diff options
Diffstat (limited to 'arch/x86')
163 files changed, 5630 insertions, 2684 deletions
diff --git a/arch/x86/Kconfig b/arch/x86/Kconfig index 49270655e827..4e001bbbb425 100644 --- a/arch/x86/Kconfig +++ b/arch/x86/Kconfig @@ -119,6 +119,7 @@ config X86 select ARCH_WANT_HUGE_PMD_SHARE select ARCH_WANT_LD_ORPHAN_WARN select ARCH_WANTS_THP_SWAP if X86_64 + select ARCH_HAS_PARANOID_L1D_FLUSH select BUILDTIME_TABLE_SORT select CLKEVT_I8253 select CLOCKSOURCE_VALIDATE_LAST_CYCLE @@ -144,8 +145,6 @@ config X86 select GENERIC_PENDING_IRQ if SMP select GENERIC_PTDUMP select GENERIC_SMP_IDLE_THREAD - select GENERIC_STRNCPY_FROM_USER - select GENERIC_STRNLEN_USER select GENERIC_TIME_VSYSCALL select GENERIC_GETTIMEOFDAY select GENERIC_VDSO_TIME_NS @@ -202,7 +201,6 @@ config X86 select HAVE_FUNCTION_TRACER select HAVE_GCC_PLUGINS 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 @@ -261,6 +259,7 @@ config X86 select STACK_VALIDATION if HAVE_STACK_VALIDATION && (HAVE_STATIC_CALL_INLINE || RETPOLINE) select SYSCTL_EXCEPTION_TRACE select THREAD_INFO_IN_TASK + select TRACE_IRQFLAGS_SUPPORT select USER_STACKTRACE_SUPPORT select VIRT_TO_BUS select HAVE_ARCH_KCSAN if X86_64 @@ -2767,32 +2766,6 @@ config AMD_NB def_bool y depends on CPU_SUP_AMD && PCI -config X86_SYSFB - bool "Mark VGA/VBE/EFI FB as generic system framebuffer" - help - Firmwares often provide initial graphics framebuffers so the BIOS, - bootloader or kernel can show basic video-output during boot for - user-guidance and debugging. Historically, x86 used the VESA BIOS - Extensions and EFI-framebuffers for this, which are mostly limited - to x86. - This option, if enabled, marks VGA/VBE/EFI framebuffers as generic - framebuffers so the new generic system-framebuffer drivers can be - used on x86. If the framebuffer is not compatible with the generic - modes, it is advertised as fallback platform framebuffer so legacy - drivers like efifb, vesafb and uvesafb can pick it up. - If this option is not selected, all system framebuffers are always - marked as fallback platform framebuffers as usual. - - Note: Legacy fbdev drivers, including vesafb, efifb, uvesafb, will - not be able to pick up generic system framebuffers if this option - is selected. You are highly encouraged to enable simplefb as - replacement if you select this option. simplefb can correctly deal - with generic system framebuffers. But you should still keep vesafb - and others enabled as fallback if a system framebuffer is - incompatible with simplefb. - - If unsure, say Y. - endmenu diff --git a/arch/x86/Kconfig.debug b/arch/x86/Kconfig.debug index 80b57e7f4947..d3a6f74a94bd 100644 --- a/arch/x86/Kconfig.debug +++ b/arch/x86/Kconfig.debug @@ -1,8 +1,5 @@ # SPDX-License-Identifier: GPL-2.0 -config TRACE_IRQFLAGS_SUPPORT - def_bool y - config TRACE_IRQFLAGS_NMI_SUPPORT def_bool y diff --git a/arch/x86/Makefile b/arch/x86/Makefile index 307fd0000a83..7488cfbbd2f6 100644 --- a/arch/x86/Makefile +++ b/arch/x86/Makefile @@ -31,8 +31,8 @@ REALMODE_CFLAGS := -m16 -g -Os -DDISABLE_BRANCH_PROFILING \ REALMODE_CFLAGS += -ffreestanding REALMODE_CFLAGS += -fno-stack-protector -REALMODE_CFLAGS += $(call __cc-option, $(CC), $(REALMODE_CFLAGS), -Wno-address-of-packed-member) -REALMODE_CFLAGS += $(call __cc-option, $(CC), $(REALMODE_CFLAGS), $(cc_stack_align4)) +REALMODE_CFLAGS += -Wno-address-of-packed-member +REALMODE_CFLAGS += $(cc_stack_align4) REALMODE_CFLAGS += $(CLANG_FLAGS) export REALMODE_CFLAGS @@ -48,8 +48,7 @@ export BITS # # https://gcc.gnu.org/bugzilla/show_bug.cgi?id=53383 # -KBUILD_CFLAGS += -mno-sse -mno-mmx -mno-sse2 -mno-3dnow -KBUILD_CFLAGS += $(call cc-option,-mno-avx,) +KBUILD_CFLAGS += -mno-sse -mno-mmx -mno-sse2 -mno-3dnow -mno-avx # Intel CET isn't enabled in the kernel KBUILD_CFLAGS += $(call cc-option,-fcf-protection=none) @@ -59,9 +58,8 @@ ifeq ($(CONFIG_X86_32),y) UTS_MACHINE := i386 CHECKFLAGS += -D__i386__ - biarch := $(call cc-option,-m32) - KBUILD_AFLAGS += $(biarch) - KBUILD_CFLAGS += $(biarch) + KBUILD_AFLAGS += -m32 + KBUILD_CFLAGS += -m32 KBUILD_CFLAGS += -msoft-float -mregparm=3 -freg-struct-return @@ -72,10 +70,10 @@ ifeq ($(CONFIG_X86_32),y) # Align the stack to the register width instead of using the default # alignment of 16 bytes. This reduces stack usage and the number of # alignment instructions. - KBUILD_CFLAGS += $(call cc-option,$(cc_stack_align4)) + KBUILD_CFLAGS += $(cc_stack_align4) # CPU-specific tuning. Anything which can be shared with UML should go here. - include arch/x86/Makefile_32.cpu + include $(srctree)/arch/x86/Makefile_32.cpu KBUILD_CFLAGS += $(cflags-y) # temporary until string.h is fixed @@ -93,7 +91,6 @@ else UTS_MACHINE := x86_64 CHECKFLAGS += -D__x86_64__ - biarch := -m64 KBUILD_AFLAGS += -m64 KBUILD_CFLAGS += -m64 @@ -104,7 +101,7 @@ else KBUILD_CFLAGS += $(call cc-option,-falign-loops=1) # Don't autogenerate traditional x87 instructions - KBUILD_CFLAGS += $(call cc-option,-mno-80387) + KBUILD_CFLAGS += -mno-80387 KBUILD_CFLAGS += $(call cc-option,-mno-fp-ret-in-387) # By default gcc and clang use a stack alignment of 16 bytes for x86. @@ -114,20 +111,17 @@ else # default alignment which keep the stack *mis*aligned. # Furthermore an alignment to the register width reduces stack usage # and the number of alignment instructions. - KBUILD_CFLAGS += $(call cc-option,$(cc_stack_align8)) + KBUILD_CFLAGS += $(cc_stack_align8) # Use -mskip-rax-setup if supported. KBUILD_CFLAGS += $(call cc-option,-mskip-rax-setup) # FIXME - should be integrated in Makefile.cpu (Makefile_32.cpu) - cflags-$(CONFIG_MK8) += $(call cc-option,-march=k8) - cflags-$(CONFIG_MPSC) += $(call cc-option,-march=nocona) - - cflags-$(CONFIG_MCORE2) += \ - $(call cc-option,-march=core2,$(call cc-option,-mtune=generic)) - cflags-$(CONFIG_MATOM) += $(call cc-option,-march=atom) \ - $(call cc-option,-mtune=atom,$(call cc-option,-mtune=generic)) - cflags-$(CONFIG_GENERIC_CPU) += $(call cc-option,-mtune=generic) + cflags-$(CONFIG_MK8) += -march=k8 + cflags-$(CONFIG_MPSC) += -march=nocona + cflags-$(CONFIG_MCORE2) += -march=core2 + cflags-$(CONFIG_MATOM) += -march=atom + cflags-$(CONFIG_GENERIC_CPU) += -mtune=generic KBUILD_CFLAGS += $(cflags-y) KBUILD_CFLAGS += -mno-red-zone @@ -158,18 +152,6 @@ export CONFIG_X86_X32_ABI ifdef CONFIG_FUNCTION_GRAPH_TRACER ifndef CONFIG_HAVE_FENTRY ACCUMULATE_OUTGOING_ARGS := 1 - else - ifeq ($(call cc-option-yn, -mfentry), n) - ACCUMULATE_OUTGOING_ARGS := 1 - - # GCC ignores '-maccumulate-outgoing-args' when used with '-Os'. - # If '-Os' is enabled, disable it and print a warning. - ifdef CONFIG_CC_OPTIMIZE_FOR_SIZE - undefine CONFIG_CC_OPTIMIZE_FOR_SIZE - $(warning Disabling CONFIG_CC_OPTIMIZE_FOR_SIZE. Your compiler does not have -mfentry so you cannot optimize for size with CONFIG_FUNCTION_GRAPH_TRACER.) - endif - - endif endif endif @@ -193,7 +175,7 @@ ifdef CONFIG_RETPOLINE # only been fixed starting from gcc stable version 8.4.0 and # onwards, but not for older ones. See gcc bug #86952. ifndef CONFIG_CC_IS_CLANG - KBUILD_CFLAGS += $(call cc-option,-fno-jump-tables) + KBUILD_CFLAGS += -fno-jump-tables endif endif @@ -275,9 +257,10 @@ endif $(BOOT_TARGETS): vmlinux $(Q)$(MAKE) $(build)=$(boot) $@ -PHONY += install bzlilo -install bzlilo: - $(Q)$(MAKE) $(build)=$(boot) $@ +PHONY += install +install: + $(CONFIG_SHELL) $(srctree)/$(boot)/install.sh $(KERNELRELEASE) \ + $(KBUILD_IMAGE) System.map "$(INSTALL_PATH)" PHONY += vdso_install vdso_install: diff --git a/arch/x86/Makefile_32.cpu b/arch/x86/Makefile_32.cpu index cd3056759880..e7355f8b51c2 100644 --- a/arch/x86/Makefile_32.cpu +++ b/arch/x86/Makefile_32.cpu @@ -2,13 +2,7 @@ # CPU tuning section - shared with UML. # Must change only cflags-y (or [yn]), not CFLAGS! That makes a difference for UML. -#-mtune exists since gcc 3.4 -HAS_MTUNE := $(call cc-option-yn, -mtune=i386) -ifeq ($(HAS_MTUNE),y) tune = $(call cc-option,-mtune=$(1),$(2)) -else -tune = $(call cc-option,-mcpu=$(1),$(2)) -endif cflags-$(CONFIG_M486SX) += -march=i486 cflags-$(CONFIG_M486) += -march=i486 diff --git a/arch/x86/boot/Makefile b/arch/x86/boot/Makefile index dfbc26a8e924..b5aecb524a8a 100644 --- a/arch/x86/boot/Makefile +++ b/arch/x86/boot/Makefile @@ -133,7 +133,7 @@ quiet_cmd_genimage = GENIMAGE $3 cmd_genimage = $(BASH) $(srctree)/$(src)/genimage.sh $2 $3 $(obj)/bzImage \ $(obj)/mtools.conf '$(FDARGS)' $(FDINITRD) -PHONY += bzdisk fdimage fdimage144 fdimage288 hdimage isoimage install +PHONY += bzdisk fdimage fdimage144 fdimage288 hdimage isoimage # This requires write access to /dev/fd0 # All images require syslinux to be installed; hdimage also requires @@ -156,8 +156,3 @@ hdimage: $(imgdeps) isoimage: $(imgdeps) $(call cmd,genimage,isoimage,$(obj)/image.iso) @$(kecho) 'Kernel: $(obj)/image.iso is ready' - -install: - $(CONFIG_SHELL) $(srctree)/$(src)/install.sh \ - $(KERNELRELEASE) $(obj)/bzImage \ - System.map "$(INSTALL_PATH)" diff --git a/arch/x86/boot/boot.h b/arch/x86/boot/boot.h index ca866f1cca2e..34c9dbb6a47d 100644 --- a/arch/x86/boot/boot.h +++ b/arch/x86/boot/boot.h @@ -18,7 +18,7 @@ #ifndef __ASSEMBLY__ -#include <stdarg.h> +#include <linux/stdarg.h> #include <linux/types.h> #include <linux/edd.h> #include <asm/setup.h> diff --git a/arch/x86/boot/compressed/efi_thunk_64.S b/arch/x86/boot/compressed/efi_thunk_64.S index 95a223b3e56a..8bb92e9f4e97 100644 --- a/arch/x86/boot/compressed/efi_thunk_64.S +++ b/arch/x86/boot/compressed/efi_thunk_64.S @@ -5,9 +5,8 @@ * Early support for invoking 32-bit EFI services from a 64-bit kernel. * * Because this thunking occurs before ExitBootServices() we have to - * restore the firmware's 32-bit GDT before we make EFI service calls, - * since the firmware's 32-bit IDT is still currently installed and it - * needs to be able to service interrupts. + * restore the firmware's 32-bit GDT and IDT before we make EFI service + * calls. * * On the plus side, we don't have to worry about mangling 64-bit * addresses into 32-bits because we're executing with an identity @@ -39,7 +38,7 @@ SYM_FUNC_START(__efi64_thunk) /* * Convert x86-64 ABI params to i386 ABI */ - subq $32, %rsp + subq $64, %rsp movl %esi, 0x0(%rsp) movl %edx, 0x4(%rsp) movl %ecx, 0x8(%rsp) @@ -49,14 +48,19 @@ SYM_FUNC_START(__efi64_thunk) leaq 0x14(%rsp), %rbx sgdt (%rbx) + addq $16, %rbx + sidt (%rbx) + /* - * Switch to gdt with 32-bit segments. This is the firmware GDT - * that was installed when the kernel started executing. This - * pointer was saved at the EFI stub entry point in head_64.S. + * Switch to IDT and GDT with 32-bit segments. This is the firmware GDT + * and IDT that was installed when the kernel started executing. The + * pointers were saved at the EFI stub entry point in head_64.S. * * Pass the saved DS selector to the 32-bit code, and use far return to * restore the saved CS selector. */ + leaq efi32_boot_idt(%rip), %rax + lidt (%rax) leaq efi32_boot_gdt(%rip), %rax lgdt (%rax) @@ -67,7 +71,7 @@ SYM_FUNC_START(__efi64_thunk) pushq %rax lretq -1: addq $32, %rsp +1: addq $64, %rsp movq %rdi, %rax pop %rbx @@ -128,10 +132,13 @@ SYM_FUNC_START_LOCAL(efi_enter32) /* * Some firmware will return with interrupts enabled. Be sure to - * disable them before we switch GDTs. + * disable them before we switch GDTs and IDTs. */ cli + lidtl (%ebx) + subl $16, %ebx + lgdtl (%ebx) movl %cr4, %eax @@ -166,6 +173,11 @@ SYM_DATA_START(efi32_boot_gdt) .quad 0 SYM_DATA_END(efi32_boot_gdt) +SYM_DATA_START(efi32_boot_idt) + .word 0 + .quad 0 +SYM_DATA_END(efi32_boot_idt) + SYM_DATA_START(efi32_boot_cs) .word 0 SYM_DATA_END(efi32_boot_cs) diff --git a/arch/x86/boot/compressed/head_64.S b/arch/x86/boot/compressed/head_64.S index a2347ded77ea..572c535cf45b 100644 --- a/arch/x86/boot/compressed/head_64.S +++ b/arch/x86/boot/compressed/head_64.S @@ -319,6 +319,9 @@ SYM_INNER_LABEL(efi32_pe_stub_entry, SYM_L_LOCAL) movw %cs, rva(efi32_boot_cs)(%ebp) movw %ds, rva(efi32_boot_ds)(%ebp) + /* Store firmware IDT descriptor */ + sidtl rva(efi32_boot_idt)(%ebp) + /* Disable paging */ movl %cr0, %eax btrl $X86_CR0_PG_BIT, %eax diff --git a/arch/x86/boot/compressed/kaslr.c b/arch/x86/boot/compressed/kaslr.c index e36690778497..67c3208b668a 100644 --- a/arch/x86/boot/compressed/kaslr.c +++ b/arch/x86/boot/compressed/kaslr.c @@ -668,7 +668,7 @@ static bool process_mem_region(struct mem_vector *region, if (slot_area_index == MAX_SLOT_AREA) { debug_putstr("Aborted e820/efi memmap scan when walking immovable regions(slot_areas full)!\n"); - return 1; + return true; } } #endif diff --git a/arch/x86/configs/i386_defconfig b/arch/x86/configs/i386_defconfig index 9c9c4a888b1d..e81885384f60 100644 --- a/arch/x86/configs/i386_defconfig +++ b/arch/x86/configs/i386_defconfig @@ -156,7 +156,6 @@ CONFIG_FORCEDETH=y CONFIG_8139TOO=y # CONFIG_8139TOO_PIO is not set CONFIG_R8169=y -CONFIG_INPUT_POLLDEV=y CONFIG_INPUT_EVDEV=y CONFIG_INPUT_JOYSTICK=y CONFIG_INPUT_TABLET=y diff --git a/arch/x86/configs/x86_64_defconfig b/arch/x86/configs/x86_64_defconfig index b60bd2d86034..e8a7a0af2bda 100644 --- a/arch/x86/configs/x86_64_defconfig +++ b/arch/x86/configs/x86_64_defconfig @@ -148,7 +148,6 @@ CONFIG_SKY2=y CONFIG_FORCEDETH=y CONFIG_8139TOO=y CONFIG_R8169=y -CONFIG_INPUT_POLLDEV=y CONFIG_INPUT_EVDEV=y CONFIG_INPUT_JOYSTICK=y CONFIG_INPUT_TABLET=y diff --git a/arch/x86/crypto/Makefile b/arch/x86/crypto/Makefile index d0959e7b809f..f307c93fc90a 100644 --- a/arch/x86/crypto/Makefile +++ b/arch/x86/crypto/Makefile @@ -88,6 +88,12 @@ nhpoly1305-avx2-y := nh-avx2-x86_64.o nhpoly1305-avx2-glue.o obj-$(CONFIG_CRYPTO_CURVE25519_X86) += curve25519-x86_64.o +obj-$(CONFIG_CRYPTO_SM4_AESNI_AVX_X86_64) += sm4-aesni-avx-x86_64.o +sm4-aesni-avx-x86_64-y := sm4-aesni-avx-asm_64.o sm4_aesni_avx_glue.o + +obj-$(CONFIG_CRYPTO_SM4_AESNI_AVX2_X86_64) += sm4-aesni-avx2-x86_64.o +sm4-aesni-avx2-x86_64-y := sm4-aesni-avx2-asm_64.o sm4_aesni_avx2_glue.o + quiet_cmd_perlasm = PERLASM $@ cmd_perlasm = $(PERL) $< > $@ $(obj)/%.S: $(src)/%.pl FORCE diff --git a/arch/x86/crypto/aesni-intel_glue.c b/arch/x86/crypto/aesni-intel_glue.c index 2144e54a6c89..0fc961bef299 100644 --- a/arch/x86/crypto/aesni-intel_glue.c +++ b/arch/x86/crypto/aesni-intel_glue.c @@ -849,6 +849,8 @@ static int xts_crypt(struct skcipher_request *req, bool encrypt) return -EINVAL; err = skcipher_walk_virt(&walk, req, false); + if (!walk.nbytes) + return err; if (unlikely(tail > 0 && walk.nbytes < walk.total)) { int blocks = DIV_ROUND_UP(req->cryptlen, AES_BLOCK_SIZE) - 2; @@ -862,7 +864,10 @@ static int xts_crypt(struct skcipher_request *req, bool encrypt) skcipher_request_set_crypt(&subreq, req->src, req->dst, blocks * AES_BLOCK_SIZE, req->iv); req = &subreq; + err = skcipher_walk_virt(&walk, req, false); + if (err) + return err; } else { tail = 0; } diff --git a/arch/x86/crypto/sm4-aesni-avx-asm_64.S b/arch/x86/crypto/sm4-aesni-avx-asm_64.S new file mode 100644 index 000000000000..fa2c3f50aecb --- /dev/null +++ b/arch/x86/crypto/sm4-aesni-avx-asm_64.S @@ -0,0 +1,589 @@ +/* SPDX-License-Identifier: GPL-2.0-or-later */ +/* + * SM4 Cipher Algorithm, AES-NI/AVX optimized. + * as specified in + * https://tools.ietf.org/id/draft-ribose-cfrg-sm4-10.html + * + * Copyright (C) 2018 Markku-Juhani O. Saarinen <mjos@iki.fi> + * Copyright (C) 2020 Jussi Kivilinna <jussi.kivilinna@iki.fi> + * Copyright (c) 2021 Tianjia Zhang <tianjia.zhang@linux.alibaba.com> + */ + +/* Based on SM4 AES-NI work by libgcrypt and Markku-Juhani O. Saarinen at: + * https://github.com/mjosaarinen/sm4ni + */ + +#include <linux/linkage.h> +#include <asm/frame.h> + +#define rRIP (%rip) + +#define RX0 %xmm0 +#define RX1 %xmm1 +#define MASK_4BIT %xmm2 +#define RTMP0 %xmm3 +#define RTMP1 %xmm4 +#define RTMP2 %xmm5 +#define RTMP3 %xmm6 +#define RTMP4 %xmm7 + +#define RA0 %xmm8 +#define RA1 %xmm9 +#define RA2 %xmm10 +#define RA3 %xmm11 + +#define RB0 %xmm12 +#define RB1 %xmm13 +#define RB2 %xmm14 +#define RB3 %xmm15 + +#define RNOT %xmm0 +#define RBSWAP %xmm1 + + +/* Transpose four 32-bit words between 128-bit vectors. */ +#define transpose_4x4(x0, x1, x2, x3, t1, t2) \ + vpunpckhdq x1, x0, t2; \ + vpunpckldq x1, x0, x0; \ + \ + vpunpckldq x3, x2, t1; \ + vpunpckhdq x3, x2, x2; \ + \ + vpunpckhqdq t1, x0, x1; \ + vpunpcklqdq t1, x0, x0; \ + \ + vpunpckhqdq x2, t2, x3; \ + vpunpcklqdq x2, t2, x2; + +/* pre-SubByte transform. */ +#define transform_pre(x, lo_t, hi_t, mask4bit, tmp0) \ + vpand x, mask4bit, tmp0; \ + vpandn x, mask4bit, x; \ + vpsrld $4, x, x; \ + \ + vpshufb tmp0, lo_t, tmp0; \ + vpshufb x, hi_t, x; \ + vpxor tmp0, x, x; + +/* post-SubByte transform. Note: x has been XOR'ed with mask4bit by + * 'vaeslastenc' instruction. + */ +#define transform_post(x, lo_t, hi_t, mask4bit, tmp0) \ + vpandn mask4bit, x, tmp0; \ + vpsrld $4, x, x; \ + vpand x, mask4bit, x; \ + \ + vpshufb tmp0, lo_t, tmp0; \ + vpshufb x, hi_t, x; \ + vpxor tmp0, x, x; + + +.section .rodata.cst164, "aM", @progbits, 164 +.align 16 + +/* + * Following four affine transform look-up tables are from work by + * Markku-Juhani O. Saarinen, at https://github.com/mjosaarinen/sm4ni + * + * These allow exposing SM4 S-Box from AES SubByte. + */ + +/* pre-SubByte affine transform, from SM4 field to AES field. */ +.Lpre_tf_lo_s: + .quad 0x9197E2E474720701, 0xC7C1B4B222245157 +.Lpre_tf_hi_s: + .quad 0xE240AB09EB49A200, 0xF052B91BF95BB012 + +/* post-SubByte affine transform, from AES field to SM4 field. */ +.Lpost_tf_lo_s: + .quad 0x5B67F2CEA19D0834, 0xEDD14478172BBE82 +.Lpost_tf_hi_s: + .quad 0xAE7201DD73AFDC00, 0x11CDBE62CC1063BF + +/* For isolating SubBytes from AESENCLAST, inverse shift row */ +.Linv_shift_row: + .byte 0x00, 0x0d, 0x0a, 0x07, 0x04, 0x01, 0x0e, 0x0b + .byte 0x08, 0x05, 0x02, 0x0f, 0x0c, 0x09, 0x06, 0x03 + +/* Inverse shift row + Rotate left by 8 bits on 32-bit words with vpshufb */ +.Linv_shift_row_rol_8: + .byte 0x07, 0x00, 0x0d, 0x0a, 0x0b, 0x04, 0x01, 0x0e + .byte 0x0f, 0x08, 0x05, 0x02, 0x03, 0x0c, 0x09, 0x06 + +/* Inverse shift row + Rotate left by 16 bits on 32-bit words with vpshufb */ +.Linv_shift_row_rol_16: + .byte 0x0a, 0x07, 0x00, 0x0d, 0x0e, 0x0b, 0x04, 0x01 + .byte 0x02, 0x0f, 0x08, 0x05, 0x06, 0x03, 0x0c, 0x09 + +/* Inverse shift row + Rotate left by 24 bits on 32-bit words with vpshufb */ +.Linv_shift_row_rol_24: + .byte 0x0d, 0x0a, 0x07, 0x00, 0x01, 0x0e, 0x0b, 0x04 + .byte 0x05, 0x02, 0x0f, 0x08, 0x09, 0x06, 0x03, 0x0c + +/* 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 input word byte-swap */ +.Lbswap32_mask: + .byte 3, 2, 1, 0, 7, 6, 5, 4, 11, 10, 9, 8, 15, 14, 13, 12 + +.align 4 +/* 4-bit mask */ +.L0f0f0f0f: + .long 0x0f0f0f0f + + +.text +.align 16 + +/* + * void sm4_aesni_avx_crypt4(const u32 *rk, u8 *dst, + * const u8 *src, int nblocks) + */ +.align 8 +SYM_FUNC_START(sm4_aesni_avx_crypt4) + /* input: + * %rdi: round key array, CTX + * %rsi: dst (1..4 blocks) + * %rdx: src (1..4 blocks) + * %rcx: num blocks (1..4) + */ + FRAME_BEGIN + + vmovdqu 0*16(%rdx), RA0; + vmovdqa RA0, RA1; + vmovdqa RA0, RA2; + vmovdqa RA0, RA3; + cmpq $2, %rcx; + jb .Lblk4_load_input_done; + vmovdqu 1*16(%rdx), RA1; + je .Lblk4_load_input_done; + vmovdqu 2*16(%rdx), RA2; + cmpq $3, %rcx; + je .Lblk4_load_input_done; + vmovdqu 3*16(%rdx), RA3; + +.Lblk4_load_input_done: + + vmovdqa .Lbswap32_mask rRIP, RTMP2; + vpshufb RTMP2, RA0, RA0; + vpshufb RTMP2, RA1, RA1; + vpshufb RTMP2, RA2, RA2; + vpshufb RTMP2, RA3, RA3; + + vbroadcastss .L0f0f0f0f rRIP, MASK_4BIT; + vmovdqa .Lpre_tf_lo_s rRIP, RTMP4; + vmovdqa .Lpre_tf_hi_s rRIP, RB0; + vmovdqa .Lpost_tf_lo_s rRIP, RB1; + vmovdqa .Lpost_tf_hi_s rRIP, RB2; + vmovdqa .Linv_shift_row rRIP, RB3; + vmovdqa .Linv_shift_row_rol_8 rRIP, RTMP2; + vmovdqa .Linv_shift_row_rol_16 rRIP, RTMP3; + transpose_4x4(RA0, RA1, RA2, RA3, RTMP0, RTMP1); + +#define ROUND(round, s0, s1, s2, s3) \ + vbroadcastss (4*(round))(%rdi), RX0; \ + vpxor s1, RX0, RX0; \ + vpxor s2, RX0, RX0; \ + vpxor s3, RX0, RX0; /* s1 ^ s2 ^ s3 ^ rk */ \ + \ + /* sbox, non-linear part */ \ + transform_pre(RX0, RTMP4, RB0, MASK_4BIT, RTMP0); \ + vaesenclast MASK_4BIT, RX0, RX0; \ + transform_post(RX0, RB1, RB2, MASK_4BIT, RTMP0); \ + \ + /* linear part */ \ + vpshufb RB3, RX0, RTMP0; \ + vpxor RTMP0, s0, s0; /* s0 ^ x */ \ + vpshufb RTMP2, RX0, RTMP1; \ + vpxor RTMP1, RTMP0, RTMP0; /* x ^ rol(x,8) */ \ + vpshufb RTMP3, RX0, RTMP1; \ + vpxor RTMP1, RTMP0, RTMP0; /* x ^ rol(x,8) ^ rol(x,16) */ \ + vpshufb .Linv_shift_row_rol_24 rRIP, RX0, RTMP1; \ + vpxor RTMP1, s0, s0; /* s0 ^ x ^ rol(x,24) */ \ + vpslld $2, RTMP0, RTMP1; \ + vpsrld $30, RTMP0, RTMP0; \ + vpxor RTMP0, s0, s0; \ + /* s0 ^ x ^ rol(x,2) ^ rol(x,10) ^ rol(x,18) ^ rol(x,24) */ \ + vpxor RTMP1, s0, s0; + + leaq (32*4)(%rdi), %rax; +.align 16 +.Lroundloop_blk4: + ROUND(0, RA0, RA1, RA2, RA3); + ROUND(1, RA1, RA2, RA3, RA0); + ROUND(2, RA2, RA3, RA0, RA1); + ROUND(3, RA3, RA0, RA1, RA2); + leaq (4*4)(%rdi), %rdi; + cmpq %rax, %rdi; + jne .Lroundloop_blk4; + +#undef ROUND + + vmovdqa .Lbswap128_mask rRIP, RTMP2; + + transpose_4x4(RA0, RA1, RA2, RA3, RTMP0, RTMP1); + vpshufb RTMP2, RA0, RA0; + vpshufb RTMP2, RA1, RA1; + vpshufb RTMP2, RA2, RA2; + vpshufb RTMP2, RA3, RA3; + + vmovdqu RA0, 0*16(%rsi); + cmpq $2, %rcx; + jb .Lblk4_store_output_done; + vmovdqu RA1, 1*16(%rsi); + je .Lblk4_store_output_done; + vmovdqu RA2, 2*16(%rsi); + cmpq $3, %rcx; + je .Lblk4_store_output_done; + vmovdqu RA3, 3*16(%rsi); + +.Lblk4_store_output_done: + vzeroall; + FRAME_END + ret; +SYM_FUNC_END(sm4_aesni_avx_crypt4) + +.align 8 +SYM_FUNC_START_LOCAL(__sm4_crypt_blk8) + /* input: + * %rdi: round key array, CTX + * RA0, RA1, RA2, RA3, RB0, RB1, RB2, RB3: eight parallel + * plaintext blocks + * output: + * RA0, RA1, RA2, RA3, RB0, RB1, RB2, RB3: eight parallel + * ciphertext blocks + */ + FRAME_BEGIN + + vmovdqa .Lbswap32_mask rRIP, RTMP2; + vpshufb RTMP2, RA0, RA0; + vpshufb RTMP2, RA1, RA1; + vpshufb RTMP2, RA2, RA2; + vpshufb RTMP2, RA3, RA3; + vpshufb RTMP2, RB0, RB0; + vpshufb RTMP2, RB1, RB1; + vpshufb RTMP2, RB2, RB2; + vpshufb RTMP2, RB3, RB3; + + vbroadcastss .L0f0f0f0f rRIP, MASK_4BIT; + transpose_4x4(RA0, RA1, RA2, RA3, RTMP0, RTMP1); + transpose_4x4(RB0, RB1, RB2, RB3, RTMP0, RTMP1); + +#define ROUND(round, s0, s1, s2, s3, r0, r1, r2, r3) \ + vbroadcastss (4*(round))(%rdi), RX0; \ + vmovdqa .Lpre_tf_lo_s rRIP, RTMP4; \ + vmovdqa .Lpre_tf_hi_s rRIP, RTMP1; \ + vmovdqa RX0, RX1; \ + vpxor s1, RX0, RX0; \ + vpxor s2, RX0, RX0; \ + vpxor s3, RX0, RX0; /* s1 ^ s2 ^ s3 ^ rk */ \ + vmovdqa .Lpost_tf_lo_s rRIP, RTMP2; \ + vmovdqa .Lpost_tf_hi_s rRIP, RTMP3; \ + vpxor r1, RX1, RX1; \ + vpxor r2, RX1, RX1; \ + vpxor r3, RX1, RX1; /* r1 ^ r2 ^ r3 ^ rk */ \ + \ + /* sbox, non-linear part */ \ + transform_pre(RX0, RTMP4, RTMP1, MASK_4BIT, RTMP0); \ + transform_pre(RX1, RTMP4, RTMP1, MASK_4BIT, RTMP0); \ + vmovdqa .Linv_shift_row rRIP, RTMP4; \ + vaesenclast MASK_4BIT, RX0, RX0; \ + vaesenclast MASK_4BIT, RX1, RX1; \ + transform_post(RX0, RTMP2, RTMP3, MASK_4BIT, RTMP0); \ + transform_post(RX1, RTMP2, RTMP3, MASK_4BIT, RTMP0); \ + \ + /* linear part */ \ + vpshufb RTMP4, RX0, RTMP0; \ + vpxor RTMP0, s0, s0; /* s0 ^ x */ \ + vpshufb RTMP4, RX1, RTMP2; \ + vmovdqa .Linv_shift_row_rol_8 rRIP, RTMP4; \ + vpxor RTMP2, r0, r0; /* r0 ^ x */ \ + vpshufb RTMP4, RX0, RTMP1; \ + vpxor RTMP1, RTMP0, RTMP0; /* x ^ rol(x,8) */ \ + vpshufb RTMP4, RX1, RTMP3; \ + vmovdqa .Linv_shift_row_rol_16 rRIP, RTMP4; \ + vpxor RTMP3, RTMP2, RTMP2; /* x ^ rol(x,8) */ \ + vpshufb RTMP4, RX0, RTMP1; \ + vpxor RTMP1, RTMP0, RTMP0; /* x ^ rol(x,8) ^ rol(x,16) */ \ + vpshufb RTMP4, RX1, RTMP3; \ + vmovdqa .Linv_shift_row_rol_24 rRIP, RTMP4; \ + vpxor RTMP3, RTMP2, RTMP2; /* x ^ rol(x,8) ^ rol(x,16) */ \ + vpshufb RTMP4, RX0, RTMP1; \ + vpxor RTMP1, s0, s0; /* s0 ^ x ^ rol(x,24) */ \ + /* s0 ^ x ^ rol(x,2) ^ rol(x,10) ^ rol(x,18) ^ rol(x,24) */ \ + vpslld $2, RTMP0, RTMP1; \ + vpsrld $30, RTMP0, RTMP0; \ + vpxor RTMP0, s0, s0; \ + vpxor RTMP1, s0, s0; \ + vpshufb RTMP4, RX1, RTMP3; \ + vpxor RTMP3, r0, r0; /* r0 ^ x ^ rol(x,24) */ \ + /* r0 ^ x ^ rol(x,2) ^ rol(x,10) ^ rol(x,18) ^ rol(x,24) */ \ + vpslld $2, RTMP2, RTMP3; \ + vpsrld $30, RTMP2, RTMP2; \ + vpxor RTMP2, r0, r0; \ + vpxor RTMP3, r0, r0; + + leaq (32*4)(%rdi), %rax; +.align 16 +.Lroundloop_blk8: + ROUND(0, RA0, RA1, RA2, RA3, RB0, RB1, RB2, RB3); + ROUND(1, RA1, RA2, RA3, RA0, RB1, RB2, RB3, RB0); + ROUND(2, RA2, RA3, RA0, RA1, RB2, RB3, RB0, RB1); + ROUND(3, RA3, RA0, RA1, RA2, RB3, RB0, RB1, RB2); + leaq (4*4)(%rdi), %rdi; + cmpq %rax, %rdi; + jne .Lroundloop_blk8; + +#undef ROUND + + vmovdqa .Lbswap128_mask rRIP, RTMP2; + + transpose_4x4(RA0, RA1, RA2, RA3, RTMP0, RTMP1); + transpose_4x4(RB0, RB1, RB2, RB3, RTMP0, RTMP1); + vpshufb RTMP2, RA0, RA0; + vpshufb RTMP2, RA1, RA1; + vpshufb RTMP2, RA2, RA2; + vpshufb RTMP2, RA3, RA3; + vpshufb RTMP2, RB0, RB0; + vpshufb RTMP2, RB1, RB1; + vpshufb RTMP2, RB2, RB2; + vpshufb RTMP2, RB3, RB3; + + FRAME_END + ret; +SYM_FUNC_END(__sm4_crypt_blk8) + +/* + * void sm4_aesni_avx_crypt8(const u32 *rk, u8 *dst, + * const u8 *src, int nblocks) + */ +.align 8 +SYM_FUNC_START(sm4_aesni_avx_crypt8) + /* input: + * %rdi: round key array, CTX + * %rsi: dst (1..8 blocks) + * %rdx: src (1..8 blocks) + * %rcx: num blocks (1..8) + */ + FRAME_BEGIN + + cmpq $5, %rcx; + jb sm4_aesni_avx_crypt4; + vmovdqu (0 * 16)(%rdx), RA0; + vmovdqu (1 * 16)(%rdx), RA1; + vmovdqu (2 * 16)(%rdx), RA2; + vmovdqu (3 * 16)(%rdx), RA3; + vmovdqu (4 * 16)(%rdx), RB0; + vmovdqa RB0, RB1; + vmovdqa RB0, RB2; + vmovdqa RB0, RB3; + je .Lblk8_load_input_done; + vmovdqu (5 * 16)(%rdx), RB1; + cmpq $7, %rcx; + jb .Lblk8_load_input_done; + vmovdqu (6 * 16)(%rdx), RB2; + je .Lblk8_load_input_done; + vmovdqu (7 * 16)(%rdx), RB3; + +.Lblk8_load_input_done: + call __sm4_crypt_blk8; + + cmpq $6, %rcx; + vmovdqu RA0, (0 * 16)(%rsi); + vmovdqu RA1, (1 * 16)(%rsi); + vmovdqu RA2, (2 * 16)(%rsi); + vmovdqu RA3, (3 * 16)(%rsi); + vmovdqu RB0, (4 * 16)(%rsi); + jb .Lblk8_store_output_done; + vmovdqu RB1, (5 * 16)(%rsi); + je .Lblk8_store_output_done; + vmovdqu RB2, (6 * 16)(%rsi); + cmpq $7, %rcx; + je .Lblk8_store_output_done; + vmovdqu RB3, (7 * 16)(%rsi); + +.Lblk8_store_output_done: + vzeroall; + FRAME_END + ret; +SYM_FUNC_END(sm4_aesni_avx_crypt8) + +/* + * void sm4_aesni_avx_ctr_enc_blk8(const u32 *rk, u8 *dst, + * const u8 *src, u8 *iv) + */ +.align 8 +SYM_FUNC_START(sm4_aesni_avx_ctr_enc_blk8) + /* input: + * %rdi: round key array, CTX + * %rsi: dst (8 blocks) + * %rdx: src (8 blocks) + * %rcx: iv (big endian, 128bit) + */ + FRAME_BEGIN + + /* load IV and byteswap */ + vmovdqu (%rcx), RA0; + + vmovdqa .Lbswap128_mask rRIP, RBSWAP; + vpshufb RBSWAP, RA0, RTMP0; /* be => le */ + + vpcmpeqd RNOT, RNOT, RNOT; + vpsrldq $8, RNOT, RNOT; /* low: -1, high: 0 */ + +#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; + + /* construct IVs */ + inc_le128(RTMP0, RNOT, RTMP2); /* +1 */ + vpshufb RBSWAP, RTMP0, RA1; + inc_le128(RTMP0, RNOT, RTMP2); /* +2 */ + vpshufb RBSWAP, RTMP0, RA2; + inc_le128(RTMP0, RNOT, RTMP2); /* +3 */ + vpshufb RBSWAP, RTMP0, RA3; + inc_le128(RTMP0, RNOT, RTMP2); /* +4 */ + vpshufb RBSWAP, RTMP0, RB0; + inc_le128(RTMP0, RNOT, RTMP2); /* +5 */ + vpshufb RBSWAP, RTMP0, RB1; + inc_le128(RTMP0, RNOT, RTMP2); /* +6 */ + vpshufb RBSWAP, RTMP0, RB2; + inc_le128(RTMP0, RNOT, RTMP2); /* +7 */ + vpshufb RBSWAP, RTMP0, RB3; + inc_le128(RTMP0, RNOT, RTMP2); /* +8 */ + vpshufb RBSWAP, RTMP0, RTMP1; + + /* store new IV */ + vmovdqu RTMP1, (%rcx); + + call __sm4_crypt_blk8; + + vpxor (0 * 16)(%rdx), RA0, RA0; + vpxor (1 * 16)(%rdx), RA1, RA1; + vpxor (2 * 16)(%rdx), RA2, RA2; + vpxor (3 * 16)(%rdx), RA3, RA3; + vpxor (4 * 16)(%rdx), RB0, RB0; + vpxor (5 * 16)(%rdx), RB1, RB1; + vpxor (6 * 16)(%rdx), RB2, RB2; + vpxor (7 * 16)(%rdx), RB3, RB3; + + vmovdqu RA0, (0 * 16)(%rsi); + vmovdqu RA1, (1 * 16)(%rsi); + vmovdqu RA2, (2 * 16)(%rsi); + vmovdqu RA3, (3 * 16)(%rsi); + vmovdqu RB0, (4 * 16)(%rsi); + vmovdqu RB1, (5 * 16)(%rsi); + vmovdqu RB2, (6 * 16)(%rsi); + vmovdqu RB3, (7 * 16)(%rsi); + + vzeroall; + FRAME_END + ret; +SYM_FUNC_END(sm4_aesni_avx_ctr_enc_blk8) + +/* + * void sm4_aesni_avx_cbc_dec_blk8(const u32 *rk, u8 *dst, + * const u8 *src, u8 *iv) + */ +.align 8 +SYM_FUNC_START(sm4_aesni_avx_cbc_dec_blk8) + /* input: + * %rdi: round key array, CTX + * %rsi: dst (8 blocks) + * %rdx: src (8 blocks) + * %rcx: iv + */ + FRAME_BEGIN + + vmovdqu (0 * 16)(%rdx), RA0; + vmovdqu (1 * 16)(%rdx), RA1; + vmovdqu (2 * 16)(%rdx), RA2; + vmovdqu (3 * 16)(%rdx), RA3; + vmovdqu (4 * 16)(%rdx), RB0; + vmovdqu (5 * 16)(%rdx), RB1; + vmovdqu (6 * 16)(%rdx), RB2; + vmovdqu (7 * 16)(%rdx), RB3; + + call __sm4_crypt_blk8; + + vmovdqu (7 * 16)(%rdx), RNOT; + vpxor (%rcx), RA0, RA0; + vpxor (0 * 16)(%rdx), RA1, RA1; + vpxor (1 * 16)(%rdx), RA2, RA2; + vpxor (2 * 16)(%rdx), RA3, RA3; + vpxor (3 * 16)(%rdx), RB0, RB0; + vpxor (4 * 16)(%rdx), RB1, RB1; + vpxor (5 * 16)(%rdx), RB2, RB2; + vpxor (6 * 16)(%rdx), RB3, RB3; + vmovdqu RNOT, (%rcx); /* store new IV */ + + vmovdqu RA0, (0 * 16)(%rsi); + vmovdqu RA1, (1 * 16)(%rsi); + vmovdqu RA2, (2 * 16)(%rsi); + vmovdqu RA3, (3 * 16)(%rsi); + vmovdqu RB0, (4 * 16)(%rsi); + vmovdqu RB1, (5 * 16)(%rsi); + vmovdqu RB2, (6 * 16)(%rsi); + vmovdqu RB3, (7 * 16)(%rsi); + + vzeroall; + FRAME_END + ret; +SYM_FUNC_END(sm4_aesni_avx_cbc_dec_blk8) + +/* + * void sm4_aesni_avx_cfb_dec_blk8(const u32 *rk, u8 *dst, + * const u8 *src, u8 *iv) + */ +.align 8 +SYM_FUNC_START(sm4_aesni_avx_cfb_dec_blk8) + /* input: + * %rdi: round key array, CTX + * %rsi: dst (8 blocks) + * %rdx: src (8 blocks) + * %rcx: iv + */ + FRAME_BEGIN + + /* Load input */ + vmovdqu (%rcx), RA0; + vmovdqu 0 * 16(%rdx), RA1; + vmovdqu 1 * 16(%rdx), RA2; + vmovdqu 2 * 16(%rdx), RA3; + vmovdqu 3 * 16(%rdx), RB0; + vmovdqu 4 * 16(%rdx), RB1; + vmovdqu 5 * 16(%rdx), RB2; + vmovdqu 6 * 16(%rdx), RB3; + + /* Update IV */ + vmovdqu 7 * 16(%rdx), RNOT; + vmovdqu RNOT, (%rcx); + + call __sm4_crypt_blk8; + + vpxor (0 * 16)(%rdx), RA0, RA0; + vpxor (1 * 16)(%rdx), RA1, RA1; + vpxor (2 * 16)(%rdx), RA2, RA2; + vpxor (3 * 16)(%rdx), RA3, RA3; + vpxor (4 * 16)(%rdx), RB0, RB0; + vpxor (5 * 16)(%rdx), RB1, RB1; + vpxor (6 * 16)(%rdx), RB2, RB2; + vpxor (7 * 16)(%rdx), RB3, RB3; + + vmovdqu RA0, (0 * 16)(%rsi); + vmovdqu RA1, (1 * 16)(%rsi); + vmovdqu RA2, (2 * 16)(%rsi); + vmovdqu RA3, (3 * 16)(%rsi); + vmovdqu RB0, (4 * 16)(%rsi); + vmovdqu RB1, (5 * 16)(%rsi); + vmovdqu RB2, (6 * 16)(%rsi); + vmovdqu RB3, (7 * 16)(%rsi); + + vzeroall; + FRAME_END + ret; +SYM_FUNC_END(sm4_aesni_avx_cfb_dec_blk8) diff --git a/arch/x86/crypto/sm4-aesni-avx2-asm_64.S b/arch/x86/crypto/sm4-aesni-avx2-asm_64.S new file mode 100644 index 000000000000..d2ffd7f76ee2 --- /dev/null +++ b/arch/x86/crypto/sm4-aesni-avx2-asm_64.S @@ -0,0 +1,497 @@ +// SPDX-License-Identifier: GPL-2.0-or-later +/* + * SM4 Cipher Algorithm, AES-NI/AVX2 optimized. + * as specified in + * https://tools.ietf.org/id/draft-ribose-cfrg-sm4-10.html + * + * Copyright (C) 2018 Markku-Juhani O. Saarinen <mjos@iki.fi> + * Copyright (C) 2020 Jussi Kivilinna <jussi.kivilinna@iki.fi> + * Copyright (c) 2021 Tianjia Zhang <tianjia.zhang@linux.alibaba.com> + */ + +/* Based on SM4 AES-NI work by libgcrypt and Markku-Juhani O. Saarinen at: + * https://github.com/mjosaarinen/sm4ni + */ + +#include <linux/linkage.h> +#include <asm/frame.h> + +#define rRIP (%rip) + +/* vector registers */ +#define RX0 %ymm0 +#define RX1 %ymm1 +#define MASK_4BIT %ymm2 +#define RTMP0 %ymm3 +#define RTMP1 %ymm4 +#define RTMP2 %ymm5 +#define RTMP3 %ymm6 +#define RTMP4 %ymm7 + +#define RA0 %ymm8 +#define RA1 %ymm9 +#define RA2 %ymm10 +#define RA3 %ymm11 + +#define RB0 %ymm12 +#define RB1 %ymm13 +#define RB2 %ymm14 +#define RB3 %ymm15 + +#define RNOT %ymm0 +#define RBSWAP %ymm1 + +#define RX0x %xmm0 +#define RX1x %xmm1 +#define MASK_4BITx %xmm2 + +#define RNOTx %xmm0 +#define RBSWAPx %xmm1 + +#define RTMP0x %xmm3 +#define RTMP1x %xmm4 +#define RTMP2x %xmm5 +#define RTMP3x %xmm6 +#define RTMP4x %xmm7 + + +/* helper macros */ + +/* Transpose four 32-bit words between 128-bit vector lanes. */ +#define transpose_4x4(x0, x1, x2, x3, t1, t2) \ + vpunpckhdq x1, x0, t2; \ + vpunpckldq x1, x0, x0; \ + \ + vpunpckldq x3, x2, t1; \ + vpunpckhdq x3, x2, x2; \ + \ + vpunpckhqdq t1, x0, x1; \ + vpunpcklqdq t1, x0, x0; \ + \ + vpunpckhqdq x2, t2, x3; \ + vpunpcklqdq x2, t2, x2; + +/* post-SubByte transform. */ +#define transform_pre(x, lo_t, hi_t, mask4bit, tmp0) \ + vpand x, mask4bit, tmp0; \ + vpandn x, mask4bit, x; \ + vpsrld $4, x, x; \ + \ + vpshufb tmp0, lo_t, tmp0; \ + vpshufb x, hi_t, x; \ + vpxor tmp0, x, x; + +/* post-SubByte transform. Note: x has been XOR'ed with mask4bit by + * 'vaeslastenc' instruction. */ +#define transform_post(x, lo_t, hi_t, mask4bit, tmp0) \ + vpandn mask4bit, x, tmp0; \ + vpsrld $4, x, x; \ + vpand x, mask4bit, x; \ + \ + vpshufb tmp0, lo_t, tmp0; \ + vpshufb x, hi_t, x; \ + vpxor tmp0, x, x; + + +.section .rodata.cst164, "aM", @progbits, 164 +.align 16 + +/* + * Following four affine transform look-up tables are from work by + * Markku-Juhani O. Saarinen, at https://github.com/mjosaarinen/sm4ni + * + * These allow exposing SM4 S-Box from AES SubByte. + */ + +/* pre-SubByte affine transform, from SM4 field to AES field. */ +.Lpre_tf_lo_s: + .quad 0x9197E2E474720701, 0xC7C1B4B222245157 +.Lpre_tf_hi_s: + .quad 0xE240AB09EB49A200, 0xF052B91BF95BB012 + +/* post-SubByte affine transform, from AES field to SM4 field. */ +.Lpost_tf_lo_s: + .quad 0x5B67F2CEA19D0834, 0xEDD14478172BBE82 +.Lpost_tf_hi_s: + .quad 0xAE7201DD73AFDC00, 0x11CDBE62CC1063BF + +/* For isolating SubBytes from AESENCLAST, inverse shift row */ +.Linv_shift_row: + .byte 0x00, 0x0d, 0x0a, 0x07, 0x04, 0x01, 0x0e, 0x0b + .byte 0x08, 0x05, 0x02, 0x0f, 0x0c, 0x09, 0x06, 0x03 + +/* Inverse shift row + Rotate left by 8 bits on 32-bit words with vpshufb */ +.Linv_shift_row_rol_8: + .byte 0x07, 0x00, 0x0d, 0x0a, 0x0b, 0x04, 0x01, 0x0e + .byte 0x0f, 0x08, 0x05, 0x02, 0x03, 0x0c, 0x09, 0x06 + +/* Inverse shift row + Rotate left by 16 bits on 32-bit words with vpshufb */ +.Linv_shift_row_rol_16: + .byte 0x0a, 0x07, 0x00, 0x0d, 0x0e, 0x0b, 0x04, 0x01 + .byte 0x02, 0x0f, 0x08, 0x05, 0x06, 0x03, 0x0c, 0x09 + +/* Inverse shift row + Rotate left by 24 bits on 32-bit words with vpshufb */ +.Linv_shift_row_rol_24: + .byte 0x0d, 0x0a, 0x07, 0x00, 0x01, 0x0e, 0x0b, 0x04 + .byte 0x05, 0x02, 0x0f, 0x08, 0x09, 0x06, 0x03, 0x0c + +/* 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 input word byte-swap */ +.Lbswap32_mask: + .byte 3, 2, 1, 0, 7, 6, 5, 4, 11, 10, 9, 8, 15, 14, 13, 12 + +.align 4 +/* 4-bit mask */ +.L0f0f0f0f: + .long 0x0f0f0f0f + +.text +.align 16 + +.align 8 +SYM_FUNC_START_LOCAL(__sm4_crypt_blk16) + /* input: + * %rdi: round key array, CTX + * RA0, RA1, RA2, RA3, RB0, RB1, RB2, RB3: sixteen parallel + * plaintext blocks + * output: + * RA0, RA1, RA2, RA3, RB0, RB1, RB2, RB3: sixteen parallel + * ciphertext blocks + */ + FRAME_BEGIN + + vbroadcasti128 .Lbswap32_mask rRIP, RTMP2; + vpshufb RTMP2, RA0, RA0; + vpshufb RTMP2, RA1, RA1; + vpshufb RTMP2, RA2, RA2; + vpshufb RTMP2, RA3, RA3; + vpshufb RTMP2, RB0, RB0; + vpshufb RTMP2, RB1, RB1; + vpshufb RTMP2, RB2, RB2; + vpshufb RTMP2, RB3, RB3; + + vpbroadcastd .L0f0f0f0f rRIP, MASK_4BIT; + transpose_4x4(RA0, RA1, RA2, RA3, RTMP0, RTMP1); + transpose_4x4(RB0, RB1, RB2, RB3, RTMP0, RTMP1); + +#define