), GFP_KERNEL); - if (!new_dev) { - pr_err("failed to alloc mem for delayed spi dev %s\n", - sdev->modalias); - return; - } - *new_dev = *sdev; - - spi_devs[spi_next_dev++] = new_dev; -} - -static void __init intel_scu_i2c_device_register(int bus, - struct i2c_board_info *idev) -{ - struct i2c_board_info *new_dev; - - if (i2c_next_dev == MAX_SCU_I2C) { - pr_err("too many SCU I2C devices"); - return; - } - - new_dev = kzalloc(sizeof(*idev), GFP_KERNEL); - if (!new_dev) { - pr_err("failed to alloc mem for delayed i2c dev %s\n", - idev->type); - return; - } - *new_dev = *idev; - - i2c_bus[i2c_next_dev] = bus; - i2c_devs[i2c_next_dev++] = new_dev; -} - -/* Called by IPC driver */ -void intel_scu_devices_create(void) -{ - int i; - - for (i = 0; i < ipc_next_dev; i++) - platform_device_add(ipc_devs[i]); - - for (i = 0; i < spi_next_dev; i++) - spi_register_board_info(spi_devs[i], 1); - - for (i = 0; i < i2c_next_dev; i++) { - struct i2c_adapter *adapter; - struct i2c_client *client; - - adapter = i2c_get_adapter(i2c_bus[i]); - if (adapter) { - client = i2c_new_client_device(adapter, i2c_devs[i]); - if (IS_ERR(client)) - pr_err("can't create i2c device %s\n", - i2c_devs[i]->type); - } else - i2c_register_board_info(i2c_bus[i], i2c_devs[i], 1); - } - intel_scu_notifier_post(SCU_AVAILABLE, NULL); -} -EXPORT_SYMBOL_GPL(intel_scu_devices_create); - -/* Called by IPC driver */ -void intel_scu_devices_destroy(void) -{ - int i; - - intel_scu_notifier_post(SCU_DOWN, NULL); - - for (i = 0; i < ipc_next_dev; i++) - platform_device_del(ipc_devs[i]); -} -EXPORT_SYMBOL_GPL(intel_scu_devices_destroy); - -static void __init install_irq_resource(struct platform_device *pdev, int irq) -{ - /* Single threaded */ - static struct resource res __initdata = { - .name = "IRQ", - .flags = IORESOURCE_IRQ, - }; - res.start = irq; - platform_device_add_resources(pdev, &res, 1); -} - -static void __init sfi_handle_ipc_dev(struct sfi_device_table_entry *pentry, - struct devs_id *dev) -{ - struct platform_device *pdev; - void *pdata = NULL; - - pr_debug("IPC bus, name = %16.16s, irq = 0x%2x\n", - pentry->name, pentry->irq); - - /* - * We need to call platform init of IPC devices to fill misc_pdata - * structure. It will be used in msic_init for initialization. - */ - pdata = intel_mid_sfi_get_pdata(dev, pentry); - if (IS_ERR(pdata)) - return; - - /* - * On Medfield the platform device creation is handled by the MSIC - * MFD driver so we don't need to do it here. - */ - if (dev->msic && intel_mid_has_msic()) - return; - - pdev = platform_device_alloc(pentry->name, 0); - if (pdev == NULL) { - pr_err("out of memory for SFI platform device '%s'.\n", - pentry->name); - return; - } - install_irq_resource(pdev, pentry->irq); - - pdev->dev.platform_data = pdata; - if (dev->delay) - intel_scu_ipc_device_register(pdev); - else - platform_device_add(pdev); -} - -static void __init sfi_handle_spi_dev(struct sfi_device_table_entry *pentry, - struct devs_id *dev) -{ - struct spi_board_info spi_info; - void *pdata = NULL; - - memset(&spi_info, 0, sizeof(spi_info)); - strncpy(spi_info.modalias, pentry->name, SFI_NAME_LEN); - spi_info.irq = ((pentry->irq == (u8)0xff) ? 0 : pentry->irq); - spi_info.bus_num = pentry->host_num; - spi_info.chip_select = pentry->addr; - spi_info.max_speed_hz = pentry->max_freq; - pr_debug("SPI bus=%d, name=%16.16s, irq=0x%2x, max_freq=%d, cs=%d\n", - spi_info.bus_num, - spi_info.modalias, - spi_info.irq, - spi_info.max_speed_hz, - spi_info.chip_select); - - pdata = intel_mid_sfi_get_pdata(dev, &spi_info); - if (IS_ERR(pdata)) - return; - - spi_info.platform_data = pdata; - if (dev->delay) - intel_scu_spi_device_register(&spi_info); - else - spi_register_board_info(&spi_info, 1); -} - -static void __init sfi_handle_i2c_dev(struct sfi_device_table_entry *pentry, - struct devs_id *dev) -{ - struct i2c_board_info i2c_info; - void *pdata = NULL; - - memset(&i2c_info, 0, sizeof(i2c_info)); - strncpy(i2c_info.type, pentry->name, SFI_NAME_LEN); - i2c_info.irq = ((pentry->irq == (u8)0xff) ? 0 : pentry->irq); - i2c_info.addr = pentry->addr; - pr_debug("I2C bus = %d, name = %16.16s, irq = 0x%2x, addr = 0x%x\n", - pentry->host_num, - i2c_info.type, - i2c_info.irq, - i2c_info.addr); - pdata = intel_mid_sfi_get_pdata(dev, &i2c_info); - i2c_info.platform_data = pdata; - if (IS_ERR(pdata)) - return; - - if (dev->delay) - intel_scu_i2c_device_register(pentry->host_num, &i2c_info); - else - i2c_register_board_info(pentry->host_num, &i2c_info, 1); -} - -static void __init sfi_handle_sd_dev(struct sfi_device_table_entry *pentry, - struct devs_id *dev) -{ - struct mid_sd_board_info sd_info; - void *pdata; - - memset(&sd_info, 0, sizeof(sd_info)); - strncpy(sd_info.name, pentry->name, SFI_NAME_LEN); - sd_info.bus_num = pentry->host_num; - sd_info.max_clk = pentry->max_freq; - sd_info.addr = pentry->addr; - pr_debug("SD bus = %d, name = %16.16s, max_clk = %d, addr = 0x%x\n", - sd_info.bus_num, - sd_info.name, - sd_info.max_clk, - sd_info.addr); - pdata = intel_mid_sfi_get_pdata(dev, &sd_info); - if (IS_ERR(pdata)) - return; - - /* Nothing we can do with this for