ROUND(round, s0, s1, s2, s3, r0, r1, r2, r3) \ + vpbroadcastd (4*(round))(%rdi), RX0; \ + vbroadcasti128 .Lpre_tf_lo_s rRIP, RTMP4; \ + vbroadcasti128 .Lpre_tf_hi_s rRIP, RTMP1; \ + vmovdqa RX0, RX1; \ + vpxor s1, RX0, RX0; \ + vpxor s2, RX0, RX0; \ + vpxor s3, RX0, RX0; /* s1 ^ s2 ^ s3 ^ rk */ \ + vbroadcasti128 .Lpost_tf_lo_s rRIP, RTMP2; \ + vbroadcasti128 .Lpost_tf_hi_s rRIP, RTMP3; \ + vpxor r1, RX1, RX1; \ + vpxor r2, RX1, RX1; \ + vpxor r3, RX1, RX1; /* r1 ^ r2 ^ r3 ^ rk */ \ + \ + /* sbox, non-linear part */ \ + transform_pre(RX0, RTMP4, RTMP1, MASK_4BIT, RTMP0); \ + transform_pre(RX1, RTMP4, RTMP1, MASK_4BIT, RTMP0); \ + vextracti128 $1, RX0, RTMP4x; \ + vextracti128 $1, RX1, RTMP0x; \ + vaesenclast MASK_4BITx, RX0x, RX0x; \ + vaesenclast MASK_4BITx, RTMP4x, RTMP4x; \ + vaesenclast MASK_4BITx, RX1x, RX1x; \ + vaesenclast MASK_4BITx, RTMP0x, RTMP0x; \ + vinserti128 $1, RTMP4x, RX0, RX0; \ + vbroadcasti128 .Linv_shift_row rRIP, RTMP4; \ + vinserti128 $1, RTMP0x, RX1, RX1; \ + transform_post(RX0, RTMP2, RTMP3, MASK_4BIT, RTMP0); \ + transform_post(RX1, RTMP2, RTMP3, MASK_4BIT, RTMP0); \ + \ + /* linear part */ \ + vpshufb RTMP4, RX0, RTMP0; \ + vpxor RTMP0, s0, s0; /* s0 ^ x */ \ + vpshufb RTMP4, RX1, RTMP2; \ + vbroadcasti128 .Linv_shift_row_rol_8 rRIP, RTMP4; \ + vpxor RTMP2, r0, r0; /* r0 ^ x */ \ + vpshufb RTMP4, RX0, RTMP1; \ + vpxor RTMP1, RTMP0, RTMP0; /* x ^ rol(x,8) */ \ + vpshufb RTMP4, RX1, RTMP3; \ + vbroadcasti128 .Linv_shift_row_rol_16 rRIP, RTMP4; \ + vpxor RTMP3, RTMP2, RTMP2; /* x ^ rol(x,8) */ \ + vpshufb RTMP4, RX0, RTMP1; \ + vpxor RTMP1, RTMP0, RTMP0; /* x ^ rol(x,8) ^ rol(x,16) */ \ + vpshufb RTMP4, RX1, RTMP3; \ + vbroadcasti128 .Linv_shift_row_rol_24 rRIP, RTMP4; \ + vpxor RTMP3, RTMP2, RTMP2; /* x ^ rol(x,8) ^ rol(x,16) */ \ + vpshufb RTMP4, RX0, RTMP1; \ + vpxor RTMP1, s0, s0; /* s0 ^ x ^ rol(x,24) */ \ + vpslld $2, RTMP0, RTMP1; \ + vpsrld $30, RTMP0, RTMP0; \ + vpxor RTMP0, s0, s0; \ + /* s0 ^ x ^ rol(x,2) ^ rol(x,10) ^ rol(x,18) ^ rol(x,24) */ \ + vpxor RTMP1, s0, s0; \ + vpshufb RTMP4, RX1, RTMP3; \ + vpxor RTMP3, r0, r0; /* r0 ^ x ^ rol(x,24) */ \ + vpslld $2, RTMP2, RTMP3; \ + vpsrld $30, RTMP2, RTMP2; \ + vpxor RTMP2, r0, r0; \ + /* r0 ^ x ^ rol(x,2) ^ rol(x,10) ^ rol(x,18) ^ rol(x,24) */ \ + vpxor RTMP3, r0, r0; + + leaq (32*4)(%rdi), %rax; +.align 16 +.Lroundloop_blk8: + ROUND(0, RA0, RA1, RA2, RA3, RB0, RB1, RB2, RB3); + ROUND(1, RA1, RA2, RA3, RA0, RB1, RB2, RB3, RB0); + ROUND(2, RA2, RA3, RA0, RA1, RB2, RB3, RB0, RB1); + ROUND(3, RA3, RA0, RA1, RA2, RB3, RB0, RB1, RB2); + leaq (4*4)(%rdi), %rdi; + cmpq %rax, %rdi; + jne .Lroundloop_blk8; + +#undef ROUND + + vbroadcasti128 .Lbswap128_mask rRIP, RTMP2; + + transpose_4x4(RA0, RA1, RA2, RA3, RTMP0, RTMP1); + transpose_4x4(RB0, RB1, RB2, RB3, RTMP0, RTMP1); + vpshufb RTMP2, RA0, RA0; + vpshufb RTMP2, RA1, RA1; + vpshufb RTMP2, RA2, RA2; + vpshufb RTMP2, RA3, RA3; + vpshufb RTMP2, RB0, RB0; + vpshufb RTMP2, RB1, RB1; + vpshufb RTMP2, RB2, RB2; + vpshufb RTMP2, RB3, RB3; + + FRAME_END + ret; +SYM_FUNC_END(__sm4_crypt_blk16) + +#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; + +/* + * void sm4_aesni_avx2_ctr_enc_blk16(const u32 *rk, u8 *dst, + * const u8 *src, u8 *iv) + */ +.align 8 +SYM_FUNC_START(sm4_aesni_avx2_ctr_enc_blk16) + /* input: + * %rdi: round key array, CTX + * %rsi: dst (16 blocks) + * %rdx: src (16 blocks) + * %rcx: iv (big endian, 128bit) + */ + FRAME_BEGIN + + movq 8(%rcx), %rax; + bswapq %rax; + + vzeroupper; + + vbroadcasti128 .Lbswap128_mask rRIP, RTMP3; + vpcmpeqd RNOT, RNOT, RNOT; + vpsrldq $8, RNOT, RNOT; /* ab: -1:0 ; cd: -1:0 */ + vpaddq RNOT, RNOT, RTMP2; /* ab: -2:0 ; cd: -2:0 */ + + /* load IV and byteswap */ + vmovdqu (%rcx), RTMP4x; + vpshufb RTMP3x, RTMP4x, RTMP4x; + vmovdqa RTMP4x, RTMP0x; + inc_le128(RTMP4x, RNOTx, RTMP1x); + vinserti128 $1, RTMP4x, RTMP0, RTMP0; + vpshufb RTMP3, RTMP0, RA0; /* +1 ; +0 */ + + /* check need for handling 64-bit overflow and carry */ + cmpq $(0xffffffffffffffff - 16), %rax; + ja .Lhandle_ctr_carry; + + /* construct IVs */ + vpsubq RTMP2, RTMP0, RTMP0; /* +3 ; +2 */ + vpshufb RTMP3, RTMP0, RA1; + vpsubq RTMP2, RTMP0, RTMP0; /* +5 ; +4 */ + vpshufb RTMP3, RTMP0, RA2; + vpsubq RTMP2, RTMP0, RTMP0; /* +7 ; +6 */ + vpshufb RTMP3, RTMP0, RA3; + vpsubq RTMP2, RTMP0, RTMP0; /* +9 ; +8 */ + vpshufb RTMP3, RTMP0, RB0; + vpsubq RTMP2, RTMP0, RTMP0; /* +11 ; +10 */ + vpshufb RTMP3, RTMP0, RB1; + vpsubq RTMP2, RTMP0, RTMP0; /* +13 ; +12 */ + vpshufb RTMP3, RTMP0, RB2; + vpsubq RTMP2, RTMP0, RTMP0; /* +15 ; +14 */ + vpshufb RTMP3, RTMP0, RB3; + vpsubq RTMP2, RTMP0, RTMP0; /* +16 */ + vpshufb RTMP3x, RTMP0x, RTMP0x; + + jmp .Lctr_carry_done; + +.Lhandle_ctr_carry: + /* construct IVs */ + inc_le128(RTMP0, RNOT, RTMP1); + inc_le128(RTMP0, RNOT, RTMP1); + vpshufb RTMP3, RTMP0, RA1; /* +3 ; +2 */ + inc_le128(RTMP0, RNOT, RTMP1); + inc_le128(RTMP0, RNOT, RTMP1); + vpshufb RTMP3, RTMP0, RA2; /* +5 ; +4 */ + inc_le128(RTMP0, RNOT, RTMP1); + inc_le128(RTMP0, RNOT, RTMP1); + vpshufb RTMP3, RTMP0, RA3; /* +7 ; +6 */ + inc_le128(RTMP0, RNOT, RTMP1); + inc_le128(RTMP0, RNOT, RTMP1); + vpshufb RTMP3, RTMP0, RB0; /* +9 ; +8 */ + inc_le128(RTMP0, RNOT, RTMP1); + inc_le128(RTMP0, RNOT, RTMP1); + vpshufb RTMP3, RTMP0, RB1; /* +11 ; +10 */ + inc_le128(RTMP0, RNOT, RTMP1); + inc_le128(RTMP0, RNOT, RTMP1); + vpshufb RTMP3, RTMP0, RB2; /* +13 ; +12 */ + inc_le128(RTMP0, RNOT, RTMP1); + inc_le128(RTMP0, RNOT, RTMP1); + vpshufb RTMP3, RTMP0, RB3; /* +15 ; +14 */ + inc_le128(RTMP0, RNOT, RTMP1); + vextracti128 $1, RTMP0, RTMP0x; + vpshufb RTMP3x, RTMP0x, RTMP0x; /* +16 */ + +.align 4 +.Lctr_carry_done: + /* store new IV */ + vmovdqu RTMP0x, (%rcx); + + call __sm4_crypt_blk16; + + vpxor (0 * 32)(%rdx), RA0, RA0; + vpxor (1 * 32)(%rdx), RA1, RA1; + vpxor (2 * 32)(%rdx), RA2, RA2; + vpxor (3 * 32)(%rdx), RA3, RA3; + vpxor (4 * 32)(%rdx), RB0, RB0; + vpxor (5 * 32)(%rdx), RB1, RB1; + vpxor (6 * 32)(%rdx), RB2, RB2; + vpxor (7 * 32)(%rdx), RB3, RB3; + + vmovdqu RA0, (0 * 32)(%rsi); + vmovdqu RA1, (1 * 32)(%rsi); + vmovdqu RA2, (2 * 32)(%rsi); + vmovdqu RA3, (3 * 32)(%rsi); + vmovdqu RB0, (4 * 32)(%rsi); + vmovdqu RB1, (5 * 32)(%rsi); + vmovdqu RB2, (6 * 32)(%rsi); + vmovdqu RB3, (7 * 32)(%rsi); + + vzeroall; + FRAME_END + ret; +SYM_FUNC_END(sm4_aesni_avx2_ctr_enc_blk16) + +/* + * void sm4_aesni_avx2_cbc_dec_blk16(const u32 *rk, u8 *dst, + * const u8 *src, u8 *iv) + */ +.align 8 +SYM_FUNC_START(sm4_aesni_avx2_cbc_dec_blk16) + /* input: + * %rdi: round key array, CTX + * %rsi: dst (16 blocks) + * %rdx: src (16 blocks) + * %rcx: iv + */ + FRAME_BEGIN + + vzeroupper; + + vmovdqu (0 * 32)(%rdx), RA0; + vmovdqu (1 * 32)(%rdx), RA1; + vmovdqu (2 * 32)(%rdx), RA2; + vmovdqu (3 * 32)(%rdx), RA3; + vmovdqu (4 * 32)(%rdx), RB0; + vmovdqu (5 * 32)(%rdx), RB1; + vmovdqu (6 * 32)(%rdx), RB2; + vmovdqu (7 * 32)(%rdx), RB3; + + call __sm4_crypt_blk16; + + vmovdqu (%rcx), RNOTx; + vinserti128 $1, (%rdx), RNOT, RNOT; + vpxor RNOT, RA0, RA0; + vpxor (0 * 32 + 16)(%rdx), RA1, RA1; + vpxor (1 * 32 + 16)(%rdx), RA2, RA2; + vpxor (2 * 32 + 16)(%rdx), RA3, RA3; + vpxor (3 * 32 + 16)(%rdx), RB0, RB0; + vpxor (4 * 32 + 16)(%rdx), RB1, RB1; + vpxor (5 * 32 + 16)(%rdx), RB2, RB2; + vpxor (6 * 32 + 16)(%rdx), RB3, RB3; + vmovdqu (7 * 32 + 16)(%rdx), RNOTx; + vmovdqu RNOTx, (%rcx); /* store new IV */ + + vmovdqu RA0, (0 * 32)(%rsi); + vmovdqu RA1, (1 * 32)(%rsi); + vmovdqu RA2, (2 * 32)(%rsi); + vmovdqu RA3, (3 * 32)(%rsi); + vmovdqu RB0, (4 * 32)(%rsi); + vmovdqu RB1, (5 * 32)(%rsi); + vmovdqu RB2, (6 * 32)(%rsi); + vmovdqu RB3, (7 * 32)(%rsi); + + vzeroall; + FRAME_END + ret; +SYM_FUNC_END(sm4_aesni_avx2_cbc_dec_blk16) + +/* + * void sm4_aesni_avx2_cfb_dec_blk16(const u32 *rk, u8 *dst, + * const u8 *src, u8 *iv) + */ +.align 8 +SYM_FUNC_START(sm4_aesni_avx2_cfb_dec_blk16) + /* input: + * %rdi: round key array, CTX + * %rsi: dst (16 blocks) + * %rdx: src (16 blocks) + * %rcx: iv + */ + FRAME_BEGIN + + vzeroupper; + + /* Load input */ + vmovdqu (%rcx), RNOTx; + vinserti128 $1, (%rdx), RNOT, RA0; + vmovdqu (0 * 32 + 16)(%rdx), RA1; + vmovdqu (1 * 32 + 16)(%rdx), RA2; + vmovdqu (2 * 32 + 16)(%rdx), RA3; + vmovdqu (3 * 32 + 16)(%rdx), RB0; + vmovdqu (4 * 32 + 16)(%rdx), RB1; + vmovdqu (5 * 32 + 16)(%rdx), RB2; + vmovdqu (6 * 32 + 16)(%rdx), RB3; + + /* Update IV */ + vmovdqu (7 * 32 + 16)(%rdx), RNOTx; + vmovdqu RNOTx, (%rcx); + + call __sm4_crypt_blk16; + + vpxor (0 * 32)(%rdx), RA0, RA0; + vpxor (1 * 32)(%rdx), RA1, RA1; + vpxor (2 * 32)(%rdx), RA2, RA2; + vpxor (3 * 32)(%rdx), RA3, RA3; + vpxor (4 * 32)(%rdx), RB0, RB0; + vpxor (5 * 32)(%rdx), RB1, RB1; + vpxor (6 * 32)(%rdx), RB2, RB2; + vpxor (7 * 32)(%rdx), RB3, RB3; + + vmovdqu RA0, (0 * 32)(%rsi); + vmovdqu RA1, (1 * 32)(%rsi); + vmovdqu RA2, (2 * 32)(%rsi); + vmovdqu RA3, (3 * 32)(%rsi); + vmovdqu RB0, (4 * 32)(%rsi); + vmovdqu RB1, (5 * 32)(%rsi); + vmovdqu RB2, (6 * 32)(%rsi); + vmovdqu RB3, (7 * 32)(%rsi); + + vzeroall; + FRAME_END + ret; +SYM_FUNC_END(sm4_aesni_avx2_cfb_dec_blk16) diff --git a/arch/x86/crypto/sm4-avx.h b/arch/x86/crypto/sm4-avx.h new file mode 100644 index 000000000000..1bceab7516aa --- /dev/null +++ b/arch/x86/crypto/sm4-avx.h @@ -0,0 +1,24 @@ +/* SPDX-License-Identifier: GPL-2.0-or-later */ +#ifndef ASM_X86_SM4_AVX_H +#define ASM_X86_SM4_AVX_H + +#include <linux/types.h> +#include <crypto/sm4.h> + +typedef void (*sm4_crypt_func)(const u32 *rk, u8 *dst, const u8 *src, u8 *iv); + +int sm4_avx_ecb_encrypt(struct skcipher_request *req); +int sm4_avx_ecb_decrypt(struct skcipher_request *req); + +int sm4_cbc_encrypt(struct skcipher_request *req); +int sm4_avx_cbc_decrypt(struct skcipher_request *req, + unsigned int bsize, sm4_crypt_func func); + +int sm4_cfb_encrypt(struct skcipher_request *req); +int sm4_avx_cfb_decrypt(struct skcipher_request *req, + unsigned int bsize, sm4_crypt_func func); + +int sm4_avx_ctr_crypt(struct skcipher_request *req, + unsigned int bsize, sm4_crypt_func func); + +#endif diff --git a/arch/x86/crypto/sm4_aesni_avx2_glue.c b/arch/x86/crypto/sm4_aesni_avx2_glue.c new file mode 100644 index 000000000000..84bc718f49a3 --- /dev/null +++ b/arch/x86/crypto/sm4_aesni_avx2_glue.c @@ -0,0 +1,169 @@ +/* SPDX-License-Identifier: GPL-2.0-or-later */ +/* + * SM4 Cipher Algorithm, AES-NI/AVX2 optimized. + * as specified in + * https://tools.ietf.org/id/draft-ribose-cfrg-sm4-10.html + * + * Copyright (c) 2021, Alibaba Group. + * Copyright (c) 2021 Tianjia Zhang <tianjia.zhang@linux.alibaba.com> + */ + +#include <linux/module.h> +#include <linux/crypto.h> +#include <linux/kernel.h> +#include <asm/simd.h> +#include <crypto/internal/simd.h> +#include <crypto/internal/skcipher.h> +#include <crypto/sm4.h> +#include "sm4-avx.h" + +#define SM4_CRYPT16_BLOCK_SIZE (SM4_BLOCK_SIZE * 16) + +asmlinkage void sm4_aesni_avx2_ctr_enc_blk16(const u32 *rk, u8 *dst, + const u8 *src, u8 *iv); +asmlinkage void sm4_aesni_avx2_cbc_dec_blk16(const u32 *rk, u8 *dst, + const u8 *src, u8 *iv); +asmlinkage void sm4_aesni_avx2_cfb_dec_blk16(const u32 *rk, u8 *dst, + const u8 *src, u8 *iv); + +static int sm4_skcipher_setkey(struct crypto_skcipher *tfm, const u8 *key, + unsigned int key_len) +{ + struct sm4_ctx *ctx = crypto_skcipher_ctx(tfm); + + return sm4_expandkey(ctx, key, key_len); +} + +static int cbc_decrypt(struct skcipher_request *req) +{ + return sm4_avx_cbc_decrypt(req, SM4_CRYPT16_BLOCK_SIZE, + sm4_aesni_avx2_cbc_dec_blk16); +} + + +static int cfb_decrypt(struct skcipher_request *req) +{ + return sm4_avx_cfb_decrypt(req, SM4_CRYPT16_BLOCK_SIZE, + sm4_aesni_avx2_cfb_dec_blk16); +} + +static int ctr_crypt(struct skcipher_request *req) +{ + return sm4_avx_ctr_crypt(req, SM4_CRYPT16_BLOCK_SIZE, + sm4_aesni_avx2_ctr_enc_blk16); +} + +static struct skcipher_alg sm4_aesni_avx2_skciphers[] = { + { + .base = { + .cra_name = "__ecb(sm4)", + .cra_driver_name = "__ecb-sm4-aesni-avx2", + .cra_priority = 500, + .cra_flags = CRYPTO_ALG_INTERNAL, + .cra_blocksize = SM4_BLOCK_SIZE, + .cra_ctxsize = sizeof(struct sm4_ctx), + .cra_module = THIS_MODULE, + }, + .min_keysize = SM4_KEY_SIZE, + .max_keysize = SM4_KEY_SIZE, + .walksize = 16 * SM4_BLOCK_SIZE, + .setkey = sm4_skcipher_setkey, + .encrypt = sm4_avx_ecb_encrypt, + .decrypt = sm4_avx_ecb_decrypt, + }, { + .base = { + .cra_name = "__cbc(sm4)", + .cra_driver_name = "__cbc-sm4-aesni-avx2", + .cra_priority = 500, + .cra_flags = CRYPTO_ALG_INTERNAL, + .cra_blocksize = SM4_BLOCK_SIZE, + .cra_ctxsize = sizeof(struct sm4_ctx), + .cra_module = THIS_MODULE, + }, + .min_keysize = SM4_KEY_SIZE, + .max_keysize = SM4_KEY_SIZE, + .ivsize = SM4_BLOCK_SIZE, + .walksize = 16 * SM4_BLOCK_SIZE, + .setkey = sm4_skcipher_setkey, + .encrypt = sm4_cbc_encrypt, + .decrypt = cbc_decrypt, + }, { + .base = { + .cra_name = "__cfb(sm4)", + .cra_driver_name = "__cfb-sm4-aesni-avx2", + .cra_priority = 500, + .cra_flags = CRYPTO_ALG_INTERNAL, + .cra_blocksize = 1, + .cra_ctxsize = sizeof(struct sm4_ctx), + .cra_module = THIS_MODULE, + }, + .min_keysize = SM4_KEY_SIZE, + .max_keysize = SM4_KEY_SIZE, + .ivsize = SM4_BLOCK_SIZE, + .chunksize = SM4_BLOCK_SIZE, + .walksize = 16 * SM4_BLOCK_SIZE, + .setkey = sm4_skcipher_setkey, + .encrypt = sm4_cfb_encrypt, + .decrypt = cfb_decrypt, + }, { + .base = { + .cra_name = "__ctr(sm4)", + .cra_driver_name = "__ctr-sm4-aesni-avx2", + .cra_priority = 500, + .cra_flags = CRYPTO_ALG_INTERNAL, + .cra_blocksize = 1, + .cra_ctxsize = sizeof(struct sm4_ctx), + .cra_module = THIS_MODULE, + }, + .min_keysize = SM4_KEY_SIZE, + .max_keysize = SM4_KEY_SIZE, + .ivsize = SM4_BLOCK_SIZE, + .chunksize = SM4_BLOCK_SIZE, + .walksize = 16 * SM4_BLOCK_SIZE, + .setkey = sm4_skcipher_setkey, + .encrypt = ctr_crypt, + .decrypt = ctr_crypt, + } +}; + +static struct simd_skcipher_alg * +simd_sm4_aesni_avx2_skciphers[ARRAY_SIZE(sm4_aesni_avx2_skciphers)]; + +static int __init sm4_init(void) +{ + const char *feature_name; + + if (!boot_cpu_has(X86_FEATURE_AVX) || + !boot_cpu_has(X86_FEATURE_AVX2) || + !boot_cpu_has(X86_FEATURE_AES) || + !boot_cpu_has(X86_FEATURE_OSXSAVE)) { + pr_info("AVX2 or AES-NI instructions are not detected.\n"); + return -ENODEV; + } + + if (!cpu_has_xfeatures(XFEATURE_MASK_SSE | XFEATURE_MASK_YMM, + &feature_name)) { + pr_info("CPU feature '%s' is not supported.\n", feature_name); + return -ENODEV; + } + + return simd_register_skciphers_compat(sm4_aesni_avx2_skciphers, + ARRAY_SIZE(sm4_aesni_avx2_skciphers), + simd_sm4_aesni_avx2_skciphers); +} + +static void __exit sm4_exit(void) +{ + simd_unregister_skciphers(sm4_aesni_avx2_skciphers, + ARRAY_SIZE(sm4_aesni_avx2_skciphers), + simd_sm4_aesni_avx2_skciphers); +} + +module_init(sm4_init); +module_exit(sm4_exit); + +MODULE_LICENSE("GPL v2"); +MODULE_AUTHOR("Tianjia Zhang <tianjia.zhang@linux.alibaba.com>"); +MODULE_DESCRIPTION("SM4 Cipher Algorithm, AES-NI/AVX2 optimized"); +MODULE_ALIAS_CRYPTO("sm4"); +MODULE_ALIAS_CRYPTO("sm4-aesni-avx2"); diff --git a/arch/x86/crypto/sm4_aesni_avx_glue.c b/arch/x86/crypto/sm4_aesni_avx_glue.c new file mode 100644 index 000000000000..7800f77d68ad --- /dev/null +++ b/arch/x86/crypto/sm4_aesni_avx_glue.c @@ -0,0 +1,487 @@ +/* SPDX-License-Identifier: GPL-2.0-or-later */ +/* + * SM4 Cipher Algorithm, AES-NI/AVX optimized. + * as specified in + * https://tools.ietf.org/id/draft-ribose-cfrg-sm4-10.html + * + * Copyright (c) 2021, Alibaba Group. + * Copyright (c) 2021 Tianjia Zhang <tianjia.zhang@linux.alibaba.com> + */ + +#include <linux/module.h> +#include <linux/crypto.h> +#include <linux/kernel.h> +#include <asm/simd.h> +#include <crypto/internal/simd.h> +#include <crypto/internal/skcipher.h> +#include <crypto/sm4.h> +#include "sm4-avx.h" + +#define SM4_CRYPT8_BLOCK_SIZE (SM4_BLOCK_SIZE * 8) + +asmlinkage void sm4_aesni_avx_crypt4(const u32 *rk, u8 *dst, + const u8 *src, int nblocks); +asmlinkage void sm4_aesni_avx_crypt8(const u32 *rk, u8 *dst, + const u8 *src, int nblocks); +asmlinkage void sm4_aesni_avx_ctr_enc_blk8(const u32 *rk, u8 *dst, + const u8 *src, u8 *iv); +asmlinkage void sm4_aesni_avx_cbc_dec_blk8(const u32 *rk, u8 *dst, + const u8 *src, u8 *iv); +asmlinkage void sm4_aesni_avx_cfb_dec_blk8(const u32 *rk, u8 *dst, + const u8 *src, u8 *iv); + +static int sm4_skcipher_setkey(struct crypto_skcipher *tfm, const u8 *key, + unsigned int key_len) +{ + struct sm4_ctx *ctx = crypto_skcipher_ctx(tfm); + + return sm4_expandkey(ctx, key, key_len); +} + +static int ecb_do_crypt(struct skcipher_request *req, const u32 *rkey) +{ + struct skcipher_walk walk; + unsigned int nbytes; + int err; + + err = skcipher_walk_virt(&walk, req, false); + + while ((nbytes = walk.nbytes) > 0) { + const u8 *src = walk.src.virt.addr; + u8 *dst = walk.dst.virt.addr; + + kernel_fpu_begin(); + while (nbytes >= SM4_CRYPT8_BLOCK_SIZE) { + sm4_aesni_avx_crypt8(rkey, dst, src, 8); + dst += SM4_CRYPT8_BLOCK_SIZE; + src += SM4_CRYPT8_BLOCK_SIZE; + nbytes -= SM4_CRYPT8_BLOCK_SIZE; + } + while (nbytes >= SM4_BLOCK_SIZE) { + unsigned int nblocks = min(nbytes >> 4, 4u); + sm4_aesni_avx_crypt4(rkey, dst, src, nblocks); + dst += nblocks * SM4_BLOCK_SIZE; + src += nblocks * SM4_BLOCK_SIZE; + nbytes -= nblocks * SM4_BLOCK_SIZE; + } + kernel_fpu_end(); + + err = skcipher_walk_done(&walk, nbytes); + } + + return err; +} + +int sm4_avx_ecb_encrypt(struct skcipher_request *req) +{ + struct crypto_skcipher *tfm = crypto_skcipher_reqtfm(req); + struct sm4_ctx *ctx = crypto_skcipher_ctx(tfm); + + return ecb_do_crypt(req, ctx->rkey_enc); +} +EXPORT_SYMBOL_GPL(sm4_avx_ecb_encrypt); + +int sm4_avx_ecb_decrypt(struct skcipher_request *req) +{ + struct crypto_skcipher *tfm = crypto_skcipher_reqtfm(req); + struct sm4_ctx *ctx = crypto_skcipher_ctx(tfm); + + return ecb_do_crypt(req, ctx->rkey_dec); +} +EXPORT_SYMBOL_GPL(sm4_avx_ecb_decrypt); + +int sm4_cbc_encrypt(struct skcipher_request *req) +{ + struct crypto_skcipher *tfm = crypto_skcipher_reqtfm(req); + struct sm4_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) > 0) { + const u8 *iv = walk.iv; + const u8 *src = walk.src.virt.addr; + u8 *dst = walk.dst.virt.addr; + + while (nbytes >= SM4_BLOCK_SIZE) { + crypto_xor_cpy(dst, src, iv, SM4_BLOCK_SIZE); + sm4_crypt_block(ctx->rkey_enc, dst, dst); + iv = dst; + src += SM4_BLOCK_SIZE; + dst += SM4_BLOCK_SIZE; + nbytes -= SM4_BLOCK_SIZE; + } + if (iv != walk.iv) + memcpy(walk.iv, iv, SM4_BLOCK_SIZE); + + err = skcipher_walk_done(&walk, nbytes); + } + + return err; +} +EXPORT_SYMBOL_GPL(sm4_cbc_encrypt); + +int sm4_avx_cbc_decrypt(struct skcipher_request *req, + unsigned int bsize, sm4_crypt_func func) +{ + struct crypto_skcipher *tfm = crypto_skcipher_reqtfm(req); + struct sm4_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) > 0) { + const u8 *src = walk.src.virt.addr; + u8 *dst = walk.dst.virt.addr; + + kernel_fpu_begin(); + + while (nbytes >= bsize) { + func(ctx->rkey_dec, dst, src, walk.iv); + dst += bsize; + src += bsize; + nbytes -= bsize; + } + + while (nbytes >= SM4_BLOCK_SIZE) { + u8 keystream[SM4_BLOCK_SIZE * 8]; + u8 iv[SM4_BLOCK_SIZE]; + unsigned int nblocks = min(nbytes >> 4, 8u); + int i; + + sm4_aesni_avx_crypt8(ctx->rkey_dec, keystream, + src, nblocks); + + src += ((int)nblocks - 2) * SM4_BLOCK_SIZE; + dst += (nblocks - 1) * SM4_BLOCK_SIZE; + memcpy(iv, src + SM4_BLOCK_SIZE, SM4_BLOCK_SIZE); + + for (i = nblocks - 1; i > 0; i--) { + crypto_xor_cpy(dst, src, + &keystream[i * SM4_BLOCK_SIZE], + SM4_BLOCK_SIZE); + src -= SM4_BLOCK_SIZE; + dst -= SM4_BLOCK_SIZE; + } + crypto_xor_cpy(dst, walk.iv, keystream, SM4_BLOCK_SIZE); + memcpy(walk.iv, iv, SM4_BLOCK_SIZE); + dst += nblocks * SM4_BLOCK_SIZE; + src += (nblocks + 1) * SM4_BLOCK_SIZE; + nbytes -= nblocks * SM4_BLOCK_SIZE; + } + + kernel_fpu_end(); + err = skcipher_walk_done(&walk, nbytes); + } + + return err; +} +EXPORT_SYMBOL_GPL(sm4_avx_cbc_decrypt); + +static int cbc_decrypt(struct skcipher_request *req) +{ + return sm4_avx_cbc_decrypt(req, SM4_CRYPT8_BLOCK_SIZE, + sm4_aesni_avx_cbc_dec_blk8); +} + +int sm4_cfb_encrypt(struct skcipher_request *req) +{ + struct crypto_skcipher *tfm = crypto_skcipher_reqtfm(req); + struct sm4_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) > 0) { + u8 keystream[SM4_BLOCK_SIZE]; + const u8 *iv = walk.iv; + const u8 *src = walk.src.virt.addr; + u8 *dst = walk.dst.virt.addr; + + while (nbytes >= SM4_BLOCK_SIZE) { + sm4_crypt_block(ctx->rkey_enc, keystream, iv); + crypto_xor_cpy(dst, src, keystream, SM4_BLOCK_SIZE); + iv = dst; + src += SM4_BLOCK_SIZE; + dst += SM4_BLOCK_SIZE; + nbytes -= SM4_BLOCK_SIZE; + } + if (iv != walk.iv) + memcpy(walk.iv, iv, SM4_BLOCK_SIZE); + + /* tail */ + if (walk.nbytes == walk.total && nbytes > 0) { + sm4_crypt_block(ctx->rkey_enc, keystream, walk.iv); + crypto_xor_cpy(dst, src, keystream, nbytes); + nbytes = 0; + } + + err = skcipher_walk_done(&walk, nbytes); + } + + return err; +} +EXPORT_SYMBOL_GPL(sm4_cfb_encrypt); + +int sm4_avx_cfb_decrypt(struct skcipher_request *req, + unsigned int bsize, sm4_crypt_func func) +{ + struct crypto_skcipher *tfm = crypto_skcipher_reqtfm(req); + struct sm4_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) > 0) { + const u8 *src = walk.src.virt.addr; + u8 *dst = walk.dst.virt.addr; + + kernel_fpu_begin(); + + while (nbytes >= bsize) { + func(ctx->rkey_enc, dst, src, walk.iv); + dst += bsize; + src += bsize; + nbytes -= bsize; + } + + while (nbytes >= SM4_BLOCK_SIZE) { + u8 keystream[SM4_BLOCK_SIZE * 8]; + unsigned int nblocks = min(nbytes >> 4, 8u); + + memcpy(keystream, walk.iv, SM4_BLOCK_SIZE); + if (nblocks > 1) + memcpy(&keystream[SM4_BLOCK_SIZE], src, + (nblocks - 1) * SM4_BLOCK_SIZE); + memcpy(walk.iv, src + (nblocks - 1) * SM4_BLOCK_SIZE, + SM4_BLOCK_SIZE); + + sm4_aesni_avx_crypt8(ctx->rkey_enc, keystream, + keystream, nblocks); + + crypto_xor_cpy(dst, src, keystream, + nblocks * SM4_BLOCK_SIZE); + dst += nblocks * SM4_BLOCK_SIZE; + src += nblocks * SM4_BLOCK_SIZE; + nbytes -= nblocks * SM4_BLOCK_SIZE; + } + + kernel_fpu_end(); + + /* tail */ + if (walk.nbytes == walk.total && nbytes > 0) { + u8 keystream[SM4_BLOCK_SIZE]; + + sm4_crypt_block(ctx->rkey_enc, keystream, walk.iv); + crypto_xor_cpy(dst, src, keystream, nbytes); + nbytes = 0; + } + + err = skcipher_walk_done(&walk, nbytes); + } + + return err; +} +EXPORT_SYMBOL_GPL(sm4_avx_cfb_decrypt); + +static int cfb_decrypt(struct skcipher_request *req) +{ + return sm4_avx_cfb_decrypt(req, SM4_CRYPT8_BLOCK_SIZE, + sm4_aesni_avx_cfb_dec_blk8); +} + +int sm4_avx_ctr_crypt(struct skcipher_request *req, + unsigned int bsize, sm4_crypt_func func) +{ + struct crypto_skcipher *tfm = crypto_skcipher_reqtfm(req); + struct sm4_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) > 0) { + const u8 *src = walk.src.virt.addr; + u8 *dst = walk.dst.virt.addr; + + kernel_fpu_begin(); + + while (nbytes >= bsize) { + func(ctx->rkey_enc, dst, src, walk.iv); + dst += bsize; + src += bsize; + nbytes -= bsize; + } + + while (nbytes >= SM4_BLOCK_SIZE) { + u8 keystream[SM4_BLOCK_SIZE * 8]; + unsigned int nblocks = min(nbytes >> 4, 8u); + int i; + + for (i = 0; i < nblocks; i++) { + memcpy(&keystream[i * SM4_BLOCK_SIZE], + walk.iv, SM4_BLOCK_SIZE); + crypto_inc(walk.iv, SM4_BLOCK_SIZE); + } + sm4_aesni_avx_crypt8(ctx->rkey_enc, keystream, + keystream, nblocks); + + crypto_xor_cpy(dst, src, keystream, + nblocks * SM4_BLOCK_SIZE); + dst += nblocks * SM4_BLOCK_SIZE; + src += nblocks * SM4_BLOCK_SIZE; + nbytes -= nblocks * SM4_BLOCK_SIZE; + } + + kernel_fpu_end(); + + /* tail */ + if (walk.nbytes == walk.total && nbytes > 0) { + u8 keystream[SM4_BLOCK_SIZE]; + + memcpy(keystream, walk.iv, SM4_BLOCK_SIZE); + crypto_inc(walk.iv, SM4_BLOCK_SIZE); + + sm4_crypt_block(ctx->rkey_enc, keystream, keystream); + + crypto_xor_cpy(dst, src, keystream, nbytes); + dst += nbytes; + src += nbytes; + nbytes = 0; + } + + err = skcipher_walk_done(&walk, nbytes); + } + + return err; +} +EXPORT_SYMBOL_GPL(sm4_avx_ctr_crypt); + +static int ctr_crypt(struct skcipher_request *req) +{ + return sm4_avx_ctr_crypt(req, SM4_CRYPT8_BLOCK_SIZE, + sm4_aesni_avx_ctr_enc_blk8); +} + +static struct skcipher_alg sm4_aesni_avx_skciphers[] = { + { + .base = { + .cra_name = "__ecb(sm4)", + .cra_driver_name = "__ecb-sm4-aesni-avx", + .cra_priority = 400, + .cra_flags = CRYPTO_ALG_INTERNAL, + .cra_blocksize = SM4_BLOCK_SIZE, + .cra_ctxsize = sizeof(struct sm4_ctx), + .cra_module = THIS_MODULE, + }, + .min_keysize = SM4_KEY_SIZE, + .max_keysize = SM4_KEY_SIZE, + .walksize = 8 * SM4_BLOCK_SIZE, + .setkey = sm4_skcipher_setkey, + .encrypt = sm4_avx_ecb_encrypt, + .decrypt = sm4_avx_ecb_decrypt, + }, { + .base = { + .cra_name = "__cbc(sm4)", + .cra_driver_name = "__cbc-sm4-aesni-avx", + .cra_priority = 400, + .cra_flags = CRYPTO_ALG_INTERNAL, + .cra_blocksize = SM4_BLOCK_SIZE, + .cra_ctxsize = sizeof(struct sm4_ctx), + .cra_module = THIS_MODULE, + }, + .min_keysize = SM4_KEY_SIZE, + .max_keysize = SM4_KEY_SIZE, + .ivsize = SM4_BLOCK_SIZE, + .walksize = 8 * SM4_BLOCK_SIZE, + .setkey = sm4_skcipher_setkey, + .encrypt = sm4_cbc_encrypt, + .decrypt = cbc_decrypt, + }, { + .base = { + .cra_name = "__cfb(sm4)", + .cra_driver_name = "__cfb-sm4-aesni-avx", + .cra_priority = 400, + .cra_flags = CRYPTO_ALG_INTERNAL, + .cra_blocksize = 1, + .cra_ctxsize = sizeof(struct sm4_ctx), + .cra_module = THIS_MODULE, + }, + .min_keysize = SM4_KEY_SIZE, + .max_keysize = SM4_KEY_SIZE, + .ivsize = SM4_BLOCK_SIZE, + .chunksize = SM4_BLOCK_SIZE, + .walksize = 8 * SM4_BLOCK_SIZE, + .setkey = sm4_skcipher_setkey, + .encrypt = sm4_cfb_encrypt, + .decrypt = cfb_decrypt, + }, { + .base = { + .cra_name = "__ctr(sm4)", + .cra_driver_name = "__ctr-sm4-aesni-avx", + .cra_priority = 400, + .cra_flags = CRYPTO_ALG_INTERNAL, + .cra_blocksize = 1, + .cra_ctxsize = sizeof(struct sm4_ctx), + .cra_module = THIS_MODULE, + }, + .min_keysize = SM4_KEY_SIZE, + .max_keysize = SM4_KEY_SIZE, + .ivsize = SM4_BLOCK_SIZE, + .chunksize = SM4_BLOCK_SIZE, + .walksize = 8 * SM4_BLOCK_SIZE, + .setkey = sm4_skcipher_setkey, + .encrypt = ctr_crypt, + .decrypt = ctr_crypt, + } +}; + +static struct simd_skcipher_alg * +simd_sm4_aesni_avx_skciphers[ARRAY_SIZE(sm4_aesni_avx_skciphers)]; + +static int __init sm4_init(void) +{ + const char *feature_name; + + if (!boot_cpu_has(X86_FEATURE_AVX) || + !boot_cpu_has(X86_FEATURE_AES) || + !boot_cpu_has(X86_FEATURE_OSXSAVE)) { + pr_info("AVX or AES-NI instructions are not detected.\n"); + return -ENODEV; + } + + if (!cpu_has_xfeatures(XFEATURE_MASK_SSE | XFEATURE_MASK_YMM, + &feature_name)) { + pr_info("CPU feature '%s' is not supported.\n", feature_name); + return -ENODEV; + } + + return simd_register_skciphers_compat(sm4_aesni_avx_skciphers, + ARRAY_SIZE(sm4_aesni_avx_skciphers), + simd_sm4_aesni_avx_skciphers); +} + +static void __exit sm4_exit(void) +{ + simd_unregister_skciphers(sm4_aesni_avx_skciphers, + ARRAY_SIZE(sm4_aesni_avx_skciphers), + simd_sm4_aesni_avx_skciphers); +} + +module_init(sm4_init); +module_exit(sm4_exit); + +MODULE_LICENSE("GPL v2"); +MODULE_AUTHOR("Tianjia Zhang <tianjia.zhang@linux.alibaba.com>"); +MODULE_DESCRIPTION("SM4 Cipher Algorithm, AES-NI/AVX optimized"); +MODULE_ALIAS_CRYPTO("sm4"); +MODULE_ALIAS_CRYPTO("sm4-aesni-avx"); diff --git a/arch/x86/entry/syscalls/syscall_32.tbl b/arch/x86/entry/syscalls/syscall_32.tbl index ce763a12311c..960a021d543e 100644 --- a/arch/x86/entry/syscalls/syscall_32.tbl +++ b/arch/x86/entry/syscalls/syscall_32.tbl @@ -145,7 +145,7 @@ 131 i386 quotactl sys_quotactl 132 i386 getpgid sys_getpgid 133 i386 fchdir sys_fchdir -134 i386 bdflush sys_bdflush +134 i386 bdflush sys_ni_syscall 135 i386 sysfs sys_sysfs 136 i386 personality sys_personality 137 i386 afs_syscall @@ -286,7 +286,7 @@ 272 i386 fadvise64_64 sys_ia32_fadvise64_64 273 i386 vserver 274 i386 mbind sys_mbind -275 i386 get_mempolicy sys_get_mempolicy compat_sys_get_mempolicy +275 i386 get_mempolicy sys_get_mempolicy 276 i386 set_mempolicy sys_set_mempolicy 277 i386 mq_open sys_mq_open compat_sys_mq_open 278 i386 mq_unlink sys_mq_unlink @@ -328,7 +328,7 @@ 314 i386 sync_file_range sys_ia32_sync_file_range 315 i386 tee sys_tee 316 i386 vmsplice sys_vmsplice -317 i386 move_pages sys_move_pages compat_sys_move_pages +317 i386 move_pages sys_move_pages 318 i386 getcpu sys_getcpu 319 i386 epoll_pwait sys_epoll_pwait 320 i386 utimensat sys_utimensat_time32 @@ -452,3 +452,4 @@ 445 i386 landlock_add_rule sys_landlock_add_rule 446 i386 landlock_restrict_self sys_landlock_restrict_self 447 i386 memfd_secret sys_memfd_secret +448 i386 process_mrelease sys_process_mrelease diff --git a/arch/x86/entry/syscalls/syscall_64.tbl b/arch/x86/entry/syscalls/syscall_64.tbl index f6b57799c1ea..18b5500ea8bf 100644 --- a/arch/x86/entry/syscalls/syscall_64.tbl +++ b/arch/x86/entry/syscalls/syscall_64.tbl @@ -369,6 +369,7 @@ 445 common landlock_add_rule sys_landlock_add_rule 446 common landlock_restrict_self sys_landlock_restrict_self 447 common memfd_secret sys_memfd_secret +448 common process_mrelease sys_process_mrelease # # Due to a historical design error, certain syscalls are numbered differently @@ -397,7 +398,7 @@ 530 x32 set_robust_list compat_sys_set_robust_list 531 x32 get_robust_list compat_sys_get_robust_list 532 x32 vmsplice sys_vmsplice -533 x32 move_pages compat_sys_move_pages +533 x32 move_pages sys_move_pages 534 x32 preadv compat_sys_preadv64 535 x32 pwritev compat_sys_pwritev64 536 x32 rt_tgsigqueueinfo compat_sys_rt_tgsigqueueinfo diff --git a/arch/x86/entry/vdso/Makefile b/arch/x86/entry/vdso/Makefile index 05c4abc2fdfd..a2dddcc189f6 100644 --- a/arch/x86/entry/vdso/Makefile +++ b/arch/x86/entry/vdso/Makefile @@ -131,7 +131,7 @@ $(obj)/%-x32.o: $(obj)/%.o FORCE targets += vdsox32.lds $(vobjx32s-y) $(obj)/%.so: OBJCOPYFLAGS := -S --remove-section __ex_table -$(obj)/%.so: $(obj)/%.so.dbg +$(obj)/%.so: $(obj)/%.so.dbg FORCE $(call if_changed,objcopy) $(obj)/vdsox32.so.dbg: $(obj)/vdsox32.lds $(vobjx32s) FORCE diff --git a/arch/x86/events/Kconfig b/arch/x86/events/Kconfig index 39d9ded9e25a..d6cdfe631674 100644 --- a/arch/x86/events/Kconfig +++ b/arch/x86/events/Kconfig @@ -34,4 +34,14 @@ config PERF_EVENTS_AMD_POWER (CPUID Fn8000_0007_EDX[12]) interface to calculate the average power consumption on Family 15h processors. +config PERF_EVENTS_AMD_UNCORE + tristate "AMD Uncore performance events" + depends on PERF_EVENTS && CPU_SUP_AMD + default y + help + Include support for AMD uncore performance events for use with + e.g., perf stat -e amd_l3/.../,amd_df/.../. + + To compile this driver as a module, choose M here: the + module will be called 'amd-uncore'. endmenu diff --git a/arch/x86/events/amd/Makefile b/arch/x86/events/amd/Makefile index fe8795a67385..6cbe38d5fd9d 100644 --- a/arch/x86/events/amd/Makefile +++ b/arch/x86/events/amd/Makefile @@ -1,8 +1,9 @@ # SPDX-License-Identifier: GPL-2.0 -obj-$(CONFIG_CPU_SUP_AMD) += core.o uncore.o +obj-$(CONFIG_CPU_SUP_AMD) += core.o obj-$(CONFIG_PERF_EVENTS_AMD_POWER) += power.o obj-$(CONFIG_X86_LOCAL_APIC) += ibs.o +obj-$(CONFIG_PERF_EVENTS_AMD_UNCORE) += amd-uncore.o +amd-uncore-objs := uncore.o ifdef CONFIG_AMD_IOMMU obj-$(CONFIG_CPU_SUP_AMD) += iommu.o endif - diff --git a/arch/x86/events/amd/ibs.c b/arch/x86/events/amd/ibs.c index 40669eac9d6d..9739019d4b67 100644 --- a/arch/x86/events/amd/ibs.c +++ b/arch/x86/events/amd/ibs.c @@ -26,6 +26,7 @@ static u32 ibs_caps; #include <linux/hardirq.h> #include <asm/nmi.h> +#include <asm/amd-ibs.h> #define IBS_FETCH_CONFIG_MASK (IBS_FETCH_RAND_EN | IBS_FETCH_MAX_CNT) #define IBS_OP_CONFIG_MASK IBS_OP_MAX_CNT @@ -90,6 +91,7 @@ struct perf_ibs { unsigned long offset_mask[1]; int offset_max; unsigned int fetch_count_reset_broken : 1; + unsigned int fetch_ignore_if_zero_rip : 1; struct cpu_perf_ibs __percpu *pcpu; struct attribute **format_attrs; @@ -99,15 +101,6 @@ struct perf_ibs { u64 (*get_count)(u64 config); }; -struct perf_ibs_data { - u32 size; - union { - u32 data[0]; /* data buffer starts here */ - u32 caps; - }; - u64 regs[MSR_AMD64_IBS_REG_COUNT_MAX]; -}; - static int perf_event_set_period(struct hw_perf_event *hwc, u64 min, u64 max, u64 *hw_period) { @@ -328,11 +321,14 @@ static int perf_ibs_set_period(struct perf_ibs *perf_ibs, static u64 get_ibs_fetch_count(u64 config) { - return (config & IBS_FETCH_CNT) >> 12; + union ibs_fetch_ctl fetch_ctl = (union ibs_fetch_ctl)config; + + return fetch_ctl.fetch_cnt << 4; } static u64 get_ibs_op_count(u64 config) { + union ibs_op_ctl op_ctl = (union ibs_op_ctl)config; u64 count = 0; /* @@ -340,12 +336,12 @@ static u64 get_ibs_op_count(u64 config) * and the lower 7 bits of CurCnt are randomized. * Otherwise CurCnt has the full 27-bit current counter value. */ - if (config & IBS_OP_VAL) { - count = (config & IBS_OP_MAX_CNT) << 4; + if (op_ctl.op_val) { + count = op_ctl.opmaxcnt << 4; if (ibs_caps & IBS_CAPS_OPCNTEXT) - count += config & IBS_OP_MAX_CNT_EXT_MASK; + count += op_ctl.opmaxcnt_ext << 20; } else if (ibs_caps & IBS_CAPS_RDWROPCNT) { - count = (config & IBS_OP_CUR_CNT) >> 32; + count = op_ctl.opcurcnt; } return count; @@ -570,6 +566,7 @@ static struct perf_ibs perf_ibs_op = { .start = perf_ibs_start, .stop = perf_ibs_stop, .read = perf_ibs_read, + .capabilities = PERF_PMU_CAP_NO_EXCLUDE, }, .msr = MSR_AMD64_IBSOPCTL, .config_mask = IBS_OP_CONFIG_MASK, @@ -672,6 +669,10 @@ fail: if (check_rip && (ibs_data.regs[2] & IBS_RIP_INVALID)) { regs.flags &= ~PERF_EFLAGS_EXACT; } else { + /* Workaround for erratum #1197 */ + if (perf_ibs->fetch_ignore_if_zero_rip && !