now */ - sd_info.platform_data = pdata; - - pr_debug("Successfully registered %16.16s", sd_info.name); -} - -extern struct devs_id *const __x86_intel_mid_dev_start[], - *const __x86_intel_mid_dev_end[]; - -static struct devs_id __init *get_device_id(u8 type, char *name) -{ - struct devs_id *const *dev_table; - - for (dev_table = __x86_intel_mid_dev_start; - dev_table < __x86_intel_mid_dev_end; dev_table++) { - struct devs_id *dev = *dev_table; - if (dev->type == type && - !strncmp(dev->name, name, SFI_NAME_LEN)) { - return dev; - } - } - - return NULL; -} - -static int __init sfi_parse_devs(struct sfi_table_header *table) -{ - struct sfi_table_simple *sb; - struct sfi_device_table_entry *pentry; - struct devs_id *dev = NULL; - int num, i, ret; - int polarity; - struct irq_alloc_info info; - - sb = (struct sfi_table_simple *)table; - num = SFI_GET_NUM_ENTRIES(sb, struct sfi_device_table_entry); - pentry = (struct sfi_device_table_entry *)sb->pentry; - - for (i = 0; i < num; i++, pentry++) { - int irq = pentry->irq; - - if (irq != (u8)0xff) { /* native RTE case */ - /* these SPI2 devices are not exposed to system as PCI - * devices, but they have separate RTE entry in IOAPIC - * so we have to enable them one by one here - */ - if (intel_mid_identify_cpu() == - INTEL_MID_CPU_CHIP_TANGIER) { - if (!strncmp(pentry->name, "r69001-ts-i2c", 13)) - /* active low */ - polarity = 1; - else if (!strncmp(pentry->name, - "synaptics_3202", 14)) - /* active low */ - polarity = 1; - else if (irq == 41) - /* fast_int_1 */ - polarity = 1; - else - /* active high */ - polarity = 0; - } else { - /* PNW and CLV go with active low */ - polarity = 1; - } - - ioapic_set_alloc_attr(&info, NUMA_NO_NODE, 1, polarity); - ret = mp_map_gsi_to_irq(irq, IOAPIC_MAP_ALLOC, &info); - WARN_ON(ret < 0); - } - - dev = get_device_id(pentry->type, pentry->name); - - if (!dev) - continue; - - switch (pentry->type) { - case SFI_DEV_TYPE_IPC: - sfi_handle_ipc_dev(pentry, dev); - break; - case SFI_DEV_TYPE_SPI: - sfi_handle_spi_dev(pentry, dev); - break; - case SFI_DEV_TYPE_I2C: - sfi_handle_i2c_dev(pentry, dev); - break; - case SFI_DEV_TYPE_SD: - sfi_handle_sd_dev(pentry, dev); - break; - case SFI_DEV_TYPE_UART: - case SFI_DEV_TYPE_HSI: - default: - break; - } - } - return 0; -} - -static int __init intel_mid_platform_init(void) -{ - sfi_table_parse(SFI_SIG_GPIO, NULL, NULL, sfi_parse_gpio); - sfi_table_parse(SFI_SIG_DEVS, NULL, NULL, sfi_parse_devs); - return 0; -} -arch_initcall(intel_mid_platform_init); diff --git a/arch/x86/platform/iris/iris.c b/arch/x86/platform/iris/iris.c index 1ac8578258af..b42bfdab01a9 100644 --- a/arch/x86/platform/iris/iris.c +++ b/arch/x86/platform/iris/iris.c @@ -27,7 +27,6 @@ MODULE_LICENSE("GPL"); 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 bool force; diff --git a/arch/x86/platform/pvh/head.S b/arch/x86/platform/pvh/head.S index 43b4d864817e..d2ccadc247e6 100644 --- a/arch/x86/platform/pvh/head.S +++ b/arch/x86/platform/pvh/head.S @@ -16,6 +16,7 @@ #include <asm/boot.h> #include <asm/processor-flags.h> #include <asm/msr.h> +#include <asm/nospec-branch.h> #include <xen/interface/elfnote.h> __HEAD @@ -105,6 +106,7 @@ SYM_CODE_START_LOCAL(pvh_start_xen) /* startup_64 expects boot_params in %rsi. */ mov $_pa(pvh_bootparams), %rsi mov $_pa(startup_64), %rax + ANNOTATE_RETPOLINE_SAFE jmp *%rax #else /* CONFIG_X86_64 */ diff --git a/arch/x86/platform/sfi/Makefile b/arch/x86/platform/sfi/Makefile deleted file mode 100644 index 4eba24c2af67..000000000000 --- a/arch/x86/platform/sfi/Makefile +++ /dev/null @@ -1,2 +0,0 @@ -# SPDX-License-Identifier: GPL-2.0-only -obj-$(CONFIG_SFI) += sfi.o diff --git a/arch/x86/platform/sfi/sfi.c b/arch/x86/platform/sfi/sfi.c deleted file mode 100644 index 6259563760f9..000000000000 --- a/arch/x86/platform/sfi/sfi.c +++ /dev/null @@ -1,100 +0,0 @@ -// SPDX-License-Identifier: GPL-2.0-only -/* - * sfi.c - x86 architecture SFI support. - * - * Copyright (c) 2009, Intel Corporation. - */ - -#define KMSG_COMPONENT "SFI" -#define pr_fmt(fmt) KMSG_COMPONENT ": " fmt - -#include <linux/acpi.h> -#include <linux/init.h> -#include <linux/sfi.h> -#include <linux/io.h> - -#include <asm/irqdomain.h> -#include <asm/io_apic.h> -#include <asm/mpspec.h> -#include <asm/setup.h> -#include <asm/apic.h> - -#ifdef CONFIG_X86_LOCAL_APIC -static unsigned long sfi_lapic_addr __initdata = APIC_DEFAULT_PHYS_BASE; - -/* All CPUs enumerated by SFI must be present and enabled */ -static void __init mp_sfi_register_lapic(u8 id) -{ - if (MAX_LOCAL_APIC - id <= 0) { - pr_warn("Processor #%d invalid (max %d)\n", id, MAX_LOCAL_APIC); - return; - } - - pr_info("registering lapic[%d]\n", id); - - generic_processor_info(id, GET_APIC_VERSION(apic_read(APIC_LVR))); -} - -static int __init sfi_parse_cpus(struct sfi_table_header *table) -{ - struct sfi_table_simple *sb; - struct sfi_cpu_table_entry *pentry; - int i; - int cpu_num; - - sb = (struct sfi_table_simple *)table; - cpu_num = SFI_GET_NUM_ENTRIES(sb, struct sfi_cpu_table_entry); - pentry = (struct sfi_cpu_table_entry *)sb->pentry; - - for (i = 0; i < cpu_num; i++) { - mp_sfi_register_lapic(pentry->apic_id); - pentry++; - } - - smp_found_config = 1; - return 0; -} -#endif /* CONFIG_X86_LOCAL_APIC */ - -#ifdef CONFIG_X86_IO_APIC - -static int __init sfi_parse_ioapic(struct sfi_table_header *table) -{ - struct sfi_table_simple *sb; - struct sfi_apic_table_entry *pentry; - int i, num; - struct ioapic_domain_cfg cfg = { - .type = IOAPIC_DOMAIN_STRICT, - .ops = &mp_ioapic_irqdomain_ops, - }; - - sb = (struct sfi_table_simple *)table; - num = SFI_GET_NUM_ENTRIES(sb, struct sfi_apic_table_entry); - pentry = (struct sfi_apic_table_entry *)sb->pentry; - - for (i = 0; i < num; i++) { - mp_register_ioapic(i, pentry->phys_addr, gsi_top, &cfg); - pentry++; - } - - WARN(pic_mode, KERN_WARNING - "SFI: pic_mod shouldn't be 1 when IOAPIC table is present\n"); - pic_mode = 0; - return 0; -} -#endif /* CONFIG_X86_IO_APIC */ - -/* - * sfi_platform_init(): register lapics & io-apics - */ -int __init sfi_platform_init(void) -{ -#ifdef CONFIG_X86_LOCAL_APIC - register_lapic_address(sfi_lapic_addr); - sfi_table_parse(SFI_SIG_CPUS, NULL, NULL, sfi_parse_cpus); -#endif -#ifdef CONFIG_X86_IO_APIC - sfi_table_parse(SFI_SIG_APIC, NULL, NULL, sfi_parse_ioapic); -#endif - return 0; -} diff --git a/arch/x86/power/Makefile b/arch/x86/power/Makefile index 6907b523e856..379777572bc9 100644 --- a/arch/x86/power/Makefile +++ b/arch/x86/power/Makefile @@ -1,9 +1,12 @@ # SPDX-License-Identifier: GPL-2.0 -OBJECT_FILES_NON_STANDARD_hibernate_asm_$(BITS).o := y # __restore_processor_state() restores %gs after S3 resume and so should not # itself be stack-protected CFLAGS_cpu.o := -fno-stack-protector +# Clang may incorrectly inline functions with stack protector enabled into +# __restore_processor_state(): https://bugs.llvm.org/show_bug.cgi?id=47479 +CFLAGS_REMOVE_cpu.o := $(CC_FLAGS_LTO) + obj-$(CONFIG_PM_SLEEP) += cpu.o obj-$(CONFIG_HIBERNATION) += hibernate_$(BITS).o hibernate_asm_$(BITS).o hibernate.o diff --git a/arch/x86/power/hibernate_asm_64.S b/arch/x86/power/hibernate_asm_64.S index 7918b8415f13..d9bed596d849 100644 --- a/arch/x86/power/hibernate_asm_64.S +++ b/arch/x86/power/hibernate_asm_64.S @@ -21,6 +21,53 @@ #include <asm/asm-offsets.h> #include <asm/processor-flags.h> #include <asm/frame.h> +#include <asm/nospec-branch.h> + + /* code below belongs to the image kernel */ + .align PAGE_SIZE +SYM_FUNC_START(restore_registers) + /* go back to the original page tables */ + movq %r9, %cr3 + + /* Flush TLB, including "global" things (vmalloc) */ + movq mmu_cr4_features(%rip), %rax + movq %rax, %rdx + andq $~(X86_CR4_PGE), %rdx + movq %rdx, %cr4; # turn off PGE + movq %cr3, %rcx; # flush TLB + movq %rcx, %cr3 + movq %rax, %cr4; # turn PGE back on + + /* We don't restore %rax, it must be 0 anyway */ + movq $saved_context, %rax + movq pt_regs_sp(%rax), %rsp + movq pt_regs_bp(%rax), %rbp + movq pt_regs_si(%rax), %rsi + movq pt_regs_di(%rax), %rdi + movq pt_regs_bx(%rax), %rbx + movq pt_regs_cx(%rax), %rcx + movq pt_regs_dx(%rax), %rdx + movq pt_regs_r8(%rax), %r8 + movq pt_regs_r9(%rax), %r9 + movq pt_regs_r10(%rax), %r10 + movq pt_regs_r11(%rax), %r11 + movq pt_regs_r12(%rax), %r12 + movq pt_regs_r13(%rax), %r13 + movq pt_regs_r14(%rax), %r14 + movq pt_regs_r15(%rax), %r15 + pushq pt_regs_flags(%rax) + popfq + + /* Saved in save_processor_state. */ + lgdt saved_context_gdt_desc(%rax) + + xorl %eax, %eax + + /* tell the hibernation core that we've just restored the memory */ + movq %rax, in_suspend(%rip) + + ret +SYM_FUNC_END(restore_registers) SYM_FUNC_START(swsusp_arch_suspend) movq $saved_context, %rax @@ -52,7 +99,7 @@ SYM_FUNC_START(swsusp_arch_suspend) ret SYM_FUNC_END(swsusp_arch_suspend) -SYM_CODE_START(restore_image) +SYM_FUNC_START(restore_image) /* prepare to jump to the image kernel */ movq restore_jump_address(%rip), %r8 movq restore_cr3(%rip), %r9 @@ -66,11 +113,12 @@ SYM_CODE_START(restore_image) /* jump to relocated restore code */ movq relocated_restore_code(%rip), %rcx + ANNOTATE_RETPOLINE_SAFE jmpq *%rcx -SYM_CODE_END(restore_image) +SYM_FUNC_END(restore_image) /* code below has been relocated to a safe page */ -SYM_CODE_START(core_restore_code) +SYM_FUNC_START(core_restore_code) /* switch to temporary page tables */ movq %rax, %cr3 /* flush TLB */ @@ -97,51 +145,6 @@ SYM_CODE_START(core_restore_code) .Ldone: /* jump to the restore_registers address from the image header */ + ANNOTATE_RETPOLINE_SAFE jmpq *%r8 -SYM_CODE_END(core_restore_code) - - /* code below belongs to the image kernel */ - .align PAGE_SIZE -SYM_FUNC_START(restore_registers) - /* go back to the original page tables */ - movq %r9, %cr3 - - /* Flush TLB, including "global" things (vmalloc) */ - movq mmu_cr4_features(%rip), %rax - movq %rax, %rdx - andq $~(X86_CR4_PGE), %rdx - movq %rdx, %cr4; # turn off PGE - movq %cr3, %rcx; # flush TLB - movq %rcx, %cr3 - movq %rax, %cr4; # turn PGE back on - - /* We don't restore %rax, it must be 0 anyway */ - movq $saved_context, %rax - movq pt_regs_sp(%rax), %rsp - movq pt_regs_bp(%rax), %rbp - movq pt_regs_si(%rax), %rsi - movq pt_regs_di(%rax), %rdi - movq pt_regs_bx(%rax), %rbx - movq pt_regs_cx(%rax), %rcx - movq pt_regs_dx(%rax), %rdx - movq pt_regs_r8(%rax), %r8 - movq pt_regs_r9(%rax), %r9 - movq pt_regs_r10(%rax), %r10 - movq pt_regs_r11(%rax), %r11 - movq pt_regs_r12(%rax), %r12 - movq pt_regs_r13(%rax), %r13 - movq pt_regs_r14(%rax), %r14 - movq pt_regs_r15(%rax), %r15 - pushq pt_regs_flags(%rax) - popfq - - /* Saved in save_processor_state. */ - lgdt saved_context_gdt_desc(%rax) - - xorl %eax, %eax - - /* tell the hibernation core that we've just restored the memory */ - movq %rax, in_suspend(%rip) - - ret -SYM_FUNC_END(restore_registers) +SYM_FUNC_END(core_restore_code) diff --git a/arch/x86/tools/Makefile b/arch/x86/tools/Makefile index 55b1ab378974..bddfc9a46645 100644 --- a/arch/x86/tools/Makefile +++ b/arch/x86/tools/Makefile @@ -29,14 +29,14 @@ posttest: $(obj)/insn_decoder_test vmlinux $(obj)/insn_sanity hostprogs += insn_decoder_test insn_sanity # -I needed for generated C source and C source which in the kernel tree. -HOSTCFLAGS_insn_decoder_test.o := -Wall -I$(objtree)/arch/x86/lib/ -I$(srctree)/arch/x86/include/uapi/ -I$(srctree)/arch/x86/include/ -I$(srctree)/arch/x86/lib/ -I$(srctree)/include/uapi/ +HOSTCFLAGS_insn_decoder_test.o := -Wall -I$(srctree)/tools/arch/x86/lib/ -I$(srctree)/tools/arch/x86/include/ -I$(objtree)/arch/x86/lib/ -HOSTCFLAGS_insn_sanity.o := -Wall -I$(objtree)/arch/x86/lib/ -I$(srctree)/arch/x86/include/ -I$(srctree)/arch/x86/lib/ -I$(srctree)/include/ +HOSTCFLAGS_insn_sanity.o := -Wall -I$(srctree)/tools/arch/x86/lib/ -I$(srctree)/tools/arch/x86/include/ -I$(objtree)/arch/x86/lib/ # Dependencies are also needed. -$(obj)/insn_decoder_test.o: $(srctree)/arch/x86/lib/insn.c $(srctree)/arch/x86/lib/inat.c $(srctree)/arch/x86/include/asm/inat_types.h $(srctree)/arch/x86/include/asm/inat.h $(srctree)/arch/x86/include/asm/insn.h $(objtree)/arch/x86/lib/inat-tables.c +$(obj)/insn_decoder_test.o: $(srctree)/tools/arch/x86/lib/insn.c $(srctree)/tools/arch/x86/lib/inat.c $(srctree)/tools/arch/x86/include/asm/inat_types.h $(srctree)/tools/arch/x86/include/asm/inat.h $(srctree)/tools/arch/x86/include/asm/insn.h $(objtree)/arch/x86/lib/inat-tables.c -$(obj)/insn_sanity.o: $(srctree)/arch/x86/lib/insn.c $(srctree)/arch/x86/lib/inat.c $(srctree)/arch/x86/include/asm/inat_types.h $(srctree)/arch/x86/include/asm/inat.h $(srctree)/arch/x86/include/asm/insn.h $(objtree)/arch/x86/lib/inat-tables.c +$(obj)/insn_sanity.o: $(srctree)/tools/arch/x86/lib/insn.c $(srctree)/tools/arch/x86/lib/inat.c $(srctree)/tools/arch/x86/include/asm/inat_types.h $(srctree)/tools/arch/x86/include/asm/inat.h $(srctree)/tools/arch/x86/include/asm/insn.h $(objtree)/arch/x86/lib/inat-tables.c HOST_EXTRACFLAGS += -I$(srctree)/tools/include hostprogs += relocs diff --git a/arch/x86/tools/insn_sanity.c b/arch/x86/tools/insn_sanity.c index 185ceba9d289..c6a0000ae635 100644 --- a/arch/x86/tools/insn_sanity.c +++ b/arch/x86/tools/insn_sanity.c @@ -14,10 +14,6 @@ #include <sys/types.h> #include <sys/stat.h> #include <fcntl.h> - -#define unlikely(cond) (cond) -#define ARRAY_SIZE(a) (sizeof(a)/sizeof(a[0])) - #include <asm/insn.h> #include <inat.c> #include <insn.c> diff --git a/arch/x86/tools/relocs.c b/arch/x86/tools/relocs.c index ce7188cbdae5..04c5a44b9682 100644 --- a/arch/x86/tools/relocs.c +++ b/arch/x86/tools/relocs.c @@ -61,8 +61,8 @@ static const char * const sym_regex_kernel[S_NSYMTYPES] = { "(__iommu_table|__apicdrivers|__smp_locks)(|_end)|" "__(start|end)_pci_.*|" "__(start|end)_builtin_fw|" - "__(start|stop)___ksymtab(|_gpl|_unused|_unused_gpl|_gpl_future)|" - "__(start|stop)___kcrctab(|_gpl|_unused|_unused_gpl|_gpl_future)|" + "__(start|stop)___ksymtab(|_gpl)|" + "__(start|stop)___kcrctab(|_gpl)|" "__(start|stop)___param|" "__(start|stop)___modver|" "__(start|stop)___bug_table|" @@ -867,9 +867,11 @@ static int do_reloc32(struct section *sec, Elf_Rel *rel, Elf_Sym *sym, case R_386_PC32: case R_386_PC16: case R_386_PC8: + case R_386_PLT32: /* - * NONE can be ignored and PC relative relocations don't - * need to be adjusted. + * NONE can be ignored and PC relative relocations don't need + * to be adjusted. Because sym must be defined, R_386_PLT32 can + * be treated the same way as R_386_PC32. */ break; @@ -910,9 +912,11 @@ static int do_reloc_real(struct section *sec, Elf_Rel *rel, Elf_Sym *sym, case R_386_PC32: case R_386_PC16: case R_386_PC8: + case R_386_PLT32: /* - * NONE can be ignored and PC relative relocations don't - * need to be adjusted. + * NONE can be ignored and PC relative relocations don't need + * to be adjusted. Because sym must be defined, R_386_PLT32 can + * be treated the same way as R_386_PC32. */ break; diff --git a/arch/x86/um/os-Linux/task_size.c b/arch/x86/um/os-Linux/task_size.c index e62174638f00..1dc9adc20b1c 100644 --- a/arch/x86/um/os-Linux/task_size.c +++ b/arch/x86/um/os-Linux/task_size.c @@ -145,7 +145,7 @@ out: unsigned long os_get_top_address(void) { /* The old value of CONFIG_TOP_ADDR */ - return 0x7fc0000000; + return 0x7fc0002000; } #endif diff --git a/arch/x86/um/shared/sysdep/stub_32.h b/arch/x86/um/shared/sysdep/stub_32.h index 51fd256c75f0..c3891c1ada26 100644 --- a/arch/x86/um/shared/sysdep/stub_32.h +++ b/arch/x86/um/shared/sysdep/stub_32.h @@ -7,8 +7,8 @@ #define __SYSDEP_STUB_H #include <asm/ptrace.h> +#include <generated/asm-offsets.h> -#define STUB_SYSCALL_RET EAX #define STUB_MMAP_NR __NR_mmap2 #define MMAP_OFFSET(o) ((o) >> UM_KERN_PAGE_SHIFT) @@ -77,17 +77,28 @@ static inline void trap_myself(void) __asm("int3"); } -static inline void remap_stack(int fd, unsigned long offset) +static void inline remap_stack_and_trap(void) { - __asm__ volatile ("movl %%eax,%%ebp ; movl %0,%%eax ; int $0x80 ;" - "movl %7, %%ebx ; movl %%eax, (%%ebx)" - : : "g" (STUB_MMAP_NR), "b" (STUB_DATA), - "c" (UM_KERN_PAGE_SIZE), - "d" (PROT_READ | PROT_WRITE), - "S" (MAP_FIXED | MAP_SHARED), "D" (fd), - "a" (offset), - "i" (&((struct stub_data *) STUB_DATA)->err) - : "memory"); + __asm__ volatile ( + "movl %%esp,%%ebx ;" + "andl %0,%%ebx ;" + "movl %1,%%eax ;" + "movl %%ebx,%%edi ; addl %2,%%edi ; movl (%%edi),%%edi ;" + "movl %%ebx,%%ebp ; addl %3,%%ebp ; movl (%%ebp),%%ebp ;" + "int $0x80 ;" + "addl %4,%%ebx ; movl %%eax, (%%ebx) ;" + "int $3" + : : + "g" (~(UM_KERN_PAGE_SIZE - 1)), + "g" (STUB_MMAP_NR), + "g" (UML_STUB_FIELD_FD), + "g" (UML_STUB_FIELD_OFFSET), + "g" (UML_STUB_FIELD_CHILD_ERR), + "c" (UM_KERN_PAGE_SIZE), + "d" (PROT_READ | PROT_WRITE), + "S" (MAP_FIXED | MAP_SHARED) + : + "memory"); } #endif diff --git a/arch/x86/um/shared/sysdep/stub_64.h b/arch/x86/um/shared/sysdep/stub_64.h index 994df93c5ed3..6e2626b77a2e 100644 --- a/arch/x86/um/shared/sysdep/stub_64.h +++ b/arch/x86/um/shared/sysdep/stub_64.h @@ -7,8 +7,8 @@ #define __SYSDEP_STUB_H #include <sysdep/ptrace_user.h> +#include <generated/asm-offsets.h> -#define STUB_SYSCALL_RET PT_INDEX(RAX) #define STUB_MMAP_NR __NR_mmap #define MMAP_OFFSET(o) (o) @@ -82,18 +82,30 @@ static inline void trap_myself(void) __asm("int3"); } -static inline void remap_stack(long fd, unsigned long offset) +static inline void remap_stack_and_trap(void) { - __asm__ volatile ("movq %4,%%r10 ; movq %5,%%r8 ; " - "movq %6, %%r9; " __syscall "; movq %7, %%rbx ; " - "movq %%rax, (%%rbx)": - : "a" (STUB_MMAP_NR), "D" (STUB_DATA), - "S" (UM_KERN_PAGE_SIZE), - "d" (PROT_READ | PROT_WRITE), - "g" (MAP_FIXED | MAP_SHARED), "g" (fd), - "g" (offset), - "i" (&((struct stub_data *) STUB_DATA)->err) - : __syscall_clobber, "r10", "r8", "r9" ); + __asm__ volatile ( + "movq %0,%%rax ;" + "movq %%rsp,%%rdi ;" + "andq %1,%%rdi ;" + "movq %2,%%r10 ;" + "movq %%rdi,%%r8 ; addq %3,%%r8 ; movq (%%r8),%%r8 ;" + "movq %%rdi,%%r9 ; addq %4,%%r9 ; movq (%%r9),%%r9 ;" + __syscall ";" + "movq %%rsp,%%rdi ; andq %1,%%rdi ;" + "addq %5,%%rdi ; movq %%rax, (%%rdi) ;" + "int3" + : : + "g" (STUB_MMAP_NR), + "g" (~(UM_KERN_PAGE_SIZE - 1)), + "g" (MAP_FIXED | MAP_SHARED), + "g" (UML_STUB_FIELD_FD), + "g" (UML_STUB_FIELD_OFFSET), + "g" (UML_STUB_FIELD_CHILD_ERR), + "S" (UM_KERN_PAGE_SIZE), + "d" (PROT_READ | PROT_WRITE) + : + __syscall_clobber, "r10", "r8", "r9"); } #endif diff --git a/arch/x86/um/stub_32.S b/arch/x86/um/stub_32.S index a193e88536a9..8291899e6aaf 100644 --- a/arch/x86/um/stub_32.S +++ b/arch/x86/um/stub_32.S @@ -5,21 +5,22 @@ .globl batch_syscall_stub batch_syscall_stub: - /* load pointer to first operation */ - mov $(STUB_DATA+8), %esp - + /* %esp comes in as "top of page" */ + mov %esp, %ecx + /* %esp has pointer to first operation */ + add $8, %esp again: /* load length of additional data */ mov 0x0(%esp), %eax /* if(length == 0) : end of list */ /* write possible 0 to header */ - mov %eax, STUB_DATA+4 + mov %eax, 0x4(%ecx) cmpl $0, %eax jz done /* save current pointer */ - mov %esp, STUB_DATA+4 + mov %esp, 0x4(%ecx) /* skip additional data */ add %eax, %esp @@ -38,6 +39,10 @@ again: /* execute syscall */ int $0x80 + /* restore top of page pointer in %ecx */ + mov %esp, %ecx + andl $(~UM_KERN_PAGE_SIZE) + 1, %ecx + /* check return value */ pop %ebx cmp %ebx, %eax @@ -45,7 +50,7 @@ again: done: /* save return value */ - mov %eax, STUB_DATA + mov %eax, (%ecx) /* stop */ int3 diff --git a/arch/x86/um/stub_64.S b/arch/x86/um/stub_64.S index 8a95c5b2eaf9..f3404640197a 100644 --- a/arch/x86/um/stub_64.S +++ b/arch/x86/um/stub_64.S @@ -4,9 +4,8 @@ .section .__syscall_stub, "ax" .globl batch_syscall_stub batch_syscall_stub: - mov $(STUB_DATA), %rbx - /* load pointer to first operation */ - mov %rbx, %rsp + /* %rsp has the pointer to first operation */ + mov %rsp, %rbx add $0x10, %rsp again: /* load length of additional data */ diff --git a/arch/x86/um/stub_segv.c b/arch/x86/um/stub_segv.c index 27361cbb7ca9..21836eaf1725 100644 --- a/arch/x86/um/stub_segv.c +++ b/arch/x86/um/stub_segv.c @@ -11,10 +11,11 @@ void __attribute__ ((__section__ (".