(ibs_data.regs[1])) + goto out; + set_linear_ip(®s, ibs_data.regs[1]); regs.flags |= PERF_EFLAGS_EXACT; } @@ -769,6 +770,9 @@ static __init void perf_event_ibs_init(void) if (boot_cpu_data.x86 >= 0x16 && boot_cpu_data.x86 <= 0x18) perf_ibs_fetch.fetch_count_reset_broken = 1; + if (boot_cpu_data.x86 == 0x19 && boot_cpu_data.x86_model < 0x10) + perf_ibs_fetch.fetch_ignore_if_zero_rip = 1; + perf_ibs_pmu_init(&perf_ibs_fetch, "ibs_fetch"); if (ibs_caps & IBS_CAPS_OPCNT) { diff --git a/arch/x86/events/amd/power.c b/arch/x86/events/amd/power.c index 16a2369c586e..37d5b380516e 100644 --- a/arch/x86/events/amd/power.c +++ b/arch/x86/events/amd/power.c @@ -213,6 +213,7 @@ static struct pmu pmu_class = { .stop = pmu_event_stop, .read = pmu_event_read, .capabilities = PERF_PMU_CAP_NO_EXCLUDE, + .module = THIS_MODULE, }; static int power_cpu_exit(unsigned int cpu) diff --git a/arch/x86/events/amd/uncore.c b/arch/x86/events/amd/uncore.c index 582c0ffb5e98..0d04414b97d2 100644 --- a/arch/x86/events/amd/uncore.c +++ b/arch/x86/events/amd/uncore.c @@ -12,11 +12,11 @@ #include <linux/init.h> #include <linux/cpu.h> #include <linux/cpumask.h> +#include <linux/cpufeature.h> +#include <linux/smp.h> -#include <asm/cpufeature.h> #include <asm/perf_event.h> #include <asm/msr.h> -#include <asm/smp.h> #define NUM_COUNTERS_NB 4 #define NUM_COUNTERS_L2 4 @@ -347,6 +347,7 @@ static struct pmu amd_nb_pmu = { .stop = amd_uncore_stop, .read = amd_uncore_read, .capabilities = PERF_PMU_CAP_NO_EXCLUDE | PERF_PMU_CAP_NO_INTERRUPT, + .module = THIS_MODULE, }; static struct pmu amd_llc_pmu = { @@ -360,6 +361,7 @@ static struct pmu amd_llc_pmu = { .stop = amd_uncore_stop, .read = amd_uncore_read, .capabilities = PERF_PMU_CAP_NO_EXCLUDE | PERF_PMU_CAP_NO_INTERRUPT, + .module = THIS_MODULE, }; static struct amd_uncore *amd_uncore_alloc(unsigned int cpu) @@ -452,7 +454,7 @@ static int amd_uncore_cpu_starting(unsigned int cpu) if (amd_uncore_llc) { uncore = *per_cpu_ptr(amd_uncore_llc, cpu); - uncore->id = per_cpu(cpu_llc_id, cpu); + uncore->id = get_llc_id(cpu); uncore = amd_uncore_find_online_sibling(uncore, amd_uncore_llc); *per_cpu_ptr(amd_uncore_llc, cpu) = uncore; @@ -659,12 +661,34 @@ fail_prep: fail_llc: if (boot_cpu_has(X86_FEATURE_PERFCTR_NB)) perf_pmu_unregister(&amd_nb_pmu); - if (amd_uncore_llc) - free_percpu(amd_uncore_llc); + free_percpu(amd_uncore_llc); fail_nb: - if (amd_uncore_nb) - free_percpu(amd_uncore_nb); + free_percpu(amd_uncore_nb); return ret; } -device_initcall(amd_uncore_init); + +static void __exit amd_uncore_exit(void) +{ + cpuhp_remove_state(CPUHP_AP_PERF_X86_AMD_UNCORE_ONLINE); + cpuhp_remove_state(CPUHP_AP_PERF_X86_AMD_UNCORE_STARTING); + cpuhp_remove_state(CPUHP_PERF_X86_AMD_UNCORE_PREP); + + if (boot_cpu_has(X86_FEATURE_PERFCTR_LLC)) { + perf_pmu_unregister(&amd_llc_pmu); + free_percpu(amd_uncore_llc); + amd_uncore_llc = NULL; + } + + if (boot_cpu_has(X86_FEATURE_PERFCTR_NB)) { + perf_pmu_unregister(&amd_nb_pmu); + free_percpu(amd_uncore_nb); + amd_uncore_nb = NULL; + } +} + +module_init(amd_uncore_init); +module_exit(amd_uncore_exit); + +MODULE_DESCRIPTION("AMD Uncore Driver"); +MODULE_LICENSE("GPL v2"); diff --git a/arch/x86/events/core.c b/arch/x86/events/core.c index 1eb45139fcc6..2a57dbed4894 100644 --- a/arch/x86/events/core.c +++ b/arch/x86/events/core.c @@ -1087,10 +1087,8 @@ int x86_schedule_events(struct cpu_hw_events *cpuc, int n, int *assign) * validate an event group (assign == NULL) */ if (!unsched && assign) { - for (i = 0; i < n; i++) { - e = cpuc->event_list[i]; + for (i = 0; i < n; i++) static_call_cond(x86_pmu_commit_scheduling)(cpuc, i, assign[i]); - } } else { for (i = n0; i < n; i++) { e = cpuc->event_list[i]; @@ -2489,13 +2487,15 @@ void perf_clear_dirty_counters(void) return; for_each_set_bit(i, cpuc->dirty, X86_PMC_IDX_MAX) { - /* Metrics and fake events don't have corresponding HW counters. */ - if (is_metric_idx(i) || (i == INTEL_PMC_IDX_FIXED_VLBR)) - continue; - else if (i >= INTEL_PMC_IDX_FIXED) + if (i >= INTEL_PMC_IDX_FIXED) { + /* Metrics and fake events don't have corresponding HW counters. */ + if ((i - INTEL_PMC_IDX_FIXED) >= hybrid(cpuc->pmu, num_counters_fixed)) + continue; + wrmsrl(MSR_ARCH_PERFMON_FIXED_CTR0 + (i - INTEL_PMC_IDX_FIXED), 0); - else + } else { wrmsrl(x86_pmu_event_addr(i), 0); + } } bitmap_zero(cpuc->dirty, X86_PMC_IDX_MAX); diff --git a/arch/x86/events/intel/core.c b/arch/x86/events/intel/core.c index fca7a6e2242f..7011e87be6d0 100644 --- a/arch/x86/events/intel/core.c +++ b/arch/x86/events/intel/core.c @@ -2904,24 +2904,28 @@ static int handle_pmi_common(struct pt_regs *regs, u64 status) */ static int intel_pmu_handle_irq(struct pt_regs *regs) { - struct cpu_hw_events *cpuc; + struct cpu_hw_events *cpuc = this_cpu_ptr(&cpu_hw_events); + bool late_ack = hybrid_bit(cpuc->pmu, late_ack); + bool mid_ack = hybrid_bit(cpuc->pmu, mid_ack); int loops; u64 status; int handled; int pmu_enabled; - cpuc = this_cpu_ptr(&cpu_hw_events); - /* * Save the PMU state. * It needs to be restored when leaving the handler. */ pmu_enabled = cpuc->enabled; /* - * No known reason to not always do late ACK, - * but just in case do it opt-in. + * In general, the early ACK is only applied for old platforms. + * For the big core starts from Haswell, the late ACK should be + * applied. + * For the small core after Tremont, we have to do the ACK right + * before re-enabling counters, which is in the middle of the + * NMI handler. */ - if (!x86_pmu.late_ack) + if (!late_ack && !mid_ack) apic_write(APIC_LVTPC, APIC_DM_NMI); intel_bts_disable_local(); cpuc->enabled = 0; @@ -2958,6 +2962,8 @@ again: goto again; done: + if (mid_ack) + apic_write(APIC_LVTPC, APIC_DM_NMI); /* Only restore PMU state when it's active. See x86_pmu_disable(). */ cpuc->enabled = pmu_enabled; if (pmu_enabled) @@ -2969,7 +2975,7 @@ done: * have been reset. This avoids spurious NMIs on * Haswell CPUs. */ - if (x86_pmu.late_ack) + if (late_ack) apic_write(APIC_LVTPC, APIC_DM_NMI); return handled; } @@ -5026,9 +5032,9 @@ static ssize_t freeze_on_smi_store(struct device *cdev, x86_pmu.attr_freeze_on_smi = val; - get_online_cpus(); + cpus_read_lock(); on_each_cpu(flip_smm_bit, &val, 1); - put_online_cpus(); + cpus_read_unlock(); done: mutex_unlock(&freeze_on_smi_mutex); @@ -5071,9 +5077,9 @@ static ssize_t set_sysctl_tfa(struct device *cdev, allow_tsx_force_abort = val; - get_online_cpus(); + cpus_read_lock(); on_each_cpu(update_tfa_sched, NULL, 1); - put_online_cpus(); + cpus_read_unlock(); return count; } @@ -6129,7 +6135,6 @@ __init int intel_pmu_init(void) static_branch_enable(&perf_is_hybrid); x86_pmu.num_hybrid_pmus = X86_HYBRID_NUM_PMUS; - x86_pmu.late_ack = true; x86_pmu.pebs_aliases = NULL; x86_pmu.pebs_prec_dist = true; x86_pmu.pebs_block = true; @@ -6167,6 +6172,7 @@ __init int intel_pmu_init(void) pmu = &x86_pmu.hybrid_pmu[X86_HYBRID_PMU_CORE_IDX]; pmu->name = "cpu_core"; pmu->cpu_type = hybrid_big; + pmu->late_ack = true; if (cpu_feature_enabled(X86_FEATURE_HYBRID_CPU)) { pmu->num_counters = x86_pmu.num_counters + 2; pmu->num_counters_fixed = x86_pmu.num_counters_fixed + 1; @@ -6192,6 +6198,7 @@ __init int intel_pmu_init(void) pmu = &x86_pmu.hybrid_pmu[X86_HYBRID_PMU_ATOM_IDX]; pmu->name = "cpu_atom"; pmu->cpu_type = hybrid_small; + pmu->mid_ack = true; pmu->num_counters = x86_pmu.num_counters; pmu->num_counters_fixed = x86_pmu.num_counters_fixed; pmu->max_pebs_events = x86_pmu.max_pebs_events; diff --git a/arch/x86/events/intel/pt.c b/arch/x86/events/intel/pt.c index 915847655c06..7f406c14715f 100644 --- a/arch/x86/events/intel/pt.c +++ b/arch/x86/events/intel/pt.c @@ -62,7 +62,7 @@ static struct pt_cap_desc { PT_CAP(single_range_output, 0, CPUID_ECX, BIT(2)), PT_CAP(output_subsys, 0, CPUID_ECX, BIT(3)), PT_CAP(payloads_lip, 0, CPUID_ECX, BIT(31)), - PT_CAP(num_address_ranges, 1, CPUID_EAX, 0x3), + PT_CAP(num_address_ranges, 1, CPUID_EAX, 0x7), PT_CAP(mtc_periods, 1, CPUID_EAX, 0xffff0000), PT_CAP(cycle_thresholds, 1, CPUID_EBX, 0xffff), PT_CAP(psb_periods, 1, CPUID_EBX, 0xffff0000), @@ -1708,7 +1708,7 @@ static __init int pt_init(void) if (!boot_cpu_has(X86_FEATURE_INTEL_PT)) return -ENODEV; - get_online_cpus(); + cpus_read_lock(); for_each_online_cpu(cpu) { u64 ctl; @@ -1716,7 +1716,7 @@ static __init int pt_init(void) if (!ret && (ctl & RTIT_CTL_TRACEEN)) prior_warn++; } - put_online_cpus(); + cpus_read_unlock(); if (prior_warn) { x86_add_exclusive(x86_lbr_exclusive_pt); diff --git a/arch/x86/events/intel/uncore.c b/arch/x86/events/intel/uncore.c index 9bf4dbbc26e2..c72e368dd164 100644 --- a/arch/x86/events/intel/uncore.c +++ b/arch/x86/events/intel/uncore.c @@ -842,6 +842,18 @@ static const struct attribute_group uncore_pmu_attr_group = { .attrs = uncore_pmu_attrs, }; +void uncore_get_alias_name(char *pmu_name, struct intel_uncore_pmu *pmu) +{ + struct intel_uncore_type *type = pmu->type; + + if (type->num_boxes == 1) + sprintf(pmu_name, "uncore_type_%u", type->type_id); + else { + sprintf(pmu_name, "uncore_type_%u_%d", + type->type_id, type->box_ids[pmu->pmu_idx]); + } +} + static void uncore_get_pmu_name(struct intel_uncore_pmu *pmu) { struct intel_uncore_type *type = pmu->type; @@ -851,12 +863,7 @@ static void uncore_get_pmu_name(struct intel_uncore_pmu *pmu) * Use uncore_type_&typeid_&boxid as name. */ if (!type->name) { - if (type->num_boxes == 1) - sprintf(pmu->name, "uncore_type_%u", type->type_id); - else { - sprintf(pmu->name, "uncore_type_%u_%d", - type->type_id, type->box_ids[pmu->pmu_idx]); - } + uncore_get_alias_name(pmu->name, pmu); return; } @@ -865,9 +872,13 @@ static void uncore_get_pmu_name(struct intel_uncore_pmu *pmu) sprintf(pmu->name, "uncore_%s", type->name); else sprintf(pmu->name, "uncore"); - } else - sprintf(pmu->name, "uncore_%s_%d", type->name, pmu->pmu_idx); - + } else { + /* + * Use the box ID from the discovery table if applicable. + */ + sprintf(pmu->name, "uncore_%s_%d", type->name, + type->box_ids ? type->box_ids[pmu->pmu_idx] : pmu->pmu_idx); + } } static int uncore_pmu_register(struct intel_uncore_pmu *pmu) @@ -1663,6 +1674,7 @@ struct intel_uncore_init_fun { void (*cpu_init)(void); int (*pci_init)(void); void (*mmio_init)(void); + bool use_discovery; }; static const struct intel_uncore_init_fun nhm_uncore_init __initconst = { @@ -1765,6 +1777,13 @@ static const struct intel_uncore_init_fun snr_uncore_init __initconst = { .mmio_init = snr_uncore_mmio_init, }; +static const struct intel_uncore_init_fun spr_uncore_init __initconst = { + .cpu_init = spr_uncore_cpu_init, + .pci_init = spr_uncore_pci_init, + .mmio_init = spr_uncore_mmio_init, + .use_discovery = true, +}; + static const struct intel_uncore_init_fun generic_uncore_init __initconst = { .cpu_init = intel_uncore_generic_uncore_cpu_init, .pci_init = intel_uncore_generic_uncore_pci_init, @@ -1809,6 +1828,7 @@ static const struct x86_cpu_id intel_uncore_match[] __initconst = { X86_MATCH_INTEL_FAM6_MODEL(ROCKETLAKE, &rkl_uncore_init), X86_MATCH_INTEL_FAM6_MODEL(ALDERLAKE, &adl_uncore_init), X86_MATCH_INTEL_FAM6_MODEL(ALDERLAKE_L, &adl_uncore_init), + X86_MATCH_INTEL_FAM6_MODEL(SAPPHIRERAPIDS_X, &spr_uncore_init), X86_MATCH_INTEL_FAM6_MODEL(ATOM_TREMONT_D, &snr_uncore_init), {}, }; @@ -1832,8 +1852,13 @@ static int __init intel_uncore_init(void) uncore_init = (struct intel_uncore_init_fun *)&generic_uncore_init; else return -ENODEV; - } else + } else { uncore_init = (struct intel_uncore_init_fun *)id->driver_data; + if (uncore_no_discover && uncore_init->use_discovery) + return -ENODEV; + if (uncore_init->use_discovery && !intel_uncore_has_discovery_tables()) + return -ENODEV; + } if (uncore_init->pci_init) { pret = uncore_init->pci_init(); diff --git a/arch/x86/events/intel/uncore.h b/arch/x86/events/intel/uncore.h index 187d7287039c..b9687980aab6 100644 --- a/arch/x86/events/intel/uncore.h +++ b/arch/x86/events/intel/uncore.h @@ -561,6 +561,7 @@ struct event_constraint * uncore_get_constraint(struct intel_uncore_box *box, struct perf_event *event); void uncore_put_constraint(struct intel_uncore_box *box, struct perf_event *event); u64 uncore_shared_reg_config(struct intel_uncore_box *box, int idx); +void uncore_get_alias_name(char *pmu_name, struct intel_uncore_pmu *pmu); extern struct intel_uncore_type *empty_uncore[]; extern struct intel_uncore_type **uncore_msr_uncores; @@ -608,6 +609,9 @@ void snr_uncore_mmio_init(void); int icx_uncore_pci_init(void); void icx_uncore_cpu_init(void); void icx_uncore_mmio_init(void); +int spr_uncore_pci_init(void); +void spr_uncore_cpu_init(void); +void spr_uncore_mmio_init(void); /* uncore_nhmex.c */ void nhmex_uncore_cpu_init(void); diff --git a/arch/x86/events/intel/uncore_discovery.c b/arch/x86/events/intel/uncore_discovery.c index aba9bff95413..3049c646fa20 100644 --- a/arch/x86/events/intel/uncore_discovery.c +++ b/arch/x86/events/intel/uncore_discovery.c @@ -337,17 +337,17 @@ static const struct attribute_group generic_uncore_format_group = { .attrs = generic_uncore_formats_attr, }; -static void intel_generic_uncore_msr_init_box(struct intel_uncore_box *box) +void intel_generic_uncore_msr_init_box(struct intel_uncore_box *box) { wrmsrl(uncore_msr_box_ctl(box), GENERIC_PMON_BOX_CTL_INT); } -static void intel_generic_uncore_msr_disable_box(struct intel_uncore_box *box) +void intel_generic_uncore_msr_disable_box(struct intel_uncore_box *box) { wrmsrl(uncore_msr_box_ctl(box), GENERIC_PMON_BOX_CTL_FRZ); } -static void intel_generic_uncore_msr_enable_box(struct intel_uncore_box *box) +void intel_generic_uncore_msr_enable_box(struct intel_uncore_box *box) { wrmsrl(uncore_msr_box_ctl(box), 0); } @@ -377,7 +377,7 @@ static struct intel_uncore_ops generic_uncore_msr_ops = { .read_counter = uncore_msr_read_counter, }; -static void intel_generic_uncore_pci_init_box(struct intel_uncore_box *box) +void intel_generic_uncore_pci_init_box(struct intel_uncore_box *box) { struct pci_dev *pdev = box->pci_dev; int box_ctl = uncore_pci_box_ctl(box); @@ -386,7 +386,7 @@ static void intel_generic_uncore_pci_init_box(struct intel_uncore_box *box) pci_write_config_dword(pdev, box_ctl, GENERIC_PMON_BOX_CTL_INT); } -static void intel_generic_uncore_pci_disable_box(struct intel_uncore_box *box) +void intel_generic_uncore_pci_disable_box(struct intel_uncore_box *box) { struct pci_dev *pdev = box->pci_dev; int box_ctl = uncore_pci_box_ctl(box); @@ -394,7 +394,7 @@ static void intel_generic_uncore_pci_disable_box(struct intel_uncore_box *box) pci_write_config_dword(pdev, box_ctl, GENERIC_PMON_BOX_CTL_FRZ); } -static void intel_generic_uncore_pci_enable_box(struct intel_uncore_box *box) +void intel_generic_uncore_pci_enable_box(struct intel_uncore_box *box) { struct pci_dev *pdev = box->pci_dev; int box_ctl = uncore_pci_box_ctl(box); @@ -411,8 +411,8 @@ static void intel_generic_uncore_pci_enable_event(struct intel_uncore_box *box, pci_write_config_dword(pdev, hwc->config_base, hwc->config); } -static void intel_generic_uncore_pci_disable_event(struct intel_uncore_box *box, - struct perf_event *event) +void intel_generic_uncore_pci_disable_event(struct intel_uncore_box *box, + struct perf_event *event) { struct pci_dev *pdev = box->pci_dev; struct hw_perf_event *hwc = &event->hw; @@ -420,8 +420,8 @@ static void intel_generic_uncore_pci_disable_event(struct intel_uncore_box *box, pci_write_config_dword(pdev, hwc->config_base, 0); } -static u64 intel_generic_uncore_pci_read_counter(struct intel_uncore_box *box, - struct perf_event *event) +u64 intel_generic_uncore_pci_read_counter(struct intel_uncore_box *box, + struct perf_event *event) { struct pci_dev *pdev = box->pci_dev; struct hw_perf_event *hwc = &event->hw; @@ -454,7 +454,7 @@ static unsigned int generic_uncore_mmio_box_ctl(struct intel_uncore_box *box) return type->box_ctls[box->dieid] + type->mmio_offsets[box->pmu->pmu_idx]; } -static void intel_generic_uncore_mmio_init_box(struct intel_uncore_box *box) +void intel_generic_uncore_mmio_init_box(struct intel_uncore_box *box) { unsigned int box_ctl = generic_uncore_mmio_box_ctl(box); struct intel_uncore_type *type = box->pmu->type; @@ -478,7 +478,7 @@ static void intel_generic_uncore_mmio_init_box(struct intel_uncore_box *box) writel(GENERIC_PMON_BOX_CTL_INT, box->io_addr); } -static void intel_generic_uncore_mmio_disable_box(struct intel_uncore_box *box) +void intel_generic_uncore_mmio_disable_box(struct intel_uncore_box *box) { if (!box->io_addr) return; @@ -486,7 +486,7 @@ static void intel_generic_uncore_mmio_disable_box(struct intel_uncore_box *box) writel(GENERIC_PMON_BOX_CTL_FRZ, box->io_addr); } -static void intel_generic_uncore_mmio_enable_box(struct intel_uncore_box *box) +void intel_generic_uncore_mmio_enable_box(struct intel_uncore_box *box) { if (!box->io_addr) return; @@ -505,8 +505,8 @@ static void intel_generic_uncore_mmio_enable_event(struct intel_uncore_box *box, writel(hwc->config, box->io_addr + hwc->config_base); } -static void intel_generic_uncore_mmio_disable_event(struct intel_uncore_box *box, - struct perf_event *event) +void intel_generic_uncore_mmio_disable_event(struct intel_uncore_box *box, + struct perf_event *event) { struct hw_perf_event *hwc = &event->hw; @@ -568,8 +568,8 @@ static bool uncore_update_uncore_type(enum uncore_access_type type_id, return true; } -static struct intel_uncore_type ** -intel_uncore_generic_init_uncores(enum uncore_access_type type_id) +struct intel_uncore_type ** +intel_uncore_generic_init_uncores(enum uncore_access_type type_id, int num_extra) { struct intel_uncore_discovery_type *type; struct intel_uncore_type **uncores; @@ -577,7 +577,7 @@ intel_uncore_generic_init_uncores(enum uncore_access_type type_id) struct rb_node *node; int i = 0; - uncores = kcalloc(num_discovered_types[type_id] + 1, + uncores = kcalloc(num_discovered_types[type_id] + num_extra + 1, sizeof(struct intel_uncore_type *), GFP_KERNEL); if (!uncores) return empty_uncore; @@ -606,17 +606,17 @@ intel_uncore_generic_init_uncores(enum uncore_access_type type_id) void intel_uncore_generic_uncore_cpu_init(void) { - uncore_msr_uncores = intel_uncore_generic_init_uncores(UNCORE_ACCESS_MSR); + uncore_msr_uncores = intel_uncore_generic_init_uncores(UNCORE_ACCESS_MSR, 0); } int intel_uncore_generic_uncore_pci_init(void) { - uncore_pci_uncores = intel_uncore_generic_init_uncores(UNCORE_ACCESS_PCI); + uncore_pci_uncores = intel_uncore_generic_init_uncores(UNCORE_ACCESS_PCI, 0); return 0; } void intel_uncore_generic_uncore_mmio_init(void) { - uncore_mmio_uncores = intel_uncore_generic_init_uncores(UNCORE_ACCESS_MMIO); + uncore_mmio_uncores = intel_uncore_generic_init_uncores(UNCORE_ACCESS_MMIO, 0); } diff --git a/arch/x86/events/intel/uncore_discovery.h b/arch/x86/events/intel/uncore_discovery.h index 1d652939a01c..7280c8a3c831 100644 --- a/arch/x86/events/intel/uncore_discovery.h +++ b/arch/x86/events/intel/uncore_discovery.h @@ -129,3 +129,24 @@ void intel_uncore_clear_discovery_tables(void); void intel_uncore_generic_uncore_cpu_init(void); int intel_uncore_generic_uncore_pci_init(void); void intel_uncore_generic_uncore_mmio_init(void); + +void intel_generic_uncore_msr_init_box(struct intel_uncore_box *box); +void intel_generic_uncore_msr_disable_box(struct intel_uncore_box *box); +void intel_generic_uncore_msr_enable_box(struct intel_uncore_box *box); + +void intel_generic_uncore_mmio_init_box(struct intel_uncore_box *box); +void intel_generic_uncore_mmio_disable_box(struct intel_uncore_box *box); +void intel_generic_uncore_mmio_enable_box(struct intel_uncore_box *box); +void intel_generic_uncore_mmio_disable_event(struct intel_uncore_box *box, + struct perf_event *event); + +void intel_generic_uncore_pci_init_box(struct intel_uncore_box *box); +void intel_generic_uncore_pci_disable_box(struct intel_uncore_box *box); +void intel_generic_uncore_pci_enable_box(struct intel_uncore_box *box); +void intel_generic_uncore_pci_disable_event(struct intel_uncore_box *box, + struct perf_event *event); +u64 intel_generic_uncore_pci_read_counter(struct intel_uncore_box *box, + struct perf_event *event); + +struct intel_uncore_type ** +intel_uncore_generic_init_uncores(enum uncore_access_type type_id, int num_extra); diff --git a/arch/x86/events/intel/uncore_snbep.c b/arch/x86/events/intel/uncore_snbep.c index 609c24aec71a..5ddc0f30db6f 100644 --- a/arch/x86/events/intel/uncore_snbep.c +++ b/arch/x86/events/intel/uncore_snbep.c @@ -1,6 +1,7 @@ // SPDX-License-Identifier: GPL-2.0 /* SandyBridge-EP/IvyTown uncore support */ #include "uncore.h" +#include "uncore_discovery.h" /* SNB-EP pci bus to socket mapping */ #define SNBEP_CPUNODEID 0x40 @@ -454,6 +455,17 @@ #define ICX_NUMBER_IMC_CHN 2 #define ICX_IMC_MEM_STRIDE 0x4 +/* SPR */ +#define SPR_RAW_EVENT_MASK_EXT 0xffffff + +/* SPR CHA */ +#define SPR_CHA_PMON_CTL_TID_EN (1 << 16) +#define SPR_CHA_PMON_EVENT_MASK (SNBEP_PMON_RAW_EVENT_MASK | \ + SPR_CHA_PMON_CTL_TID_EN) +#define SPR_CHA_PMON_BOX_FILTER_TID 0x3ff + +#define SPR_C0_MSR_PMON_BOX_FILTER0 0x200e + DEFINE_UNCORE_FORMAT_ATTR(event, event, "config:0-7"); DEFINE_UNCORE_FORMAT_ATTR(event2, event, "config:0-6"); DEFINE_UNCORE_FORMAT_ATTR(event_ext, event, "config:0-7,21"); @@ -466,6 +478,7 @@ DEFINE_UNCORE_FORMAT_ATTR(umask_ext4, umask, "config:8-15,32-55"); DEFINE_UNCORE_FORMAT_ATTR(qor, qor, "config:16"); DEFINE_UNCORE_FORMAT_ATTR(edge, edge, "config:18"); DEFINE_UNCORE_FORMAT_ATTR(tid_en, tid_en, "config:19"); +DEFINE_UNCORE_FORMAT_ATTR(tid_en2, tid_en, "config:16"); DEFINE_UNCORE_FORMAT_ATTR(inv, inv, "config:23"); DEFINE_UNCORE_FORMAT_ATTR(thresh9, thresh, "config:24-35"); DEFINE_UNCORE_FORMAT_ATTR(thresh8, thresh, "config:24-31"); @@ -3838,26 +3851,32 @@ clear_attr_update: return ret; } -static int skx_iio_set_mapping(struct intel_uncore_type *type) -{ - return pmu_iio_set_mapping(type, &skx_iio_mapping_group); -} - -static void skx_iio_cleanup_mapping(struct intel_uncore_type *type) +static void +pmu_iio_cleanup_mapping(struct intel_uncore_type *type, struct attribute_group *ag) { - struct attribute **attr = skx_iio_mapping_group.attrs; + struct attribute **attr = ag->attrs; if (!attr) return; for (; *attr; attr++) kfree((*attr)->name); - kfree(attr_to_ext_attr(*skx_iio_mapping_group.attrs)); - kfree(skx_iio_mapping_group.attrs); - skx_iio_mapping_group.attrs = NULL; + kfree(attr_to_ext_attr(*ag->attrs)); + kfree(ag->attrs); + ag->attrs = NULL; kfree(type->topology); } +static int skx_iio_set_mapping(struct intel_uncore_type *type) +{ + return pmu_iio_set_mapping(type, &skx_iio_mapping_group); +} + +static void skx_iio_cleanup_mapping(struct intel_uncore_type *type) +{ + pmu_iio_cleanup_mapping(type, &skx_iio_mapping_group); +} + static struct intel_uncore_type skx_uncore_iio = { .name = "iio", .num_counters = 4, @@ -4501,6 +4520,11 @@ static int snr_iio_set_mapping(struct intel_uncore_type *type) return pmu_iio_set_mapping(type, &snr_iio_mapping_group); } +static void snr_iio_cleanup_mapping(struct intel_uncore_type *type) +{ + pmu_iio_cleanup_mapping(type, &snr_iio_mapping_group); +} + static struct intel_uncore_type snr_uncore_iio = { .name = "iio", .num_counters = 4, @@ -4517,7 +4541,7 @@ static struct intel_uncore_type snr_uncore_iio = { .attr_update = snr_iio_attr_update, .get_topology = snr_iio_get_topology, .set_mapping = snr_iio_set_mapping, - .cleanup_mapping = skx_iio_cleanup_mapping, + .cleanup_mapping = snr_iio_cleanup_mapping, }; static struct intel_uncore_type snr_uncore_irp = { @@ -4783,13 +4807,15 @@ int snr_uncore_pci_init(void) return 0; } -static struct pci_dev *snr_uncore_get_mc_dev(int id) +#define SNR_MC_DEVICE_ID 0x3451 + +static struct pci_dev *snr_uncore_get_mc_dev(unsigned int device, int id) { struct pci_dev *mc_dev = NULL; int pkg; while (1) { - mc_dev = pci_get_device(PCI_VENDOR_ID_INTEL, 0x3451, mc_dev); + mc_dev = pci_get_device(PCI_VENDOR_ID_INTEL, device, mc_dev); if (!mc_dev) break; pkg = uncore_pcibus_to_dieid(mc_dev->bus); @@ -4799,19 +4825,20 @@ static struct pci_dev *snr_uncore_get_mc_dev(int id) return mc_dev; } -static void __snr_uncore_mmio_init_box(struct intel_uncore_box *box, - unsigned int box_ctl, int mem_offset) +static int snr_uncore_mmio_map(struct intel_uncore_box *box, + unsigned int box_ctl, int mem_offset, + unsigned int device) { - struct pci_dev *pdev = snr_uncore_get_mc_dev(box->dieid); + struct pci_dev *pdev = snr_uncore_get_mc_dev(device, box->dieid); struct intel_uncore_type *type = box->pmu->type; resource_size_t addr; u32 pci_dword; if (!pdev) - return; + return -ENODEV; pci_read_config_dword(pdev, SNR_IMC_MMIO_BASE_OFFSET, &pci_dword); - addr = (pci_dword & SNR_IMC_MMIO_BASE_MASK) << 23; + addr = ((resource_size_t)pci_dword & SNR_IMC_MMIO_BASE_MASK) << 23; pci_read_config_dword(pdev, mem_offset, &pci_dword); addr |= (pci_dword & SNR_IMC_MMIO_MEM0_MASK) << 12; @@ -4821,16 +4848,25 @@ static void __snr_uncore_mmio_init_box(struct intel_uncore_box *box, box->io_addr = ioremap(addr, type->mmio_map_size); if (!box->io_addr) { pr_warn("perf uncore: Failed to ioremap for %s.\n", type->name); - return; + return -EINVAL; } - writel(IVBEP_PMON_BOX_CTL_INT, box->io_addr); + return 0; +} + +static void __snr_uncore_mmio_init_box(struct intel_uncore_box *box, + unsigned int box_ctl, int mem_offset, + unsigned int device) +{ + if (!snr_uncore_mmio_map(box, box_ctl, mem_offset, device)) + writel(IVBEP_PMON_BOX_CTL_INT, box->io_addr); } static void snr_uncore_mmio_init_box(struct intel_uncore_box *box) { __snr_uncore_mmio_init_box(box, uncore_mmio_box_ctl(box), - SNR_IMC_MMIO_MEM0_OFFSET); + SNR_IMC_MMIO_MEM0_OFFSET, + SNR_MC_DEVICE_ID); } static void snr_uncore_mmio_disable_box(struct intel_uncore_box *box) @@ -5092,6 +5128,11 @@ static int icx_iio_set_mapping(struct intel_uncore_type *type) return pmu_iio_set_mapping(type, &icx_iio_mapping_group); } +static void icx_iio_cleanup_mapping(struct intel_uncore_type *type) +{ + pmu_iio_cleanup_mapping(type, &icx_iio_mapping_group); +} + static struct intel_uncore_type icx_uncore_iio = { .name = "iio", .num_counters = 4, @@ -5109,7 +5150,7 @@ static struct intel_uncore_type icx_uncore_iio = { .attr_update = icx_iio_attr_update, .get_topology = icx_iio_get_topology, .set_mapping = icx_iio_set_mapping, - .cleanup_mapping = skx_iio_cleanup_mapping, + .cleanup_mapping = icx_iio_cleanup_mapping, }; static struct intel_uncore_type icx_uncore_irp = { @@ -5405,7 +5446,8 @@ static void icx_uncore_imc_init_box(struct intel_uncore_box *box) int mem_offset = (box->pmu->pmu_idx / ICX_NUMBER_IMC_CHN) * ICX_IMC_MEM_STRIDE + SNR_IMC_MMIO_MEM0_OFFSET; - __snr_uncore_mmio_init_box(box, box_ctl, mem_offset); + __snr_uncore_mmio_init_box(box, box_ctl, mem_offset, + SNR_MC_DEVICE_ID); } static struct intel_uncore_ops icx_uncore_mmio_ops = { @@ -5475,7 +5517,8 @@ static void icx_uncore_imc_freerunning_init_box(struct intel_uncore_box *box) int mem_offset = box->pmu->pmu_idx * ICX_IMC_MEM_STRIDE + SNR_IMC_MMIO_MEM0_OFFSET; - __snr_uncore_mmio_init_box(box, uncore_mmio_box_ctl(box), mem_offset); + snr_uncore_mmio_map(box, uncore_mmio_box_ctl(box), + mem_offset, SNR_MC_DEVICE_ID); } static struct intel_uncore_ops icx_uncore_imc_freerunning_ops = { @@ -5509,3 +5552,497 @@ void icx_uncore_mmio_init(void) } /* end of ICX uncore support */ + +/* SPR uncore support */ + +static void spr_uncore_msr_enable_event(struct intel_uncore_box *box, + struct perf_event *event) +{ + struct hw_perf_event *hwc = &event->hw; + struct hw_perf_event_extra *reg1 = &hwc->extra_reg; + + if (reg1->idx != EXTRA_REG_NONE) + wrmsrl(reg1->reg, reg1->config); + + wrmsrl(hwc->config_base, hwc->config); +} + +static void spr_uncore_msr_disable_event(struct intel_uncore_box *box, + struct perf_event *event) +{ + struct hw_perf_event *hwc = &event->hw; + struct hw_perf_event_extra *reg1 = &hwc->extra_reg; + + if (reg1->idx != EXTRA_REG_NONE) + wrmsrl(reg1->reg, 0); + + wrmsrl(hwc->config_base, 0); +} + +static int spr_cha_hw_config(struct intel_uncore_box *box, struct perf_event *event) +{ + struct hw_perf_event_extra *reg1 = &event->hw.extra_reg; + bool tie_en = !!(event->hw.config & SPR_CHA_PMON_CTL_TID_EN); + struct intel_uncore_type *type = box->pmu->type; + + if (tie_en) { + reg1->reg = SPR_C0_MSR_PMON_BOX_FILTER0 + + HSWEP_CBO_MSR_OFFSET * type->box_ids[box->pmu->pmu_idx]; + reg1->config = event->attr.config1 & SPR_CHA_PMON_BOX_FILTER_TID; + reg1->idx = 0; + } + + return 0; +} + +static struct intel_uncore_ops spr_uncore_chabox_ops = { + .init_box = intel_generic_uncore_msr_init_box, + .disable_box = intel_generic_uncore_msr_disable_box, + .enable_box = intel_generic_uncore_msr_enable_box, + .disable_event = spr_uncore_msr_disable_event, + .enable_event = spr_uncore_msr_enable_event, + .read_counter = uncore_msr_read_counter, + .hw_config = spr_cha_hw_config, + .get_constraint = uncore_get_constraint, + .put_constraint = uncore_put_constraint, +}; + +static struct attribute *spr_uncore_cha_formats_attr[] = { + &format_attr_event.attr, + &format_attr_umask_ext4.attr, + &format_attr_tid_en2.attr, + &format_attr_edge.attr, + &format_attr_inv.attr, + &format_attr_thresh8.attr, + &format_attr_filter_tid5.attr, + NULL, +}; +static const struct attribute_group spr_uncore_chabox_format_group = { + .name = "format", + .attrs = spr_uncore_cha_formats_attr, +}; + +static ssize_t alias_show(struct device *dev, + struct device_attribute *attr, + char *buf) +{ + struct intel_uncore_pmu *pmu = dev_to_uncore_pmu(dev); + char pmu_name[UNCORE_PMU_NAME_LEN]; + + uncore_get_alias_name(pmu_name, pmu); + return sysfs_emit(buf, "%s\n", pmu_name); +} + +static DEVICE_ATTR_RO(alias); + +static struct attribute *uncore_alias_attrs[] = { + &dev_attr_alias.attr, + NULL +}; + +ATTRIBUTE_GROUPS(uncore_alias); + +static struct intel_uncore_type spr_uncore_chabox = { + .name = "cha", + .event_mask = SPR_CHA_PMON_EVENT_MASK, + .event_mask_ext = SPR_RAW_EVENT_MASK_EXT, + .num_shared_regs = 1, + .ops = &spr_uncore_chabox_ops, + .format_group = &spr_uncore_chabox_format_group, + .attr_update = uncore_alias_groups, +}; + +static struct intel_uncore_type spr_uncore_iio = { + .name = "iio", + .event_mask = SNBEP_PMON_RAW_EVENT_MASK, + .event_mask_ext = SNR_IIO_PMON_RAW_EVENT_MASK_EXT, + .format_group = &snr_uncore_iio_format_group, + .attr_update = uncore_alias_groups, +}; + +static struct attribute *spr_uncore_raw_formats_attr[] = { + &format_attr_event.attr, + &format_attr_umask_ext4.attr, + &format_attr_edge.attr, + &format_attr_inv.attr, + &format_attr_thresh8.attr, + NULL, +}; + +static const struct attribute_group spr_uncore_raw_format_group = { + .name = "format", + .attrs = spr_uncore_raw_formats_attr, +}; + +#define SPR_UNCORE_COMMON_FORMAT() \ + .event_mask = SNBEP_PMON_RAW_EVENT_MASK, \ + .event_mask_ext = SPR_RAW_EVENT_MASK_EXT, \ + .format_group = &spr_uncore_raw_format_group, \ + .attr_update = uncore_alias_groups + +static struct intel_uncore_type spr_uncore_irp = { + SPR_UNCORE_COMMON_FORMAT(), + .name = "irp", + +}; + +static struct intel_uncore_type spr_uncore_m2pcie = { + SPR_UNCORE_COMMON_FORMAT(), + .name = "m2pcie", +}; + +static struct intel_uncore_type spr_uncore_pcu = { + .name = "pcu", + .attr_update = uncore_alias_groups, +}; + +static void spr_uncore_mmio_enable_event(struct intel_uncore_box *box, + struct perf_event *event) +{ + struct hw_perf_event *hwc = &event->hw; + + if (!box->io_addr) + return; + + if (uncore_pmc_fixed(hwc->idx)) + writel(SNBEP_PMON_CTL_EN, box->io_addr + hwc->config_base); + else + writel(hwc->config, box->io_addr + hwc->config_base); +} + +static struct intel_uncore_ops spr_uncore_mmio_ops = { + .init_box = intel_generic_uncore_mmio_init_box, + .exit_box = uncore_mmio_exit_box, + .disable_box = intel_generic_uncore_mmio_disable_box, + .enable_box = intel_generic_uncore_mmio_enable_box, + .disable_event = intel_generic_uncore_mmio_disable_event, + .enable_event = spr_uncore_mmio_enable_event, + .read_counter = uncore_mmio_read_counter, +}; + +static struct intel_uncore_type spr_uncore_imc = { + SPR_UNCORE_COMMON_FORMAT(), + .name = "imc", + .fixed_ctr_bits = 48, + .fixed_ctr = SNR_IMC_MMIO_PMON_FIXED_CTR, + .fixed_ctl = SNR_IMC_MMIO_PMON_FIXED_CTL, + .ops = &spr_uncore_mmio_ops, +}; + +static void spr_uncore_pci_enable_event(struct intel_uncore_box *box, + struct perf_event *event) +{ + struct pci_dev *pdev = box->pci_dev; + struct hw_perf_event *hwc = &event->hw; + + pci_write_config_dword(pdev, hwc->config_base + 4, (u32)(hwc->config >> 32)); + pci_write_config_dword(pdev, hwc->config_base, (u32)hwc->config); +} + +static struct intel_uncore_ops spr_uncore_pci_ops = { + .init_box = intel_generic_uncore_pci_init_box, + .disable_box = intel_generic_uncore_pci_disable_box, + .enable_box = intel_generic_uncore_pci_enable_box, + .disable_event = intel_generic_uncore_pci_disable_event, + .enable_event = spr_uncore_pci_enable_event, + .read_counter = intel_generic_uncore_pci_read_counter, +}; + +#define SPR_UNCORE_PCI_COMMON_FORMAT() \ + SPR_UNCORE_COMMON_FORMAT(), \ + .ops = &spr_uncore_pci_ops + +static struct intel_uncore_type spr_uncore_m2m = { + SPR_UNCORE_PCI_COMMON_FORMAT(), + .name = "m2m", +}; + +static struct intel_uncore_type spr_uncore_upi = { + SPR_UNCORE_PCI_COMMON_FORMAT(), + .name = "upi", +}; + +static struct intel_uncore_type spr_uncore_m3upi = { + SPR_UNCORE_PCI_COMMON_FORMAT(), + .name = "m3upi", +}; + +static struct intel_uncore_type spr_uncore_mdf = { + SPR_UNCORE_COMMON_FORMAT(), + .name = "mdf", +}; + +#define UNCORE_SPR_NUM_UNCORE_TYPES 12 +#define UNCORE_SPR_IIO 1 +#define UNCORE_SPR_IMC 6 + +static struct intel_uncore_type *spr_uncores[UNCORE_SPR_NUM_UNCORE_TYPES] = { + &spr_uncore_chabox, + &spr_uncore_iio, + &spr_uncore_irp, + &spr_uncore_m2pcie, + &spr_uncore_pcu, + NULL, + &spr_uncore_imc, + &spr_uncore_m2m, + &spr_uncore_upi, + &spr_uncore_m3upi, + NULL, + &spr_uncore_mdf, +}; + +enum perf_uncore_spr_iio_freerunning_type_id { + SPR_IIO_MSR_IOCLK, + SPR_IIO_MSR_BW_IN, + SPR_IIO_MSR_BW_OUT, + + SPR_IIO_FREERUNNING_TYPE_MAX, +}; + +static struct freerunning_counters spr_iio_freerunning[] = { + [SPR_IIO_MSR_IOCLK] = { 0x340e, 0x1, 0x10, 1, 48 }, + [SPR_IIO_MSR_BW_IN] = { 0x3800, 0x1, 0x10, 8, 48 }, + [SPR_IIO_MSR_BW_OUT] = { 0x3808, 0x1, 0x10, 8, 48 }, +}; + +static struct uncore_event_desc spr_uncore_iio_freerunning_events[] = { + /* Free-Running IIO CLOCKS Counter */ + INTEL_UNCORE_EVENT_DESC(ioclk, "event=0xff,umask=0x10"), + /* Free-Running IIO BANDWIDTH IN Counters */ + INTEL_UNCORE_EVENT_DESC(bw_in_port0, "event=0xff,umask=0x20"), + INTEL_UNCORE_EVENT_DESC(bw_in_port0.scale, "3.814697266e-6"), + INTEL_UNCORE_EVENT_DESC(bw_in_port0.unit, "MiB"), + INTEL_UNCORE_EVENT_DESC(bw_in_port1, "event=0xff,umask=0x21"), + INTEL_UNCORE_EVENT_DESC(bw_in_port1.scale, "3.814697266e-6"), + INTEL_UNCORE_EVENT_DESC(bw_in_port1.unit, "MiB"), + INTEL_UNCORE_EVENT_DESC(bw_in_port2, "event=0xff,umask=0x22"), + INTEL_UNCORE_EVENT_DESC(bw_in_port2.scale, "3.814697266e-6"), + INTEL_UNCORE_EVENT_DESC(bw_in_port2.unit, "MiB"), + INTEL_UNCORE_EVENT_DESC(bw_in_port3, "event=0xff,umask=0x23"), + INTEL_UNCORE_EVENT_DESC(bw_in_port3.scale, "3.814697266e-6"), + INTEL_UNCORE_EVENT_DESC(bw_in_port3.unit, "MiB"), + INTEL_UNCORE_EVENT_DESC(bw_in_port4, "event=0xff,umask=0x24"), + INTEL_UNCORE_EVENT_DESC(bw_in_port4.scale, "3.814697266e-6"), + INTEL_UNCORE_EVENT_DESC(bw_in_port4.unit, "MiB"), + INTEL_UNCORE_EVENT_DESC(bw_in_port5, "event=0xff,umask=0x25"), + INTEL_UNCORE_EVENT_DESC(bw_in_port5.scale, "3.814697266e-6"), + INTEL_UNCORE_EVENT_DESC(bw_in_port5.unit, "MiB"), + INTEL_UNCORE_EVENT_DESC(bw_in_port6, "event=0xff,umask=0x26"), + INTEL_UNCORE_EVENT_DESC(bw_in_port6.scale, "3.814697266e-6"), + INTEL_UNCORE_EVENT_DESC(bw_in_port6.unit, "MiB"), + INTEL_UNCORE_EVENT_DESC(bw_in_port7, "event=0xff,umask=0x27"), + INTEL_UNCORE_EVENT_DESC(bw_in_port7.scale, "3.814697266e-6"), + INTEL_UNCORE_EVENT_DESC(bw_in_port7.unit, "MiB"), + /* Free-Running IIO BANDWIDTH OUT Counters */ + INTEL_UNCORE_EVENT_DESC(bw_out_port0, "event=0xff,umask=0x30"), + INTEL_UNCORE_EVENT_DESC(bw_out_port0.scale, "3.814697266e-6"), + INTEL_UNCORE_EVENT_DESC(bw_out_port0.unit, "MiB"), + INTEL_UNCORE_EVENT_DESC(bw_out_port1, "event=0xff,umask=0x31"), + INTEL_UNCORE_EVENT_DESC(bw_out_port1.scale, "3.814697266e-6"), + INTEL_UNCORE_EVENT_DESC(bw_out_port1.unit, "MiB"), + INTEL_UNCORE_EVENT_DESC(bw_out_port2, "event=0xff,umask=0x32"), + INTEL_UNCORE_EVENT_DESC(bw_out_port2.scale, "3.814697266e-6"), + INTEL_UNCORE_EVENT_DESC(bw_out_port2.unit, "MiB"), + INTEL_UNCORE_EVENT_DESC(bw_out_port3, "event=0xff,umask=0x33"), + INTEL_UNCORE_EVENT_DESC(bw_out_port3.scale, "3.814697266e-6"), + INTEL_UNCORE_EVENT_DESC(bw_out_port3.unit, "MiB"), + INTEL_UNCORE_EVENT_DESC(bw_out_port4, "event=0xff,umask=0x34"), + INTEL_UNCORE_EVENT_DESC(bw_out_port4.scale, "3.814697266e-6"), + INTEL_UNCORE_EVENT_DESC(bw_out_port4.unit, "MiB"), + INTEL_UNCORE_EVENT_DESC(bw_out_port5, "event=0xff,umask=0x35"), + INTEL_UNCORE_EVENT_DESC(bw_out_port5.scale, "3.814697266e-6"), + INTEL_UNCORE_EVENT_DESC(bw_out_port5.unit, "MiB"), + INTEL_UNCORE_EVENT_DESC(bw_out_port6, "event=0xff,umask=0x36"), + INTEL_UNCORE_EVENT_DESC(bw_out_port6.scale, "3.814697266e-6"), + INTEL_UNCORE_EVENT_DESC(bw_out_port6.unit, "MiB"), + INTEL_UNCORE_EVENT_DESC(bw_out_port7, "event=0xff,umask=0x37"), + INTEL_UNCORE_EVENT_DESC(bw_out_port7.scale, "3.814697266e-6"), + INTEL_UNCORE_EVENT_DESC(bw_out_port7.unit, "MiB"), + { /* end: all zeroes */ }, +}; + +static struct intel_uncore_type spr_uncore_iio_free_running = { + .name = "iio_free_running", + .num_counters = 17, + .num_freerunning_types = SPR_IIO_FREERUNNING_TYPE_MAX, + .freerunning = spr_iio_freerunning, + .ops = &skx_uncore_iio_freerunning_ops, + .event_descs = spr_uncore_iio_freerunning_events, + .format_group = &skx_uncore_iio_freerunning_format_group, +}; + +enum perf_uncore_spr_imc_freerunning_type_id { + SPR_IMC_DCLK, + SPR_IMC_PQ_CYCLES, + + SPR_IMC_FREERUNNING_TYPE_MAX, +}; + +static struct freerunning_counters spr_imc_freerunning[] = { + [SPR_IMC_DCLK] = { 0x22b0, 0x0, 0, 1, 48 }, + [SPR_IMC_PQ_CYCLES] = { 0x2318, 0x8, 0, 2, 48 }, +}; + +static struct uncore_event_desc spr_uncore_imc_freerunning_events[] = { + INTEL_UNCORE_EVENT_DESC(dclk, "event=0xff,umask=0x10"), + + INTEL_UNCORE_EVENT_DESC(rpq_cycles, "event=0xff,umask=0x20"), + INTEL_UNCORE_EVENT_DESC(wpq_cycles, "event=0xff,umask=0x21"), + { /* end: all zeroes */ }, +}; + +#define SPR_MC_DEVICE_ID 0x3251 + +static void spr_uncore_imc_freerunning_init_box(struct intel_uncore_box *box) +{ + int mem_offset = box->pmu->pmu_idx * ICX_IMC_MEM_STRIDE + SNR_IMC_MMIO_MEM0_OFFSET; + + snr_uncore_mmio_map(box, uncore_mmio_box_ctl(box), + mem_offset, SPR_MC_DEVICE_ID); +} + +static struct intel_uncore_ops spr_uncore_imc_freerunning_ops = { + .init_box = spr_uncore_imc_freerunning_init_box, + .exit_box = uncore_mmio_exit_box, + .read_counter = uncore_mmio_read_counter, + .hw_config = uncore_freerunning_hw_config, +}; + +static struct intel_uncore_type spr_uncore_imc_free_running = { + .name = "imc_free_running", + .num_counters = 3, + .mmio_map_size = SNR_IMC_MMIO_SIZE, + .num_freerunning_types = SPR_IMC_FREERUNNING_TYPE_MAX, + .freerunning = spr_imc_freerunning, + .ops = &spr_uncore_imc_freerunning_ops, + .event_descs = spr_uncore_imc_freerunning_events, + .format_group = &skx_uncore_iio_freerunning_format_group, +}; + +#define UNCORE_SPR_MSR_EXTRA_UNCORES 1 +#define UNCORE_SPR_MMIO_EXTRA_UNCORES 1 + +static struct intel_uncore_type *spr_msr_uncores[UNCORE_SPR_MSR_EXTRA_UNCORES] = { + &spr_uncore_iio_free_running, +}; + +static struct intel_uncore_type *spr_mmio_uncores[UNCORE_SPR_MMIO_EXTRA_UNCORES] = { + &spr_uncore_imc_free_running, +}; + +static void uncore_type_customized_copy(struct intel_uncore_type *to_type, + struct intel_uncore_type *from_type) +{ + if (!to_type || !from_type) + return; + + if (from_type->name) + to_type->name = from_type->name; + if (from_type->fixed_ctr_bits) + to_type->fixed_ctr_bits = from_type->fixed_ctr_bits; + if (from_type->event_mask) + to_type->event_mask = from_type->event_mask; + if (from_type->event_mask_ext) + to_type->event_mask_ext = from_type->event_mask_ext; + if (from_type->fixed_ctr) + to_type->fixed_ctr = from_type->fixed_ctr; + if (from_type->fixed_ctl) + to_type->fixed_ctl = from_type->fixed_ctl; + if (from_type->fixed_ctr_bits) + to_type->fixed_ctr_bits = from_type->fixed_ctr_bits; + if (from_type->num_shared_regs) + to_type->num_shared_regs = from_type->num_shared_regs; + if (from_type->constraints) + to_type->constraints = from_type->constraints; + if (from_type->ops) + to_type->ops = from_type->ops; + if (from_type->event_descs) + to_type->event_descs = from_type->event_descs; + if (from_type->format_group) + to_type->format_group = from_type->format_group; + if (from_type->attr_update) + to_type->attr_update = from_type->attr_update; +} + +static struct intel_uncore_type ** +uncore_get_uncores(enum uncore_access_type type_id, int num_extra, + struct intel_uncore_type **extra) +{ + struct intel_uncore_type **types, **start_types; + int i; + + start_types = types = intel_uncore_generic_init_uncores(type_id, num_extra); + + /* Only copy the customized features */ + for (; *types; types++) { + if ((*types)->type_id >= UNCORE_SPR_NUM_UNCORE_TYPES) + continue; + uncore_type_customized_copy(*types, spr_uncores[(*types)->type_id]); + } + + for (i = 0; i < num_extra; i++, types++) + *types = extra[i]; + + return start_types; +} + +static struct intel_uncore_type * +uncore_find_type_by_id(struct intel_uncore_type **types, int type_id) +{ + for (; *types; types++) { + if (type_id == (*types)->type_id) + return *types; + } + + return NULL; +} + +static int uncore_type_max_boxes(struct intel_uncore_type **types, + int type_id) +{ + struct intel_uncore_type *type; + int i, max = 0; + + type = uncore_find_type_by_id(types, type_id); + if (!type) + return 0; + + for (i = 0; i < type->num_boxes; i++) { + if (type->box_ids[i] > max) + max = type->box_ids[i]; + } + + return max + 1; +} + +void spr_uncore_cpu_init(void) +{ + uncore_msr_uncores = uncore_get_uncores(UNCORE_ACCESS_MSR, + UNCORE_SPR_MSR_EXTRA_UNCORES, + spr_msr_uncores); + + spr_uncore_iio_free_running.num_boxes = uncore_type_max_boxes(uncore_msr_uncores, UNCORE_SPR_IIO); +} + +int spr_uncore_pci_init(void) +{ + uncore_pci_uncores = uncore_get_uncores(UNCORE_ACCESS_PCI, 0, NULL); + return 0; +} + +void spr_uncore_mmio_init(void) +{ + int ret = snbep_pci2phy_map_init(0x3250, SKX_CPUNODEID, SKX_GIDNIDMAP, true); + + if (ret) + uncore_mmio_uncores = uncore_get_uncores(UNCORE_ACCESS_MMIO, 0, NULL); + else { + uncore_mmio_uncores = uncore_get_uncores(UNCORE_ACCESS_MMIO, + UNCORE_SPR_MMIO_EXTRA_UNCORES, + spr_mmio_uncores); + + spr_uncore_imc_free_running.num_boxes = uncore_type_max_boxes(uncore_mmio_uncores, UNCORE_SPR_IMC) / 2; + } +} + +/* end of SPR uncore support */ diff --git a/arch/x86/events/perf_event.h b/arch/x86/events/perf_event.h index 2bf1c7ea2758..e3ac05c97b5e 100644 --- a/arch/x86/events/perf_event.h +++ b/arch/x86/events/perf_event.h @@ -656,6 +656,10 @@ struct x86_hybrid_pmu { struct event_constraint *event_constraints; struct event_constraint *pebs_constraints; struct extra_reg *extra_regs; + + unsigned int late_ack :1, + mid_ack :1, + enabled_ack :1; }; static __always_inline struct x86_hybrid_pmu *hybrid_pmu(struct pmu *pmu) @@ -686,6 +690,16 @@ extern struct static_key_false perf_is_hybrid; __Fp; \ })) +#define hybrid_bit(_pmu, _field) \ +({ \ + bool __Fp = x86_pmu._field; \ + \ + if (is_hybrid() && (_pmu)) \ + __Fp = hybrid_pmu(_pmu)->_field; \ + \ + __Fp; \ +}) + enum hybrid_pmu_type { hybrid_big = 0x40, hybrid_small = 0x20, @@ -755,6 +769,7 @@ struct x86_pmu { /* PMI handler bits */ unsigned int late_ack :1, + mid_ack :1, enabled_ack :1; /* * sysfs attrs @@ -1115,9 +1130,10 @@ void x86_pmu_stop(struct perf_event *event, int flags); static inline void x86_pmu_disable_event(struct perf_event *event) { + u64 disable_mask = __this_cpu_read(cpu_hw_events.perf_ctr_virt_mask); struct hw_perf_event *hwc = &event->hw; - wrmsrl(hwc->config_base, hwc->config); + wrmsrl(hwc->config_base, hwc->config & ~disable_mask); if (is_counter_pair(hwc)) wrmsrl(x86_pmu_config_addr(hwc->idx + 1), 0); diff --git a/arch/x86/hyperv/hv_init.c b/arch/x86/hyperv/hv_init.c index 6952e219cba3..708a2712a516 100644 --- a/arch/x86/hyperv/hv_init.c +++ b/arch/x86/hyperv/hv_init.c @@ -7,10 +7,10 @@ * Author : K. Y. Srinivasan <kys@microsoft.com> */ -#include <linux/acpi.h> #include <linux/efi.h> #include <linux/types.h> #include <linux/bitfield.h> +#include <linux/io.h> #include <asm/apic.h> #include <asm/desc.h> #include <asm/hypervisor.h> @@ -39,71 +39,50 @@ EXPORT_SYMBOL_GPL(hv_hypercall_pg); /* Storage to save the hypercall page temporarily for hibernation */ static void *hv_hypercall_pg_saved; -u32 *hv_vp_index; -EXPORT_SYMBOL_GPL(hv_vp_index); - struct hv_vp_assist_page **hv_vp_assist_page; 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); - static int hv_cpu_init(unsigned int cpu) { - u64 msr_vp_index; + union hv_vp_assist_msr_contents msr = { 0 }; struct hv_vp_assist_page **hvp = &hv_vp_assist_page[smp_processor_id()]; - void **input_arg; - struct page *pg; - - /* hv_cpu_init() can be called with IRQs disabled from hv_resume() */ - 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); - } - - msr_vp_index = hv_get_register(HV_REGISTER_VP_INDEX); - - hv_vp_index[smp_processor_id()] = msr_vp_index; + int ret; - if (msr_vp_index > hv_max_vp_index) - hv_max_vp_index = msr_vp_index; + ret = hv_common_cpu_init(cpu); + if (ret) + return ret; if (!hv_vp_assist_page) return 0; - /* - * The VP ASSIST PAGE is an "overlay" page (see Hyper-V TLFS's Section - * 5.2.1 "GPA Overlay Pages"). Here it must be zeroed out to make sure - * we always write the EOI MSR in hv_apic_eoi_write() *after* the - * EOI optimization is disabled in hv_cpu_die(), otherwise a CPU may - * not be stopped in the case of CPU offlining and the VM will hang. - */ if (!*hvp) { - *hvp = __vmalloc(PAGE_SIZE, GFP_KERNEL | __GFP_ZERO); - } - - if (*hvp) { - u64 val; - - val = vmalloc_to_pfn(*hvp); - val = (val << HV_X64_MSR_VP_ASSIST_PAGE_ADDRESS_SHIFT) | - HV_X64_MSR_VP_ASSIST_PAGE_ENABLE; - - wrmsrl(HV_X64_MSR_VP_ASSIST_PAGE, val); + if (hv_root_partition) { + /* + * For root partition we get the hypervisor provided VP assist + * page, instead of allocating a new page. + */ + rdmsrl(HV_X64_MSR_VP_ASSIST_PAGE, msr.as_uint64); + *hvp = memremap(msr.pfn << + HV_X64_MSR_VP_ASSIST_PAGE_ADDRESS_SHIFT, + PAGE_SIZE, MEMREMAP_WB); + } else { + /* + * The VP assist page is an "overlay" page (see Hyper-V TLFS's + * Section 5.2.1 "GPA Overlay Pages"). Here it must be zeroed + * out to make sure we always write the EOI MSR in + * hv_apic_eoi_write() *after* the EOI optimization is disabled + * in hv_cpu_die(), otherwise a CPU may not be stopped in the + * case of CPU offlining and the VM will hang. + */ + *hvp = __vmalloc(PAGE_SIZE, GFP_KERNEL | __GFP_ZERO); + if (*hvp) + msr.pfn = vmalloc_to_pfn(*hvp); + } + WARN_ON(!(*hvp)); + if (*hvp) { + msr.enable = 1; + wrmsrl(HV_X64_MSR_VP_ASSIST_PAGE, msr.as_uint64); + } } return 0; @@ -198,29 +177,26 @@ static int hv_cpu_die(unsigned int cpu) { struct hv_reenlightenment_control re_ctrl; unsigned int new_cpu; - unsigned long flags; - void **input_arg; - void *pg; - local_irq_save(flags); - input_arg = (void **)this_cpu_ptr(hyperv_pcpu_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; + hv_common_cpu_die(cpu); + + if (hv_vp_assist_page && hv_vp_assist_page[cpu]) { + union hv_vp_assist_msr_contents msr = { 0 }; + if (hv_root_partition) { + /* + * For root partition the VP assist page is mapped to + * hypervisor provided page, and thus we unmap the + * page here and nullify it, so that in future we have + * correct page address mapped in hv_cpu_init. + */ + memunmap(hv_vp_assist_page[cpu]); + hv_vp_assist_page[cpu] = NULL; + rdmsrl(HV_X64_MSR_VP_ASSIST_PAGE, msr.as_uint64); + msr.enable = 0; + } + wrmsrl(HV_X64_MSR_VP_ASSIST_PAGE, msr.as_uint64); } - local_irq_restore(flags); - - 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); - if (hv_reenlightenment_cb == NULL) return 0; @@ -368,7 +344,7 @@ void __init hyperv_init(void) { u64 guest_id, required_msrs; union hv_x64_msr_hypercall_contents hypercall_msr; - int cpuhp, i; + int cpuhp; if (x86_hyper_type != X86_HYPER_MS_HYPERV) return; @@ -380,36 +356,14 @@ void __init hyperv_init(void) if ((ms_hyperv.features & required_msrs) != required_msrs) return; - /* - * Allocate the per-CPU state for the hypercall input arg. - * If this allocation fails, we will not be able to setup - * (per-CPU) hypercall input page and thus this failure is - * fatal on Hyper-V. - */ - hyperv_pcpu_input_arg = alloc_percpu(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); - if (!hv_vp_index) + if (hv_common_init()) return; - for (i = 0; i < num_possible_cpus(); i++) - hv_vp_index[i] = VP_INVAL; - hv_vp_assist_page = kcalloc(num_possible_cpus(), sizeof(*hv_vp_assist_page), GFP_KERNEL); if (!hv_vp_assist_page) { ms_hyperv.hints &= ~HV_X64_ENLIGHTENED_VMCS_RECOMMENDED; - goto free_vp_index; + goto common_free; } cpuhp = cpuhp_setup_state(CPUHP_AP_ONLINE_DYN, "x86/hyperv_init:online", @@ -507,9 +461,8 @@ remove_cpuhp_state: free_vp_assist_page: kfree(hv_vp_assist_page); hv_vp_assist_page = NULL; -free_vp_index: - kfree(hv_vp_index); - hv_vp_index = NULL; +common_free: + hv_common_free(); } /* @@ -539,7 +492,6 @@ void hyperv_cleanup(void) hypercall_msr.as_uint64 = 0; wrmsrl(HV_X64_MSR_REFERENCE_TSC, hypercall_msr.as_uint64); } -EXPORT_SYMBOL_GPL(hyperv_cleanup); void hyperv_report_panic(struct pt_regs *regs, long err, bool in_die) { @@ -595,12 +547,6 @@ bool hv_is_hyperv_initialized(void) } EXPORT_SYMBOL_GPL(hv_is_hyperv_initialized); -bool hv_is_hibernation_supported(void) -{ - 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.priv_high & HV_ISOLATION)) @@ -613,4 +559,3 @@ 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/ia32/ia32_aout.c b/arch/x86/ia32/ia32_aout.c index 5e5b9fc2747f..9bd15241fadb 100644 --- a/arch/x86/ia32/ia32_aout.c +++ b/arch/x86/ia32/ia32_aout.c @@ -202,8 +202,7 @@ static int load_aout_binary(struct linux_binprm *bprm) error = vm_mmap(bprm->file, N_TXTADDR(ex), ex.a_text, PROT_READ | PROT_EXEC, - MAP_FIXED | MAP_PRIVATE | MAP_DENYWRITE | - MAP_32BIT, + MAP_FIXED | MAP_PRIVATE | MAP_32BIT, fd_offset); if (error != N_TXTADDR(ex)) @@ -211,8 +210,7 @@ static int load_aout_binary(struct linux_binprm *bprm) error = vm_mmap(bprm->file, N_DATADDR(ex), ex.a_data, PROT_READ | PROT_WRITE | PROT_EXEC, - MAP_FIXED | MAP_PRIVATE | MAP_DENYWRITE | - MAP_32BIT, + MAP_FIXED | MAP_PRIVATE | MAP_32BIT, fd_offset + ex.a_text); if (error != N_DATADDR(ex)) return error; @@ -293,7 +291,7 @@ static int load_aout_library(struct file *file) /* Now use mmap to map the library into memory. */ error = vm_mmap(file, start_addr, ex.a_text + ex.a_data, PROT_READ | PROT_WRITE | PROT_EXEC, - MAP_FIXED | MAP_PRIVATE | MAP_DENYWRITE | MAP_32BIT, + MAP_FIXED | MAP_PRIVATE | MAP_32BIT, N_TXTOFF(ex)); retval = error; if (error != start_addr) diff --git a/arch/x86/include/asm/amd-ibs.h b/arch/x86/include/asm/amd-ibs.h new file mode 100644 index 000000000000..46e1df45efc0 --- /dev/null +++ b/arch/x86/include/asm/amd-ibs.h @@ -0,0 +1,132 @@ +/* SPDX-License-Identifier: GPL-2.0 */ +/* + * From PPR Vol 1 for AMD Family 19h Model 01h B1 + * 55898 Rev 0.35 - Feb 5, 2021 + */ + +#include <asm/msr-index.h> + +/* + * IBS Hardware MSRs + */ + +/* MSR 0xc0011030: IBS Fetch Control */ +union ibs_fetch_ctl { + __u64 val; + struct { + __u64 fetch_maxcnt:16,/* 0-15: instruction fetch max. count */ + fetch_cnt:16, /* 16-31: instruction fetch count */ + fetch_lat:16, /* 32-47: instruction fetch latency */ + fetch_en:1, /* 48: instruction fetch enable */ + fetch_val:1, /* 49: instruction fetch valid */ + fetch_comp:1, /* 50: instruction fetch complete */ + ic_miss:1, /* 51: i-cache miss */ + phy_addr_valid:1,/* 52: physical address valid */ + l1tlb_pgsz:2, /* 53-54: i-cache L1TLB page size + * (needs IbsPhyAddrValid) */ + l1tlb_miss:1, /* 55: i-cache fetch missed in L1TLB */ + l2tlb_miss:1, /* 56: i-cache fetch missed in L2TLB */ + rand_en:1, /* 57: random tagging enable */ + fetch_l2_miss:1,/* 58: L2 miss for sampled fetch + * (needs IbsFetchComp) */ + reserved:5; /* 59-63: reserved */ + }; +}; + +/* MSR 0xc0011033: IBS Execution Control */ +union ibs_op_ctl { + __u64 val; + struct { + __u64 opmaxcnt:16, /* 0-15: periodic op max. count */ + reserved0:1, /* 16: reserved */ + op_en:1, /* 17: op sampling enable */ + op_val:1, /* 18: op sample valid */ + cnt_ctl:1, /* 19: periodic op counter control */ + opmaxcnt_ext:7, /* 20-26: upper 7 bits of periodic op maximum count */ + reserved1:5, /* 27-31: reserved */ + opcurcnt:27, /* 32-58: periodic op counter current count */ + reserved2:5; /* 59-63: reserved */ + }; +}; + +/* MSR 0xc0011035: IBS Op Data 2 */ +union ibs_op_data { + __u64 val; + struct { + __u64 comp_to_ret_ctr:16, /* 0-15: op completion to retire count */ + tag_to_ret_ctr:16, /* 15-31: op tag to retire count */ + reserved1:2, /* 32-33: reserved */ + op_return:1, /* 34: return op */ + op_brn_taken:1, /* 35: taken branch op */ + op_brn_misp:1, /* 36: mispredicted branch op */ + op_brn_ret:1, /* 37: branch op retired */ + op_rip_invalid:1, /* 38: RIP is invalid */ + op_brn_fuse:1, /* 39: fused branch op */ + op_microcode:1, /* 40: microcode op */ + reserved2:23; /* 41-63: reserved */ + }; +}; + +/* MSR 0xc0011036: IBS Op Data 2 */ +union ibs_op_data2 { + __u64 val; + struct { + __u64 data_src:3, /* 0-2: data source */ + reserved0:1, /* 3: reserved */ + rmt_node:1, /* 4: destination node */ + cache_hit_st:1, /* 5: cache hit state */ + reserved1:57; /* 5-63: reserved */ + }; +}; + +/* MSR 0xc0011037: IBS Op Data 3 */ +union ibs_op_data3 { + __u64 val; + struct { + __u64 ld_op:1, /* 0: load op */ + st_op:1, /* 1: store op */ + dc_l1tlb_miss:1, /* 2: data cache L1TLB miss */ + dc_l2tlb_miss:1, /* 3: data cache L2TLB hit in 2M page */ + dc_l1tlb_hit_2m:1, /* 4: data cache L1TLB hit in 2M page */ + dc_l1tlb_hit_1g:1, /* 5: data cache L1TLB hit in 1G page */ + dc_l2tlb_hit_2m:1, /* 6: data cache L2TLB hit in 2M page */ + dc_miss:1, /* 7: data cache miss */ + dc_mis_acc:1, /* 8: misaligned access */ + reserved:4, /* 9-12: reserved */ + dc_wc_mem_acc:1, /* 13: write combining memory access */ + dc_uc_mem_acc:1, /* 14: uncacheable memory access */ + dc_locked_op:1, /* 15: locked operation */ + dc_miss_no_mab_alloc:1, /* 16: DC miss with no MAB allocated */ + dc_lin_addr_valid:1, /* 17: data cache linear address valid */ + dc_phy_addr_valid:1, /* 18: data cache physical address valid */ + dc_l2_tlb_hit_1g:1, /* 19: data cache L2 hit in 1GB page */ + l2_miss:1, /* 20: L2 cache miss */ + sw_pf:1, /* 21: software prefetch */ + op_mem_width:4, /* 22-25: load/store size in bytes */ + op_dc_miss_open_mem_reqs:6, /* 26-31: outstanding mem reqs on DC fill */ + dc_miss_lat:16, /* 32-47: data cache miss latency */ + tlb_refill_lat:16; /* 48-63: L1 TLB refill latency */ + }; +}; + +/* MSR 0xc001103c: IBS Fetch Control Extended */ +union ic_ibs_extd_ctl { + __u64 val; + struct { + __u64 itlb_refill_lat:16, /* 0-15: ITLB Refill latency for sampled fetch */ + reserved:48; /* 16-63: reserved */ + }; +}; + +/* + * IBS driver related + */ + +struct perf_ibs_data { + u32 size; + union { + u32 data[0]; /* data buffer starts here */ + u32 caps; + }; + u64 regs[MSR_AMD64_IBS_REG_COUNT_MAX]; +}; diff --git a/arch/x86/include/asm/compat.h b/arch/x86/include/asm/compat.h index be09c7eac89f..7516e4199b3c 100644 --- a/arch/x86/include/asm/compat.h +++ b/arch/x86/include/asm/compat.h @@ -12,6 +12,9 @@ #include <asm/user32.h> #include <asm/unistd.h> +#define compat_mode_t compat_mode_t +typedef u16 compat_mode_t; + #include <asm-generic/compat.h> #define COMPAT_USER_HZ 100 @@ -19,13 +22,9 @@ typedef u16 __compat_uid_t; typedef u16 __compat_gid_t; -typedef u32 __compat_uid32_t; -typedef u32 __compat_gid32_t; -typedef u16 compat_mode_t; typedef u16 compat_dev_t; typedef u16 compat_nlink_t; typedef u16 compat_ipc_pid_t; -typedef u32 compat_caddr_t; typedef __kernel_fsid_t compat_fsid_t; struct compat_stat { @@ -92,13 +91,6 @@ struct compat_statfs { #define COMPAT_RLIM_INFINITY 0xffffffff -typedef u32 compat_old_sigset_t; /* at least 32 bits */ - -#define _COMPAT_NSIG 64 -#define _COMPAT_NSIG_BPW 32 - -typedef u32 compat_sigset_word; - #define COMPAT_OFF_T_MAX 0x7fffffff struct compat_ipc64_perm { @@ -164,19 +156,6 @@ struct compat_shmid64_ds { (!!(task_pt_regs(current)->orig_ax & __X32_SYSCALL_BIT)) #endif -static inline void __user *arch_compat_alloc_user_space(long len) -{ - compat_uptr_t sp = task_pt_regs(current)->sp; - - /* - * -128 for the x32 ABI redzone. For IA32, it is not strictly - * necessary, but not harmful. - */ - sp -= 128; - - return (void __user *)round_down(sp - len, 16); -} - static inline bool in_x32_syscall(void) { #ifdef CONFIG_X86_X32_ABI diff --git a/arch/x86/include/asm/hyperv-tlfs.h b/arch/x86/include/asm/hyperv-tlfs.h index f1366ce609e3..2322d6bd5883 100644 --- a/arch/x86/include/asm/hyperv-tlfs.h +++ b/arch/x86/include/asm/hyperv-tlfs.h @@ -288,6 +288,15 @@ union hv_x64_msr_hypercall_contents { } __packed; }; +union hv_vp_assist_msr_contents { + u64 as_uint64; + struct { + u64 enable:1; + u64 reserved:11; + u64 pfn:52; + } __packed; +}; + struct hv_reenlightenment_control { __u64 vector:8; __u64 reserved1:8; diff --git a/arch/x86/include/asm/i8259.h b/arch/x86/include/asm/i8259.h index 89789e8c80f6..637fa1df3512 100644 --- a/arch/x86/include/asm/i8259.h +++ b/arch/x86/include/asm/i8259.h @@ -19,6 +19,8 @@ extern unsigned int cached_irq_mask; #define PIC_MASTER_OCW3 PIC_MASTER_ISR #define PIC_SLAVE_CMD 0xa0 #define PIC_SLAVE_IMR 0xa1 +#define PIC_ELCR1 0x4d0 +#define PIC_ELCR2 0x4d1 /* i8259A PIC related value */ #define PIC_CASCADE_IR 2 diff --git a/arch/x86/include/asm/kfence.h b/arch/x86/include/asm/kfence.h index 05b48b33baf0..ff5c7134a37a 100644 --- a/arch/x86/include/asm/kfence.h +++ b/arch/x86/include/asm/kfence.h @@ -8,6 +8,8 @@ #ifndef _ASM_X86_KFENCE_H #define _ASM_X86_KFENCE_H +#ifndef MODULE + #include <linux/bug.h> #include <linux/kfence.h> @@ -66,4 +68,6 @@ static inline bool kfence_protect_page(unsigned long addr, bool protect) return true; } +#endif /* !MODULE */ + #endif /* _ASM_X86_KFENCE_H */ diff --git a/arch/x86/include/asm/kvm-x86-ops.h b/arch/x86/include/asm/kvm-x86-ops.h index a12a4987154e..cefe1d81e2e8 100644 --- a/arch/x86/include/asm/kvm-x86-ops.h +++ b/arch/x86/include/asm/kvm-x86-ops.h @@ -72,7 +72,6 @@ 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) diff --git a/arch/x86/include/asm/kvm_host.h b/arch/x86/include/asm/kvm_host.h index 974cbfb1eefe..f8f48a7ec577 100644 --- a/arch/x86/include/asm/kvm_host.h +++ b/arch/x86/include/asm/kvm_host.h @@ -37,9 +37,21 @@ #define __KVM_HAVE_ARCH_VCPU_DEBUGFS -#define KVM_MAX_VCPUS 288 -#define KVM_SOFT_MAX_VCPUS 240 -#define KVM_MAX_VCPU_ID 1023 +#define KVM_MAX_VCPUS 1024 +#define KVM_SOFT_MAX_VCPUS 710 + +/* + * In x86, the VCPU ID corresponds to the APIC ID, and APIC IDs + * might be larger than the actual number of VCPUs because the + * APIC ID encodes CPU topology information. + * + * In the worst case, we'll need less than one extra bit for the + * Core ID, and less than one extra bit for the Package (Die) ID, + * so ratio of 4 should be enough. + */ +#define KVM_VCPU_ID_RATIO 4 +#define KVM_MAX_VCPU_ID (KVM_MAX_VCPUS * KVM_VCPU_ID_RATIO) + /* memory slots that are not exposed to userspace */ #define KVM_PRIVATE_MEM_SLOTS 3 @@ -124,13 +136,6 @@ #define KVM_HPAGE_MASK(x) (~(KVM_HPAGE_SIZE(x) - 1)) #define KVM_PAGES_PER_HPAGE(x) (KVM_HPAGE_SIZE(x) / PAGE_SIZE) -static inline gfn_t gfn_to_index(gfn_t gfn, gfn_t base_gfn, int level) -{ - /* KVM_HPAGE_GFN_SHIFT(PG_LEVEL_4K) must be 0. */ - return (gfn >> KVM_HPAGE_GFN_SHIFT(level)) - - (base_gfn >> KVM_HPAGE_GFN_SHIFT(level)); -} - #define KVM_PERMILLE_MMU_PAGES 20 #define KVM_MIN_ALLOC_MMU_PAGES 64UL #define KVM_MMU_HASH_SHIFT 12 @@ -229,7 +234,8 @@ enum x86_intercept_stage; KVM_GUESTDBG_USE_HW_BP | \ KVM_GUESTDBG_USE_SW_BP | \ KVM_GUESTDBG_INJECT_BP | \ - KVM_GUESTDBG_INJECT_DB) + KVM_GUESTDBG_INJECT_DB | \ + KVM_GUESTDBG_BLOCKIRQ) #define PFERR_PRESENT_BIT 0 @@ -447,6 +453,7 @@ struct kvm_mmu { u64 *pae_root; u64 *pml4_root; + u64 *pml5_root; /* * check zero bits on shadow page table entries, these @@ -482,6 +489,7 @@ struct kvm_pmc { * ctrl value for fixed counters. */ u64 current_config; + bool is_paused; }; struct kvm_pmu { @@ -522,7 +530,6 @@ struct kvm_pmu_ops; enum { KVM_DEBUGREG_BP_ENABLED = 1, KVM_DEBUGREG_WONT_EXIT = 2, - KVM_DEBUGREG_RELOAD = 4, }; struct kvm_mtrr_range { @@ -723,7 +730,6 @@ struct kvm_vcpu_arch { u64 reserved_gpa_bits; int maxphyaddr; - int max_tdp_level; /* emulate context */ @@ -988,6 +994,12 @@ struct kvm_hv { /* How many vCPUs have VP index != vCPU index */ atomic_t num_mismatched_vp_indexes; + /* + * How many SynICs use 'AutoEOI' feature + * (protected by arch.apicv_update_lock) + */ + unsigned int synic_auto_eoi_used; + struct hv_partition_assist_pg *hv_pa_pg; struct kvm_hv_syndbg hv_syndbg; }; @@ -1002,9 +1014,8 @@ struct msr_bitmap_range { /* Xen emulation context */ struct kvm_xen { bool long_mode; - bool shinfo_set; u8 upcall_vector; - struct gfn_to_hva_cache shinfo_cache; + gfn_t shinfo_gfn; }; enum kvm_irqchip_mode { @@ -1038,6 +1049,13 @@ struct kvm_arch { struct list_head lpage_disallowed_mmu_pages; struct kvm_page_track_notifier_node mmu_sp_tracker; struct kvm_page_track_notifier_head track_notifier_head; + /* + * Protects marking pages unsync during page faults, as TDP MMU page + * faults only take mmu_lock for read. For simplicity, the unsync + * pages lock is always taken when marking pages unsync regardless of + * whether mmu_lock is held for read or write. + */ + spinlock_t mmu_unsync_pages_lock; struct list_head assigned_dev_head; struct iommu_domain *iommu_domain; @@ -1054,6 +1072,9 @@ struct kvm_arch { struct kvm_apic_map __rcu *apic_map; atomic_t apic_map_dirty; + /* Protects apic_access_memslot_enabled and apicv_inhibit_reasons */ + struct mutex apicv_update_lock; + bool apic_access_memslot_enabled; unsigned long apicv_inhibit_reasons; @@ -1206,9 +1227,17 @@ struct kvm_vm_stat { u64 mmu_recycled; u64 mmu_cache_miss; u64 mmu_unsync; - u64 lpages; + union { + struct { + atomic64_t pages_4k; + atomic64_t pages_2m; + atomic64_t pages_1g; + }; + atomic64_t pages[KVM_NR_PAGE_SIZES]; + }; u64 nx_lpage_splits; u64 max_mmu_page_hash_collisions; + u64 max_mmu_rmap_size; }; struct kvm_vcpu_stat { @@ -1352,7 +1381,6 @@ struct kvm_x86_ops { void (*enable_irq_window)(struct kvm_vcpu *vcpu); void (*update_cr8_intercept)(struct kvm_vcpu *vcpu, int tpr, int irr); bool (*check_apicv_inhibit_reasons)(ulong bit); - void (*pre_update_apicv_exec_ctrl)(struct kvm *kvm, bool activate); void (*refresh_apicv_exec_ctrl)(struct kvm_vcpu *vcpu); void (*hwapic_irr_update)(struct kvm_vcpu *vcpu, int max_irr); void (*hwapic_isr_update)(struct kvm_vcpu *vcpu, int isr); @@ -1536,12 +1564,12 @@ void kvm_mmu_uninit_vm(struct kvm *kvm); void kvm_mmu_after_set_cpuid(struct kvm_vcpu *vcpu); void kvm_mmu_reset_context(struct kvm_vcpu *vcpu); void kvm_mmu_slot_remove_write_access(struct kvm *kvm, - struct kvm_memory_slot *memslot, + const struct kvm_memory_slot *memslot, int start_level); void kvm_mmu_zap_collapsible_sptes(struct kvm *kvm, const struct kvm_memory_slot *memslot); void kvm_mmu_slot_leaf_clear_dirty(struct kvm *kvm, - struct kvm_memory_slot *memslot); + const struct kvm_memory_slot *memslot); 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); @@ -1737,6 +1765,9 @@ void kvm_vcpu_update_apicv(struct kvm_vcpu *vcpu); void kvm_request_apicv_update(struct kvm *kvm, bool activate, unsigned long bit); +void __kvm_request_apicv_update(struct kvm *kvm, bool activate, + unsigned long bit); + int kvm_emulate_hypercall(struct kvm_vcpu *vcpu); int kvm_mmu_page_fault(struct kvm_vcpu *vcpu, gpa_t cr2_or_gpa, u64 error_code, @@ -1747,8 +1778,8 @@ void kvm_mmu_invalidate_gva(struct kvm_vcpu *vcpu, struct kvm_mmu *mmu, void kvm_mmu_invpcid_gva(struct kvm_vcpu *vcpu, gva_t gva, unsigned long pcid); void kvm_mmu_new_pgd(struct kvm_vcpu *vcpu, gpa_t new_pgd); -void kvm_configure_mmu(bool enable_tdp, int tdp_max_root_level, - int tdp_huge_page_level); +void kvm_configure_mmu(bool enable_tdp, int tdp_forced_root_level, + int tdp_max_root_level, int tdp_huge_page_level); static inline u16 kvm_read_ldt(void) { @@ -1772,11 +1803,6 @@ static inline unsigned long read_msr(unsigned long msr) } #endif -static inline u32 get_rdx_init_val(void) -{ - return 0x600; /* P6 family */ -} - static inline void kvm_inject_gp(struct kvm_vcpu *vcpu, u32 error_code) { kvm_queue_exception_e(vcpu, GP_VECTOR, error_code); @@ -1809,31 +1835,6 @@ enum { #define kvm_arch_vcpu_memslots_id(vcpu) ((vcpu)->arch.hflags & HF_SMM_MASK ? 1 : 0) #define kvm_memslots_for_spte_role(kvm, role) __kvm_memslots(kvm, (role).smm) -asmlinkage void kvm_spurious_fault(void); - -/* - * Hardware virtualization extension instructions may fault if a - * reboot turns off virtualization while processes are running. - * Usually after catching the fault we just panic; during reboot - * instead the instruction is ignored. - */ -#define __kvm_handle_fault_on_reboot(insn) \ - "666: \n\t" \ - insn "\n\t" \ - "jmp 668f \n\t" \ - "667: \n\t" \ - "1: \n\t" \ - ".pushsection .discard.instr_begin \n\t" \ - ".long 1b - . \n\t" \ - ".popsection \n\t" \ - "call kvm_spurious_fault \n\t" \ - "1: \n\t" \ - ".pushsection .discard.instr_end \n\t" \ - ".long 1b - . \n\t" \ - ".popsection \n\t" \ - "668: \n\t" \ - _ASM_EXTABLE(666b, 667b) - #define KVM_ARCH_WANT_MMU_NOTIFIER int kvm_cpu_has_injectable_intr(struct kvm_vcpu *v); diff --git a/arch/x86/include/asm/mce.h b/arch/x86/include/asm/mce.h index 0607ec4f5091..da9321548f6f 100644 --- a/arch/x86/include/asm/mce.h +++ b/arch/x86/include/asm/mce.h @@ -265,6 +265,7 @@ enum mcp_flags { MCP_TIMESTAMP = BIT(0), /* log time stamp */ MCP_UC = BIT(1), /* log uncorrected errors */ MCP_DONTLOG = BIT(2), /* only clear, don't log */ + MCP_QUEUE_LOG = BIT(3), /* only queue to genpool */ }; bool machine_check_poll(enum mcp_flags flags, mce_banks_t *b); diff --git a/arch/x86/include/asm/mshyperv.h b/arch/x86/include/asm/mshyperv.h index 67ff0d637e55..adccbc209169 100644 --- a/arch/x86/include/asm/mshyperv.h +++ b/arch/x86/include/asm/mshyperv.h @@ -36,8 +36,6 @@ void hyperv_vector_handler(struct pt_regs *regs); 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; @@ -170,8 +168,6 @@ 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); diff --git a/arch/x86/include/asm/nospec-branch.h b/arch/x86/include/asm/nospec-branch.h index 3ad8c6d3cbb3..ec2d5c8c6694 100644 --- a/arch/x86/include/asm/nospec-branch.h +++ b/arch/x86/include/asm/nospec-branch.h @@ -252,6 +252,8 @@ DECLARE_STATIC_KEY_FALSE(switch_mm_always_ibpb); DECLARE_STATIC_KEY_FALSE(mds_user_clear); DECLARE_STATIC_KEY_FALSE(mds_idle_clear); +DECLARE_STATIC_KEY_FALSE(switch_mm_cond_l1d_flush); + #include <asm/segment.h> /** diff --git a/arch/x86/include/asm/pc-conf-reg.h b/arch/x86/include/asm/pc-conf-reg.h new file mode 100644 index 000000000000..56bceceacf5f --- /dev/null +++ b/arch/x86/include/asm/pc-conf-reg.h @@ -0,0 +1,33 @@ +/* SPDX-License-Identifier: GPL-2.0 */ +/* + * Support for the configuration register space at port I/O locations + * 0x22 and 0x23 variously used by PC architectures, e.g. the MP Spec, + * Cyrix CPUs, numerous chipsets. + */ +#ifndef _ASM_X86_PC_CONF_REG_H +#define _ASM_X86_PC_CONF_REG_H + +#include <linux/io.h> +#include <linux/spinlock.h> +#include <linux/types.h> + +#define PC_CONF_INDEX 0x22 +#define PC_CONF_DATA 0x23 + +#define PC_CONF_MPS_IMCR 0x70 + +extern raw_spinlock_t pc_conf_lock; + +static inline u8 pc_conf_get(u8 reg) +{ + outb(reg, PC_CONF_INDEX); + return inb(PC_CONF_DATA); +} + +static inline void pc_conf_set(u8 reg, u8 data) +{ + outb(reg, PC_CONF_INDEX); + outb(data, PC_CONF_DATA); +} + +#endif /* _ASM_X86_PC_CONF_REG_H */ diff --git a/arch/x86/include/asm/processor-cyrix.h b/arch/x86/include/asm/processor-cyrix.h index df700a6cc869..efe3e46e454b 100644 --- a/arch/x86/include/asm/processor-cyrix.h +++ b/arch/x86/include/asm/processor-cyrix.h @@ -5,14 +5,14 @@ * Access order is always 0x22 (=offset), 0x23 (=value) */ +#include <asm/pc-conf-reg.h> + static inline u8 getCx86(u8 reg) { - outb(reg, 0x22); - return inb(0x23); + return pc_conf_get(reg); } static inline void setCx86(u8 reg, u8 data) { - outb(reg, 0x22); - outb(data, 0x23); + pc_conf_set(reg, data); } diff --git a/arch/x86/include/asm/processor.h b/arch/x86/include/asm/processor.h index f3020c54e2cb..9ad2acaaae9b 100644 --- a/arch/x86/include/asm/processor.h +++ b/arch/x86/include/asm/processor.h @@ -136,6 +136,8 @@ struct cpuinfo_x86 { u16 logical_die_id; /* Index into per_cpu list: */ u16 cpu_index; + /* Is SMT active on this core? */ + bool smt_active; u32 microcode; /* Address space bits used by the cache internally */ u8 x86_cache_bits; @@ -795,6 +797,8 @@ extern int set_tsc_mode(unsigned int val); DECLARE_PER_CPU(u64, msr_misc_features_shadow); +extern u16 get_llc_id(unsigned int cpu); + #ifdef CONFIG_CPU_SUP_AMD extern u32 amd_get_nodes_per_socket(void); extern u32 amd_get_highest_perf(void); diff --git a/arch/x86/include/asm/signal.h b/arch/x86/include/asm/signal.h index 6fd8410a3910..2dfb5fea13af 100644 --- a/arch/x86/include/asm/signal.h +++ b/arch/x86/include/asm/signal.h @@ -29,6 +29,7 @@ typedef struct { #define SA_X32_ABI 0x01000000u #ifndef CONFIG_COMPAT +#define compat_sigset_t compat_sigset_t typedef sigset_t compat_sigset_t; #endif diff --git a/arch/x86/include/asm/svm.h b/arch/x86/include/asm/svm.h index e322676039f4..b00dbc5fac2b 100644 --- a/arch/x86/include/asm/svm.h +++ b/arch/x86/include/asm/svm.h @@ -184,6 +184,8 @@ struct __attribute__ ((__packed__)) vmcb_control_area { #define V_IGN_TPR_SHIFT 20 #define V_IGN_TPR_MASK (1 << V_IGN_TPR_SHIFT) +#define V_IRQ_INJECTION_BITS_MASK (V_IRQ_MASK | V_INTR_PRIO_MASK | V_IGN_TPR_MASK) + #define V_INTR_MASKING_SHIFT 24 #define V_INTR_MASKING_MASK (1 << V_INTR_MASKING_SHIFT) diff --git a/arch/x86/include/asm/sysfb.h b/arch/x86/include/asm/sysfb.h deleted file mode 100644 index 9834eef7f034..000000000000 --- a/arch/x86/include/asm/sysfb.h +++ /dev/null @@ -1,94 +0,0 @@ -/* SPDX-License-Identifier: GPL-2.0-or-later */ -#ifndef _ARCH_X86_KERNEL_SYSFB_H -#define _ARCH_X86_KERNEL_SYSFB_H - -/* - * Generic System Framebuffers on x86 - * Copyright (c) 2012-2013 David Herrmann <dh.herrmann@gmail.com> - */ - -#include <linux/kernel.h> -#include <linux/platform_data/simplefb.h> -#include <linux/screen_info.h> - -enum { - M_I17, /* 17-Inch iMac */ - M_I20, /* 20-Inch iMac */ - M_I20_SR, /* 20-Inch iMac (Santa Rosa) */ - M_I24, /* 24-Inch iMac */ - M_I24_8_1, /* 24-Inch iMac, 8,1th gen */ - M_I24_10_1, /* 24-Inch iMac, 10,1th gen */ - M_I27_11_1, /* 27-Inch iMac, 11,1th gen */ - M_MINI, /* Mac Mini */ - M_MINI_3_1, /* Mac Mini, 3,1th gen */ - M_MINI_4_1, /* Mac Mini, 4,1th gen */ - M_MB, /* MacBook */ - M_MB_2, /* MacBook, 2nd rev. */ - M_MB_3, /* MacBook, 3rd rev. */ - M_MB_5_1, /* MacBook, 5th rev. */ - M_MB_6_1, /* MacBook, 6th rev. */ - M_MB_7_1, /* MacBook, 7th rev. */ - M_MB_SR, /* MacBook, 2nd gen, (Santa Rosa) */ - M_MBA, /* MacBook Air */ - M_MBA_3, /* Macbook Air, 3rd rev */ - M_MBP, /* MacBook Pro */ - M_MBP_2, /* MacBook Pro 2nd gen */ - M_MBP_2_2, /* MacBook Pro 2,2nd gen */ - M_MBP_SR, /* MacBook Pro (Santa Rosa) */ - M_MBP_4, /* MacBook Pro, 4th gen */ - M_MBP_5_1, /* MacBook Pro, 5,1th gen */ - M_MBP_5_2, /* MacBook Pro, 5,2th gen */ - M_MBP_5_3, /* MacBook Pro, 5,3rd gen */ - M_MBP_6_1, /* MacBook Pro, 6,1th gen */ - M_MBP_6_2, /* MacBook Pro, 6,2th gen */ - M_MBP_7_1, /* MacBook Pro, 7,1th gen */ - M_MBP_8_2, /* MacBook Pro, 8,2nd gen */ - M_UNKNOWN /* placeholder */ -}; - -struct efifb_dmi_info { - char *optname; - unsigned long base; - int stride; - int width; - int height; - int flags; -}; - -#ifdef CONFIG_EFI - -extern struct efifb_dmi_info efifb_dmi_list[]; -void sysfb_apply_efi_quirks(void); - -#else /* CONFIG_EFI */ - -static inline void sysfb_apply_efi_quirks(void) -{ -} - -#endif /* CONFIG_EFI */ - -#ifdef CONFIG_X86_SYSFB - -bool parse_mode(const struct screen_info *si, - struct simplefb_platform_data *mode); -int create_simplefb(const struct screen_info *si, - const struct simplefb_platform_data *mode); - -#else /* CONFIG_X86_SYSFB */ - -static inline bool parse_mode(const struct screen_info *si, - struct simplefb_platform_data *mode) -{ - return false; -} - -static inline int create_simplefb(const struct screen_info *si, - const struct simplefb_platform_data *mode) -{ - return -EINVAL; -} - -#endif /* CONFIG_X86_SYSFB */ - -#endif /* _ARCH_X86_KERNEL_SYSFB_H */ diff --git a/arch/x86/include/asm/thread_info.h b/arch/x86/include/asm/thread_info.h index de406d93b515..cf132663c219 100644 --- a/arch/x86/include/asm/thread_info.h +++ b/arch/x86/include/asm/thread_info.h @@ -81,7 +81,7 @@ struct thread_info { #define TIF_SINGLESTEP 4 /* reenable singlestep on user return*/ #define TIF_SSBD 5 /* Speculative store bypass disable */ #define TIF_SPEC_IB 9 /* Indirect branch speculation mitigation */ -#define TIF_SPEC_FORCE_UPDATE 10 /* Force speculation MSR update in context switch */ +#define TIF_SPEC_L1D_FLUSH 10 /* Flush L1D on mm switches (processes) */ #define TIF_USER_RETURN_NOTIFY 11 /* notify kernel of userspace return */ #define TIF_UPROBE 12 /* breakpointed or singlestepping */ #define TIF_PATCH_PENDING 13 /* pending live patching update */ @@ -93,6 +93,7 @@ struct thread_info { #define TIF_MEMDIE 20 /* is terminating due to OOM killer */ #define TIF_POLLING_NRFLAG 21 /* idle is polling for TIF_NEED_RESCHED */ #define TIF_IO_BITMAP 22 /* uses I/O bitmap */ +#define TIF_SPEC_FORCE_UPDATE 23 /* Force speculation MSR update in context switch */ #define TIF_FORCED_TF 24 /* true if TF in eflags artificially */ #define TIF_BLOCKSTEP 25 /* set when we want DEBUGCTLMSR_BTF */ #define TIF_LAZY_MMU_UPDATES 27 /* task is updating the mmu lazily */ @@ -104,7 +105,7 @@ struct thread_info { #define _TIF_SINGLESTEP (1 << TIF_SINGLESTEP) #define _TIF_SSBD (1 << TIF_SSBD) #define _TIF_SPEC_IB (1 << TIF_SPEC_IB) -#define _TIF_SPEC_FORCE_UPDATE (1 << TIF_SPEC_FORCE_UPDATE) +#define _TIF_SPEC_L1D_FLUSH (1 << TIF_SPEC_L1D_FLUSH) #define _TIF_USER_RETURN_NOTIFY (1 << TIF_USER_RETURN_NOTIFY) #define _TIF_UPROBE (1 << TIF_UPROBE) #define _TIF_PATCH_PENDING (1 << TIF_PATCH_PENDING) @@ -115,6 +116,7 @@ struct thread_info { #define _TIF_SLD (1 << TIF_SLD) #define _TIF_POLLING_NRFLAG (1 << TIF_POLLING_NRFLAG) #define _TIF_IO_BITMAP (1 << TIF_IO_BITMAP) +#define _TIF_SPEC_FORCE_UPDATE (1 << TIF_SPEC_FORCE_UPDATE) #define _TIF_FORCED_TF (1 << TIF_FORCED_TF) #define _TIF_BLOCKSTEP (1 << TIF_BLOCKSTEP) #define _TIF_LAZY_MMU_UPDATES (1 << TIF_LAZY_MMU_UPDATES) diff --git a/arch/x86/include/asm/tlbflush.h b/arch/x86/include/asm/tlbflush.h index fa952eadbc2e..b587a9ee9cb2 100644 --- a/arch/x86/include/asm/tlbflush.h +++ b/arch/x86/include/asm/tlbflush.h @@ -83,7 +83,7 @@ struct tlb_state { /* Last user mm for optimizing IBPB */ union { struct mm_struct *last_user_mm; - unsigned long last_user_mm_ibpb; + unsigned long last_user_mm_spec; }; u16 loaded_mm_asid; diff --git a/arch/x86/include/asm/uaccess_64.h b/arch/x86/include/asm/uaccess_64.h index e7265a552f4f..45697e04d771 100644 --- a/arch/x86/include/asm/uaccess_64.h +++ b/arch/x86/include/asm/uaccess_64.h @@ -58,13 +58,6 @@ raw_copy_to_user(void __user *dst, const void *src, unsigned long size) return copy_user_generic((__force void *)dst, src, size); } -static __always_inline __must_check -unsigned long raw_copy_in_user(void __user *dst, const void __user *src, unsigned long size) -{ - return copy_user_generic((__force void *)dst, - (__force void *)src, size); -} - extern long __copy_user_nocache(void *dst, const void __user *src, unsigned size, int zerorest); diff --git a/arch/x86/include/uapi/asm/kvm.h b/arch/x86/include/uapi/asm/kvm.h index a6c327f8ad9e..2ef1f6513c68 100644 --- a/arch/x86/include/uapi/asm/kvm.h +++ b/arch/x86/include/uapi/asm/kvm.h @@ -295,6 +295,7 @@ struct kvm_debug_exit_arch { #define KVM_GUESTDBG_USE_HW_BP 0x00020000 #define KVM_GUESTDBG_INJECT_DB 0x00040000 #define KVM_GUESTDBG_INJECT_BP 0x00080000 +#define KVM_GUESTDBG_BLOCKIRQ 0x00100000 /* for KVM_SET_GUEST_DEBUG */ struct kvm_guest_debug_arch { diff --git a/arch/x86/kernel/Makefile b/arch/x86/kernel/Makefile index 3e625c61f008..8f4e8fa6ed75 100644 --- a/arch/x86/kernel/Makefile +++ b/arch/x86/kernel/Makefile @@ -136,9 +136,6 @@ obj-$(CONFIG_X86_CHECK_BIOS_CORRUPTION) += check.o obj-$(CONFIG_SWIOTLB) += pci-swiotlb.o obj-$(CONFIG_OF) += devicetree.o obj-$(CONFIG_UPROBES) += uprobes.o -obj-y += sysfb.o -obj-$(CONFIG_X86_SYSFB) += sysfb_simplefb.o -obj-$(CONFIG_EFI) += sysfb_efi.o obj-$(CONFIG_PERF_EVENTS) += perf_regs.o obj-$(CONFIG_TRACING) += tracepoint.o diff --git a/arch/x86/kernel/acpi/boot.c b/arch/x86/kernel/acpi/boot.c index e55e0c1fad8c..14bcd59bcdee 100644 --- a/arch/x86/kernel/acpi/boot.c +++ b/arch/x86/kernel/acpi/boot.c @@ -558,10 +558,10 @@ acpi_parse_nmi_src(union acpi_subtable_headers * header, const unsigned long end * If a PIC-mode SCI is not recognized or gives spurious IRQ7's * it may require Edge Trigger -- use "acpi_sci=edge" * - * Port 0x4d0-4d1 are ECLR1 and ECLR2, the Edge/Level Control Registers + * Port 0x4d0-4d1 are ELCR1 and ELCR2, the Edge/Level Control Registers * for the 8259 PIC. bit[n] = 1 means irq[n] is Level, otherwise Edge. - * ECLR1 is IRQs 0-7 (IRQ 0, 1, 2 must be 0) - * ECLR2 is IRQs 8-15 (IRQ 8, 13 must be 0) + * ELCR1 is IRQs 0-7 (IRQ 0, 1, 2 must be 0) + * ELCR2 is IRQs 8-15 (IRQ 8, 13 must be 0) */ void __init acpi_pic_sci_set_trigger(unsigned int irq, u16 trigger) @@ -570,7 +570,7 @@ void __init acpi_pic_sci_set_trigger(unsigned int irq, u16 trigger) unsigned int old, new; /* Real old ELCR mask */ - old = inb(0x4d0) | (inb(0x4d1) << 8); + old = inb(PIC_ELCR1) | (inb(PIC_ELCR2) << 8); /* * If we use ACPI to set PCI IRQs, then we should clear ELCR @@ -596,8 +596,8 @@ void __init acpi_pic_sci_set_trigger(unsigned int irq, u16 trigger) return; pr_warn("setting ELCR to %04x (from %04x)\n", new, old); - outb(new, 0x4d0); - outb(new >> 8, 0x4d1); + outb(new, PIC_ELCR1); + outb(new >> 8, PIC_ELCR2); } int acpi_gsi_to_irq(u32 gsi, unsigned int *irqp) diff --git a/arch/x86/kernel/amd_gart_64.c b/arch/x86/kernel/amd_gart_64.c index 9ac696487b13..ed837383de5c 100644 --- a/arch/x86/kernel/amd_gart_64.c +++ b/arch/x86/kernel/amd_gart_64.c @@ -331,7 +331,7 @@ static int __dma_map_cont(struct device *dev, struct scatterlist *start, int i; if (iommu_start == -1) - return -1; + return -ENOMEM; for_each_sg(start, s, nelems, i) { unsigned long pages, addr; @@ -380,13 +380,13 @@ static int gart_map_sg(struct device *dev, struct scatterlist *sg, int nents, enum dma_data_direction dir, unsigned long attrs) { struct scatterlist *s, *ps, *start_sg, *sgmap; - int need = 0, nextneed, i, out, start; + int need = 0, nextneed, i, out, start, ret; unsigned long pages = 0; unsigned int seg_size; unsigned int max_seg_size; if (nents == 0) - return 0; + return -EINVAL; out = 0; start = 0; @@ -414,8 +414,9 @@ static int gart_map_sg(struct device *dev, struct scatterlist *sg, int nents, if (!iommu_merge || !nextneed || !need || s->offset || (s->length + seg_size > max_seg_size) || (ps->offset + ps->length) % PAGE_SIZE) { - if (dma_map_cont(dev, start_sg, i - start, - sgmap, pages, need) < 0) + ret = dma_map_cont(dev, start_sg, i - start, + sgmap, pages, need); + if (ret < 0) goto error; out++; @@ -432,7 +433,8 @@ static int gart_map_sg(struct device *dev, struct scatterlist *sg, int nents, pages += iommu_num_pages(s->offset, s->length, PAGE_SIZE); ps = s; } - if (dma_map_cont(dev, start_sg, i - start, sgmap, pages, need) < 0) + ret = dma_map_cont(dev, start_sg, i - start, sgmap, pages, need); + if (ret < 0) goto error; out++; flush_gart(); @@ -456,9 +458,7 @@ error: panic("dma_map_sg: overflow on %lu pages\n", pages); iommu_full(dev, pages << PAGE_SHIFT, dir); - for_each_sg(sg, s, nents, i) - s->dma_address = DMA_MAPPING_ERROR; - return 0; + return ret; } /* allocate and map a coherent mapping */ diff --git a/arch/x86/kernel/amd_nb.c b/arch/x86/kernel/amd_nb.c index 23dda362dc0f..c92c9c774c0e 100644 --- a/arch/x86/kernel/amd_nb.c +++ b/arch/x86/kernel/amd_nb.c @@ -25,6 +25,8 @@ #define PCI_DEVICE_ID_AMD_17H_M60H_DF_F4 0x144c #define PCI_DEVICE_ID_AMD_17H_M70H_DF_F4 0x1444 #define PCI_DEVICE_ID_AMD_19H_DF_F4 0x1654 +#define PCI_DEVICE_ID_AMD_19H_M40H_ROOT 0x14b5 +#define PCI_DEVICE_ID_AMD_19H_M40H_DF_F4 0x167d #define PCI_DEVICE_ID_AMD_19H_M50H_DF_F4 0x166e /* Protect the PCI config register pairs used for SMN and DF indirect access. */ @@ -37,6 +39,7 @@ static const struct pci_device_id amd_root_ids[] = { { PCI_DEVICE(PCI_VENDOR_ID_AMD, PCI_DEVICE_ID_AMD_17H_M10H_ROOT) }, { PCI_DEVICE(PCI_VENDOR_ID_AMD, PCI_DEVICE_ID_AMD_17H_M30H_ROOT) }, { PCI_DEVICE(PCI_VENDOR_ID_AMD, PCI_DEVICE_ID_AMD_17H_M60H_ROOT) }, + { PCI_DEVICE(PCI_VENDOR_ID_AMD, PCI_DEVICE_ID_AMD_19H_M40H_ROOT) }, {} }; @@ -58,6 +61,7 @@ static const struct pci_device_id amd_nb_misc_ids[] = { { PCI_DEVICE(PCI_VENDOR_ID_AMD, PCI_DEVICE_ID_AMD_CNB17H_F3) }, { PCI_DEVICE(PCI_VENDOR_ID_AMD, PCI_DEVICE_ID_AMD_17H_M70H_DF_F3) }, { PCI_DEVICE(PCI_VENDOR_ID_AMD, PCI_DEVICE_ID_AMD_19H_DF_F3) }, + { PCI_DEVICE(PCI_VENDOR_ID_AMD, PCI_DEVICE_ID_AMD_19H_M40H_DF_F3) }, { PCI_DEVICE(PCI_VENDOR_ID_AMD, PCI_DEVICE_ID_AMD_19H_M50H_DF_F3) }, {} }; @@ -74,6 +78,7 @@ static const struct pci_device_id amd_nb_link_ids[] = { { PCI_DEVICE(PCI_VENDOR_ID_AMD, PCI_DEVICE_ID_AMD_17H_M60H_DF_F4) }, { PCI_DEVICE(PCI_VENDOR_ID_AMD, PCI_DEVICE_ID_AMD_17H_M70H_DF_F4) }, { PCI_DEVICE(PCI_VENDOR_ID_AMD, PCI_DEVICE_ID_AMD_19H_DF_F4) }, + { PCI_DEVICE(PCI_VENDOR_ID_AMD, PCI_DEVICE_ID_AMD_19H_M40H_DF_F4) }, { PCI_DEVICE(PCI_VENDOR_ID_AMD, PCI_DEVICE_ID_AMD_19H_M50H_DF_F4) }, { PCI_DEVICE(PCI_VENDOR_ID_AMD, PCI_DEVICE_ID_AMD_CNB17H_F4) }, {} diff --git a/arch/x86/kernel/aperture_64.c b/arch/x86/kernel/aperture_64.c index 294ed4392a0e..10562885f5fc 100644 --- a/arch/x86/kernel/aperture_64.c +++ b/arch/x86/kernel/aperture_64.c @@ -109,14 +109,13 @@ static u32 __init allocate_aperture(void) * memory. Unfortunately we cannot move it up because that would * make the IOMMU useless. */ - addr = memblock_find_in_range(GART_MIN_ADDR, GART_MAX_ADDR, - aper_size, aper_size); + addr = memblock_phys_alloc_range(aper_size, aper_size, + GART_MIN_ADDR, GART_MAX_ADDR); if (!addr) { pr_err("Cannot allocate aperture memory hole [mem %#010lx-%#010lx] (%uKB)\n", addr, addr + aper_size - 1, aper_size >> 10); return 0; } - memblock_reserve(addr, aper_size); pr_info("Mapping aperture over RAM [mem %#010lx-%#010lx] (%uKB)\n", addr, addr + aper_size - 1, aper_size >> 10); register_nosave_region(addr >> PAGE_SHIFT, diff --git a/arch/x86/kernel/apic/apic.c b/arch/x86/kernel/apic/apic.c index d262811ce14b..b70344bf6600 100644 --- a/arch/x86/kernel/apic/apic.c +++ b/arch/x86/kernel/apic/apic.c @@ -38,6 +38,7 @@ #include <asm/trace/irq_vectors.h> #include <asm/irq_remapping.h> +#include <asm/pc-conf-reg.h> #include <asm/perf_event.h> #include <asm/x86_init.h> #include <linux/atomic.h> @@ -132,18 +133,14 @@ static int enabled_via_apicbase __ro_after_init; */ static inline void imcr_pic_to_apic(void) { - /* select IMCR register */ - outb(0x70, 0x22); /* NMI and 8259 INTR go through APIC */ - outb(0x01, 0x23); + pc_conf_set(PC_CONF_MPS_IMCR, 0x01); } static inline void imcr_apic_to_pic(void) { - /* select IMCR register */ - outb(0x70, 0x22); /* NMI and 8259 INTR go directly to BSP */ - outb(0x00, 0x23); + pc_conf_set(PC_CONF_MPS_IMCR, 0x00); } #endif diff --git a/arch/x86/kernel/apic/io_apic.c b/arch/x86/kernel/apic/io_apic.c index d5c691a3208b..c1bb384935b0 100644 --- a/arch/x86/kernel/apic/io_apic.c +++ b/arch/x86/kernel/apic/io_apic.c @@ -764,7 +764,7 @@ static bool irq_active_low(int idx) static bool EISA_ELCR(unsigned int irq) { if (irq < nr_legacy_irqs()) { - unsigned int port = 0x4d0 + (irq >> 3); + unsigned int port = PIC_ELCR1 + (irq >> 3); return (inb(port) >> (irq & 7)) & 1; } apic_printk(APIC_VERBOSE, KERN_INFO @@ -1986,7 +1986,8 @@ static struct irq_chip ioapic_chip __read_mostly = { .irq_set_affinity = ioapic_set_affinity, .irq_retrigger = irq_chip_retrigger_hierarchy, .irq_get_irqchip_state = ioapic_irq_get_chip_state, - .flags = IRQCHIP_SKIP_SET_WAKE, + .flags = IRQCHIP_SKIP_SET_WAKE | + IRQCHIP_AFFINITY_PRE_STARTUP, }; static struct irq_chip ioapic_ir_chip __read_mostly = { @@ -1999,7 +2000,8 @@ static struct irq_chip ioapic_ir_chip __read_mostly = { .irq_set_affinity = ioapic_set_affinity, .irq_retrigger = irq_chip_retrigger_hierarchy, .irq_get_irqchip_state = ioapic_irq_get_chip_state, - .flags = IRQCHIP_SKIP_SET_WAKE, + .flags = IRQCHIP_SKIP_SET_WAKE | + IRQCHIP_AFFINITY_PRE_STARTUP, }; static inline void init_IO_APIC_traps(void) diff --git a/arch/x86/kernel/apic/msi.c b/arch/x86/kernel/apic/msi.c index 44ebe25e7703..dbacb9ec8843 100644 --- a/arch/x86/kernel/apic/msi.c +++ b/arch/x86/kernel/apic/msi.c @@ -58,11 +58,13 @@ msi_set_affinity(struct irq_data *irqd, const struct cpumask *mask, bool force) * The quirk bit is not set in this case. * - The new vector is the same as the old vector * - The old vector is MANAGED_IRQ_SHUTDOWN_VECTOR (interrupt starts up) + * - The interrupt is not yet started up * - The new destination CPU is the same as the old destination CPU */ if (!irqd_msi_nomask_quirk(irqd) || cfg->vector == old_cfg.vector || old_cfg.vector == MANAGED_IRQ_SHUTDOWN_VECTOR || + !irqd_is_started(irqd) || cfg->dest_apicid == old_cfg.dest_apicid) { irq_msi_update_msg(irqd, cfg); return ret; @@ -150,7 +152,8 @@ static struct irq_chip pci_msi_controller = { .irq_ack = irq_chip_ack_parent, .irq_retrigger = irq_chip_retrigger_hierarchy, .irq_set_affinity = msi_set_affinity, - .flags = IRQCHIP_SKIP_SET_WAKE, + .flags = IRQCHIP_SKIP_SET_WAKE | + IRQCHIP_AFFINITY_PRE_STARTUP, }; int pci_msi_prepare(struct irq_domain *domain, struct device *dev, int nvec, @@ -219,7 +222,8 @@ static struct irq_chip pci_msi_ir_controller = { .irq_mask = pci_msi_mask_irq, .irq_ack = irq_chip_ack_parent, .irq_retrigger = irq_chip_retrigger_hierarchy, - .flags = IRQCHIP_SKIP_SET_WAKE, + .flags = IRQCHIP_SKIP_SET_WAKE | + IRQCHIP_AFFINITY_PRE_STARTUP, }; static struct msi_domain_info pci_msi_ir_domain_info = { @@ -273,7 +277,8 @@ static struct irq_chip dmar_msi_controller = { .irq_retrigger = irq_chip_retrigger_hierarchy, .irq_compose_msi_msg = dmar_msi_compose_msg, .irq_write_msi_msg = dmar_msi_write_msg, - .flags = IRQCHIP_SKIP_SET_WAKE, + .flags = IRQCHIP_SKIP_SET_WAKE | + IRQCHIP_AFFINITY_PRE_STARTUP, }; static int dmar_msi_init(struct irq_domain *domain, diff --git a/arch/x86/kernel/apic/vector.c b/arch/x86/kernel/apic/vector.c index fb67ed5e7e6a..c132daabe615 100644 --- a/arch/x86/kernel/apic/vector.c +++ b/arch/x86/kernel/apic/vector.c @@ -1299,7 +1299,7 @@ static void __init print_PIC(void) pr_debug("... PIC ISR: %04x\n", v); - v = inb(0x4d1) << 8 | inb(0x4d0); + v = inb(PIC_ELCR2) << 8 | inb(PIC_ELCR1); pr_debug("... PIC ELCR: %04x\n", v); } diff --git a/arch/x86/kernel/cpu/amd.c b/arch/x86/kernel/cpu/amd.c index b7c003013d41..2131af9f2fa2 100644 --- a/arch/x86/kernel/cpu/amd.c +++ b/arch/x86/kernel/cpu/amd.c @@ -438,7 +438,7 @@ static void srat_detect_node(struct cpuinfo_x86 *c) node = numa_cpu_node(cpu); if (node == NUMA_NO_NODE) - node = per_cpu(cpu_llc_id, cpu); + node = get_llc_id(cpu); /* * On multi-fabric platform (e.g. Numascale NumaChip) a diff --git a/arch/x86/kernel/cpu/bugs.c b/arch/x86/kernel/cpu/bugs.c index d41b70fe4918..ecfca3bbcd96 100644 --- a/arch/x86/kernel/cpu/bugs.c +++ b/arch/x86/kernel/cpu/bugs.c @@ -43,6 +43,7 @@ static void __init mds_select_mitigation(void); static void __init mds_print_mitigation(void); static void __init taa_select_mitigation(void); static void __init srbds_select_mitigation(void); +static void __init l1d_flush_select_mitigation(void); /* The base value of the SPEC_CTRL MSR that always has to be preserved. */ u64 x86_spec_ctrl_base; @@ -76,6 +77,13 @@ EXPORT_SYMBOL_GPL(mds_user_clear); DEFINE_STATIC_KEY_FALSE(mds_idle_clear); EXPORT_SYMBOL_GPL(mds_idle_clear); +/* + * Controls whether l1d flush based mitigations are enabled, + * based on hw features and admin setting via boot parameter + * defaults to false + */ +DEFINE_STATIC_KEY_FALSE(switch_mm_cond_l1d_flush); + void __init check_bugs(void) { identify_boot_cpu(); @@ -111,6 +119,7 @@ void __init check_bugs(void) mds_select_mitigation(); taa_select_mitigation(); srbds_select_mitigation(); + l1d_flush_select_mitigation(); /* * As MDS and TAA mitigations are inter-related, print MDS @@ -492,6 +501,34 @@ static int __init srbds_parse_cmdline(char *str) early_param("srbds", srbds_parse_cmdline); #undef pr_fmt +#define pr_fmt(fmt) "L1D Flush : " fmt + +enum l1d_flush_mitigations { + L1D_FLUSH_OFF = 0, + L1D_FLUSH_ON, +}; + +static enum l1d_flush_mitigations l1d_flush_mitigation __initdata = L1D_FLUSH_OFF; + +static void __init l1d_flush_select_mitigation(void) +{ + if (!l1d_flush_mitigation || !boot_cpu_has(X86_FEATURE_FLUSH_L1D)) + return; + + static_branch_enable(&switch_mm_cond_l1d_flush); + pr_info("Conditional flush on switch_mm() enabled\n"); +} + +static int __init l1d_flush_parse_cmdline(char *str) +{ + if (!strcmp(str, "on")) + l1d_flush_mitigation = L1D_FLUSH_ON; + + return 0; +} +early_param("l1d_flush", l1d_flush_parse_cmdline); + +#undef pr_fmt #define pr_fmt(fmt) "Spectre V1 : " fmt enum spectre_v1_mitigation { @@ -1215,6 +1252,24 @@ static void task_update_spec_tif(struct task_struct *tsk) speculation_ctrl_update_current(); } +static int l1d_flush_prctl_set(struct task_struct *task, unsigned long ctrl) +{ + + if (!static_branch_unlikely(&switch_mm_cond_l1d_flush)) + return -EPERM; + + switch (ctrl) { + case PR_SPEC_ENABLE: + set_ti_thread_flag(&task->thread_info, TIF_SPEC_L1D_FLUSH); + return 0; + case PR_SPEC_DISABLE: + clear_ti_thread_flag(&task->thread_info, TIF_SPEC_L1D_FLUSH); + return 0; + default: + return -ERANGE; + } +} + static int ssb_prctl_set(struct task_struct *task, unsigned long ctrl) { if (ssb_mode != SPEC_STORE_BYPASS_PRCTL && @@ -1324,6 +1379,8 @@ int arch_prctl_spec_ctrl_set(struct task_struct *task, unsigned long which, return ssb_prctl_set(task, ctrl); case PR_SPEC_INDIRECT_BRANCH: return ib_prctl_set(task, ctrl); + case PR_SPEC_L1D_FLUSH: + return l1d_flush_prctl_set(task, ctrl); default: return -ENODEV; } @@ -1340,6 +1397,17 @@ void arch_seccomp_spec_mitigate(struct task_struct *task) } #endif +static int l1d_flush_prctl_get(struct task_struct *task) +{ + if (!static_branch_unlikely(&switch_mm_cond_l1d_flush)) + return PR_SPEC_FORCE_DISABLE; + + if (test_ti_thread_flag(&task->thread_info, TIF_SPEC_L1D_FLUSH)) + return PR_SPEC_PRCTL | PR_SPEC_ENABLE; + else + return PR_SPEC_PRCTL | PR_SPEC_DISABLE; +} + static int ssb_prctl_get(struct task_struct *task) { switch (ssb_mode) { @@ -1390,6 +1458,8 @@ int arch_prctl_spec_ctrl_get(struct task_struct *task, unsigned long which) return ssb_prctl_get(task); case PR_SPEC_INDIRECT_BRANCH: return ib_prctl_get(task); + case PR_SPEC_L1D_FLUSH: + return l1d_flush_prctl_get(task); default: return -ENODEV; } diff --git a/arch/x86/kernel/cpu/common.c b/arch/x86/kernel/cpu/common.c index 64b805bd6a54..0f8885949e8c 100644 --- a/arch/x86/kernel/cpu/common.c +++ b/arch/x86/kernel/cpu/common.c @@ -79,6 +79,12 @@ EXPORT_SYMBOL(smp_num_siblings); /* Last level cache ID of each logical CPU */ DEFINE_PER_CPU_READ_MOSTLY(u16, cpu_llc_id) = BAD_APICID; +u16 get_llc_id(unsigned int cpu) +{ + return per_cpu(cpu_llc_id, cpu); +} +EXPORT_SYMBOL_GPL(get_llc_id); + /* correctly size the local cpu masks */ void __init setup_cpu_local_masks(void) { diff --git a/arch/x86/kernel/cpu/mce/core.c b/arch/x86/kernel/cpu/mce/core.c index 22791aadc085..8cb7816d03b4 100644 --- a/arch/x86/kernel/cpu/mce/core.c +++ b/arch/x86/kernel/cpu/mce/core.c @@ -817,7 +817,10 @@ log_it: if (mca_cfg.dont_log_ce && !mce_usable_address(&m)) goto clear_it; - mce_log(&m); + if (flags & MCP_QUEUE_LOG) + mce_gen_pool_add(&m); + else + mce_log(&m); clear_it: /* @@ -1639,10 +1642,12 @@ static void __mcheck_cpu_init_generic(void) m_fl = MCP_DONTLOG; /* - * Log the machine checks left over from the previous reset. + * Log the machine checks left over from the previous reset. Log them + * only, do not start processing them. That will happen in mcheck_late_init() + * when all consumers have been registered on the notifier chain. */ bitmap_fill(all_banks, MAX_NR_BANKS); - machine_check_poll(MCP_UC | m_fl, &all_banks); + machine_check_poll(MCP_UC | MCP_QUEUE_LOG | m_fl, &all_banks); cr4_set_bits(X86_CR4_MCE); diff --git a/arch/x86/kernel/cpu/mce/inject.c b/arch/x86/kernel/cpu/mce/inject.c index 4e86d97f9653..0bfc14041bbb 100644 --- a/arch/x86/kernel/cpu/mce/inject.c +++ b/arch/x86/kernel/cpu/mce/inject.c @@ -235,7 +235,7 @@ static void __maybe_unused raise_mce(struct mce *m) unsigned long start; int cpu; - get_online_cpus(); + cpus_read_lock(); cpumask_copy(mce_inject_cpumask, cpu_online_mask); cpumask_clear_cpu(get_cpu(), mce_inject_cpumask); for_each_online_cpu(cpu) { @@ -269,7 +269,7 @@ static void __maybe_unused raise_mce(struct mce *m) } raise_local(); put_cpu(); - put_online_cpus(); + cpus_read_unlock(); } else { preempt_disable(); raise_local(); @@ -529,7 +529,7 @@ static void do_inject(void) cpu = get_nbc_for_node(topology_die_id(cpu)); } - get_online_cpus(); + cpus_read_lock(); if (!cpu_online(cpu)) goto err; @@ -553,7 +553,7 @@ static void do_inject(void) } err: - put_online_cpus(); + cpus_read_unlock(); } diff --git a/arch/x86/kernel/cpu/microcode/core.c b/arch/x86/kernel/cpu/microcode/core.c index 6a6318e9590c..efb69be41ab1 100644 --- a/arch/x86/kernel/cpu/microcode/core.c +++ b/arch/x86/kernel/cpu/microcode/core.c @@ -55,7 +55,7 @@ LIST_HEAD(microcode_cache); * All non cpu-hotplug-callback call sites use: * * - microcode_mutex to synchronize with each other; - * - get/put_online_cpus() to synchronize with + * - cpus_read_lock/unlock() to synchronize with * the cpu-hotplug-callback call sites. * * We guarantee that only a single cpu is being @@ -431,7 +431,7 @@ static ssize_t microcode_write(struct file *file, const char __user *buf, return ret; } - get_online_cpus(); + cpus_read_lock(); mutex_lock(µcode_mutex); if (do_microcode_update(buf, len) == 0) @@ -441,7 +441,7 @@ static ssize_t microcode_write(struct file *file, const char __user *buf, perf_check_microcode(); mutex_unlock(µcode_mutex); - put_online_cpus(); + cpus_read_unlock(); return ret; } @@ -629,7 +629,7 @@ static ssize_t reload_store(struct device *dev, if (val != 1) return size; - get_online_cpus(); + cpus_read_lock(); ret = check_online_cpus(); if (ret) @@ -644,7 +644,7 @@ static ssize_t reload_store(struct device *dev, mutex_unlock(µcode_mutex); put: - put_online_cpus(); + cpus_read_unlock(); if (ret == 0) ret = size; @@ -853,14 +853,14 @@ static int __init microcode_init(void) if (IS_ERR(microcode_pdev)) return PTR_ERR(microcode_pdev); - get_online_cpus(); + cpus_read_lock(); mutex_lock(µcode_mutex); error = subsys_interface_register(&mc_cpu_interface); if (!error) perf_check_microcode(); mutex_unlock(µcode_mutex); - put_online_cpus(); + cpus_read_unlock(); if (error) goto out_pdev; @@ -892,13 +892,13 @@ static int __init microcode_init(void) &cpu_root_microcode_group); out_driver: - get_online_cpus(); + cpus_read_lock(); mutex_lock(µcode_mutex); subsys_interface_unregister(&mc_cpu_interface); mutex_unlock(µcode_mutex); - put_online_cpus(); + cpus_read_unlock(); out_pdev: platform_device_unregister(microcode_pdev); diff --git a/arch/x86/kernel/cpu/mshyperv.c b/arch/x86/kernel/cpu/mshyperv.c index cc8f1773deca..e095c28d27ae 100644 --- a/arch/x86/kernel/cpu/mshyperv.c +++ b/arch/x86/kernel/cpu/mshyperv.c @@ -17,7 +17,6 @@ #include <linux/irq.h> #include <linux/kexec.h> #include <linux/i8253.h> -#include <linux/panic_notifier.h> #include <linux/random.h> #include <asm/processor.h> #include <asm/hypervisor.h> @@ -36,10 +35,7 @@ /* 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); #if IS_ENABLED(CONFIG_HYPERV) static void (*vmbus_handler)(void); @@ -65,14 +61,12 @@ void hv_setup_vmbus_handler(void (*handler)(void)) { vmbus_handler = handler; } -EXPORT_SYMBOL_GPL(hv_setup_vmbus_handler); void hv_remove_vmbus_handler(void) { /* We have no way to deallocate the interrupt gate */ vmbus_handler = NULL; } -EXPORT_SYMBOL_GPL(hv_remove_vmbus_handler); /* * Routines to do per-architecture handling of stimer0 @@ -107,25 +101,21 @@ void hv_setup_kexec_handler(void (*handler)(void)) { hv_kexec_handler = handler; } -EXPORT_SYMBOL_GPL(hv_setup_kexec_handler); void hv_remove_kexec_handler(void) { hv_kexec_handler = NULL; } -EXPORT_SYMBOL_GPL(hv_remove_kexec_handler); void hv_setup_crash_handler(void (*handler)(struct pt_regs *regs)) { hv_crash_handler = handler; } -EXPORT_SYMBOL_GPL(hv_setup_crash_handler); void hv_remove_crash_handler(void) { hv_crash_handler = NULL; } -EXPORT_SYMBOL_GPL(hv_remove_crash_handler); #ifdef CONFIG_KEXEC_CORE static void hv_machine_shutdown(void) @@ -237,7 +227,7 @@ static void __init hv_smp_prepare_cpus(unsigned int max_cpus) for_each_present_cpu(i) { if (i == 0) continue; - ret = hv_call_add_logical_proc(numa_cpu_node(i), i, i); + ret = hv_call_add_logical_proc(numa_cpu_node(i), i, cpu_physical_id(i)); BUG_ON(ret); } @@ -335,16 +325,6 @@ static void __init ms_hyperv_init_platform(void) ms_hyperv.nested_features); } - /* - * Hyper-V expects to get crash register data or kmsg when - * crash enlightment is available and system crashes. Set - * crash_kexec_post_notifiers to be true to make sure that - * calling crash enlightment interface before running kdump - * kernel. - */ - if (ms_hyperv.misc_features & HV_FEATURE_GUEST_CRASH_MSR_AVAILABLE) - crash_kexec_post_notifiers = true; - #ifdef CONFIG_X86_LOCAL_APIC if (ms_hyperv.features & HV_ACCESS_FREQUENCY_MSRS && ms_hyperv.misc_features & HV_FEATURE_FREQUENCY_MSRS_AVAILABLE) { @@ -373,10 +353,17 @@ static void __init ms_hyperv_init_platform(void) machine_ops.crash_shutdown = hv_machine_crash_shutdown; #endif if (ms_hyperv.features & HV_ACCESS_TSC_INVARIANT) { + /* + * Writing to synthetic MSR 0x40000118 updates/changes the + * guest visible CPUIDs. Setting bit 0 of this MSR enables + * guests to report invariant TSC feature through CPUID + * instruction, CPUID 0x800000007/EDX, bit 8. See code in + * early_init_intel() where this bit is examined. The + * setting of this MSR bit should happen before init_intel() + * is called. + */ wrmsrl(HV_X64_MSR_TSC_INVARIANT_CONTROL, 0x1); setup_force_cpu_cap(X86_FEATURE_TSC_RELIABLE); - } else { - mark_tsc_unstable("running on Hyper-V"); } /* @@ -437,6 +424,13 @@ static void __init ms_hyperv_init_platform(void) /* Register Hyper-V specific clocksource */ hv_init_clocksource(); #endif + /* + * TSC should be marked as unstable only after Hyper-V + * clocksource has been initialized. This ensures that the + * stability of the sched_clock is not altered. + */ + if (!(ms_hyperv.features & HV_ACCESS_TSC_INVARIANT)) + mark_tsc_unstable("running on Hyper-V"); } static bool __init ms_hyperv_x2apic_available(void) diff --git a/arch/x86/kernel/cpu/mtrr/mtrr.c b/arch/x86/kernel/cpu/mtrr/mtrr.c index a76694bffe86..2746cac9d8a9 100644 --- a/arch/x86/kernel/cpu/mtrr/mtrr.c +++ b/arch/x86/kernel/cpu/mtrr/mtrr.c @@ -336,7 +336,7 @@ int mtrr_add_page(unsigned long base, unsigned long size, replace = -1; /* No CPU hotplug when we change MTRR entries */ - get_online_cpus(); + cpus_read_lock(); /* Search for existing MTRR */ mutex_lock(&mtrr_mutex); @@ -398,7 +398,7 @@ int mtrr_add_page(unsigned long base, unsigned long size, error = i; out: mutex_unlock(&mtrr_mutex); - put_online_cpus(); + cpus_read_unlock(); return error; } @@ -485,7 +485,7 @@ int mtrr_del_page(int reg, unsigned long base, unsigned long size) max = num_var_ranges; /* No CPU hotplug when we change MTRR entries */ - get_online_cpus(); + cpus_read_lock(); mutex_lock(&mtrr_mutex); if (reg < 0) { /* Search for existing MTRR */ @@ -520,7 +520,7 @@ int mtrr_del_page(int reg, unsigned long base, unsigned long size) error = reg; out: mutex_unlock(&mtrr_mutex); - put_online_cpus(); + cpus_read_unlock(); return error; } diff --git a/arch/x86/kernel/cpu/resctrl/core.c b/arch/x86/kernel/cpu/resctrl/core.c index 23001ae03e82..4b8813bafffd 100644 --- a/arch/x86/kernel/cpu/resctrl/core.c +++ b/arch/x86/kernel/cpu/resctrl/core.c @@ -57,128 +57,57 @@ static void mba_wrmsr_amd(struct rdt_domain *d, struct msr_param *m, struct rdt_resource *r); -#define domain_init(id) LIST_HEAD_INIT(rdt_resources_all[id].domains) +#define domain_init(id) LIST_HEAD_INIT(rdt_resources_all[id].r_resctrl.domains) -struct rdt_resource rdt_resources_all[] = { +struct rdt_hw_resource rdt_resources_all[] = { [RDT_RESOURCE_L3] = { - .rid = RDT_RESOURCE_L3, - .name = "L3", - .domains = domain_init(RDT_RESOURCE_L3), - .msr_base = MSR_IA32_L3_CBM_BASE, - .msr_update = cat_wrmsr, - .cache_level = 3, - .cache = { - .min_cbm_bits = 1, - .cbm_idx_mult = 1, - .cbm_idx_offset = 0, - }, - .parse_ctrlval = parse_cbm, - .format_str = "%d=%0*x", - .fflags = RFTYPE_RES_CACHE, - }, - [RDT_RESOURCE_L3DATA] = - { - .rid = RDT_RESOURCE_L3DATA, - .name = "L3DATA", - .domains = domain_init(RDT_RESOURCE_L3DATA), - .msr_base = MSR_IA32_L3_CBM_BASE, - .msr_update = cat_wrmsr, - .cache_level = 3, - .cache = { - .min_cbm_bits = 1, - .cbm_idx_mult = 2, - .cbm_idx_offset = 0, + .r_resctrl = { + .rid = RDT_RESOURCE_L3, + .name = "L3", + .cache_level = 3, + .cache = { + .min_cbm_bits = 1, + }, + .domains = domain_init(RDT_RESOURCE_L3), + .parse_ctrlval = parse_cbm, + .format_str = "%d=%0*x", + .fflags = RFTYPE_RES_CACHE, }, - .parse_ctrlval = parse_cbm, - .format_str = "%d=%0*x", - .fflags = RFTYPE_RES_CACHE, - }, - [RDT_RESOURCE_L3CODE] = - { - .rid = RDT_RESOURCE_L3CODE, - .name = "L3CODE", - .domains = domain_init(RDT_RESOURCE_L3CODE), .msr_base = MSR_IA32_L3_CBM_BASE, .msr_update = cat_wrmsr, - .cache_level = 3, - .cache = { - .min_cbm_bits = 1, - .cbm_idx_mult = 2, - .cbm_idx_offset = 1, - }, - .parse_ctrlval = parse_cbm, - .format_str = "%d=%0*x", - .fflags = RFTYPE_RES_CACHE, }, [RDT_RESOURCE_L2] = { - .rid = RDT_RESOURCE_L2, - .name = "L2", - .domains = domain_init(RDT_RESOURCE_L2), - .msr_base = MSR_IA32_L2_CBM_BASE, - .msr_update = cat_wrmsr, - .cache_level = 2, - .cache = { - .min_cbm_bits = 1, - .cbm_idx_mult = 1, - .cbm_idx_offset = 0, + .r_resctrl = { + .rid = RDT_RESOURCE_L2, + .name = "L2", + .cache_level = 2, + .cache = { + .min_cbm_bits = 1, + }, + .domains = domain_init(RDT_RESOURCE_L2), + .parse_ctrlval = parse_cbm, + .format_str = "%d=%0*x", + .fflags = RFTYPE_RES_CACHE, }, - .parse_ctrlval = parse_cbm, - .format_str = "%d=%0*x", - .fflags = RFTYPE_RES_CACHE, - }, - [RDT_RESOURCE_L2DATA] = - { - .rid = RDT_RESOURCE_L2DATA, - .name = "L2DATA", - .domains = domain_init(RDT_RESOURCE_L2DATA), .msr_base = MSR_IA32_L2_CBM_BASE, .msr_update = cat_wrmsr, - .cache_level = 2, - .cache = { - .min_cbm_bits = 1, - .cbm_idx_mult = 2, - .cbm_idx_offset = 0, - }, - .parse_ctrlval = parse_cbm, - .format_str = "%d=%0*x", - .fflags = RFTYPE_RES_CACHE, - }, - [RDT_RESOURCE_L2CODE] = - { - .rid = RDT_RESOURCE_L2CODE, - .name = "L2CODE", - .domains = domain_init(RDT_RESOURCE_L2CODE), - .msr_base = MSR_IA32_L2_CBM_BASE, - .msr_update = cat_wrmsr, - .cache_level = 2, - .cache = { - .min_cbm_bits = 1, - .cbm_idx_mult = 2, - .cbm_idx_offset = 1, - }, - .parse_ctrlval = parse_cbm, - .format_str = "%d=%0*x", - .fflags = RFTYPE_RES_CACHE, }, [RDT_RESOURCE_MBA] = { - .rid = RDT_RESOURCE_MBA, - .name = "MB", - .domains = domain_init(RDT_RESOURCE_MBA), - .cache_level = 3, - .parse_ctrlval = parse_bw, - .format_str = "%d=%*u", - .fflags = RFTYPE_RES_MB, + .r_resctrl = { + .rid = RDT_RESOURCE_MBA, + .name = "MB", + .cache_level = 3, + .domains = domain_init(RDT_RESOURCE_MBA), + .parse_ctrlval = parse_bw, + .format_str = "%d=%*u", + .fflags = RFTYPE_RES_MB, + }, }, }; -static unsigned int cbm_idx(struct rdt_resource *r, unsigned int closid) -{ - return closid * r->cache.cbm_idx_mult + r->cache.cbm_idx_offset; -} - /* * cache_alloc_hsw_probe() - Have to probe for Intel haswell server CPUs * as they do not have CPUID enumeration support for Cache allocation. @@ -199,7 +128,8 @@ static unsigned int cbm_idx(struct rdt_resource *r, unsigned int closid) */ static inline void cache_alloc_hsw_probe(void) { - struct rdt_resource *r = &rdt_resources_all[RDT_RESOURCE_L3]; + struct rdt_hw_resource *hw_res = &rdt_resources_all[RDT_RESOURCE_L3]; + struct rdt_resource *r = &hw_res->r_resctrl; u32 l, h, max_cbm = BIT_MASK(20) - 1; if (wrmsr_safe(MSR_IA32_L3_CBM_BASE, max_cbm, 0)) @@ -211,7 +141,7 @@ static inline void cache_alloc_hsw_probe(void) if (l != max_cbm) return; - r->num_closid = 4; + hw_res->num_closid = 4; r->default_ctrl = max_cbm; r->cache.cbm_len = 20; r->cache.shareable_bits = 0xc0000; @@ -225,7 +155,7 @@ static inline void cache_alloc_hsw_probe(void) bool is_mba_sc(struct rdt_resource *r) { if (!r) - return rdt_resources_all[RDT_RESOURCE_MBA].membw.mba_sc; + return rdt_resources_all[RDT_RESOURCE_MBA].r_resctrl.membw.mba_sc; return r->membw.mba_sc; } @@ -253,12 +183,13 @@ static inline bool rdt_get_mb_table(struct rdt_resource *r) static bool __get_mem_config_intel(struct rdt_resource *r) { + struct rdt_hw_resource *hw_res = resctrl_to_arch_res(r); union cpuid_0x10_3_eax eax; union cpuid_0x10_x_edx edx; u32 ebx, ecx, max_delay; cpuid_count(0x00000010, 3, &eax.full, &ebx, &ecx, &edx.full); - r->num_closid = edx.split.cos_max + 1; + hw_res->num_closid = edx.split.cos_max + 1; max_delay = eax.split.max_delay + 1; r->default_ctrl = MAX_MBA_BW; r->membw.arch_needs_linear = true; @@ -287,12 +218,13 @@ static bool __get_mem_config_intel(struct rdt_resource *r) static bool __rdt_get_mem_config_amd(struct rdt_resource *r) { + struct rdt_hw_resource *hw_res = resctrl_to_arch_res(r); union cpuid_0x10_3_eax eax; union cpuid_0x10_x_edx edx; u32 ebx, ecx; cpuid_count(0x80000020, 1, &eax.full, &ebx, &ecx, &edx.full); - r->num_closid = edx.split.cos_max + 1; + hw_res->num_closid = edx.split.cos_max + 1; r->default_ctrl = MAX_MBA_BW_AMD; /* AMD does not use delay */ @@ -317,12 +249,13 @@ static bool __rdt_get_mem_config_amd(struct rdt_resource *r) static void rdt_get_cache_alloc_cfg(int idx, struct rdt_resource *r) { + struct rdt_hw_resource *hw_res = resctrl_to_arch_res(r); union cpuid_0x10_1_eax eax; union cpuid_0x10_x_edx edx; u32 ebx, ecx; cpuid_count(0x00000010, idx, &eax.full, &ebx, &ecx, &edx.full); - r->num_closid = edx.split.cos_max + 1; + hw_res->num_closid = edx.split.cos_max + 1; r->cache.cbm_len = eax.split.cbm_len + 1; r->default_ctrl = BIT_MASK(eax.split.cbm_len + 1) - 1; r->cache.shareable_bits = ebx & r->default_ctrl; @@ -331,43 +264,35 @@ static void rdt_get_cache_alloc_cfg(int idx, struct rdt_resource *r) r->alloc_enabled = true; } -static void rdt_get_cdp_config(int level, int type) +static void rdt_get_cdp_config(int level) { - struct rdt_resource *r_l = &rdt_resources_all[level]; - struct rdt_resource *r = &rdt_resources_all[type]; - - r->num_closid = r_l->num_closid / 2; - r->cache.cbm_len = r_l->cache.cbm_len; - r->default_ctrl = r_l->default_ctrl; - r->cache.shareable_bits = r_l->cache.shareable_bits; - r->data_width = (r->cache.cbm_len + 3) / 4; - r->alloc_capable = true; /* * By default, CDP is disabled. CDP can be enabled by mount parameter * "cdp" during resctrl file system mount time. */ - r->alloc_enabled = false; + rdt_resources_all[level].cdp_enabled = false; + rdt_resources_all[level].r_resctrl.cdp_capable = true; } static void