__syscall_stub"))) stub_segv_handler(int sig, siginfo_t *info, void *p) { + int stack; ucontext_t *uc = p; + struct faultinfo *f = (void *)(((unsigned long)&stack) & ~(UM_KERN_PAGE_SIZE - 1)); - GET_FAULTINFO_FROM_MC(*((struct faultinfo *) STUB_DATA), - &uc->uc_mcontext); + GET_FAULTINFO_FROM_MC(*f, &uc->uc_mcontext); trap_myself(); } diff --git a/arch/x86/xen/Makefile b/arch/x86/xen/Makefile index fc5c5ba4aacb..40b5779fce21 100644 --- a/arch/x86/xen/Makefile +++ b/arch/x86/xen/Makefile @@ -1,5 +1,4 @@ # SPDX-License-Identifier: GPL-2.0 -OBJECT_FILES_NON_STANDARD_xen-asm.o := y ifdef CONFIG_FUNCTION_TRACER # Do not profile debug and lowlevel utilities diff --git a/arch/x86/xen/enlighten_pv.c b/arch/x86/xen/enlighten_pv.c index 9a5a50cdaab5..dc0a337f985b 100644 --- a/arch/x86/xen/enlighten_pv.c +++ b/arch/x86/xen/enlighten_pv.c @@ -567,10 +567,16 @@ void noist_exc_debug(struct pt_regs *regs); DEFINE_IDTENTRY_RAW(xenpv_exc_nmi) { - /* On Xen PV, NMI doesn't use IST. The C part is the sane as native. */ + /* On Xen PV, NMI doesn't use IST. The C part is the same as native. */ exc_nmi(regs); } +DEFINE_IDTENTRY_RAW_ERRORCODE(xenpv_exc_double_fault) +{ + /* On Xen PV, DF doesn't use IST. The C part is the same as native. */ + exc_double_fault(regs, error_code); +} + DEFINE_IDTENTRY_RAW(xenpv_exc_debug) { /* @@ -590,6 +596,20 @@ DEFINE_IDTENTRY_RAW(exc_xen_unknown_trap) BUG(); } +#ifdef CONFIG_X86_MCE +DEFINE_IDTENTRY_RAW(xenpv_exc_machine_check) +{ + /* + * There's no IST on Xen PV, but we still need to dispatch + * to the correct handler. + */ + if (user_mode(regs)) + noist_exc_machine_check(regs); + else + exc_machine_check(regs); +} +#endif + struct trap_array_entry { void (*orig)(void); void (*xen)(void); @@ -608,9 +628,9 @@ struct trap_array_entry { static struct trap_array_entry trap_array[] = { TRAP_ENTRY_REDIR(exc_debug, true ), - TRAP_ENTRY(exc_double_fault, true ), + TRAP_ENTRY_REDIR(exc_double_fault, true ), #ifdef CONFIG_X86_MCE - TRAP_ENTRY(exc_machine_check, true ), + TRAP_ENTRY_REDIR(exc_machine_check, true ), #endif TRAP_ENTRY_REDIR(exc_nmi, true ), TRAP_ENTRY(exc_int3, false ), @@ -1015,8 +1035,6 @@ void __init xen_setup_vcpu_info_placement(void) */ if (xen_have_vcpu_info_placement) { pv_ops.irq.save_fl = __PV_IS_CALLEE_SAVE(xen_save_fl_direct); - pv_ops.irq.restore_fl = - __PV_IS_CALLEE_SAVE(xen_restore_fl_direct); pv_ops.irq.irq_disable = __PV_IS_CALLEE_SAVE(xen_irq_disable_direct); pv_ops.irq.irq_enable = @@ -1053,7 +1071,6 @@ static const struct pv_cpu_ops xen_cpu_ops __initconst = { .read_pmc = xen_read_pmc, .iret = xen_iret, - .usergs_sysret64 = xen_sysret64, .load_tr_desc = paravirt_nop, .set_ldt = xen_set_ldt, @@ -1078,9 +1095,6 @@ static const struct pv_cpu_ops xen_cpu_ops __initconst = { #endif .io_delay = xen_io_delay, - /* Xen takes care of %gs when switching to usermode for us */ - .swapgs = paravirt_nop, - .start_context_switch = paravirt_start_context_switch, .end_context_switch = xen_end_context_switch, }; diff --git a/arch/x86/xen/irq.c b/arch/x86/xen/irq.c index 850c93f346c7..dfa091d79c2e 100644 --- a/arch/x86/xen/irq.c +++ b/arch/x86/xen/irq.c @@ -42,28 +42,6 @@ asmlinkage __visible unsigned long xen_save_fl(void) } PV_CALLEE_SAVE_REGS_THUNK(xen_save_fl); -__visible void xen_restore_fl(unsigned long flags) -{ - struct vcpu_info *vcpu; - - /* convert from IF type flag */ - flags = !(flags & X86_EFLAGS_IF); - - /* See xen_irq_enable() for why preemption must be disabled. */ - preempt_disable(); - vcpu = this_cpu_read(xen_vcpu); - vcpu->evtchn_upcall_mask = flags; - - if (flags == 0) { - barrier(); /* unmask then check (avoid races) */ - if (unlikely(vcpu->evtchn_upcall_pending)) - xen_force_evtchn_callback(); - preempt_enable(); - } else - preempt_enable_no_resched(); -} -PV_CALLEE_SAVE_REGS_THUNK(xen_restore_fl); - asmlinkage __visible void xen_irq_disable(void) { /* There's a one instruction preempt window here. We need to @@ -118,7 +96,6 @@ static void xen_halt(void) static const struct pv_irq_ops xen_irq_ops __initconst = { .save_fl = PV_CALLEE_SAVE(xen_save_fl), - .restore_fl = PV_CALLEE_SAVE(xen_restore_fl), .irq_disable = PV_CALLEE_SAVE(xen_irq_disable), .irq_enable = PV_CALLEE_SAVE(xen_irq_enable), diff --git a/arch/x86/xen/p2m.c b/arch/x86/xen/p2m.c index 3301875dd196..17d80f751fcb 100644 --- a/arch/x86/xen/p2m.c +++ b/arch/x86/xen/p2m.c @@ -416,6 +416,9 @@ void __init xen_vmalloc_p2m_tree(void) xen_p2m_last_pfn = xen_max_p2m_pfn; p2m_limit = (phys_addr_t)P2M_LIMIT * 1024 * 1024 * 1024 / PAGE_SIZE; + if (!p2m_limit && IS_ENABLED(CONFIG_XEN_UNPOPULATED_ALLOC)) + p2m_limit = xen_start_info->nr_pages * XEN_EXTRA_MEM_RATIO; + vm.flags = VM_ALLOC; vm.size = ALIGN(sizeof(unsigned long) * max(xen_max_p2m_pfn, p2m_limit), PMD_SIZE * PMDS_PER_MID_PAGE); @@ -652,10 +655,9 @@ bool __set_phys_to_machine(unsigned long pfn, unsigned long mfn) pte_t *ptep; unsigned int level; - if (unlikely(pfn >= xen_p2m_size)) { - BUG_ON(mfn != INVALID_P2M_ENTRY); - return true; - } + /* Only invalid entries allowed above the highest p2m covered frame. */ + if (unlikely(pfn >= xen_p2m_size)) + return mfn == INVALID_P2M_ENTRY; /* * The interface requires atomic updates on p2m elements. @@ -710,9 +712,12 @@ int set_foreign_p2m_mapping(struct gnttab_map_grant_ref *map_ops, for (i = 0; i < count; i++) { unsigned long mfn, pfn; + struct gnttab_unmap_grant_ref unmap[2]; + int rc; /* Do not add to override if the map failed. */ - if (map_ops[i].status) + if (map_ops[i].status != GNTST_okay || + (kmap_ops && kmap_ops[i].status != GNTST_okay)) continue; if (map_ops[i].flags & GNTMAP_contains_pte) { @@ -726,16 +731,51 @@ int set_foreign_p2m_mapping(struct gnttab_map_grant_ref *map_ops, WARN(pfn_to_mfn(pfn) != INVALID_P2M_ENTRY, "page must be ballooned"); - if (unlikely(!set_phys_to_machine(pfn, FOREIGN_FRAME(mfn)))) { - ret = -ENOMEM; - goto out; + if (likely(set_phys_to_machine(pfn, FOREIGN_FRAME(mfn)))) + continue; + + /* + * Signal an error for this slot. This in turn requires + * immediate unmapping. + */ + map_ops[i].status = GNTST_general_error; + unmap[0].host_addr = map_ops[i].host_addr, + unmap[0].handle = map_ops[i].handle; + map_ops[i].handle = INVALID_GRANT_HANDLE; + if (map_ops[i].flags & GNTMAP_device_map) + unmap[0].dev_bus_addr = map_ops[i].dev_bus_addr; + else + unmap[0].dev_bus_addr = 0; + + if (kmap_ops) { + kmap_ops[i].status = GNTST_general_error; + unmap[1].host_addr = kmap_ops[i].host_addr, + unmap[1].handle = kmap_ops[i].handle; + kmap_ops[i].handle = INVALID_GRANT_HANDLE; + if (kmap_ops[i].flags & GNTMAP_device_map) + unmap[1].dev_bus_addr = kmap_ops[i].dev_bus_addr; + else + unmap[1].dev_bus_addr = 0; } + + /* + * Pre-populate both status fields, to be recognizable in + * the log message below. + */ + unmap[0].status = 1; + unmap[1].status = 1; + + rc = HYPERVISOR_grant_table_op(GNTTABOP_unmap_grant_ref, + unmap, 1 + !!kmap_ops); + if (rc || unmap[0].status != GNTST_okay || + unmap[1].status != GNTST_okay) + pr_err_once("gnttab unmap failed: rc=%d st0=%d st1=%d\n", + rc, unmap[0].status, unmap[1].status); } out: return ret; } -EXPORT_SYMBOL_GPL(set_foreign_p2m_mapping); int clear_foreign_p2m_mapping(struct gnttab_unmap_grant_ref *unmap_ops, struct gnttab_unmap_grant_ref *kunmap_ops, @@ -750,20 +790,17 @@ int clear_foreign_p2m_mapping(struct gnttab_unmap_grant_ref *unmap_ops, unsigned long mfn = __pfn_to_mfn(page_to_pfn(pages[i])); unsigned long pfn = page_to_pfn(pages[i]); - if (mfn == INVALID_P2M_ENTRY || !(mfn & FOREIGN_FRAME_BIT)) { + if (mfn != INVALID_P2M_ENTRY && (mfn & FOREIGN_FRAME_BIT)) + set_phys_to_machine(pfn, INVALID_P2M_ENTRY); + else ret = -EINVAL; - goto out; - } - - set_phys_to_machine(pfn, INVALID_P2M_ENTRY); } if (kunmap_ops) ret = HYPERVISOR_grant_table_op(GNTTABOP_unmap_grant_ref, - kunmap_ops, count); -out: + kunmap_ops, count) ?: ret; + return ret; } -EXPORT_SYMBOL_GPL(clear_foreign_p2m_mapping); #ifdef CONFIG_XEN_DEBUG_FS #include <linux/debugfs.h> diff --git a/arch/x86/xen/setup.c b/arch/x86/xen/setup.c index 7eab14d56369..1a3b75652fa4 100644 --- a/arch/x86/xen/setup.c +++ b/arch/x86/xen/setup.c @@ -59,18 +59,6 @@ static struct { } xen_remap_buf __initdata __aligned(PAGE_SIZE); static unsigned long xen_remap_mfn __initdata = INVALID_P2M_ENTRY; -/* - * The maximum amount of extra memory compared to the base size. The - * main scaling factor is the size of struct page. At extreme ratios - * of base:extra, all the base memory can be filled with page - * structures for the extra memory, leaving no space for anything - * else. - * - * 10x seems like a reasonable balance between scaling flexibility and - * leaving a practically usable system. - */ -#define EXTRA_MEM_RATIO (10) - static bool xen_512gb_limit __initdata = IS_ENABLED(CONFIG_XEN_512GB); static void __init xen_parse_512gb(void) @@ -790,20 +778,13 @@ char * __init xen_memory_setup(void) extra_pages += max_pages - max_pfn; /* - * Clamp the amount of extra memory to a EXTRA_MEM_RATIO - * factor the base size. On non-highmem systems, the base - * size is the full initial memory allocation; on highmem it - * is limited to the max size of lowmem, so that it doesn't - * get completely filled. + * Clamp the amount of extra memory to a XEN_EXTRA_MEM_RATIO + * factor the base size. * * Make sure we have no memory above max_pages, as this area * isn't handled by the p2m management. - * - * In principle there could be a problem in lowmem systems if - * the initial memory is also very large with respect to - * lowmem, but we won't try to deal with that here. */ - extra_pages = min3(EXTRA_MEM_RATIO * min(max_pfn, PFN_DOWN(MAXMEM)), + extra_pages = min3(XEN_EXTRA_MEM_RATIO * min(max_pfn, PFN_DOWN(MAXMEM)), extra_pages, max_pages - max_pfn); i = 0; addr = xen_e820_table.entries[0].addr; diff --git a/arch/x86/xen/xen-asm.S b/arch/x86/xen/xen-asm.S index 53cf8aa35032..1e626444712b 100644 --- a/arch/x86/xen/xen-asm.S +++ b/arch/x86/xen/xen-asm.S @@ -14,6 +14,7 @@ #include <asm/thread_info.h> #include <asm/asm.h> #include <asm/frame.h> +#include <asm/unwind_hints.h> #include <xen/interface/xen.h> @@ -72,34 +73,6 @@ SYM_FUNC_START(xen_save_fl_direct) ret SYM_FUNC_END(xen_save_fl_direct) - -/* - * In principle the caller should be passing us a value return from - * xen_save_fl_direct, but for robustness sake we test only the - * X86_EFLAGS_IF flag rather than the whole byte. After setting the - * interrupt mask state, it checks for unmasked pending events and - * enters the hypervisor to get them delivered if so. - */ -SYM_FUNC_START(xen_restore_fl_direct) - FRAME_BEGIN - testw $X86_EFLAGS_IF, %di - setz PER_CPU_VAR(xen_vcpu_info) + XEN_vcpu_info_mask - /* - * Preempt here doesn't