rdt_get_cdp_l3_config(void) { - rdt_get_cdp_config(RDT_RESOURCE_L3, RDT_RESOURCE_L3DATA); - rdt_get_cdp_config(RDT_RESOURCE_L3, RDT_RESOURCE_L3CODE); + rdt_get_cdp_config(RDT_RESOURCE_L3); } static void rdt_get_cdp_l2_config(void) { - rdt_get_cdp_config(RDT_RESOURCE_L2, RDT_RESOURCE_L2DATA); - rdt_get_cdp_config(RDT_RESOURCE_L2, RDT_RESOURCE_L2CODE); + rdt_get_cdp_config(RDT_RESOURCE_L2); } static void mba_wrmsr_amd(struct rdt_domain *d, struct msr_param *m, struct rdt_resource *r) { unsigned int i; + struct rdt_hw_domain *hw_dom = resctrl_to_arch_dom(d); + struct rdt_hw_resource *hw_res = resctrl_to_arch_res(r); for (i = m->low; i < m->high; i++) - wrmsrl(r->msr_base + i, d->ctrl_val[i]); + wrmsrl(hw_res->msr_base + i, hw_dom->ctrl_val[i]); } /* @@ -389,19 +314,23 @@ mba_wrmsr_intel(struct rdt_domain *d, struct msr_param *m, struct rdt_resource *r) { unsigned int i; + struct rdt_hw_domain *hw_dom = resctrl_to_arch_dom(d); + struct rdt_hw_resource *hw_res = resctrl_to_arch_res(r); /* Write the delay values for mba. */ for (i = m->low; i < m->high; i++) - wrmsrl(r->msr_base + i, delay_bw_map(d->ctrl_val[i], r)); + wrmsrl(hw_res->msr_base + i, delay_bw_map(hw_dom->ctrl_val[i], r)); } static void cat_wrmsr(struct rdt_domain *d, struct msr_param *m, struct rdt_resource *r) { unsigned int i; + struct rdt_hw_domain *hw_dom = resctrl_to_arch_dom(d); + struct rdt_hw_resource *hw_res = resctrl_to_arch_res(r); for (i = m->low; i < m->high; i++) - wrmsrl(r->msr_base + cbm_idx(r, i), d->ctrl_val[i]); + wrmsrl(hw_res->msr_base + i, hw_dom->ctrl_val[i]); } struct rdt_domain *get_domain_from_cpu(int cpu, struct rdt_resource *r) @@ -417,16 +346,22 @@ struct rdt_domain *get_domain_from_cpu(int cpu, struct rdt_resource *r) return NULL; } +u32 resctrl_arch_get_num_closid(struct rdt_resource *r) +{ + return resctrl_to_arch_res(r)->num_closid; +} + void rdt_ctrl_update(void *arg) { struct msr_param *m = arg; + struct rdt_hw_resource *hw_res = resctrl_to_arch_res(m->res); struct rdt_resource *r = m->res; int cpu = smp_processor_id(); struct rdt_domain *d; d = get_domain_from_cpu(cpu, r); if (d) { - r->msr_update(d, m, r); + hw_res->msr_update(d, m, r); return; } pr_warn_once("cpu %d not found in any domain for resource %s\n", @@ -468,6 +403,7 @@ struct rdt_domain *rdt_find_domain(struct rdt_resource *r, int id, void setup_default_ctrlval(struct rdt_resource *r, u32 *dc, u32 *dm) { + struct rdt_hw_resource *hw_res = resctrl_to_arch_res(r); int i; /* @@ -476,7 +412,7 @@ void setup_default_ctrlval(struct rdt_resource *r, u32 *dc, u32 *dm) * For Memory Allocation: Set b/w requested to 100% * and the bandwidth in MBps to U32_MAX */ - for (i = 0; i < r->num_closid; i++, dc++, dm++) { + for (i = 0; i < hw_res->num_closid; i++, dc++, dm++) { *dc = r->default_ctrl; *dm = MBA_MAX_MBPS; } @@ -484,26 +420,30 @@ void setup_default_ctrlval(struct rdt_resource *r, u32 *dc, u32 *dm) static int domain_setup_ctrlval(struct rdt_resource *r, struct rdt_domain *d) { + struct rdt_hw_resource *hw_res = resctrl_to_arch_res(r); + struct rdt_hw_domain *hw_dom = resctrl_to_arch_dom(d); struct msr_param m; u32 *dc, *dm; - dc = kmalloc_array(r->num_closid, sizeof(*d->ctrl_val), GFP_KERNEL); + dc = kmalloc_array(hw_res->num_closid, sizeof(*hw_dom->ctrl_val), + GFP_KERNEL); if (!dc) return -ENOMEM; - dm = kmalloc_array(r->num_closid, sizeof(*d->mbps_val), GFP_KERNEL); + dm = kmalloc_array(hw_res->num_closid, sizeof(*hw_dom->mbps_val), + GFP_KERNEL); if (!dm) { kfree(dc); return -ENOMEM; } - d->ctrl_val = dc; - d->mbps_val = dm; + hw_dom->ctrl_val = dc; + hw_dom->mbps_val = dm; setup_default_ctrlval(r, dc, dm); m.low = 0; - m.high = r->num_closid; - r->msr_update(d, &m, r); + m.high = hw_res->num_closid; + hw_res->msr_update(d, &m, r); return 0; } @@ -560,6 +500,7 @@ static void domain_add_cpu(int cpu, struct rdt_resource *r) { int id = get_cpu_cacheinfo_id(cpu, r->cache_level); struct list_head *add_pos = NULL; + struct rdt_hw_domain *hw_dom; struct rdt_domain *d; d = rdt_find_domain(r, id, &add_pos); @@ -575,10 +516,11 @@ static void domain_add_cpu(int cpu, struct rdt_resource *r) return; } - d = kzalloc_node(sizeof(*d), GFP_KERNEL, cpu_to_node(cpu)); - if (!d) + hw_dom = kzalloc_node(sizeof(*hw_dom), GFP_KERNEL, cpu_to_node(cpu)); + if (!hw_dom) return; + d = &hw_dom->d_resctrl; d->id = id; cpumask_set_cpu(cpu, &d->cpu_mask); @@ -607,6 +549,7 @@ static void domain_add_cpu(int cpu, struct rdt_resource *r) static void domain_remove_cpu(int cpu, struct rdt_resource *r) { int id = get_cpu_cacheinfo_id(cpu, r->cache_level); + struct rdt_hw_domain *hw_dom; struct rdt_domain *d; d = rdt_find_domain(r, id, NULL); @@ -614,6 +557,7 @@ static void domain_remove_cpu(int cpu, struct rdt_resource *r) pr_warn("Couldn't find cache id for CPU %d\n", cpu); return; } + hw_dom = resctrl_to_arch_dom(d); cpumask_clear_cpu(cpu, &d->cpu_mask); if (cpumask_empty(&d->cpu_mask)) { @@ -646,16 +590,16 @@ static void domain_remove_cpu(int cpu, struct rdt_resource *r) if (d->plr) d->plr->d = NULL; - kfree(d->ctrl_val); - kfree(d->mbps_val); + kfree(hw_dom->ctrl_val); + kfree(hw_dom->mbps_val); bitmap_free(d->rmid_busy_llc); kfree(d->mbm_total); kfree(d->mbm_local); - kfree(d); + kfree(hw_dom); return; } - if (r == &rdt_resources_all[RDT_RESOURCE_L3]) { + if (r == &rdt_resources_all[RDT_RESOURCE_L3].r_resctrl) { if (is_mbm_enabled() && cpu == d->mbm_work_cpu) { cancel_delayed_work(&d->mbm_over); mbm_setup_overflow_handler(d, 0); @@ -732,13 +676,8 @@ static int resctrl_offline_cpu(unsigned int cpu) static __init void rdt_init_padding(void) { struct rdt_resource *r; - int cl; for_each_alloc_capable_rdt_resource(r) { - cl = strlen(r->name); - if (cl > max_name_width) - max_name_width = cl; - if (r->data_width > max_data_width) max_data_width = r->data_width; } @@ -827,19 +766,22 @@ static bool __init rdt_cpu_has(int flag) static __init bool get_mem_config(void) { + struct rdt_hw_resource *hw_res = &rdt_resources_all[RDT_RESOURCE_MBA]; + if (!rdt_cpu_has(X86_FEATURE_MBA)) return false; if (boot_cpu_data.x86_vendor == X86_VENDOR_INTEL) - return __get_mem_config_intel(&rdt_resources_all[RDT_RESOURCE_MBA]); + return __get_mem_config_intel(&hw_res->r_resctrl); else if (boot_cpu_data.x86_vendor == X86_VENDOR_AMD) - return __rdt_get_mem_config_amd(&rdt_resources_all[RDT_RESOURCE_MBA]); + return __rdt_get_mem_config_amd(&hw_res->r_resctrl); return false; } static __init bool get_rdt_alloc_resources(void) { + struct rdt_resource *r; bool ret = false; if (rdt_alloc_capable) @@ -849,14 +791,16 @@ static __init bool get_rdt_alloc_resources(void) return false; if (rdt_cpu_has(X86_FEATURE_CAT_L3)) { - rdt_get_cache_alloc_cfg(1, &rdt_resources_all[RDT_RESOURCE_L3]); + r = &rdt_resources_all[RDT_RESOURCE_L3].r_resctrl; + rdt_get_cache_alloc_cfg(1, r); if (rdt_cpu_has(X86_FEATURE_CDP_L3)) rdt_get_cdp_l3_config(); ret = true; } if (rdt_cpu_has(X86_FEATURE_CAT_L2)) { /* CPUID 0x10.2 fields are same format at 0x10.1 */ - rdt_get_cache_alloc_cfg(2, &rdt_resources_all[RDT_RESOURCE_L2]); + r = &rdt_resources_all[RDT_RESOURCE_L2].r_resctrl; + rdt_get_cache_alloc_cfg(2, r); if (rdt_cpu_has(X86_FEATURE_CDP_L2)) rdt_get_cdp_l2_config(); ret = true; @@ -870,6 +814,8 @@ static __init bool get_rdt_alloc_resources(void) static __init bool get_rdt_mon_resources(void) { + struct rdt_resource *r = &rdt_resources_all[RDT_RESOURCE_L3].r_resctrl; + if (rdt_cpu_has(X86_FEATURE_CQM_OCCUP_LLC)) rdt_mon_features |= (1 << QOS_L3_OCCUP_EVENT_ID); if (rdt_cpu_has(X86_FEATURE_CQM_MBM_TOTAL)) @@ -880,7 +826,7 @@ static __init bool get_rdt_mon_resources(void) if (!rdt_mon_features) return false; - return !rdt_get_mon_l3_config(&rdt_resources_all[RDT_RESOURCE_L3]); + return !rdt_get_mon_l3_config(r); } static __init void __check_quirks_intel(void) @@ -918,42 +864,40 @@ static __init bool get_rdt_resources(void) static __init void rdt_init_res_defs_intel(void) { + struct rdt_hw_resource *hw_res; struct rdt_resource *r; for_each_rdt_resource(r) { + hw_res = resctrl_to_arch_res(r); + if (r->rid == RDT_RESOURCE_L3 || - r->rid == RDT_RESOURCE_L3DATA || - r->rid == RDT_RESOURCE_L3CODE || - r->rid == RDT_RESOURCE_L2 || - r->rid == RDT_RESOURCE_L2DATA || - r->rid == RDT_RESOURCE_L2CODE) { + r->rid == RDT_RESOURCE_L2) { r->cache.arch_has_sparse_bitmaps = false; r->cache.arch_has_empty_bitmaps = false; r->cache.arch_has_per_cpu_cfg = false; } else if (r->rid == RDT_RESOURCE_MBA) { - r->msr_base = MSR_IA32_MBA_THRTL_BASE; - r->msr_update = mba_wrmsr_intel; + hw_res->msr_base = MSR_IA32_MBA_THRTL_BASE; + hw_res->msr_update = mba_wrmsr_intel; } } } static __init void rdt_init_res_defs_amd(void) { + struct rdt_hw_resource *hw_res; struct rdt_resource *r; for_each_rdt_resource(r) { + hw_res = resctrl_to_arch_res(r); + if (r->rid == RDT_RESOURCE_L3 || - r->rid == RDT_RESOURCE_L3DATA || - r->rid == RDT_RESOURCE_L3CODE || - r->rid == RDT_RESOURCE_L2 || - r->rid == RDT_RESOURCE_L2DATA || - r->rid == RDT_RESOURCE_L2CODE) { + r->rid == RDT_RESOURCE_L2) { r->cache.arch_has_sparse_bitmaps = true; r->cache.arch_has_empty_bitmaps = true; r->cache.arch_has_per_cpu_cfg = true; } else if (r->rid == RDT_RESOURCE_MBA) { - r->msr_base = MSR_IA32_MBA_BW_BASE; - r->msr_update = mba_wrmsr_amd; + hw_res->msr_base = MSR_IA32_MBA_BW_BASE; + hw_res->msr_update = mba_wrmsr_amd; } } } diff --git a/arch/x86/kernel/cpu/resctrl/ctrlmondata.c b/arch/x86/kernel/cpu/resctrl/ctrlmondata.c index c877642e8a14..87666275eed9 100644 --- a/arch/x86/kernel/cpu/resctrl/ctrlmondata.c +++ b/arch/x86/kernel/cpu/resctrl/ctrlmondata.c @@ -57,20 +57,23 @@ static bool bw_validate(char *buf, unsigned long *data, struct rdt_resource *r) return true; } -int parse_bw(struct rdt_parse_data *data, struct rdt_resource *r, +int parse_bw(struct rdt_parse_data *data, struct resctrl_schema *s, struct rdt_domain *d) { + struct resctrl_staged_config *cfg; + struct rdt_resource *r = s->res; unsigned long bw_val; - if (d->have_new_ctrl) { + cfg = &d->staged_config[s->conf_type]; + if (cfg->have_new_ctrl) { rdt_last_cmd_printf("Duplicate domain %d\n", d->id); return -EINVAL; } if (!bw_validate(data->buf, &bw_val, r)) return -EINVAL; - d->new_ctrl = bw_val; - d->have_new_ctrl = true; + cfg->new_ctrl = bw_val; + cfg->have_new_ctrl = true; return 0; } @@ -125,13 +128,16 @@ static bool cbm_validate(char *buf, u32 *data, struct rdt_resource *r) * Read one cache bit mask (hex). Check that it is valid for the current * resource type. */ -int parse_cbm(struct rdt_parse_data *data, struct rdt_resource *r, +int parse_cbm(struct rdt_parse_data *data, struct resctrl_schema *s, struct rdt_domain *d) { struct rdtgroup *rdtgrp = data->rdtgrp; + struct resctrl_staged_config *cfg; + struct rdt_resource *r = s->res; u32 cbm_val; - if (d->have_new_ctrl) { + cfg = &d->staged_config[s->conf_type]; + if (cfg->have_new_ctrl) { rdt_last_cmd_printf("Duplicate domain %d\n", d->id); return -EINVAL; } @@ -160,12 +166,12 @@ int parse_cbm(struct rdt_parse_data *data, struct rdt_resource *r, * The CBM may not overlap with the CBM of another closid if * either is exclusive. */ - if (rdtgroup_cbm_overlaps(r, d, cbm_val, rdtgrp->closid, true)) { + if (rdtgroup_cbm_overlaps(s, d, cbm_val, rdtgrp->closid, true)) { rdt_last_cmd_puts("Overlaps with exclusive group\n"); return -EINVAL; } - if (rdtgroup_cbm_overlaps(r, d, cbm_val, rdtgrp->closid, false)) { + if (rdtgroup_cbm_overlaps(s, d, cbm_val, rdtgrp->closid, false)) { if (rdtgrp->mode == RDT_MODE_EXCLUSIVE || rdtgrp->mode == RDT_MODE_PSEUDO_LOCKSETUP) { rdt_last_cmd_puts("Overlaps with other group\n"); @@ -173,8 +179,8 @@ int parse_cbm(struct rdt_parse_data *data, struct rdt_resource *r, } } - d->new_ctrl = cbm_val; - d->have_new_ctrl = true; + cfg->new_ctrl = cbm_val; + cfg->have_new_ctrl = true; return 0; } @@ -185,9 +191,12 @@ int parse_cbm(struct rdt_parse_data *data, struct rdt_resource *r, * separated by ";". The "id" is in decimal, and must match one of * the "id"s for this resource. */ -static int parse_line(char *line, struct rdt_resource *r, +static int parse_line(char *line, struct resctrl_schema *s, struct rdtgroup *rdtgrp) { + enum resctrl_conf_type t = s->conf_type; + struct resctrl_staged_config *cfg; + struct rdt_resource *r = s->res; struct rdt_parse_data data; char *dom = NULL, *id; struct rdt_domain *d; @@ -213,9 +222,10 @@ next: if (d->id == dom_id) { data.buf = dom; data.rdtgrp = rdtgrp; - if (r->parse_ctrlval(&data, r, d)) + if (r->parse_ctrlval(&data, s, d)) return -EINVAL; if (rdtgrp->mode == RDT_MODE_PSEUDO_LOCKSETUP) { + cfg = &d->staged_config[t]; /* * In pseudo-locking setup mode and just * parsed a valid CBM that should be @@ -224,9 +234,9 @@ next: * the required initialization for single * region and return. */ - rdtgrp->plr->r = r; + rdtgrp->plr->s = s; rdtgrp->plr->d = d; - rdtgrp->plr->cbm = d->new_ctrl; + rdtgrp->plr->cbm = cfg->new_ctrl; d->plr = rdtgrp->plr; return 0; } @@ -236,28 +246,72 @@ next: return -EINVAL; } -int update_domains(struct rdt_resource *r, int closid) +static u32 get_config_index(u32 closid, enum resctrl_conf_type type) { + switch (type) { + default: + case CDP_NONE: + return closid; + case CDP_CODE: + return closid * 2 + 1; + case CDP_DATA: + return closid * 2; + } +} + +static bool apply_config(struct rdt_hw_domain *hw_dom, + struct resctrl_staged_config *cfg, u32 idx, + cpumask_var_t cpu_mask, bool mba_sc) +{ + struct rdt_domain *dom = &hw_dom->d_resctrl; + u32 *dc = !mba_sc ? hw_dom->ctrl_val : hw_dom->mbps_val; + + if (cfg->new_ctrl != dc[idx]) { + cpumask_set_cpu(cpumask_any(&dom->cpu_mask), cpu_mask); + dc[idx] = cfg->new_ctrl; + + return true; + } + + return false; +} + +int resctrl_arch_update_domains(struct rdt_resource *r, u32 closid) +{ + struct resctrl_staged_config *cfg; + struct rdt_hw_domain *hw_dom; struct msr_param msr_param; + enum resctrl_conf_type t; cpumask_var_t cpu_mask; struct rdt_domain *d; bool mba_sc; - u32 *dc; int cpu; + u32 idx; if (!zalloc_cpumask_var(&cpu_mask, GFP_KERNEL)) return -ENOMEM; - msr_param.low = closid; - msr_param.high = msr_param.low + 1; - msr_param.res = r; - mba_sc = is_mba_sc(r); + msr_param.res = NULL; list_for_each_entry(d, &r->domains, list) { - dc = !mba_sc ? d->ctrl_val : d->mbps_val; - if (d->have_new_ctrl && d->new_ctrl != dc[closid]) { - cpumask_set_cpu(cpumask_any(&d->cpu_mask), cpu_mask); - dc[closid] = d->new_ctrl; + hw_dom = resctrl_to_arch_dom(d); + for (t = 0; t < CDP_NUM_TYPES; t++) { + cfg = &hw_dom->d_resctrl.staged_config[t]; + if (!cfg->have_new_ctrl) + continue; + + idx = get_config_index(closid, t); + if (!apply_config(hw_dom, cfg, idx, cpu_mask, mba_sc)) + continue; + + if (!msr_param.res) { + msr_param.low = idx; + msr_param.high = msr_param.low + 1; + msr_param.res = r; + } else { + msr_param.low = min(msr_param.low, idx); + msr_param.high = max(msr_param.high, idx + 1); + } } } @@ -284,11 +338,11 @@ done: static int rdtgroup_parse_resource(char *resname, char *tok, struct rdtgroup *rdtgrp) { - struct rdt_resource *r; + struct resctrl_schema *s; - for_each_alloc_enabled_rdt_resource(r) { - if (!strcmp(resname, r->name) && rdtgrp->closid < r->num_closid) - return parse_line(tok, r, rdtgrp); + list_for_each_entry(s, &resctrl_schema_all, list) { + if (!strcmp(resname, s->name) && rdtgrp->closid < s->num_closid) + return parse_line(tok, s, rdtgrp); } rdt_last_cmd_printf("Unknown or unsupported resource name '%s'\n", resname); return -EINVAL; @@ -297,6 +351,7 @@ static int rdtgroup_parse_resource(char *resname, char *tok, ssize_t rdtgroup_schemata_write(struct kernfs_open_file *of, char *buf, size_t nbytes, loff_t off) { + struct resctrl_schema *s; struct rdtgroup *rdtgrp; struct rdt_domain *dom; struct rdt_resource *r; @@ -327,9 +382,9 @@ ssize_t rdtgroup_schemata_write(struct kernfs_open_file *of, goto out; } - for_each_alloc_enabled_rdt_resource(r) { - list_for_each_entry(dom, &r->domains, list) - dom->have_new_ctrl = false; + list_for_each_entry(s, &resctrl_schema_all, list) { + list_for_each_entry(dom, &s->res->domains, list) + memset(dom->staged_config, 0, sizeof(dom->staged_config)); } while ((tok = strsep(&buf, "\n")) != NULL) { @@ -349,8 +404,9 @@ ssize_t rdtgroup_schemata_write(struct kernfs_open_file *of, goto out; } - for_each_alloc_enabled_rdt_resource(r) { - ret = update_domains(r, rdtgrp->closid); + list_for_each_entry(s, &resctrl_schema_all, list) { + r = s->res; + ret = resctrl_arch_update_domains(r, rdtgrp->closid); if (ret) goto out; } @@ -371,19 +427,31 @@ out: return ret ?: nbytes; } -static void show_doms(struct seq_file *s, struct rdt_resource *r, int closid) +u32 resctrl_arch_get_config(struct rdt_resource *r, struct rdt_domain *d, + u32 closid, enum resctrl_conf_type type) +{ + struct rdt_hw_domain *hw_dom = resctrl_to_arch_dom(d); + u32 idx = get_config_index(closid, type); + + if (!is_mba_sc(r)) + return hw_dom->ctrl_val[idx]; + return hw_dom->mbps_val[idx]; +} + +static void show_doms(struct seq_file *s, struct resctrl_schema *schema, int closid) { + struct rdt_resource *r = schema->res; struct rdt_domain *dom; bool sep = false; u32 ctrl_val; - seq_printf(s, "%*s:", max_name_width, r->name); + seq_printf(s, "%*s:", max_name_width, schema->name); list_for_each_entry(dom, &r->domains, list) { if (sep) seq_puts(s, ";"); - ctrl_val = (!is_mba_sc(r) ? dom->ctrl_val[closid] : - dom->mbps_val[closid]); + ctrl_val = resctrl_arch_get_config(r, dom, closid, + schema->conf_type); seq_printf(s, r->format_str, dom->id, max_data_width, ctrl_val); sep = true; @@ -394,16 +462,17 @@ static void show_doms(struct seq_file *s, struct rdt_resource *r, int closid) int rdtgroup_schemata_show(struct kernfs_open_file *of, struct seq_file *s, void *v) { + struct resctrl_schema *schema; struct rdtgroup *rdtgrp; - struct rdt_resource *r; int ret = 0; u32 closid; rdtgrp = rdtgroup_kn_lock_live(of->kn); if (rdtgrp) { if (rdtgrp->mode == RDT_MODE_PSEUDO_LOCKSETUP) { - for_each_alloc_enabled_rdt_resource(r) - seq_printf(s, "%s:uninitialized\n", r->name); + list_for_each_entry(schema, &resctrl_schema_all, list) { + seq_printf(s, "%s:uninitialized\n", schema->name); + } } else if (rdtgrp->mode == RDT_MODE_PSEUDO_LOCKED) { if (!rdtgrp->plr->d) { rdt_last_cmd_clear(); @@ -411,15 +480,15 @@ int rdtgroup_schemata_show(struct kernfs_open_file *of, ret = -ENODEV; } else { seq_printf(s, "%s:%d=%x\n", - rdtgrp->plr->r->name, + rdtgrp->plr->s->res->name, rdtgrp->plr->d->id, rdtgrp->plr->cbm); } } else { closid = rdtgrp->closid; - for_each_alloc_enabled_rdt_resource(r) { - if (closid < r->num_closid) - show_doms(s, r, closid); + list_for_each_entry(schema, &resctrl_schema_all, list) { + if (closid < schema->num_closid) + show_doms(s, schema, closid); } } } else { @@ -449,6 +518,7 @@ void mon_event_read(struct rmid_read *rr, struct rdt_resource *r, int rdtgroup_mondata_show(struct seq_file *m, void *arg) { struct kernfs_open_file *of = m->private; + struct rdt_hw_resource *hw_res; u32 resid, evtid, domid; struct rdtgroup *rdtgrp; struct rdt_resource *r; @@ -468,7 +538,8 @@ int rdtgroup_mondata_show(struct seq_file *m, void *arg) domid = md.u.domid; evtid = md.u.evtid; - r = &rdt_resources_all[resid]; + hw_res = &rdt_resources_all[resid]; + r = &hw_res->r_resctrl; d = rdt_find_domain(r, domid, NULL); if (IS_ERR_OR_NULL(d)) { ret = -ENOENT; @@ -482,7 +553,7 @@ int rdtgroup_mondata_show(struct seq_file *m, void *arg) else if (rr.val & RMID_VAL_UNAVAIL) seq_puts(m, "Unavailable\n"); else - seq_printf(m, "%llu\n", rr.val * r->mon_scale); + seq_printf(m, "%llu\n", rr.val * hw_res->mon_scale); out: rdtgroup_kn_unlock(of->kn); diff --git a/arch/x86/kernel/cpu/resctrl/internal.h b/arch/x86/kernel/cpu/resctrl/internal.h index 6a5f60a37219..1d647188a43b 100644 --- a/arch/x86/kernel/cpu/resctrl/internal.h +++ b/arch/x86/kernel/cpu/resctrl/internal.h @@ -2,6 +2,7 @@ #ifndef _ASM_X86_RESCTRL_INTERNAL_H #define _ASM_X86_RESCTRL_INTERNAL_H +#include <linux/resctrl.h> #include <linux/sched.h> #include <linux/kernfs.h> #include <linux/fs_context.h> @@ -109,6 +110,7 @@ extern unsigned int resctrl_cqm_threshold; extern bool rdt_alloc_capable; extern bool rdt_mon_capable; extern unsigned int rdt_mon_features; +extern struct list_head resctrl_schema_all; enum rdt_group_type { RDTCTRL_GROUP = 0, @@ -161,8 +163,8 @@ struct mongroup { /** * struct pseudo_lock_region - pseudo-lock region information - * @r: RDT resource to which this pseudo-locked region - * belongs + * @s: Resctrl schema for the resource to which this + * pseudo-locked region belongs * @d: RDT domain to which this pseudo-locked region * belongs * @cbm: bitmask of the pseudo-locked region @@ -182,7 +184,7 @@ struct mongroup { * @pm_reqs: Power management QoS requests related to this region */ struct pseudo_lock_region { - struct rdt_resource *r; + struct resctrl_schema *s; struct rdt_domain *d; u32 cbm; wait_queue_head_t lock_thread_wq; @@ -303,44 +305,25 @@ struct mbm_state { }; /** - * struct rdt_domain - group of cpus sharing an RDT resource - * @list: all instances of this resource - * @id: unique id for this instance - * @cpu_mask: which cpus share this resource - * @rmid_busy_llc: - * bitmap of which limbo RMIDs are above threshold - * @mbm_total: saved state for MBM total bandwidth - * @mbm_local: saved state for MBM local bandwidth - * @mbm_over: worker to periodically read MBM h/w counters - * @cqm_limbo: worker to periodically read CQM h/w counters - * @mbm_work_cpu: - * worker cpu for MBM h/w counters - * @cqm_work_cpu: - * worker cpu for CQM h/w counters + * struct rdt_hw_domain - Arch private attributes of a set of CPUs that share + * a resource + * @d_resctrl: Properties exposed to the resctrl file system * @ctrl_val: array of cache or mem ctrl values (indexed by CLOSID) * @mbps_val: When mba_sc is enabled, this holds the bandwidth in MBps - * @new_ctrl: new ctrl value to be loaded - * @have_new_ctrl: did user provide new_ctrl for this domain - * @plr: pseudo-locked region (if any) associated with domain + * + * Members of this structure are accessed via helpers that provide abstraction. */ -struct rdt_domain { - struct list_head list; - int id; - struct cpumask cpu_mask; - unsigned long *rmid_busy_llc; - struct mbm_state *mbm_total; - struct mbm_state *mbm_local; - struct delayed_work mbm_over; - struct delayed_work cqm_limbo; - int mbm_work_cpu; - int cqm_work_cpu; +struct rdt_hw_domain { + struct rdt_domain d_resctrl; u32 *ctrl_val; u32 *mbps_val; - u32 new_ctrl; - bool have_new_ctrl; - struct pseudo_lock_region *plr; }; +static inline struct rdt_hw_domain *resctrl_to_arch_dom(struct rdt_domain *r) +{ + return container_of(r, struct rdt_hw_domain, d_resctrl); +} + /** * struct msr_param - set a range of MSRs from a domain * @res: The resource to use @@ -349,69 +332,8 @@ struct rdt_domain { */ struct msr_param { struct rdt_resource *res; - int low; - int high; -}; - -/** - * struct rdt_cache - Cache allocation related data - * @cbm_len: Length of the cache bit mask - * @min_cbm_bits: Minimum number of consecutive bits to be set - * @cbm_idx_mult: Multiplier of CBM index - * @cbm_idx_offset: Offset of CBM index. CBM index is computed by: - * closid * cbm_idx_multi + cbm_idx_offset - * in a cache bit mask - * @shareable_bits: Bitmask of shareable resource with other - * executing entities - * @arch_has_sparse_bitmaps: True if a bitmap like f00f is valid. - * @arch_has_empty_bitmaps: True if the '0' bitmap is valid. - * @arch_has_per_cpu_cfg: True if QOS_CFG register for this cache - * level has CPU scope. - */ -struct rdt_cache { - unsigned int cbm_len; - unsigned int min_cbm_bits; - unsigned int cbm_idx_mult; - unsigned int cbm_idx_offset; - unsigned int shareable_bits; - bool arch_has_sparse_bitmaps; - bool arch_has_empty_bitmaps; - bool arch_has_per_cpu_cfg; -}; - -/** - * enum membw_throttle_mode - System's memory bandwidth throttling mode - * @THREAD_THROTTLE_UNDEFINED: Not relevant to the system - * @THREAD_THROTTLE_MAX: Memory bandwidth is throttled at the core - * always using smallest bandwidth percentage - * assigned to threads, aka "max throttling" - * @THREAD_THROTTLE_PER_THREAD: Memory bandwidth is throttled at the thread - */ -enum membw_throttle_mode { - THREAD_THROTTLE_UNDEFINED = 0, - THREAD_THROTTLE_MAX, - THREAD_THROTTLE_PER_THREAD, -}; - -/** - * struct rdt_membw - Memory bandwidth allocation related data - * @min_bw: Minimum memory bandwidth percentage user can request - * @bw_gran: Granularity at which the memory bandwidth is allocated - * @delay_linear: True if memory B/W delay is in linear scale - * @arch_needs_linear: True if we can't configure non-linear resources - * @throttle_mode: Bandwidth throttling mode when threads request - * different memory bandwidths - * @mba_sc: True if MBA software controller(mba_sc) is enabled - * @mb_map: Mapping of memory B/W percentage to memory B/W delay - */ -struct rdt_membw { - u32 min_bw; - u32 bw_gran; - u32 delay_linear; - bool arch_needs_linear; - enum membw_throttle_mode throttle_mode; - bool mba_sc; - u32 *mb_map; + u32 low; + u32 high; }; static inline bool is_llc_occupancy_enabled(void) @@ -446,111 +368,103 @@ struct rdt_parse_data { }; /** - * struct rdt_resource - attributes of an RDT resource - * @rid: The index of the resource - * @alloc_enabled: Is allocation enabled on this machine - * @mon_enabled: Is monitoring enabled for this feature - * @alloc_capable: Is allocation available on this machine - * @mon_capable: Is monitor feature available on this machine - * @name: Name to use in "schemata" file - * @num_closid: Number of CLOSIDs available - * @cache_level: Which cache level defines scope of this resource - * @default_ctrl: Specifies default cache cbm or memory B/W percent. + * struct rdt_hw_resource - arch private attributes of a resctrl resource + * @r_resctrl: Attributes of the resource used directly by resctrl. + * @num_closid: Maximum number of closid this hardware can support, + * regardless of CDP. This is exposed via + * resctrl_arch_get_num_closid() to avoid confusion + * with struct resctrl_schema's property of the same name, + * which has been corrected for features like CDP. * @msr_base: Base MSR address for CBMs * @msr_update: Function pointer to update QOS MSRs - * @data_width: Character width of data when displaying - * @domains: All domains for this resource - * @cache: Cache allocation related data - * @membw: If the component has bandwidth controls, their properties. - * @format_str: Per resource format string to show domain value - * @parse_ctrlval: Per resource function pointer to parse control values - * @evt_list: List of monitoring events - * @num_rmid: Number of RMIDs available * @mon_scale: cqm counter * mon_scale = occupancy in bytes * @mbm_width: Monitor width, to detect and correct for overflow. - * @fflags: flags to choose base and info files + * @cdp_enabled: CDP state of this resource + * + * Members of this structure are either private to the architecture + * e.g. mbm_width, or accessed via helpers that provide abstraction. e.g. + * msr_update and msr_base. */ -struct rdt_resource { - int rid; - bool alloc_enabled; - bool mon_enabled; - bool alloc_capable; - bool mon_capable; - char *name; - int num_closid; - int cache_level; - u32 default_ctrl; +struct rdt_hw_resource { + struct rdt_resource r_resctrl; + u32 num_closid; unsigned int msr_base; void (*msr_update) (struct rdt_domain *d, struct msr_param *m, struct rdt_resource *r); - int data_width; - struct list_head domains; - struct rdt_cache cache; - struct rdt_membw membw; - const char *format_str; - int (*parse_ctrlval)(struct rdt_parse_data *data, - struct rdt_resource *r, - struct rdt_domain *d); - struct list_head evt_list; - int num_rmid; unsigned int mon_scale; unsigned int mbm_width; - unsigned long fflags; + bool cdp_enabled; }; -int parse_cbm(struct rdt_parse_data *data, struct rdt_resource *r, +static inline struct rdt_hw_resource *resctrl_to_arch_res(struct rdt_resource *r) +{ + return container_of(r, struct rdt_hw_resource, r_resctrl); +} + +int parse_cbm(struct rdt_parse_data *data, struct resctrl_schema *s, struct rdt_domain *d); -int parse_bw(struct rdt_parse_data *data, struct rdt_resource *r, +int parse_bw(struct rdt_parse_data *data, struct resctrl_schema *s, struct rdt_domain *d); extern struct mutex rdtgroup_mutex; -extern struct rdt_resource rdt_resources_all[]; +extern struct rdt_hw_resource rdt_resources_all[]; extern struct rdtgroup rdtgroup_default; DECLARE_STATIC_KEY_FALSE(rdt_alloc_enable_key); extern struct dentry *debugfs_resctrl; -enum { +enum resctrl_res_level { RDT_RESOURCE_L3, - RDT_RESOURCE_L3DATA, - RDT_RESOURCE_L3CODE, RDT_RESOURCE_L2, - RDT_RESOURCE_L2DATA, - RDT_RESOURCE_L2CODE, RDT_RESOURCE_MBA, /* Must be the last */ RDT_NUM_RESOURCES, }; +static inline struct rdt_resource *resctrl_inc(struct rdt_resource *res) +{ + struct rdt_hw_resource *hw_res = resctrl_to_arch_res(res); + + hw_res++; + return &hw_res->r_resctrl; +} + +static inline bool resctrl_arch_get_cdp_enabled(enum resctrl_res_level l) +{ + return rdt_resources_all[l].cdp_enabled; +} + +int resctrl_arch_set_cdp_enabled(enum resctrl_res_level l, bool enable); + +/* + * To return the common struct rdt_resource, which is contained in struct + * rdt_hw_resource, walk the resctrl member of struct rdt_hw_resource. + */ #define for_each_rdt_resource(r) \ - for (r = rdt_resources_all; r < rdt_resources_all + RDT_NUM_RESOURCES;\ - r++) + for (r = &rdt_resources_all[0].r_resctrl; \ + r <= &rdt_resources_all[RDT_NUM_RESOURCES - 1].r_resctrl; \ + r = resctrl_inc(r)) #define for_each_capable_rdt_resource(r) \ - for (r = rdt_resources_all; r < rdt_resources_all + RDT_NUM_RESOURCES;\ - r++) \ + for_each_rdt_resource(r) \ if (r->alloc_capable || r->mon_capable) #define for_each_alloc_capable_rdt_resource(r) \ - for (r = rdt_resources_all; r < rdt_resources_all + RDT_NUM_RESOURCES;\ - r++) \ + for_each_rdt_resource(r) \ if (r->alloc_capable) #define for_each_mon_capable_rdt_resource(r) \ - for (r = rdt_resources_all; r < rdt_resources_all + RDT_NUM_RESOURCES;\ - r++) \ + for_each_rdt_resource(r) \ if (r->mon_capable) #define for_each_alloc_enabled_rdt_resource(r) \ - for (r = rdt_resources_all; r < rdt_resources_all + RDT_NUM_RESOURCES;\ - r++) \ + for_each_rdt_resource(r) \ if (r->alloc_enabled) #define for_each_mon_enabled_rdt_resource(r) \ - for (r = rdt_resources_all; r < rdt_resources_all + RDT_NUM_RESOURCES;\ - r++) \ + for_each_rdt_resource(r) \ if (r->mon_enabled) /* CPUID.(EAX=10H, ECX=ResID=1).EAX */ @@ -594,7 +508,7 @@ ssize_t rdtgroup_schemata_write(struct kernfs_open_file *of, char *buf, size_t nbytes, loff_t off); int rdtgroup_schemata_show(struct kernfs_open_file *of, struct seq_file *s, void *v); -bool rdtgroup_cbm_overlaps(struct rdt_resource *r, struct rdt_domain *d, +bool rdtgroup_cbm_overlaps(struct resctrl_schema *s, struct rdt_domain *d, unsigned long cbm, int closid, bool exclusive); unsigned int rdtgroup_cbm_to_size(struct rdt_resource *r, struct rdt_domain *d, unsigned long cbm); @@ -609,7 +523,6 @@ void rdt_pseudo_lock_release(void); int rdtgroup_pseudo_lock_create(struct rdtgroup *rdtgrp); void rdtgroup_pseudo_lock_remove(struct rdtgroup *rdtgrp); struct rdt_domain *get_domain_from_cpu(int cpu, struct rdt_resource *r); -int update_domains(struct rdt_resource *r, int closid); int closids_supported(void); void closid_free(int closid); int alloc_rmid(void); diff --git a/arch/x86/kernel/cpu/resctrl/monitor.c b/arch/x86/kernel/cpu/resctrl/monitor.c index f07c10b87a87..c9f0f3d63f75 100644 --- a/arch/x86/kernel/cpu/resctrl/monitor.c +++ b/arch/x86/kernel/cpu/resctrl/monitor.c @@ -174,7 +174,7 @@ void __check_limbo(struct rdt_domain *d, bool force_free) struct rdt_resource *r; u32 crmid = 1, nrmid; - r = &rdt_resources_all[RDT_RESOURCE_L3]; + r = &rdt_resources_all[RDT_RESOURCE_L3].r_resctrl; /* * Skip RMID 0 and start from RMID 1 and check all the RMIDs that @@ -232,7 +232,7 @@ static void add_rmid_to_limbo(struct rmid_entry *entry) int cpu; u64 val; - r = &rdt_resources_all[RDT_RESOURCE_L3]; + r = &rdt_resources_all[RDT_RESOURCE_L3].r_resctrl; entry->busy = 0; cpu = get_cpu(); @@ -285,15 +285,15 @@ static u64 mbm_overflow_count(u64 prev_msr, u64 cur_msr, unsigned int width) return chunks >>= shift; } -static int __mon_event_count(u32 rmid, struct rmid_read *rr) +static u64 __mon_event_count(u32 rmid, struct rmid_read *rr) { + struct rdt_hw_resource *hw_res = resctrl_to_arch_res(rr->r); struct mbm_state *m; u64 chunks, tval; tval = __rmid_read(rmid, rr->evtid); if (tval & (RMID_VAL_ERROR | RMID_VAL_UNAVAIL)) { - rr->val = tval; - return -EINVAL; + return tval; } switch (rr->evtid) { case QOS_L3_OCCUP_EVENT_ID: @@ -307,10 +307,10 @@ static int __mon_event_count(u32 rmid, struct rmid_read *rr) break; default: /* - * Code would never reach here because - * an invalid event id would fail the __rmid_read. + * Code would never reach here because an invalid + * event id would fail the __rmid_read. */ - return -EINVAL; + return RMID_VAL_ERROR; } if (rr->first) { @@ -319,7 +319,7 @@ static int __mon_event_count(u32 rmid, struct rmid_read *rr) return 0; } - chunks = mbm_overflow_count(m->prev_msr, tval, rr->r->mbm_width); + chunks = mbm_overflow_count(m->prev_msr, tval, hw_res->mbm_width); m->chunks += chunks; m->prev_msr = tval; @@ -334,7 +334,7 @@ static int __mon_event_count(u32 rmid, struct rmid_read *rr) */ static void mbm_bw_count(u32 rmid, struct rmid_read *rr) { - struct rdt_resource *r = &rdt_resources_all[RDT_RESOURCE_L3]; + struct rdt_hw_resource *hw_res = resctrl_to_arch_res(rr->r); struct mbm_state *m = &rr->d->mbm_local[rmid]; u64 tval, cur_bw, chunks; @@ -342,8 +342,8 @@ static void mbm_bw_count(u32 rmid, struct rmid_read *rr) if (tval & (RMID_VAL_ERROR | RMID_VAL_UNAVAIL)) return; - chunks = mbm_overflow_count(m->prev_bw_msr, tval, rr->r->mbm_width); - cur_bw = (get_corrected_mbm_count(rmid, chunks) * r->mon_scale) >> 20; + chunks = mbm_overflow_count(m->prev_bw_msr, tval, hw_res->mbm_width); + cur_bw = (get_corrected_mbm_count(rmid, chunks) * hw_res->mon_scale) >> 20; if (m->delta_comp) m->delta_bw = abs(cur_bw - m->prev_bw); @@ -361,23 +361,29 @@ void mon_event_count(void *info) struct rdtgroup *rdtgrp, *entry; struct rmid_read *rr = info; struct list_head *head; + u64 ret_val; rdtgrp = rr->rgrp; - if (__mon_event_count(rdtgrp->mon.rmid, rr)) - return; + ret_val = __mon_event_count(rdtgrp->mon.rmid, rr); /* - * For Ctrl groups read data from child monitor groups. + * For Ctrl groups read data from child monitor groups and + * add them together. Count events which are read successfully. + * Discard the rmid_read's reporting errors. */ head = &rdtgrp->mon.crdtgrp_list; if (rdtgrp->type == RDTCTRL_GROUP) { list_for_each_entry(entry, head, mon.crdtgrp_list) { - if (__mon_event_count(entry->mon.rmid, rr)) - return; + if (__mon_event_count(entry->mon.rmid, rr) == 0) + ret_val = 0; } } + + /* Report error if none of rmid_reads are successful */ + if (ret_val) + rr->val = ret_val; } /* @@ -416,6 +422,8 @@ static void update_mba_bw(struct rdtgroup *rgrp, struct rdt_domain *dom_mbm) { u32 closid, rmid, cur_msr, cur_msr_val, new_msr_val; struct mbm_state *pmbm_data, *cmbm_data; + struct rdt_hw_resource *hw_r_mba; + struct rdt_hw_domain *hw_dom_mba; u32 cur_bw, delta_bw, user_bw; struct rdt_resource *r_mba; struct rdt_domain *dom_mba; @@ -425,7 +433,8 @@ static void update_mba_bw(struct rdtgroup *rgrp, struct rdt_domain *dom_mbm) if (!is_mbm_local_enabled()) return; - r_mba = &rdt_resources_all[RDT_RESOURCE_MBA]; + hw_r_mba = &rdt_resources_all[RDT_RESOURCE_MBA]; + r_mba = &hw_r_mba->r_resctrl; closid = rgrp->closid; rmid = rgrp->mon.rmid; pmbm_data = &dom_mbm->mbm_local[rmid]; @@ -435,11 +444,16 @@ static void update_mba_bw(struct rdtgroup *rgrp, struct rdt_domain *dom_mbm) pr_warn_once("Failure to get domain for MBA update\n"); return; } + hw_dom_mba = resctrl_to_arch_dom(dom_mba); cur_bw = pmbm_data->prev_bw; - user_bw = dom_mba->mbps_val[closid]; + user_bw = resctrl_arch_get_config(r_mba, dom_mba, closid, CDP_NONE); delta_bw = pmbm_data->delta_bw; - cur_msr_val = dom_mba->ctrl_val[closid]; + /* + * resctrl_arch_get_config() chooses the mbps/ctrl value to return + * based on is_mba_sc(). For now, reach into the hw_dom. + */ + cur_msr_val = hw_dom_mba->ctrl_val[closid]; /* * For Ctrl groups read data from child monitor groups. @@ -474,9 +488,9 @@ static void update_mba_bw(struct rdtgroup *rgrp, struct rdt_domain *dom_mbm) return; } - cur_msr = r_mba->msr_base + closid; + cur_msr = hw_r_mba->msr_base + closid; wrmsrl(cur_msr, delay_bw_map(new_msr_val, r_mba)); - dom_mba->ctrl_val[closid] = new_msr_val; + hw_dom_mba->ctrl_val[closid] = new_msr_val; /* * Delta values are updated dynamically package wise for each @@ -538,7 +552,7 @@ void cqm_handle_limbo(struct work_struct *work) mutex_lock(&rdtgroup_mutex); - r = &rdt_resources_all[RDT_RESOURCE_L3]; + r = &rdt_resources_all[RDT_RESOURCE_L3].r_resctrl; d = container_of(work, struct rdt_domain, cqm_limbo.work); __check_limbo(d, false); @@ -574,7 +588,7 @@ void mbm_handle_overflow(struct work_struct *work) if (!static_branch_likely(&rdt_mon_enable_key)) goto out_unlock; - r = &rdt_resources_all[RDT_RESOURCE_L3]; + r = &rdt_resources_all[RDT_RESOURCE_L3].r_resctrl; d = container_of(work, struct rdt_domain, mbm_over.work); list_for_each_entry(prgrp, &rdt_all_groups, rdtgroup_list) { @@ -671,15 +685,16 @@ static void l3_mon_evt_init(struct rdt_resource *r) int rdt_get_mon_l3_config(struct rdt_resource *r) { unsigned int mbm_offset = boot_cpu_data.x86_cache_mbm_width_offset; + struct rdt_hw_resource *hw_res = resctrl_to_arch_res(r); unsigned int cl_size = boot_cpu_data.x86_cache_size; int ret; - r->mon_scale = boot_cpu_data.x86_cache_occ_scale; + hw_res->mon_scale = boot_cpu_data.x86_cache_occ_scale; r->num_rmid = boot_cpu_data.x86_cache_max_rmid + 1; - r->mbm_width = MBM_CNTR_WIDTH_BASE; + hw_res->mbm_width = MBM_CNTR_WIDTH_BASE; if (mbm_offset > 0 && mbm_offset <= MBM_CNTR_WIDTH_OFFSET_MAX) - r->mbm_width += mbm_offset; + hw_res->mbm_width += mbm_offset; else if (mbm_offset > MBM_CNTR_WIDTH_OFFSET_MAX) pr_warn("Ignoring impossible MBM counter offset\n"); @@ -693,7 +708,7 @@ int rdt_get_mon_l3_config(struct rdt_resource *r) resctrl_cqm_threshold = cl_size * 1024 / r->num_rmid; /* h/w works in units of "boot_cpu_data.x86_cache_occ_scale" */ - resctrl_cqm_threshold /= r->mon_scale; + resctrl_cqm_threshold /= hw_res->mon_scale; ret = dom_data_init(r); if (ret) diff --git a/arch/x86/kernel/cpu/resctrl/pseudo_lock.c b/arch/x86/kernel/cpu/resctrl/pseudo_lock.c index 2207916cae65..db813f819ad6 100644 --- a/arch/x86/kernel/cpu/resctrl/pseudo_lock.c +++ b/arch/x86/kernel/cpu/resctrl/pseudo_lock.c @@ -250,7 +250,7 @@ static void pseudo_lock_region_clear(struct pseudo_lock_region *plr) plr->line_size = 0; kfree(plr->kmem); plr->kmem = NULL; - plr->r = NULL; + plr->s = NULL; if (plr->d) plr->d->plr = NULL; plr->d = NULL; @@ -294,10 +294,10 @@ static int pseudo_lock_region_init(struct pseudo_lock_region *plr) ci = get_cpu_cacheinfo(plr->cpu); - plr->size = rdtgroup_cbm_to_size(plr->r, plr->d, plr->cbm); + plr->size = rdtgroup_cbm_to_size(plr->s->res, plr->d, plr->cbm); for (i = 0; i < ci->num_leaves; i++) { - if (ci->info_list[i].level == plr->r->cache_level) { + if (ci->info_list[i].level == plr->s->res->cache_level) { plr->line_size = ci->info_list[i].coherency_line_size; return 0; } @@ -688,8 +688,8 @@ int rdtgroup_locksetup_enter(struct rdtgroup *rdtgrp) * resource, the portion of cache used by it should be made * unavailable to all future allocations from both resources. */ - if (rdt_resources_all[RDT_RESOURCE_L3DATA].alloc_enabled || - rdt_resources_all[RDT_RESOURCE_L2DATA].alloc_enabled) { + if (resctrl_arch_get_cdp_enabled(RDT_RESOURCE_L3) || + resctrl_arch_get_cdp_enabled(RDT_RESOURCE_L2)) { rdt_last_cmd_puts("CDP enabled\n"); return -EINVAL; } @@ -800,7 +800,7 @@ bool rdtgroup_cbm_overlaps_pseudo_locked(struct rdt_domain *d, unsigned long cbm unsigned long cbm_b; if (d->plr) { - cbm_len = d->plr->r->cache.cbm_len; + cbm_len = d->plr->s->res->cache.cbm_len; cbm_b = d->plr->cbm; if (bitmap_intersects(&cbm, &cbm_b, cbm_len)) return true; diff --git a/arch/x86/kernel/cpu/resctrl/rdtgroup.c b/arch/x86/kernel/cpu/resctrl/rdtgroup.c index 01fd30e7829d..b57b3db9a6a7 100644 --- a/arch/x86/kernel/cpu/resctrl/rdtgroup.c +++ b/arch/x86/kernel/cpu/resctrl/rdtgroup.c @@ -39,6 +39,9 @@ static struct kernfs_root *rdt_root; struct rdtgroup rdtgroup_default; LIST_HEAD(rdt_all_groups); +/* list of entries for the schemata file */ +LIST_HEAD(resctrl_schema_all); + /* Kernel fs node for "info" directory under root */ static struct kernfs_node *kn_info; @@ -100,12 +103,12 @@ int closids_supported(void) static void closid_init(void) { - struct rdt_resource *r; - int rdt_min_closid = 32; + struct resctrl_schema *s; + u32 rdt_min_closid = 32; /* Compute rdt_min_closid across all resources */ - for_each_alloc_enabled_rdt_resource(r) - rdt_min_closid = min(rdt_min_closid, r->num_closid); + list_for_each_entry(s, &resctrl_schema_all, list) + rdt_min_closid = min(rdt_min_closid, s->num_closid); closid_free_map = BIT_MASK(rdt_min_closid) - 1; @@ -842,16 +845,17 @@ static int rdt_last_cmd_status_show(struct kernfs_open_file *of, static int rdt_num_closids_show(struct kernfs_open_file *of, struct seq_file *seq, void *v) { - struct rdt_resource *r = of->kn->parent->priv; + struct resctrl_schema *s = of->kn->parent->priv; - seq_printf(seq, "%d\n", r->num_closid); + seq_printf(seq, "%u\n", s->num_closid); return 0; } static int rdt_default_ctrl_show(struct kernfs_open_file *of, struct seq_file *seq, void *v) { - struct rdt_resource *r = of->kn->parent->priv; + struct resctrl_schema *s = of->kn->parent->priv; + struct rdt_resource *r = s->res; seq_printf(seq, "%x\n", r->default_ctrl); return 0; @@ -860,7 +864,8 @@ static int rdt_default_ctrl_show(struct kernfs_open_file *of, static int rdt_min_cbm_bits_show(struct kernfs_open_file *of, struct seq_file *seq, void *v) { - struct rdt_resource *r = of->kn->parent->priv; + struct resctrl_schema *s = of->kn->parent->priv; + struct rdt_resource *r = s->res; seq_printf(seq, "%u\n", r->cache.min_cbm_bits); return 0; @@ -869,7 +874,8 @@ static int rdt_min_cbm_bits_show(struct kernfs_open_file *of, static int rdt_shareable_bits_show(struct kernfs_open_file *of, struct seq_file *seq, void *v) { - struct rdt_resource *r = of->kn->parent->priv; + struct resctrl_schema *s = of->kn->parent->priv; + struct rdt_resource *r = s->res; seq_printf(seq, "%x\n", r->cache.shareable_bits); return 0; @@ -892,38 +898,40 @@ static int rdt_shareable_bits_show(struct kernfs_open_file *of, static int rdt_bit_usage_show(struct kernfs_open_file *of, struct seq_file *seq, void *v) { - struct rdt_resource *r = of->kn->parent->priv; + struct resctrl_schema *s = of->kn->parent->priv; /* * Use unsigned long even though only 32 bits are used to ensure * test_bit() is used safely. */ unsigned long sw_shareable = 0, hw_shareable = 0; unsigned long exclusive = 0, pseudo_locked = 0; + struct rdt_resource *r = s->res; struct rdt_domain *dom; int i, hwb, swb, excl, psl; enum rdtgrp_mode mode; bool sep = false; - u32 *ctrl; + u32 ctrl_val; mutex_lock(&rdtgroup_mutex); hw_shareable = r->cache.shareable_bits; list_for_each_entry(dom, &r->domains, list) { if (sep) seq_putc(seq, ';'); - ctrl = dom->ctrl_val; sw_shareable = 0; exclusive = 0; seq_printf(seq, "%d=", dom->id); - for (i = 0; i < closids_supported(); i++, ctrl++) { + for (i = 0; i < closids_supported(); i++) { if (!closid_allocated(i)) continue; + ctrl_val = resctrl_arch_get_config(r, dom, i, + s->conf_type); mode = rdtgroup_mode_by_closid(i); switch (mode) { case RDT_MODE_SHAREABLE: - sw_shareable |= *ctrl; + sw_shareable |= ctrl_val; break; case RDT_MODE_EXCLUSIVE: - exclusive |= *ctrl; + exclusive |= ctrl_val; break; case RDT_MODE_PSEUDO_LOCKSETUP: /* @@ -970,7 +978,8 @@ static int rdt_bit_usage_show(struct kernfs_open_file *of, static int rdt_min_bw_show(struct kernfs_open_file *of, struct seq_file *seq, void *v) { - struct rdt_resource *r = of->kn->parent->priv; + struct resctrl_schema *s = of->kn->parent->priv; + struct rdt_resource *r = s->res; seq_printf(seq, "%u\n", r->membw.min_bw); return 0; @@ -1001,7 +1010,8 @@ static int rdt_mon_features_show(struct kernfs_open_file *of, static int rdt_bw_gran_show(struct kernfs_open_file *of, struct seq_file *seq, void *v) { - struct rdt_resource *r = of->kn->parent->priv; + struct resctrl_schema *s = of->kn->parent->priv; + struct rdt_resource *r = s->res; seq_printf(seq, "%u\n", r->membw.bw_gran); return 0; @@ -1010,7 +1020,8 @@ static int rdt_bw_gran_show(struct kernfs_open_file *of, static int rdt_delay_linear_show(struct kernfs_open_file *of, struct seq_file *seq, void *v) { - struct rdt_resource *r = of->kn->parent->priv; + struct resctrl_schema *s = of->kn->parent->priv; + struct rdt_resource *r = s->res; seq_printf(seq, "%u\n", r->membw.delay_linear); return 0; @@ -1020,8 +1031,9 @@ static int max_threshold_occ_show(struct kernfs_open_file *of, struct seq_file *seq, void *v) { struct rdt_resource *r = of->kn->parent->priv; + struct rdt_hw_resource *hw_res = resctrl_to_arch_res(r); - seq_printf(seq, "%u\n", resctrl_cqm_threshold * r->mon_scale); + seq_printf(seq, "%u\n", resctrl_cqm_threshold * hw_res->mon_scale); return 0; } @@ -1029,7 +1041,8 @@ static int max_threshold_occ_show(struct kernfs_open_file *of, static int rdt_thread_throttle_mode_show(struct kernfs_open_file *of, struct seq_file *seq, void *v) { - struct rdt_resource *r = of->kn->parent->priv; + struct resctrl_schema *s = of->kn->parent->priv; + struct rdt_resource *r = s->res; if (r->membw.throttle_mode == THREAD_THROTTLE_PER_THREAD) seq_puts(seq, "per-thread\n"); @@ -1042,7 +1055,7 @@ static int rdt_thread_throttle_mode_show(struct kernfs_open_file *of, static ssize_t max_threshold_occ_write(struct kernfs_open_file *of, char *buf, size_t nbytes, loff_t off) { - struct rdt_resource *r = of->kn->parent->priv; + struct rdt_hw_resource *hw_res; unsigned int bytes; int ret; @@ -1053,7 +1066,8 @@ static ssize_t max_threshold_occ_write(struct kernfs_open_file *of, if (bytes > (boot_cpu_data.x86_cache_size * 1024)) return -EINVAL; - resctrl_cqm_threshold = bytes / r->mon_scale; + hw_res = resctrl_to_arch_res(of->kn->parent->priv); + resctrl_cqm_threshold = bytes / hw_res->mon_scale; return nbytes; } @@ -1078,76 +1092,17 @@ static int rdtgroup_mode_show(struct kernfs_open_file *of, return 0; } -/** - * rdt_cdp_peer_get - Retrieve CDP peer if it exists - * @r: RDT resource to which RDT domain @d belongs - * @d: Cache instance for which a CDP peer is requested - * @r_cdp: RDT resource that shares hardware with @r (RDT resource peer) - * Used to return the result. - * @d_cdp: RDT domain that shares hardware with @d (RDT domain peer) - * Used to return the result. - * - * RDT resources are managed independently and by extension the RDT domains - * (RDT resource instances) are managed independently also. The Code and - * Data Prioritization (CDP) RDT resources, while managed independently, - * could refer to the same underlying hardware. For example, - * RDT_RESOURCE_L2CODE and RDT_RESOURCE_L2DATA both refer to the L2 cache. - * - * When provided with an RDT resource @r and an instance of that RDT - * resource @d rdt_cdp_peer_get() will return if there is a peer RDT - * resource and the exact instance that shares the same hardware. - * - * Return: 0 if a CDP peer was found, <0 on error or if no CDP peer exists. - * If a CDP peer was found, @r_cdp will point to the peer RDT resource - * and @d_cdp will point to the peer RDT domain. - */ -static int rdt_cdp_peer_get(struct rdt_resource *r, struct rdt_domain *d, - struct rdt_resource **r_cdp, - struct rdt_domain **d_cdp) +static enum resctrl_conf_type resctrl_peer_type(enum resctrl_conf_type my_type) { - struct rdt_resource *_r_cdp = NULL; - struct rdt_domain *_d_cdp = NULL; - int ret = 0; - - switch (r->rid) { - case RDT_RESOURCE_L3DATA: - _r_cdp = &rdt_resources_all[RDT_RESOURCE_L3CODE]; - break; - case RDT_RESOURCE_L3CODE: - _r_cdp = &rdt_resources_all[RDT_RESOURCE_L3DATA]; - break; - case RDT_RESOURCE_L2DATA: - _r_cdp = &rdt_resources_all[RDT_RESOURCE_L2CODE]; - break; - case RDT_RESOURCE_L2CODE: - _r_cdp = &rdt_resources_all[RDT_RESOURCE_L2DATA]; - break; + switch (my_type) { + case CDP_CODE: + return CDP_DATA; + case CDP_DATA: + return CDP_CODE; default: - ret = -ENOENT; - goto out; - } - - /* - * When a new CPU comes online and CDP is enabled then the new - * RDT domains (if any) associated with both CDP RDT resources - * are added in the same CPU online routine while the - * rdtgroup_mutex is held. It should thus not happen for one - * RDT domain to exist and be associated with its RDT CDP - * resource but there is no RDT domain associated with the - * peer RDT CDP resource. Hence the WARN. - */ - _d_cdp = rdt_find_domain(_r_cdp, d->id, NULL); - if (WARN_ON(IS_ERR_OR_NULL(_d_cdp))) { - _r_cdp = NULL; - _d_cdp = NULL; - ret = -EINVAL; + case CDP_NONE: + return CDP_NONE; } - -out: - *r_cdp = _r_cdp; - *d_cdp = _d_cdp; - - return ret; } /** @@ -1171,11 +1126,11 @@ out: * Return: false if CBM does not overlap, true if it does. */ static bool __rdtgroup_cbm_overlaps(struct rdt_resource *r, struct rdt_domain *d, - unsigned long cbm, int closid, bool exclusive) + unsigned long cbm, int closid, + enum resctrl_conf_type type, bool exclusive) { enum rdtgrp_mode mode; unsigned long ctrl_b; - u32 *ctrl; int i; /* Check for any overlap with regions used by hardware directly */ @@ -1186,9 +1141,8 @@ static bool __rdtgroup_cbm_overlaps(struct rdt_resource *r, struct rdt_domain *d } /* Check for overlap with other resource groups */ - ctrl = d->ctrl_val; - for (i = 0; i < closids_supported(); i++, ctrl++) { - ctrl_b = *ctrl; + for (i = 0; i < closids_supported(); i++) { + ctrl_b = resctrl_arch_get_config(r, d, i, type); mode = rdtgroup_mode_by_closid(i); if (closid_allocated(i) && i != closid && mode != RDT_MODE_PSEUDO_LOCKSETUP) { @@ -1208,7 +1162,7 @@ static bool __rdtgroup_cbm_overlaps(struct rdt_resource *r, struct rdt_domain *d /** * rdtgroup_cbm_overlaps - Does CBM overlap with other use of hardware - * @r: Resource to which domain instance @d belongs. + * @s: Schema for the resource to which domain instance @d belongs. * @d: The domain instance for which @closid is being tested. * @cbm: Capacity bitmask being tested. * @closid: Intended closid for @cbm. @@ -1226,19 +1180,19 @@ static bool __rdtgroup_cbm_overlaps(struct rdt_resource *r, struct rdt_domain *d * * Return: true if CBM overlap detected, false if there is no overlap */ -bool rdtgroup_cbm_overlaps(struct rdt_resource *r, struct rdt_domain *d, +bool rdtgroup_cbm_overlaps(struct resctrl_schema *s, struct rdt_domain *d, unsigned long cbm, int closid, bool exclusive) { - struct rdt_resource *r_cdp; - struct rdt_domain *d_cdp; + enum resctrl_conf_type peer_type = resctrl_peer_type(s->conf_type); + struct rdt_resource *r = s->res; - if (__rdtgroup_cbm_overlaps(r, d, cbm, closid, exclusive)) + if (__rdtgroup_cbm_overlaps(r, d, cbm, closid, s->conf_type, + exclusive)) return true; - if (rdt_cdp_peer_get(r, d, &r_cdp, &d_cdp) < 0) + if (!resctrl_arch_get_cdp_enabled(r->rid)) return false; - - return __rdtgroup_cbm_overlaps(r_cdp, d_cdp, cbm, closid, exclusive); + return __rdtgroup_cbm_overlaps(r, d, cbm, closid, peer_type, exclusive); } /** @@ -1256,17 +1210,21 @@ bool rdtgroup_cbm_overlaps(struct rdt_resource *r, struct rdt_domain *d, static bool rdtgroup_mode_test_exclusive(struct rdtgroup *rdtgrp) { int closid = rdtgrp->closid; + struct resctrl_schema *s; struct rdt_resource *r; bool has_cache = false; struct rdt_domain *d; + u32 ctrl; - for_each_alloc_enabled_rdt_resource(r) { + list_for_each_entry(s, &resctrl_schema_all, list) { + r = s->res; if (r->rid == RDT_RESOURCE_MBA) continue; has_cache = true; list_for_each_entry(d, &r->domains, list) { - if (rdtgroup_cbm_overlaps(r, d, d->ctrl_val[closid], - rdtgrp->closid, false)) { + ctrl = resctrl_arch_get_config(r, d, closid, + s->conf_type); + if (rdtgroup_cbm_overlaps(s, d, ctrl, closid, false)) { rdt_last_cmd_puts("Schemata overlaps\n"); return false; } @@ -1397,6 +1355,7 @@ unsigned int rdtgroup_cbm_to_size(struct rdt_resource *r, static int rdtgroup_size_show(struct kernfs_open_file *of, struct seq_file *s, void *v) { + struct resctrl_schema *schema; struct rdtgroup *rdtgrp; struct rdt_resource *r; struct rdt_domain *d; @@ -1418,8 +1377,8 @@ static int rdtgroup_size_show(struct kernfs_open_file *of, ret = -ENODEV; } else { seq_printf(s, "%*s:", max_name_width, - rdtgrp->plr->r->name); - size = rdtgroup_cbm_to_size(rdtgrp->plr->r, + rdtgrp->plr->s->name); + size = rdtgroup_cbm_to_size(rdtgrp->plr->s->res, rdtgrp->plr->d, rdtgrp->plr->cbm); seq_printf(s, "%d=%u\n", rdtgrp->plr->d->id, size); @@ -1427,18 +1386,19 @@ static int rdtgroup_size_show(struct kernfs_open_file *of, goto out; } - for_each_alloc_enabled_rdt_resource(r) { + list_for_each_entry(schema, &resctrl_schema_all, list) { + r = schema->res; sep = false; - seq_printf(s, "%*s:", max_name_width, r->name); + seq_printf(s, "%*s:", max_name_width, schema->name); list_for_each_entry(d, &r->domains, list) { if (sep) seq_putc(s, ';'); if (rdtgrp->mode == RDT_MODE_PSEUDO_LOCKSETUP) { size = 0; } else { - ctrl = (!is_mba_sc(r) ? - d->ctrl_val[rdtgrp->closid] : - d->mbps_val[rdtgrp->closid]); + ctrl = resctrl_arch_get_config(r, d, + rdtgrp->closid, + schema->conf_type); if (r->rid == RDT_RESOURCE_MBA) size = ctrl; else @@ -1757,14 +1717,14 @@ int rdtgroup_kn_mode_restore(struct rdtgroup *r, const char *name, return ret; } -static int rdtgroup_mkdir_info_resdir(struct rdt_resource *r, char *name, +static int rdtgroup_mkdir_info_resdir(void *priv, char *name, unsigned long fflags) { struct kernfs_node *kn_subdir; int ret; kn_subdir = kernfs_create_dir(kn_info, name, - kn_info->mode, r); + kn_info->mode, priv); if (IS_ERR(kn_subdir)) return PTR_ERR(kn_subdir); @@ -1781,6 +1741,7 @@ static int rdtgroup_mkdir_info_resdir(struct rdt_resource *r, char *name, static int rdtgroup_create_info_dir(struct kernfs_node *parent_kn) { + struct resctrl_schema *s; struct rdt_resource *r; unsigned long fflags; char name[32]; @@ -1795,9 +1756,11 @@ static int rdtgroup_create_info_dir(struct kernfs_node *parent_kn) if (ret) goto out_destroy; - for_each_alloc_enabled_rdt_resource(r) { + /* loop over enabled controls, these are all alloc_enabled */ + list_for_each_entry(s, &resctrl_schema_all, list) { + r = s->res; fflags = r->fflags | RF_CTRL_INFO; - ret = rdtgroup_mkdir_info_resdir(r, r->name, fflags); + ret = rdtgroup_mkdir_info_resdir(s, s->name, fflags); if (ret) goto out_destroy; } @@ -1867,7 +1830,7 @@ static void l2_qos_cfg_update(void *arg) static inline bool is_mba_linear(void) { - return rdt_resources_all[RDT_RESOURCE_MBA].membw.delay_linear; + return rdt_resources_all[RDT_RESOURCE_MBA].r_resctrl.membw.delay_linear; } static int set_cache_qos_cfg(int level, bool enable) @@ -1888,7 +1851,7 @@ static int set_cache_qos_cfg(int level, bool enable) if (!zalloc_cpumask_var(&cpu_mask, GFP_KERNEL)) return -ENOMEM; - r_l = &rdt_resources_all[level]; + r_l = &rdt_resources_all[level].r_resctrl; list_for_each_entry(d, &r_l->domains, list) { if (r_l->cache.arch_has_per_cpu_cfg) /* Pick all the CPUs in the domain instance */ @@ -1914,14 +1877,16 @@ static int set_cache_qos_cfg(int level, bool enable) /* Restore the qos cfg state when a domain comes online */ void rdt_domain_reconfigure_cdp(struct rdt_resource *r) { - if (!r->alloc_capable) + struct rdt_hw_resource *hw_res = resctrl_to_arch_res(r); + + if (!r->cdp_capable) return; - if (r == &rdt_resources_all[RDT_RESOURCE_L2DATA]) - l2_qos_cfg_update(&r->alloc_enabled); + if (r->rid == RDT_RESOURCE_L2) + l2_qos_cfg_update(&hw_res->cdp_enabled); - if (r == &rdt_resources_all[RDT_RESOURCE_L3DATA]) - l3_qos_cfg_update(&r->alloc_enabled); + if (r->rid == RDT_RESOURCE_L3) + l3_qos_cfg_update(&hw_res->cdp_enabled); } /* @@ -1932,7 +1897,8 @@ void rdt_domain_reconfigure_cdp(struct rdt_resource *r) */ static int set_mba_sc(bool mba_sc) { - struct rdt_resource *r = &rdt_resources_all[RDT_RESOURCE_MBA]; + struct rdt_resource *r = &rdt_resources_all[RDT_RESOURCE_MBA].r_resctrl; + struct rdt_hw_domain *hw_dom; struct rdt_domain *d; if (!is_mbm_enabled() || !is_mba_linear() || @@ -1940,73 +1906,60 @@ static int set_mba_sc(bool mba_sc) return -EINVAL; r->membw.mba_sc = mba_sc; - list_for_each_entry(d, &r->domains, list) - setup_default_ctrlval(r, d->ctrl_val, d->mbps_val); + list_for_each_entry(d, &r->domains, list) { + hw_dom = resctrl_to_arch_dom(d); + setup_default_ctrlval(r, hw_dom->ctrl_val, hw_dom->mbps_val); + } return 0; } -static int cdp_enable(int level, int data_type, int code_type) +static int cdp_enable(int level) { - struct rdt_resource *r_ldata = &rdt_resources_all[data_type]; - struct rdt_resource *r_lcode = &rdt_resources_all[code_type]; - struct rdt_resource *r_l = &rdt_resources_all[level]; + struct rdt_resource *r_l = &rdt_resources_all[level].r_resctrl; int ret; - if (!r_l->alloc_capable || !r_ldata->alloc_capable || - !r_lcode->alloc_capable) + if (!r_l->alloc_capable) return -EINVAL; ret = set_cache_qos_cfg(level, true); - if (!ret) { - r_l->alloc_enabled = false; - r_ldata->alloc_enabled = true; - r_lcode->alloc_enabled = true; - } + if (!ret) + rdt_resources_all[level].cdp_enabled = true; + return ret; } -static int cdpl3_enable(void) +static void cdp_disable(int level) { - return cdp_enable(RDT_RESOURCE_L3, RDT_RESOURCE_L3DATA, - RDT_RESOURCE_L3CODE); -} + struct rdt_hw_resource *r_hw = &rdt_resources_all[level]; -static int cdpl2_enable(void) -{ - return cdp_enable(RDT_RESOURCE_L2, RDT_RESOURCE_L2DATA, - RDT_RESOURCE_L2CODE); + if (r_hw->cdp_enabled) { + set_cache_qos_cfg(level, false); + r_hw->cdp_enabled = false; + } } -static void cdp_disable(int level, int data_type, int code_type) +int resctrl_arch_set_cdp_enabled(enum resctrl_res_level l, bool enable) { - struct rdt_resource *r = &rdt_resources_all[level]; + struct rdt_hw_resource *hw_res = &rdt_resources_all[l]; - r->alloc_enabled = r->alloc_capable; + if (!hw_res->r_resctrl.cdp_capable) + return -EINVAL; - if (rdt_resources_all[data_type].alloc_enabled) { - rdt_resources_all[data_type].alloc_enabled = false; - rdt_resources_all[code_type].alloc_enabled = false; - set_cache_qos_cfg(level, false); - } -} + if (enable) + return cdp_enable(l); -static void cdpl3_disable(void) -{ - cdp_disable(RDT_RESOURCE_L3, RDT_RESOURCE_L3DATA, RDT_RESOURCE_L3CODE); -} + cdp_disable(l); -static void cdpl2_disable(void) -{ - cdp_disable(RDT_RESOURCE_L2, RDT_RESOURCE_L2DATA, RDT_RESOURCE_L2CODE); + return 0; } static void cdp_disable_all(void) { - if (rdt_resources_all[RDT_RESOURCE_L3DATA].alloc_enabled) - cdpl3_disable(); - if (rdt_resources_all[RDT_RESOURCE_L2DATA].alloc_enabled) - cdpl2_disable(); + if (resctrl_arch_get_cdp_enabled(RDT_RESOURCE_L3)) + resctrl_arch_set_cdp_enabled(RDT_RESOURCE_L3, false); + if (resctrl_arch_get_cdp_enabled(RDT_RESOURCE_L2)) + resctrl_arch_set_cdp_enabled(RDT_RESOURCE_L2, false); } /* @@ -2084,10 +2037,10 @@ static int rdt_enable_ctx(struct rdt_fs_context *ctx) int ret = 0; if (ctx->enable_cdpl2) - ret = cdpl2_enable(); + ret = resctrl_arch_set_cdp_enabled(RDT_RESOURCE_L2, true); if (!ret && ctx->enable_cdpl3) - ret = cdpl3_enable(); + ret = resctrl_arch_set_cdp_enabled(RDT_RESOURCE_L3, true); if (!ret && ctx->enable_mba_mbps) ret = set_mba_sc(true); @@ -2095,6 +2048,92 @@ static int rdt_enable_ctx(struct rdt_fs_context *ctx) return ret; } +static int schemata_list_add(struct rdt_resource *r, enum resctrl_conf_type type) +{ + struct resctrl_schema *s; + const char *suffix = ""; + int ret, cl; + + s = kzalloc(sizeof(*s), GFP_KERNEL); + if (!s) + return -ENOMEM; + + s->res = r; + s->num_closid = resctrl_arch_get_num_closid(r); + if (resctrl_arch_get_cdp_enabled(r->rid)) + s->num_closid /= 2; + + s->conf_type = type; + switch (type) { + case CDP_CODE: + suffix = "CODE"; + break; + case CDP_DATA: + suffix = "DATA"; + break; + case CDP_NONE: + suffix = ""; + break; + } + + ret = snprintf(s->name, sizeof(s->name), "%s%s", r->name, suffix); + if (ret >= sizeof(s->name)) { + kfree(s); + return -EINVAL; + } + + cl = strlen(s->name); + + /* + * If CDP is supported by this resource, but not enabled, + * include the suffix. This ensures the tabular format of the + * schemata file does not change between mounts of the filesystem. + */ + if (r->cdp_capable && !resctrl_arch_get_cdp_enabled(r->rid)) + cl += 4; + + if (cl > max_name_width) + max_name_width = cl; + + INIT_LIST_HEAD(&s->list); + list_add(&s->list, &resctrl_schema_all); + + return 0; +} + +static int schemata_list_create(void) +{ + struct rdt_resource *r; + int ret = 0; + + for_each_alloc_enabled_rdt_resource(r) { + if (resctrl_arch_get_cdp_enabled(r->rid)) { + ret = schemata_list_add(r, CDP_CODE); + if (ret) + break; + + ret = schemata_list_add(r, CDP_DATA); + } else { + ret = schemata_list_add(r, CDP_NONE); + } + + if (ret) + break; + } + + return ret; +} + +static void schemata_list_destroy(void) +{ + struct resctrl_schema *s, *tmp; + + list_for_each_entry_safe(s, tmp, &resctrl_schema_all, list) { + list_del(&s->list); + kfree(s); + } +} + static int rdt_get_tree(struct fs_context *fc) { struct rdt_fs_context *ctx = rdt_fc2context(fc); @@ -2116,11 +2155,17 @@ static int rdt_get_tree(struct fs_context *fc) if (ret < 0) goto out_cdp; + ret = schemata_list_create(); + if (ret) { + schemata_list_destroy(); + goto out_mba; + } + closid_init(); ret = rdtgroup_create_info_dir(rdtgroup_default.kn); if (ret < 0) - goto out_mba; + goto out_schemata_free; if (rdt_mon_capable) { ret = mongroup_create_dir(rdtgroup_default.kn, @@ -2153,7 +2198,7 @@ static int rdt_get_tree(struct fs_context *fc) static_branch_enable_cpuslocked(&rdt_enable_key); if (is_mbm_enabled()) { - r = &rdt_resources_all[RDT_RESOURCE_L3]; + r = &rdt_resources_all[RDT_RESOURCE_L3].r_resctrl; list_for_each_entry(dom, &r->domains, list) mbm_setup_overflow_handler(dom, MBM_OVERFLOW_INTERVAL); } @@ -2170,6 +2215,8 @@ out_mongrp: kernfs_remove(kn_mongrp); out_info: kernfs_remove(kn_info); +out_schemata_free: + schemata_list_destroy(); out_mba: if (ctx->enable_mba_mbps) set_mba_sc(false); @@ -2257,6 +2304,8 @@ static int rdt_init_fs_context(struct fs_context *fc) static int reset_all_ctrls(struct rdt_resource *r) { + struct rdt_hw_resource *hw_res = resctrl_to_arch_res(r); + struct rdt_hw_domain *hw_dom; struct msr_param msr_param; cpumask_var_t cpu_mask; struct rdt_domain *d; @@ -2267,7 +2316,7 @@ static int reset_all_ctrls(struct rdt_resource *r) msr_param.res = r; msr_param.low = 0; - msr_param.high = r->num_closid; + msr_param.high = hw_res->num_closid; /* * Disable resource control for this resource by setting all @@ -2275,10 +2324,11 @@ static int reset_all_ctrls(struct rdt_resource *r) * from each domain to update the MSRs below. */ list_for_each_entry(d, &r->domains, list) { + hw_dom = resctrl_to_arch_dom(d); cpumask_set_cpu(cpumask_any(&d->cpu_mask), cpu_mask); - for (i = 0; i < r->num_closid; i++) - d->ctrl_val[i] = r->default_ctrl; + for (i = 0; i < hw_res->num_closid; i++) + hw_dom->ctrl_val[i] = r->default_ctrl; } cpu = get_cpu(); /* Update CBM on this cpu if it's in cpu_mask. */ @@ -2408,6 +2458,7 @@ static void rdt_kill_sb(struct super_block *sb) rmdir_all_sub(); rdt_pseudo_lock_release(); rdtgroup_default.mode = RDT_MODE_SHAREABLE; + schemata_list_destroy(); static_branch_disable_cpuslocked(&rdt_alloc_enable_key); static_branch_disable_cpuslocked(&rdt_mon_enable_key); static_branch_disable_cpuslocked(&rdt_enable_key); @@ -2642,23 +2693,24 @@ static u32 cbm_ensure_valid(u32 _val, struct rdt_resource *r) * Set the RDT domain up to start off with all usable allocations. That is, * all shareable and unused bits. All-zero CBM is invalid. */ -static int __init_one_rdt_domain(struct rdt_domain *d, struct rdt_resource *r, +static int __init_one_rdt_domain(struct rdt_domain *d, struct resctrl_schema *s, u32 closid) { - struct rdt_resource *r_cdp = NULL; - struct rdt_domain *d_cdp = NULL; + enum resctrl_conf_type peer_type = resctrl_peer_type(s->conf_type); + enum resctrl_conf_type t = s->conf_type; + struct resctrl_staged_config *cfg; + struct rdt_resource *r = s->res; u32 used_b = 0, unused_b = 0; unsigned long tmp_cbm; enum rdtgrp_mode mode; - u32 peer_ctl, *ctrl; + u32 peer_ctl, ctrl_val; int i; - rdt_cdp_peer_get(r, d, &r_cdp, &d_cdp); - d->have_new_ctrl = false; - d->new_ctrl = r->cache.shareable_bits; + cfg = &d->staged_config[t]; + cfg->have_new_ctrl = false; + cfg->new_ctrl = r->cache.shareable_bits; used_b = r->cache.shareable_bits; - ctrl = d->ctrl_val; - for (i = 0; i < closids_supported(); i++, ctrl++) { + for (i = 0; i < closids_supported(); i++) { if (closid_allocated(i) && i != closid) { mode = rdtgroup_mode_by_closid(i); if (mode == RDT_MODE_PSEUDO_LOCKSETUP) @@ -2673,35 +2725,38 @@ static int __init_one_rdt_domain(struct rdt_domain *d, struct rdt_resource *r, * usage to ensure there is no overlap * with an exclusive group. */ - if (d_cdp) - peer_ctl = d_cdp->ctrl_val[i]; + if (resctrl_arch_get_cdp_enabled(r->rid)) + peer_ctl = resctrl_arch_get_config(r, d, i, + peer_type); else peer_ctl = 0; - used_b |= *ctrl | peer_ctl; + ctrl_val = resctrl_arch_get_config(r, d, i, + s->conf_type); + used_b |= ctrl_val | peer_ctl; if (mode == RDT_MODE_SHAREABLE) - d->new_ctrl |= *ctrl | peer_ctl; + cfg->new_ctrl |= ctrl_val | peer_ctl; } } if (d->plr && d->plr->cbm > 0) used_b |= d->plr->cbm; unused_b = used_b ^ (BIT_MASK(r->cache.cbm_len) - 1); unused_b &= BIT_MASK(r->cache.cbm_len) - 1; - d->new_ctrl |= unused_b; + cfg->new_ctrl |= unused_b; /* * Force the initial CBM to be valid, user can * modify the CBM based on system availability. */ - d->new_ctrl = cbm_ensure_valid(d->new_ctrl, r); + cfg->new_ctrl = cbm_ensure_valid(cfg->new_ctrl, r); /* * Assign the u32 CBM to an unsigned long to ensure that * bitmap_weight() does not access out-of-bound memory. */ - tmp_cbm = d->new_ctrl; + tmp_cbm = cfg->new_ctrl; if (bitmap_weight(&tmp_cbm, r->cache.cbm_len) < r->cache.min_cbm_bits) { - rdt_last_cmd_printf("No space on %s:%d\n", r->name, d->id); + rdt_last_cmd_printf("No space on %s:%d\n", s->name, d->id); return -ENOSPC; } - d->have_new_ctrl = true; + cfg->have_new_ctrl = true; return 0; } @@ -2716,13 +2771,13 @@ static int __init_one_rdt_domain(struct rdt_domain *d, struct rdt_resource *r, * If there are no more shareable bits available on any domain then * the entire allocation will fail. */ -static int rdtgroup_init_cat(struct rdt_resource *r, u32 closid) +static int rdtgroup_init_cat(struct resctrl_schema *s, u32 closid) { struct rdt_domain *d; int ret; - list_for_each_entry(d, &r->domains, list) { - ret = __init_one_rdt_domain(d, r, closid); + list_for_each_entry(d, &s->res->domains, list) { + ret = __init_one_rdt_domain(d, s, closid); if (ret < 0) return ret; } @@ -2733,30 +2788,34 @@ static int rdtgroup_init_cat(struct rdt_resource *r, u32 closid) /* Initialize MBA resource with default values. */ static void rdtgroup_init_mba(struct rdt_resource *r) { + struct resctrl_staged_config *cfg; struct rdt_domain *d; list_for_each_entry(d, &r->domains, list) { - d->new_ctrl = is_mba_sc(r) ? MBA_MAX_MBPS : r->default_ctrl; - d->have_new_ctrl = true; + cfg = &d->staged_config[CDP_NONE]; + cfg->new_ctrl = is_mba_sc(r) ? MBA_MAX_MBPS : r->default_ctrl; + cfg->have_new_ctrl = true; } } /* Initialize the RDT group's allocations. */ static int rdtgroup_init_alloc(struct rdtgroup *rdtgrp) { + struct resctrl_schema *s; struct rdt_resource *r; int ret; - for_each_alloc_enabled_rdt_resource(r) { + list_for_each_entry(s, &resctrl_schema_all, list) { + r = s->res; if (r->rid == RDT_RESOURCE_MBA) { rdtgroup_init_mba(r); } else { - ret = rdtgroup_init_cat(r, rdtgrp->closid); + ret = rdtgroup_init_cat(s, rdtgrp->closid); if (ret < 0) return ret; } - ret = update_domains(r, rdtgrp->closid); + ret = resctrl_arch_update_domains(r, rdtgrp->closid); if (ret < 0) { rdt_last_cmd_puts("Failed to initialize allocations\n"); return ret; @@ -3124,13 +3183,13 @@ out: static int rdtgroup_show_options(struct seq_file *seq, struct kernfs_root *kf) { - if (rdt_resources_all[RDT_RESOURCE_L3DATA].alloc_enabled) + if (resctrl_arch_get_cdp_enabled(RDT_RESOURCE_L3)) seq_puts(seq, ",cdp"); - if (rdt_resources_all[RDT_RESOURCE_L2DATA].alloc_enabled) + if (resctrl_arch_get_cdp_enabled(RDT_RESOURCE_L2)) seq_puts(seq, ",cdpl2"); - if (is_mba_sc(&rdt_resources_all[RDT_RESOURCE_MBA])) + if (is_mba_sc(&rdt_resources_all[RDT_RESOURCE_MBA].r_resctrl)) seq_puts(seq, ",mba_MBps"); return 0; diff --git a/arch/x86/kernel/head_32.S b/arch/x86/kernel/head_32.S index 67f590425d90..d8c64dab0efe 100644 --- a/arch/x86/kernel/head_32.S +++ b/arch/x86/kernel/head_32.S @@ -432,7 +432,7 @@ SYM_FUNC_START(early_ignore_irq) pushl 32(%esp) pushl 40(%esp) pushl $int_msg - call printk + call _printk call dump_stack diff --git a/arch/x86/kernel/hpet.c b/arch/x86/kernel/hpet.c index 08651a4e6aa0..42fc41dd0e1f 100644 --- a/arch/x86/kernel/hpet.c +++ b/arch/x86/kernel/hpet.c @@ -508,7 +508,7 @@ static struct irq_chip hpet_msi_controller __ro_after_init = { .irq_set_affinity = msi_domain_set_affinity, .irq_retrigger = irq_chip_retrigger_hierarchy, .irq_write_msi_msg = hpet_msi_write_msg, - .flags = IRQCHIP_SKIP_SET_WAKE, + .flags = IRQCHIP_SKIP_SET_WAKE | IRQCHIP_AFFINITY_PRE_STARTUP, }; static int hpet_msi_init(struct irq_domain *domain, diff --git a/arch/x86/kernel/i8259.c b/arch/x86/kernel/i8259.c index 282b4ee1339f..15aefa3f3e18 100644 --- a/arch/x86/kernel/i8259.c +++ b/arch/x86/kernel/i8259.c @@ -235,15 +235,15 @@ static char irq_trigger[2]; */ static void restore_ELCR(char *trigger) { - outb(trigger[0], 0x4d0); - outb(trigger[1], 0x4d1); + outb(trigger[0], PIC_ELCR1); + outb(trigger[1], PIC_ELCR2); } static void save_ELCR(char *trigger) { /* IRQ 0,1,2,8,13 are marked as reserved */ - trigger[0] = inb(0x4d0) & 0xF8; - trigger[1] = inb(0x4d1) & 0xDE; + trigger[0] = inb(PIC_ELCR1) & 0xF8; + trigger[1] = inb(PIC_ELCR2) & 0xDE; } static void i8259A_resume(void) diff --git a/arch/x86/kernel/jump_label.c b/arch/x86/kernel/jump_label.c index 674906fad43b..68f091ba8443 100644 --- a/arch/x86/kernel/jump_label.c +++ b/arch/x86/kernel/jump_label.c @@ -79,9 +79,10 @@ __jump_label_patch(struct jump_entry *entry, enum jump_label_type type) return (struct jump_label_patch){.code = code, .size = size}; } -static inline void __jump_label_transform(struct jump_entry *entry, - enum jump_label_type type, - int init) +static __always_inline void +__jump_label_transform(struct jump_entry *entry, + enum jump_label_type type, + int