matter because that will deal with any - * pending interrupts. The pending check may end up being run - * on the wrong CPU, but that doesn't hurt. - */ - - /* check for unmasked and pending */ - cmpw $0x0001, PER_CPU_VAR(xen_vcpu_info) + XEN_vcpu_info_pending - jnz 1f - call check_events -1: - FRAME_END - ret -SYM_FUNC_END(xen_restore_fl_direct) - - /* * Force an event check by making a hypercall, but preserve regs * before making the call. @@ -146,6 +119,7 @@ SYM_FUNC_END(xen_read_cr2_direct); .macro xen_pv_trap name SYM_CODE_START(xen_\name) + UNWIND_HINT_EMPTY pop %rcx pop %r11 jmp \name @@ -161,7 +135,7 @@ xen_pv_trap asm_exc_overflow xen_pv_trap asm_exc_bounds xen_pv_trap asm_exc_invalid_op xen_pv_trap asm_exc_device_not_available -xen_pv_trap asm_exc_double_fault +xen_pv_trap asm_xenpv_exc_double_fault xen_pv_trap asm_exc_coproc_segment_overrun xen_pv_trap asm_exc_invalid_tss xen_pv_trap asm_exc_segment_not_present @@ -172,7 +146,7 @@ xen_pv_trap asm_exc_spurious_interrupt_bug xen_pv_trap asm_exc_coprocessor_error xen_pv_trap asm_exc_alignment_check #ifdef CONFIG_X86_MCE -xen_pv_trap asm_exc_machine_check +xen_pv_trap asm_xenpv_exc_machine_check #endif /* CONFIG_X86_MCE */ xen_pv_trap asm_exc_simd_coprocessor_error #ifdef CONFIG_IA32_EMULATION @@ -185,6 +159,7 @@ xen_pv_trap asm_exc_xen_hypervisor_callback SYM_CODE_START(xen_early_idt_handler_array) i = 0 .rept NUM_EXCEPTION_VECTORS + UNWIND_HINT_EMPTY pop %rcx pop %r11 jmp early_idt_handler_array + i*EARLY_IDT_HANDLER_SIZE @@ -211,30 +186,11 @@ hypercall_iret = hypercall_page + __HYPERVISOR_iret * 32 * rsp->rax } */ SYM_CODE_START(xen_iret) + UNWIND_HINT_EMPTY pushq $0 jmp hypercall_iret SYM_CODE_END(xen_iret) -SYM_CODE_START(xen_sysret64) - /* - * We're already on the usermode stack at this point, but - * still with the kernel gs, so we can easily switch back. - * - * tss.sp2 is scratch space. - */ - movq %rsp, PER_CPU_VAR(cpu_tss_rw + TSS_sp2) - movq PER_CPU_VAR(cpu_current_top_of_stack), %rsp - - pushq $__USER_DS - pushq PER_CPU_VAR(cpu_tss_rw + TSS_sp2) - pushq %r11 - pushq $__USER_CS - pushq %rcx - - pushq $VGCF_in_syscall - jmp hypercall_iret -SYM_CODE_END(xen_sysret64) - /* * Xen handles syscall callbacks much like ordinary exceptions, which * means we have: @@ -251,7 +207,8 @@ SYM_CODE_END(xen_sysret64) */ /* Normal 64-bit system call target */ -SYM_FUNC_START(xen_syscall_target) +SYM_CODE_START(xen_syscall_target) + UNWIND_HINT_EMPTY popq %rcx popq %r11 @@ -264,12 +221,13 @@ SYM_FUNC_START(xen_syscall_target) movq $__USER_CS, 1*8(%rsp) jmp entry_SYSCALL_64_after_hwframe -SYM_FUNC_END(xen_syscall_target) +SYM_CODE_END(xen_syscall_target) #ifdef CONFIG_IA32_EMULATION /* 32-bit compat syscall target */ -SYM_FUNC_START(xen_syscall32_target) +SYM_CODE_START(xen_syscall32_target) + UNWIND_HINT_EMPTY popq %rcx popq %r11 @@ -282,10 +240,11 @@ SYM_FUNC_START(xen_syscall32_target) movq $__USER32_CS, 1*8(%rsp) jmp entry_SYSCALL_compat_after_hwframe -SYM_FUNC_END(xen_syscall32_target) +SYM_CODE_END(xen_syscall32_target) /* 32-bit compat sysenter target */ -SYM_FUNC_START(xen_sysenter_target) +SYM_CODE_START(xen_sysenter_target) + UNWIND_HINT_EMPTY /* * NB: Xen is polite and clears TF from EFLAGS for us. This means * that we don't need to guard against single step exceptions here. @@ -302,17 +261,18 @@ SYM_FUNC_START(xen_sysenter_target) movq $__USER32_CS, 1*8(%rsp) jmp entry_SYSENTER_compat_after_hwframe -SYM_FUNC_END(xen_sysenter_target) +SYM_CODE_END(xen_sysenter_target) #else /* !CONFIG_IA32_EMULATION */ -SYM_FUNC_START_ALIAS(xen_syscall32_target) -SYM_FUNC_START(xen_sysenter_target) +SYM_CODE_START(xen_syscall32_target) +SYM_CODE_START(xen_sysenter_target) + UNWIND_HINT_EMPTY lea 16(%rsp), %rsp /* strip %rcx, %r11 */ mov $-ENOSYS, %rax pushq $0 jmp hypercall_iret -SYM_FUNC_END(xen_sysenter_target) -SYM_FUNC_END_ALIAS(xen_syscall32_target) +SYM_CODE_END(xen_sysenter_target) +SYM_CODE_END(xen_syscall32_target) #endif /* CONFIG_IA32_EMULATION */ diff --git a/arch/x86/xen/xen-head.S b/arch/x86/xen/xen-head.S index 2d7c8f34f56c..cb6538ae2fe0 100644 --- a/arch/x86/xen/xen-head.S +++ b/arch/x86/xen/xen-head.S @@ -68,8 +68,9 @@ SYM_CODE_END(asm_cpu_bringup_and_idle) .balign PAGE_SIZE SYM_CODE_START(hypercall_page) .rept (PAGE_SIZE / 32) - UNWIND_HINT_EMPTY - .skip 32 + UNWIND_HINT_FUNC + .skip 31, 0x90 + ret .endr #define HYPERCALL(n) \ diff --git a/arch/x86/xen/xen-ops.h b/arch/x86/xen/xen-ops.h index 9546c3384c75..8d7ec49a35fb 100644 --- a/arch/x86/xen/xen-ops.h +++ b/arch/x86/xen/xen-ops.h @@ -131,15 +131,12 @@ static inline void __init xen_efi_init(struct boot_params *boot_params) __visible void xen_irq_enable_direct(void); __visible void xen_irq_disable_direct(void); __visible unsigned long xen_save_fl_direct(void); -__visible void xen_restore_fl_direct(unsigned long); __visible unsigned long xen_read_cr2(void); __visible unsigned long xen_read_cr2_direct(void); /* These are not functions, and cannot be called normally */ __visible void xen_iret(void); -__visible void xen_sysret32(void); -__visible void xen_sysret64(void); extern int xen_panic_handler_init(void); |