init) { const struct jump_label_patch jlp = __jump_label_patch(entry, type); diff --git a/arch/x86/kernel/kvm.c b/arch/x86/kernel/kvm.c index a26643dc6bd6..b656456c3a94 100644 --- a/arch/x86/kernel/kvm.c +++ b/arch/x86/kernel/kvm.c @@ -884,10 +884,11 @@ static void kvm_wait(u8 *ptr, u8 val) } else { local_irq_disable(); + /* safe_halt() will enable IRQ */ if (READ_ONCE(*ptr) == val) safe_halt(); - - local_irq_enable(); + else + local_irq_enable(); } } diff --git a/arch/x86/kernel/ldt.c b/arch/x86/kernel/ldt.c index aa15132228da..525876e7b9f4 100644 --- a/arch/x86/kernel/ldt.c +++ b/arch/x86/kernel/ldt.c @@ -154,7 +154,7 @@ static struct ldt_struct *alloc_ldt_struct(unsigned int num_entries) if (num_entries > LDT_ENTRIES) return NULL; - new_ldt = kmalloc(sizeof(struct ldt_struct), GFP_KERNEL); + new_ldt = kmalloc(sizeof(struct ldt_struct), GFP_KERNEL_ACCOUNT); if (!new_ldt) return NULL; @@ -168,9 +168,9 @@ static struct ldt_struct *alloc_ldt_struct(unsigned int num_entries) * than PAGE_SIZE. */ if (alloc_size > PAGE_SIZE) - new_ldt->entries = vzalloc(alloc_size); + new_ldt->entries = __vmalloc(alloc_size, GFP_KERNEL_ACCOUNT | __GFP_ZERO); else - new_ldt->entries = (void *)get_zeroed_page(GFP_KERNEL); + new_ldt->entries = (void *)get_zeroed_page(GFP_KERNEL_ACCOUNT); if (!new_ldt->entries) { kfree(new_ldt); diff --git a/arch/x86/kernel/mpparse.c b/arch/x86/kernel/mpparse.c index 8f06449aab27..fed721f90116 100644 --- a/arch/x86/kernel/mpparse.c +++ b/arch/x86/kernel/mpparse.c @@ -19,6 +19,7 @@ #include <linux/smp.h> #include <linux/pci.h> +#include <asm/i8259.h> #include <asm/io_apic.h> #include <asm/acpi.h> #include <asm/irqdomain.h> @@ -251,7 +252,7 @@ static int __init ELCR_trigger(unsigned int irq) { unsigned int port; - port = 0x4d0 + (irq >> 3); + port = PIC_ELCR1 + (irq >> 3); return (inb(port) >> (irq & 7)) & 1; } diff --git a/arch/x86/kernel/reboot.c b/arch/x86/kernel/reboot.c index ebfb91108232..0a40df66a40d 100644 --- a/arch/x86/kernel/reboot.c +++ b/arch/x86/kernel/reboot.c @@ -388,10 +388,11 @@ static const struct dmi_system_id reboot_dmi_table[] __initconst = { }, { /* Handle problems with rebooting on the OptiPlex 990. */ .callback = set_pci_reboot, - .ident = "Dell OptiPlex 990", + .ident = "Dell OptiPlex 990 BIOS A0x", .matches = { DMI_MATCH(DMI_SYS_VENDOR, "Dell Inc."), DMI_MATCH(DMI_PRODUCT_NAME, "OptiPlex 990"), + DMI_MATCH(DMI_BIOS_VERSION, "A0"), }, }, { /* Handle problems with rebooting on Dell 300's */ diff --git a/arch/x86/kernel/setup.c b/arch/x86/kernel/setup.c index bff3a784aec5..79f164141116 100644 --- a/arch/x86/kernel/setup.c +++ b/arch/x86/kernel/setup.c @@ -5,6 +5,7 @@ * This file contains the setup_arch() code, which handles the architecture-dependent * parts of early kernel initialization. */ +#include <linux/acpi.h> #include <linux/console.h> #include <linux/crash_dump.h> #include <linux/dma-map-ops.h> @@ -572,16 +573,6 @@ void __init reserve_standard_io_resources(void) } -static __init void reserve_ibft_region(void) -{ - unsigned long addr, size = 0; - - addr = find_ibft_region(&size); - - if (size) - memblock_reserve(addr, size); -} - static bool __init snb_gfx_workaround_needed(void) { #ifdef CONFIG_PCI diff --git a/arch/x86/kernel/signal_compat.c b/arch/x86/kernel/signal_compat.c index 06743ec054d2..b52407c56000 100644 --- a/arch/x86/kernel/signal_compat.c +++ b/arch/x86/kernel/signal_compat.c @@ -34,7 +34,13 @@ static inline void signal_compat_build_tests(void) BUILD_BUG_ON(NSIGSYS != 2); /* This is part of the ABI and can never change in size: */ + BUILD_BUG_ON(sizeof(siginfo_t) != 128); BUILD_BUG_ON(sizeof(compat_siginfo_t) != 128); + + /* This is a part of the ABI and can never change in alignment */ + BUILD_BUG_ON(__alignof__(siginfo_t) != 8); + BUILD_BUG_ON(__alignof__(compat_siginfo_t) != 4); + /* * The offsets of all the (unioned) si_fields are fixed * in the ABI, of course. Make sure none of them ever diff --git a/arch/x86/kernel/smpboot.c b/arch/x86/kernel/smpboot.c index 9320285a5e29..85f6e242b6b4 100644 --- a/arch/x86/kernel/smpboot.c +++ b/arch/x86/kernel/smpboot.c @@ -610,6 +610,9 @@ void set_cpu_sibling_map(int cpu) if (threads > __max_smt_threads) __max_smt_threads = threads; + for_each_cpu(i, topology_sibling_cpumask(cpu)) + cpu_data(i).smt_active = threads > 1; + /* * This needs a separate iteration over the cpus because we rely on all * topology_sibling_cpumask links to be set-up. @@ -1552,8 +1555,13 @@ static void remove_siblinginfo(int cpu) for_each_cpu(sibling, topology_die_cpumask(cpu)) cpumask_clear_cpu(cpu, topology_die_cpumask(sibling)); - for_each_cpu(sibling, topology_sibling_cpumask(cpu)) + + for_each_cpu(sibling, topology_sibling_cpumask(cpu)) { cpumask_clear_cpu(cpu, topology_sibling_cpumask(sibling)); + if (cpumask_weight(topology_sibling_cpumask(sibling)) == 1) + cpu_data(sibling).smt_active = false; + } + for_each_cpu(sibling, cpu_llc_shared_mask(cpu)) cpumask_clear_cpu(cpu, cpu_llc_shared_mask(sibling)); cpumask_clear(cpu_llc_shared_mask(cpu)); diff --git a/arch/x86/kernel/sysfb.c b/arch/x86/kernel/sysfb.c deleted file mode 100644 index 014ebd8ca869..000000000000 --- a/arch/x86/kernel/sysfb.c +++ /dev/null @@ -1,70 +0,0 @@ -// SPDX-License-Identifier: GPL-2.0-or-later -/* - * Generic System Framebuffers on x86 - * Copyright (c) 2012-2013 David Herrmann <dh.herrmann@gmail.com> - */ - -/* - * Simple-Framebuffer support for x86 systems - * Create a platform-device for any available boot framebuffer. The - * simple-framebuffer platform device is already available on DT systems, so - * this module parses the global "screen_info" object and creates a suitable - * platform device compatible with the "simple-framebuffer" DT object. If - * the framebuffer is incompatible, we instead create a legacy - * "vesa-framebuffer", "efi-framebuffer" or "platform-framebuffer" device and - * pass the screen_info as platform_data. This allows legacy drivers - * to pick these devices up without messing with simple-framebuffer drivers. - * The global "screen_info" is still valid at all times. - * - * If CONFIG_X86_SYSFB is not selected, we never register "simple-framebuffer" - * platform devices, but only use legacy framebuffer devices for - * backwards compatibility. - * - * TODO: We set the dev_id field of all platform-devices to 0. This allows - * other x86 OF/DT parsers to create such devices, too. However, they must - * start at offset 1 for this to work. - */ - -#include <linux/err.h> -#include <linux/init.h> -#include <linux/kernel.h> -#include <linux/mm.h> -#include <linux/platform_data/simplefb.h> -#include <linux/platform_device.h> -#include <linux/screen_info.h> -#include <asm/sysfb.h> - -static __init int sysfb_init(void) -{ - struct screen_info *si = &screen_info; - struct simplefb_platform_data mode; - struct platform_device *pd; - const char *name; - bool compatible; - int ret; - - sysfb_apply_efi_quirks(); - - /* try to create a simple-framebuffer device */ - compatible = parse_mode(si, &mode); - if (compatible) { - ret = create_simplefb(si, &mode); - if (!ret) - return 0; - } - - /* if the FB is incompatible, create a legacy framebuffer device */ - if (si->orig_video_isVGA == VIDEO_TYPE_EFI) - name = "efi-framebuffer"; - else if (si->orig_video_isVGA == VIDEO_TYPE_VLFB) - name = "vesa-framebuffer"; - else - name = "platform-framebuffer"; - - pd = platform_device_register_resndata(NULL, name, 0, - NULL, 0, si, sizeof(*si)); - return PTR_ERR_OR_ZERO(pd); -} - -/* must execute after PCI subsystem for EFI quirks */ -device_initcall(sysfb_init); diff --git a/arch/x86/kernel/sysfb_efi.c b/arch/x86/kernel/sysfb_efi.c deleted file mode 100644 index 8a56a6d80098..000000000000 --- a/arch/x86/kernel/sysfb_efi.c +++ /dev/null @@ -1,284 +0,0 @@ -// SPDX-License-Identifier: GPL-2.0-or-later -/* - * Generic System Framebuffers on x86 - * Copyright (c) 2012-2013 David Herrmann <dh.herrmann@gmail.com> - * - * EFI Quirks Copyright (c) 2006 Edgar Hucek <gimli@dark-green.com> - */ - -/* - * EFI Quirks - * Several EFI systems do not correctly advertise their boot framebuffers. - * Hence, we use this static table of known broken machines and fix up the - * information so framebuffer drivers can load correctly. - */ - -#include <linux/dmi.h> -#include <linux/err.h> -#include <linux/efi.h> -#include <linux/init.h> -#include <linux/kernel.h> -#include <linux/mm.h> -#include <linux/pci.h> -#include <linux/screen_info.h> -#include <video/vga.h> - -#include <asm/efi.h> -#include <asm/sysfb.h> - -enum { - OVERRIDE_NONE = 0x0, - OVERRIDE_BASE = 0x1, - OVERRIDE_STRIDE = 0x2, - OVERRIDE_HEIGHT = 0x4, - OVERRIDE_WIDTH = 0x8, -}; - -struct efifb_dmi_info efifb_dmi_list[] = { - [M_I17] = { "i17", 0x80010000, 1472 * 4, 1440, 900, OVERRIDE_NONE }, - [M_I20] = { "i20", 0x80010000, 1728 * 4, 1680, 1050, OVERRIDE_NONE }, /* guess */ - [M_I20_SR] = { "imac7", 0x40010000, 1728 * 4, 1680, 1050, OVERRIDE_NONE }, - [M_I24] = { "i24", 0x80010000, 2048 * 4, 1920, 1200, OVERRIDE_NONE }, /* guess */ - [M_I24_8_1] = { "imac8", 0xc0060000, 2048 * 4, 1920, 1200, OVERRIDE_NONE }, - [M_I24_10_1] = { "imac10", 0xc0010000, 2048 * 4, 1920, 1080, OVERRIDE_NONE }, - [M_I27_11_1] = { "imac11", 0xc0010000, 2560 * 4, 2560, 1440, OVERRIDE_NONE }, - [M_MINI]= { "mini", 0x80000000, 2048 * 4, 1024, 768, OVERRIDE_NONE }, - [M_MINI_3_1] = { "mini31", 0x40010000, 1024 * 4, 1024, 768, OVERRIDE_NONE }, - [M_MINI_4_1] = { "mini41", 0xc0010000, 2048 * 4, 1920, 1200, OVERRIDE_NONE }, - [M_MB] = { "macbook", 0x80000000, 2048 * 4, 1280, 800, OVERRIDE_NONE }, - [M_MB_5_1] = { "macbook51", 0x80010000, 2048 * 4, 1280, 800, OVERRIDE_NONE }, - [M_MB_6_1] = { "macbook61", 0x80010000, 2048 * 4, 1280, 800, OVERRIDE_NONE }, - [M_MB_7_1] = { "macbook71", 0x80010000, 2048 * 4, 1280, 800, OVERRIDE_NONE }, - [M_MBA] = { "mba", 0x80000000, 2048 * 4, 1280, 800, OVERRIDE_NONE }, - /* 11" Macbook Air 3,1 passes the wrong stride */ - [M_MBA_3] = { "mba3", 0, 2048 * 4, 0, 0, OVERRIDE_STRIDE }, - [M_MBP] = { "mbp", 0x80010000, 1472 * 4, 1440, 900, OVERRIDE_NONE }, - [M_MBP_2] = { "mbp2", 0, 0, 0, 0, OVERRIDE_NONE }, /* placeholder */ - [M_MBP_2_2] = { "mbp22", 0x80010000, 1472 * 4, 1440, 900, OVERRIDE_NONE }, - [M_MBP_SR] = { "mbp3", 0x80030000, 2048 * 4, 1440, 900, OVERRIDE_NONE }, - [M_MBP_4] = { "mbp4", 0xc0060000, 2048 * 4, 1920, 1200, OVERRIDE_NONE }, - [M_MBP_5_1] = { "mbp51", 0xc0010000, 2048 * 4, 1440, 900, OVERRIDE_NONE }, - [M_MBP_5_2] = { "mbp52", 0xc0010000, 2048 * 4, 1920, 1200, OVERRIDE_NONE }, - [M_MBP_5_3] = { "mbp53", 0xd0010000, 2048 * 4, 1440, 900, OVERRIDE_NONE }, - [M_MBP_6_1] = { "mbp61", 0x90030000, 2048 * 4, 1920, 1200, OVERRIDE_NONE }, - [M_MBP_6_2] = { "mbp62", 0x90030000, 2048 * 4, 1680, 1050, OVERRIDE_NONE }, - [M_MBP_7_1] = { "mbp71", 0xc0010000, 2048 * 4, 1280, 800, OVERRIDE_NONE }, - [M_MBP_8_2] = { "mbp82", 0x90010000, 1472 * 4, 1440, 900, OVERRIDE_NONE }, - [M_UNKNOWN] = { NULL, 0, 0, 0, 0, OVERRIDE_NONE } -}; - -void efifb_setup_from_dmi(struct screen_info *si, const char *opt) -{ - int i; - - for (i = 0; i < M_UNKNOWN; i++) { - if (efifb_dmi_list[i].base != 0 && - !strcmp(opt, efifb_dmi_list[i].optname)) { - si->lfb_base = efifb_dmi_list[i].base; - si->lfb_linelength = efifb_dmi_list[i].stride; - si->lfb_width = efifb_dmi_list[i].width; - si->lfb_height = efifb_dmi_list[i].height; - } - } -} - -#define choose_value(dmivalue, fwvalue, field, flags) ({ \ - typeof(fwvalue) _ret_ = fwvalue; \ - if ((flags) & (field)) \ - _ret_ = dmivalue; \ - else if ((fwvalue) == 0) \ - _ret_ = dmivalue; \ - _ret_; \ - }) - -static int __init efifb_set_system(const struct dmi_system_id *id) -{ - struct efifb_dmi_info *info = id->driver_data; - - if (info->base == 0 && info->height == 0 && info->width == 0 && - info->stride == 0) - return 0; - - /* Trust the bootloader over the DMI tables */ - if (screen_info.lfb_base == 0) { -#if defined(CONFIG_PCI) - struct pci_dev *dev = NULL; - int found_bar = 0; -#endif - if (info->base) { - screen_info.lfb_base = choose_value(info->base, - screen_info.lfb_base, OVERRIDE_BASE, - info->flags); - -#if defined(CONFIG_PCI) - /* make sure that the address in the table is actually - * on a VGA device's PCI BAR */ - - for_each_pci_dev(dev) { - int i; - if ((dev->class >> 8) != PCI_CLASS_DISPLAY_VGA) - continue; - for (i = 0; i < DEVICE_COUNT_RESOURCE; i++) { - resource_size_t start, end; - unsigned long flags; - - flags = pci_resource_flags(dev, i); - if (!(flags & IORESOURCE_MEM)) - continue; - - if (flags & IORESOURCE_UNSET) - continue; - - if (pci_resource_len(dev, i) == 0) - continue; - - start = pci_resource_start(dev, i); - end = pci_resource_end(dev, i); - if (screen_info.lfb_base >= start && - screen_info.lfb_base < end) { - found_bar = 1; - break; - } - } - } - if (!found_bar) - screen_info.lfb_base = 0; -#endif - } - } - if (screen_info.lfb_base) { - screen_info.lfb_linelength = choose_value(info->stride, - screen_info.lfb_linelength, OVERRIDE_STRIDE, - info->flags); - screen_info.lfb_width = choose_value(info->width, - screen_info.lfb_width, OVERRIDE_WIDTH, - info->flags); - screen_info.lfb_height = choose_value(info->height, - screen_info.lfb_height, OVERRIDE_HEIGHT, - info->flags); - if (screen_info.orig_video_isVGA == 0) - screen_info.orig_video_isVGA = VIDEO_TYPE_EFI; - } else { - screen_info.lfb_linelength = 0; - screen_info.lfb_width = 0; - screen_info.lfb_height = 0; - screen_info.orig_video_isVGA = 0; - return 0; - } - - printk(KERN_INFO "efifb: dmi detected %s - framebuffer at 0x%08x " - "(%dx%d, stride %d)\n", id->ident, - screen_info.lfb_base, screen_info.lfb_width, - screen_info.lfb_height, screen_info.lfb_linelength); - - return 1; -} - -#define EFIFB_DMI_SYSTEM_ID(vendor, name, enumid) \ - { \ - efifb_set_system, \ - name, \ - { \ - DMI_MATCH(DMI_BIOS_VENDOR, vendor), \ - DMI_MATCH(DMI_PRODUCT_NAME, name) \ - }, \ - &efifb_dmi_list[enumid] \ - } - -static const struct dmi_system_id efifb_dmi_system_table[] __initconst = { - EFIFB_DMI_SYSTEM_ID("Apple Computer, Inc.", "iMac4,1", M_I17), - /* At least one of these two will be right; maybe both? */ - EFIFB_DMI_SYSTEM_ID("Apple Computer, Inc.", "iMac5,1", M_I20), - EFIFB_DMI_SYSTEM_ID("Apple Inc.", "iMac5,1", M_I20), - /* At least one of these two will be right; maybe both? */ - EFIFB_DMI_SYSTEM_ID("Apple Computer, Inc.", "iMac6,1", M_I24), - EFIFB_DMI_SYSTEM_ID("Apple Inc.", "iMac6,1", M_I24), - EFIFB_DMI_SYSTEM_ID("Apple Inc.", "iMac7,1", M_I20_SR), - EFIFB_DMI_SYSTEM_ID("Apple Inc.", "iMac8,1", M_I24_8_1), - EFIFB_DMI_SYSTEM_ID("Apple Inc.", "iMac10,1", M_I24_10_1), - EFIFB_DMI_SYSTEM_ID("Apple Inc.", "iMac11,1", M_I27_11_1), - EFIFB_DMI_SYSTEM_ID("Apple Computer, Inc.", "Macmini1,1", M_MINI), - EFIFB_DMI_SYSTEM_ID("Apple Inc.", "Macmini3,1", M_MINI_3_1), - EFIFB_DMI_SYSTEM_ID("Apple Inc.", "Macmini4,1", M_MINI_4_1), - EFIFB_DMI_SYSTEM_ID("Apple Computer, Inc.", "MacBook1,1", M_MB), - /* At least one of these two will be right; maybe both? */ - EFIFB_DMI_SYSTEM_ID("Apple Computer, Inc.", "MacBook2,1", M_MB), - EFIFB_DMI_SYSTEM_ID("Apple Inc.", "MacBook2,1", M_MB), - /* At least one of these two will be right; maybe both? */ - EFIFB_DMI_SYSTEM_ID("Apple Computer, Inc.", "MacBook3,1", M_MB), - EFIFB_DMI_SYSTEM_ID("Apple Inc.", "MacBook3,1", M_MB), - EFIFB_DMI_SYSTEM_ID("Apple Inc.", "MacBook4,1", M_MB), - EFIFB_DMI_SYSTEM_ID("Apple Inc.", "MacBook5,1", M_MB_5_1), - EFIFB_DMI_SYSTEM_ID("Apple Inc.", "MacBook6,1", M_MB_6_1), - EFIFB_DMI_SYSTEM_ID("Apple Inc.", "MacBook7,1", M_MB_7_1), - EFIFB_DMI_SYSTEM_ID("Apple Inc.", "MacBookAir1,1", M_MBA), - EFIFB_DMI_SYSTEM_ID("Apple Inc.", "MacBookAir3,1", M_MBA_3), - EFIFB_DMI_SYSTEM_ID("Apple Computer, Inc.", "MacBookPro1,1", M_MBP), - EFIFB_DMI_SYSTEM_ID("Apple Computer, Inc.", "MacBookPro2,1", M_MBP_2), - EFIFB_DMI_SYSTEM_ID("Apple Computer, Inc.", "MacBookPro2,2", M_MBP_2_2), - EFIFB_DMI_SYSTEM_ID("Apple Inc.", "MacBookPro2,1", M_MBP_2), - EFIFB_DMI_SYSTEM_ID("Apple Computer, Inc.", "MacBookPro3,1", M_MBP_SR), - EFIFB_DMI_SYSTEM_ID("Apple Inc.", "MacBookPro3,1", M_MBP_SR), - EFIFB_DMI_SYSTEM_ID("Apple Inc.", "MacBookPro4,1", M_MBP_4), - EFIFB_DMI_SYSTEM_ID("Apple Inc.", "MacBookPro5,1", M_MBP_5_1), - EFIFB_DMI_SYSTEM_ID("Apple Inc.", "MacBookPro5,2", M_MBP_5_2), - EFIFB_DMI_SYSTEM_ID("Apple Inc.", "MacBookPro5,3", M_MBP_5_3), - EFIFB_DMI_SYSTEM_ID("Apple Inc.", "MacBookPro6,1", M_MBP_6_1), - EFIFB_DMI_SYSTEM_ID("Apple Inc.", "MacBookPro6,2", M_MBP_6_2), - EFIFB_DMI_SYSTEM_ID("Apple Inc.", "MacBookPro7,1", M_MBP_7_1), - EFIFB_DMI_SYSTEM_ID("Apple Inc.", "MacBookPro8,2", M_MBP_8_2), - {}, -}; - -/* - * Some devices have a portrait LCD but advertise a landscape resolution (and - * pitch). We simply swap width and height for these devices so that we can - * correctly deal with some of them coming with multiple resolutions. - */ -static const struct dmi_system_id efifb_dmi_swap_width_height[] __initconst = { - { - /* - * Lenovo MIIX310-10ICR, only some batches have the troublesome - * 800x1280 portrait screen. Luckily the portrait version has - * its own BIOS version, so we match on that. - */ - .matches = { - DMI_EXACT_MATCH(DMI_SYS_VENDOR, "LENOVO"), - DMI_EXACT_MATCH(DMI_PRODUCT_VERSION, "MIIX 310-10ICR"), - DMI_EXACT_MATCH(DMI_BIOS_VERSION, "1HCN44WW"), - }, - }, - { - /* Lenovo MIIX 320-10ICR with 800x1280 portrait screen */ - .matches = { - DMI_EXACT_MATCH(DMI_SYS_VENDOR, "LENOVO"), - DMI_EXACT_MATCH(DMI_PRODUCT_VERSION, - "Lenovo MIIX 320-10ICR"), - }, - }, - { - /* Lenovo D330 with 800x1280 or 1200x1920 portrait screen */ - .matches = { - DMI_EXACT_MATCH(DMI_SYS_VENDOR, "LENOVO"), - DMI_EXACT_MATCH(DMI_PRODUCT_VERSION, - "Lenovo ideapad D330-10IGM"), - }, - }, - {}, -}; - -__init void sysfb_apply_efi_quirks(void) -{ - if (screen_info.orig_video_isVGA != VIDEO_TYPE_EFI || - !(screen_info.capabilities & VIDEO_CAPABILITY_SKIP_QUIRKS)) - dmi_check_system(efifb_dmi_system_table); - - if (screen_info.orig_video_isVGA == VIDEO_TYPE_EFI && - dmi_check_system(efifb_dmi_swap_width_height)) { - u16 temp = screen_info.lfb_width; - - screen_info.lfb_width = screen_info.lfb_height; - screen_info.lfb_height = temp; - screen_info.lfb_linelength = 4 * screen_info.lfb_width; - } -} diff --git a/arch/x86/kernel/sysfb_simplefb.c b/arch/x86/kernel/sysfb_simplefb.c deleted file mode 100644 index 298fc1edd9c9..000000000000 --- a/arch/x86/kernel/sysfb_simplefb.c +++ /dev/null @@ -1,111 +0,0 @@ -// SPDX-License-Identifier: GPL-2.0-or-later -/* - * Generic System Framebuffers on x86 - * Copyright (c) 2012-2013 David Herrmann <dh.herrmann@gmail.com> - */ - -/* - * simple-framebuffer probing - * Try to convert "screen_info" into a "simple-framebuffer" compatible mode. - * If the mode is incompatible, we return "false" and let the caller create - * legacy nodes instead. - */ - -#include <linux/err.h> -#include <linux/init.h> -#include <linux/kernel.h> -#include <linux/mm.h> -#include <linux/platform_data/simplefb.h> -#include <linux/platform_device.h> -#include <linux/screen_info.h> -#include <asm/sysfb.h> - -static const char simplefb_resname[] = "BOOTFB"; -static const struct simplefb_format formats[] = SIMPLEFB_FORMATS; - -/* try parsing x86 screen_info into a simple-framebuffer mode struct */ -__init bool parse_mode(const struct screen_info *si, - struct simplefb_platform_data *mode) -{ - const struct simplefb_format *f; - __u8 type; - unsigned int i; - - type = si->orig_video_isVGA; - if (type != VIDEO_TYPE_VLFB && type != VIDEO_TYPE_EFI) - return false; - - for (i = 0; i < ARRAY_SIZE(formats); ++i) { - f = &formats[i]; - if (si->lfb_depth == f->bits_per_pixel && - si->red_size == f->red.length && - si->red_pos == f->red.offset && - si->green_size == f->green.length && - si->green_pos == f->green.offset && - si->blue_size == f->blue.length && - si->blue_pos == f->blue.offset && - si->rsvd_size == f->transp.length && - si->rsvd_pos == f->transp.offset) { - mode->format = f->name; - mode->width = si->lfb_width; - mode->height = si->lfb_height; - mode->stride = si->lfb_linelength; - return true; - } - } - - return false; -} - -__init int create_simplefb(const struct screen_info *si, - const struct simplefb_platform_data *mode) -{ - struct platform_device *pd; - struct resource res; - u64 base, size; - u32 length; - - /* - * If the 64BIT_BASE capability is set, ext_lfb_base will contain the - * upper half of the base address. Assemble the address, then make sure - * it is valid and we can actually access it. - */ - base = si->lfb_base; - if (si->capabilities & VIDEO_CAPABILITY_64BIT_BASE) - base |= (u64)si->ext_lfb_base << 32; - if (!base || (u64)(resource_size_t)base != base) { - printk(KERN_DEBUG "sysfb: inaccessible VRAM base\n"); - return -EINVAL; - } - - /* - * Don't use lfb_size as IORESOURCE size, since it may contain the - * entire VMEM, and thus require huge mappings. Use just the part we - * need, that is, the part where the framebuffer is located. But verify - * that it does not exceed the advertised VMEM. - * Note that in case of VBE, the lfb_size is shifted by 16 bits for - * historical reasons. - */ - size = si->lfb_size; - if (si->orig_video_isVGA == VIDEO_TYPE_VLFB) - size <<= 16; - length = mode->height * mode->stride; - if (length > size) { - printk(KERN_WARNING "sysfb: VRAM smaller than advertised\n"); - return -EINVAL; - } - length = PAGE_ALIGN(length); - - /* setup IORESOURCE_MEM as framebuffer memory */ - memset(&res, 0, sizeof(res)); - res.flags = IORESOURCE_MEM | IORESOURCE_BUSY; - res.name = simplefb_resname; - res.start = base; - res.end = res.start + length - 1; - if (res.end <= res.start) - return -EINVAL; - - pd = platform_device_register_resndata(NULL, "simple-framebuffer", 0, - &res, 1, mode, sizeof(*mode)); - return PTR_ERR_OR_ZERO(pd); -} diff --git a/arch/x86/kvm/cpuid.c b/arch/x86/kvm/cpuid.c index c42613cfb5ba..fe03bd978761 100644 --- a/arch/x86/kvm/cpuid.c +++ b/arch/x86/kvm/cpuid.c @@ -208,30 +208,6 @@ static void kvm_vcpu_after_set_cpuid(struct kvm_vcpu *vcpu) kvm_mmu_after_set_cpuid(vcpu); } -static int is_efer_nx(void) -{ - return host_efer & EFER_NX; -} - -static void cpuid_fix_nx_cap(struct kvm_vcpu *vcpu) -{ - int i; - struct kvm_cpuid_entry2 *e, *entry; - - entry = NULL; - for (i = 0; i < vcpu->arch.cpuid_nent; ++i) { - e = &vcpu->arch.cpuid_entries[i]; - if (e->function == 0x80000001) { - entry = e; - break; - } - } - if (entry && cpuid_entry_has(entry, X86_FEATURE_NX) && !is_efer_nx()) { - cpuid_entry_clear(entry, X86_FEATURE_NX); - printk(KERN_INFO "kvm: guest NX capability removed\n"); - } -} - int cpuid_query_maxphyaddr(struct kvm_vcpu *vcpu) { struct kvm_cpuid_entry2 *best; @@ -302,7 +278,6 @@ int kvm_vcpu_ioctl_set_cpuid(struct kvm_vcpu *vcpu, vcpu->arch.cpuid_entries = e2; vcpu->arch.cpuid_nent = cpuid->nent; - cpuid_fix_nx_cap(vcpu); kvm_update_cpuid_runtime(vcpu); kvm_vcpu_after_set_cpuid(vcpu); @@ -401,7 +376,6 @@ static __always_inline void kvm_cpu_cap_mask(enum cpuid_leafs leaf, u32 mask) void kvm_set_cpu_caps(void) { - unsigned int f_nx = is_efer_nx() ? F(NX) : 0; #ifdef CONFIG_X86_64 unsigned int f_gbpages = F(GBPAGES); unsigned int f_lm = F(LM); @@ -515,7 +489,7 @@ void kvm_set_cpu_caps(void) F(CX8) | F(APIC) | 0 /* Reserved */ | F(SYSCALL) | F(MTRR) | F(PGE) | F(MCA) | F(CMOV) | F(PAT) | F(PSE36) | 0 /* Reserved */ | - f_nx | 0 /* Reserved */ | F(MMXEXT) | F(MMX) | + F(NX) | 0 /* Reserved */ | F(MMXEXT) | F(MMX) | F(FXSR) | F(FXSR_OPT) | f_gbpages | F(RDTSCP) | 0 /* Reserved */ | f_lm | F(3DNOWEXT) | F(3DNOW) ); @@ -765,7 +739,8 @@ static inline int __do_cpuid_func(struct kvm_cpuid_array *array, u32 function) edx.split.num_counters_fixed = min(cap.num_counters_fixed, MAX_FIXED_COUNTERS); edx.split.bit_width_fixed = cap.bit_width_fixed; - edx.split.anythread_deprecated = 1; + if (cap.version) + edx.split.anythread_deprecated = 1; edx.split.reserved1 = 0; edx.split.reserved2 = 0; @@ -940,8 +915,21 @@ static inline int __do_cpuid_func(struct kvm_cpuid_array *array, u32 function) unsigned virt_as = max((entry->eax >> 8) & 0xff, 48U); unsigned phys_as = entry->eax & 0xff; - if (!g_phys_as) + /* + * If TDP (NPT) is disabled use the adjusted host MAXPHYADDR as + * the guest operates in the same PA space as the host, i.e. + * reductions in MAXPHYADDR for memory encryption affect shadow + * paging, too. + * + * If TDP is enabled but an explicit guest MAXPHYADDR is not + * provided, use the raw bare metal MAXPHYADDR as reductions to + * the HPAs do not affect GPAs. + */ + if (!tdp_enabled) + g_phys_as = boot_cpu_data.x86_phys_bits; + else if (!g_phys_as) g_phys_as = phys_as; + entry->eax = g_phys_as | (virt_as << 8); entry->edx = 0; cpuid_entry_override(entry, CPUID_8000_0008_EBX); @@ -964,12 +952,18 @@ static inline int __do_cpuid_func(struct kvm_cpuid_array *array, u32 function) case 0x8000001a: case 0x8000001e: break; - /* Support memory encryption cpuid if host supports it */ case 0x8000001F: - if (!kvm_cpu_cap_has(X86_FEATURE_SEV)) + if (!kvm_cpu_cap_has(X86_FEATURE_SEV)) { entry->eax = entry->ebx = entry->ecx = entry->edx = 0; - else + } else { cpuid_entry_override(entry, CPUID_8000_001F_EAX); + + /* + * Enumerate '0' for "PA bits reduction", the adjusted + * MAXPHYADDR is enumerated directly (see 0x80000008). + */ + entry->ebx &= ~GENMASK(11, 6); + } break; /*Add support for Centaur's CPUID instruction*/ case 0xC0000000: diff --git a/arch/x86/kvm/debugfs.c b/arch/x86/kvm/debugfs.c index 95a98413dc32..54a83a744538 100644 --- a/arch/x86/kvm/debugfs.c +++ b/arch/x86/kvm/debugfs.c @@ -7,6 +7,8 @@ #include <linux/kvm_host.h> #include <linux/debugfs.h> #include "lapic.h" +#include "mmu.h" +#include "mmu/mmu_internal.h" static int vcpu_get_timer_advance_ns(void *data, u64 *val) { @@ -73,3 +75,112 @@ void kvm_arch_create_vcpu_debugfs(struct kvm_vcpu *vcpu, struct dentry *debugfs_ &vcpu_tsc_scaling_frac_fops); } } + +/* + * This covers statistics <1024 (11=log(1024)+1), which should be enough to + * cover RMAP_RECYCLE_THRESHOLD. + */ +#define RMAP_LOG_SIZE 11 + +static const char *kvm_lpage_str[KVM_NR_PAGE_SIZES] = { "4K", "2M", "1G" }; + +static int kvm_mmu_rmaps_stat_show(struct seq_file *m, void *v) +{ + struct kvm_rmap_head *rmap; + struct kvm *kvm = m->private; + struct kvm_memory_slot *slot; + struct kvm_memslots *slots; + unsigned int lpage_size, index; + /* Still small enough to be on the stack */ + unsigned int *log[KVM_NR_PAGE_SIZES], *cur; + int i, j, k, l, ret; + + ret = -ENOMEM; + memset(log, 0, sizeof(log)); + for (i = 0; i < KVM_NR_PAGE_SIZES; i++) { + log[i] = kcalloc(RMAP_LOG_SIZE, sizeof(unsigned int), GFP_KERNEL); + if (!log[i]) + goto out; + } + + mutex_lock(&kvm->slots_lock); + write_lock(&kvm->mmu_lock); + + for (i = 0; i < KVM_ADDRESS_SPACE_NUM; i++) { + slots = __kvm_memslots(kvm, i); + for (j = 0; j < slots->used_slots; j++) { + slot = &slots->memslots[j]; + for (k = 0; k < KVM_NR_PAGE_SIZES; k++) { + rmap = slot->arch.rmap[k]; + lpage_size = kvm_mmu_slot_lpages(slot, k + 1); + cur = log[k]; + for (l = 0; l < lpage_size; l++) { + index = ffs(pte_list_count(&rmap[l])); + if (WARN_ON_ONCE(index >= RMAP_LOG_SIZE)) + index = RMAP_LOG_SIZE - 1; + cur[index]++; + } + } + } + } + + write_unlock(&kvm->mmu_lock); + mutex_unlock(&kvm->slots_lock); + + /* index=0 counts no rmap; index=1 counts 1 rmap */ + seq_printf(m, "Rmap_Count:\t0\t1\t"); + for (i = 2; i < RMAP_LOG_SIZE; i++) { + j = 1 << (i - 1); + k = (1 << i) - 1; + seq_printf(m, "%d-%d\t", j, k); + } + seq_printf(m, "\n"); + + for (i = 0; i < KVM_NR_PAGE_SIZES; i++) { + seq_printf(m, "Level=%s:\t", kvm_lpage_str[i]); + cur = log[i]; + for (j = 0; j < RMAP_LOG_SIZE; j++) + seq_printf(m, "%d\t", cur[j]); + seq_printf(m, "\n"); + } + + ret = 0; +out: + for (i = 0; i < KVM_NR_PAGE_SIZES; i++) + kfree(log[i]); + + return ret; +} + +static int kvm_mmu_rmaps_stat_open(struct inode *inode, struct file *file) +{ + struct kvm *kvm = inode->i_private; + + if (!kvm_get_kvm_safe(kvm)) + return -ENOENT; + + return single_open(file, kvm_mmu_rmaps_stat_show, kvm); +} + +static int kvm_mmu_rmaps_stat_release(struct inode *inode, struct file *file) +{ + struct kvm *kvm = inode->i_private; + + kvm_put_kvm(kvm); + + return single_release(inode, file); +} + +static const struct file_operations mmu_rmaps_stat_fops = { + .open = kvm_mmu_rmaps_stat_open, + .read = seq_read, + .llseek = seq_lseek, + .release = kvm_mmu_rmaps_stat_release, +}; + +int kvm_arch_create_vm_debugfs(struct kvm *kvm) +{ + debugfs_create_file("mmu_rmaps_stat", 0644, kvm->debugfs_dentry, kvm, + &mmu_rmaps_stat_fops); + return 0; +} diff --git a/arch/x86/kvm/hyperv.c b/arch/x86/kvm/hyperv.c index b07592ca92f0..232a86a6faaf 100644 --- a/arch/x86/kvm/hyperv.c +++ b/arch/x86/kvm/hyperv.c @@ -88,6 +88,10 @@ static bool synic_has_vector_auto_eoi(struct kvm_vcpu_hv_synic *synic, static void synic_update_vector(struct kvm_vcpu_hv_synic *synic, int vector) { + struct kvm_vcpu *vcpu = hv_synic_to_vcpu(synic); + struct kvm_hv *hv = to_kvm_hv(vcpu->kvm); + int auto_eoi_old, auto_eoi_new; + if (vector < HV_SYNIC_FIRST_VALID_VECTOR) return; @@ -96,10 +100,30 @@ static void synic_update_vector(struct kvm_vcpu_hv_synic *synic, else __clear_bit(vector, synic->vec_bitmap); + auto_eoi_old = bitmap_weight(synic->auto_eoi_bitmap, 256); + if (synic_has_vector_auto_eoi(synic, vector)) __set_bit(vector, synic->auto_eoi_bitmap); else __clear_bit(vector, synic->auto_eoi_bitmap); + + auto_eoi_new = bitmap_weight(synic->auto_eoi_bitmap, 256); + + if (!!auto_eoi_old == !!auto_eoi_new) + return; + + mutex_lock(&vcpu->kvm->arch.apicv_update_lock); + + if (auto_eoi_new) + hv->synic_auto_eoi_used++; + else + hv->synic_auto_eoi_used--; + + __kvm_request_apicv_update(vcpu->kvm, + !hv->synic_auto_eoi_used, + APICV_INHIBIT_REASON_HYPERV); + + mutex_unlock(&vcpu->kvm->arch.apicv_update_lock); } static int synic_set_sint(struct kvm_vcpu_hv_synic *synic, int sint, @@ -933,12 +957,6 @@ int kvm_hv_activate_synic(struct kvm_vcpu *vcpu, bool dont_zero_synic_pages) synic = to_hv_synic(vcpu); - /* - * Hyper-V SynIC auto EOI SINT's are - * not compatible with APICV, so request - * to deactivate APICV permanently. - */ - kvm_request_apicv_update(vcpu->kvm, false, APICV_INHIBIT_REASON_HYPERV); synic->active = true; synic->dont_zero_synic_pages = dont_zero_synic_pages; synic->control = HV_SYNIC_CONTROL_ENABLE; @@ -1933,7 +1951,7 @@ ret_success: void kvm_hv_set_cpuid(struct kvm_vcpu *vcpu) { struct kvm_cpuid_entry2 *entry; - struct kvm_vcpu_hv *hv_vcpu = to_hv_vcpu(vcpu); + struct kvm_vcpu_hv *hv_vcpu; entry = kvm_find_cpuid_entry(vcpu, HYPERV_CPUID_INTERFACE, 0); if (entry && entry->eax == HYPERV_CPUID_SIGNATURE_EAX) { @@ -2016,6 +2034,7 @@ static void kvm_hv_hypercall_set_result(struct kvm_vcpu *vcpu, u64 result) static int kvm_hv_hypercall_complete(struct kvm_vcpu *vcpu, u64 result) { + trace_kvm_hv_hypercall_done(result); kvm_hv_hypercall_set_result(vcpu, result); ++vcpu->stat.hypercalls; return kvm_skip_emulated_instruction(vcpu); @@ -2139,6 +2158,7 @@ static bool hv_check_hypercall_access(struct kvm_vcpu_hv *hv_vcpu, u16 code) int kvm_hv_hypercall(struct kvm_vcpu *vcpu) { + struct kvm_vcpu_hv *hv_vcpu = to_hv_vcpu(vcpu); struct kvm_hv_hcall hc; u64 ret = HV_STATUS_SUCCESS; @@ -2173,17 +2193,25 @@ int kvm_hv_hypercall(struct kvm_vcpu *vcpu) hc.rep_idx = (hc.param >> HV_HYPERCALL_REP_START_OFFSET) & 0xfff; hc.rep = !!(hc.rep_cnt || hc.rep_idx); - if (hc.fast && is_xmm_fast_hypercall(&hc)) - kvm_hv_hypercall_read_xmm(&hc); - trace_kvm_hv_hypercall(hc.code, hc.fast, hc.rep_cnt, hc.rep_idx, hc.ingpa, hc.outgpa); - if (unlikely(!hv_check_hypercall_access(to_hv_vcpu(vcpu), hc.code))) { + if (unlikely(!hv_check_hypercall_access(hv_vcpu, hc.code))) { ret = HV_STATUS_ACCESS_DENIED; goto hypercall_complete; } + if (hc.fast && is_xmm_fast_hypercall(&hc)) { + if (unlikely(hv_vcpu->enforce_cpuid && + !(hv_vcpu->cpuid_cache.features_edx & + HV_X64_HYPERCALL_XMM_INPUT_AVAILABLE))) { + kvm_queue_exception(vcpu, UD_VECTOR); + return 1; + } + + kvm_hv_hypercall_read_xmm(&hc); + } + switch (hc.code) { case HVCALL_NOTIFY_LONG_SPIN_WAIT: if (unlikely(hc.rep)) { @@ -2466,6 +2494,8 @@ int kvm_get_hv_cpuid(struct kvm_vcpu *vcpu, struct kvm_cpuid2 *cpuid, ent->eax |= HV_X64_ENLIGHTENED_VMCS_RECOMMENDED; if (!cpu_smt_possible()) ent->eax |= HV_X64_NO_NONARCH_CORESHARING; + + ent->eax |= HV_DEPRECATING_AEOI_RECOMMENDED; /* * Default number of spinlock retry attempts, matches * HyperV 2016. diff --git a/arch/x86/kvm/i8254.c b/arch/x86/kvm/i8254.c index a6e218c6140d..5a69cce4d72d 100644 --- a/arch/x86/kvm/i8254.c +++ b/arch/x86/kvm/i8254.c @@ -220,7 +220,8 @@ void __kvm_migrate_pit_timer(struct kvm_vcpu *vcpu) struct kvm_pit *pit = vcpu->kvm->arch.vpit; struct hrtimer *timer; - if (!kvm_vcpu_is_bsp(vcpu) || !pit) + /* Somewhat arbitrarily make vcpu0 the owner of the PIT. */ + if (vcpu->vcpu_id || !pit) return; timer = &pit->pit_state.timer; diff --git a/arch/x86/kvm/i8259.c b/arch/x86/kvm/i8259.c index 629a09ca9860..0b80263d46d8 100644 --- a/arch/x86/kvm/i8259.c +++ b/arch/x86/kvm/i8259.c @@ -541,17 +541,17 @@ static int picdev_slave_read(struct kvm_vcpu *vcpu, struct kvm_io_device *dev, addr, len, val); } -static int picdev_eclr_write(struct kvm_vcpu *vcpu, struct kvm_io_device *dev, +static int picdev_elcr_write(struct kvm_vcpu *vcpu, struct kvm_io_device *dev, gpa_t addr, int len, const void *val) { - return picdev_write(container_of(dev, struct kvm_pic, dev_eclr), + return picdev_write(container_of(dev, struct kvm_pic, dev_elcr), addr, len, val); } -static int picdev_eclr_read(struct kvm_vcpu *vcpu, struct kvm_io_device *dev, +static int picdev_elcr_read(struct kvm_vcpu *vcpu, struct kvm_io_device *dev, gpa_t addr, int len, void *val) { - return picdev_read(container_of(dev, struct kvm_pic, dev_eclr), + return picdev_read(container_of(dev, struct kvm_pic, dev_elcr), addr, len, val); } @@ -577,9 +577,9 @@ static const struct kvm_io_device_ops picdev_slave_ops = { .write = picdev_slave_write, }; -static const struct kvm_io_device_ops picdev_eclr_ops = { - .read = picdev_eclr_read, - .write = picdev_eclr_write, +static const struct kvm_io_device_ops picdev_elcr_ops = { + .read = picdev_elcr_read, + .write = picdev_elcr_write, }; int kvm_pic_init(struct kvm *kvm) @@ -602,7 +602,7 @@ int kvm_pic_init(struct kvm *kvm) */ kvm_iodevice_init(&s->dev_master, &picdev_master_ops); kvm_iodevice_init(&s->dev_slave, &picdev_slave_ops); - kvm_iodevice_init(&s->dev_eclr, &picdev_eclr_ops); + kvm_iodevice_init(&s->dev_elcr, &picdev_elcr_ops); mutex_lock(&kvm->slots_lock); ret = kvm_io_bus_register_dev(kvm, KVM_PIO_BUS, 0x20, 2, &s->dev_master); @@ -613,7 +613,7 @@ int kvm_pic_init(struct kvm *kvm) if (ret < 0) goto fail_unreg_2; - ret = kvm_io_bus_register_dev(kvm, KVM_PIO_BUS, 0x4d0, 2, &s->dev_eclr); + ret = kvm_io_bus_register_dev(kvm, KVM_PIO_BUS, 0x4d0, 2, &s->dev_elcr); if (ret < 0) goto fail_unreg_1; @@ -647,7 +647,7 @@ void kvm_pic_destroy(struct kvm *kvm) mutex_lock(&kvm->slots_lock); kvm_io_bus_unregister_dev(vpic->kvm, KVM_PIO_BUS, &vpic->dev_master); kvm_io_bus_unregister_dev(vpic->kvm, KVM_PIO_BUS, &vpic->dev_slave); - kvm_io_bus_unregister_dev(vpic->kvm, KVM_PIO_BUS, &vpic->dev_eclr); + kvm_io_bus_unregister_dev(vpic->kvm, KVM_PIO_BUS, &vpic->dev_elcr); mutex_unlock(&kvm->slots_lock); kvm->arch.vpic = NULL; diff --git a/arch/x86/kvm/ioapic.c b/arch/x86/kvm/ioapic.c index 698969e18fe3..ff005fe738a4 100644 --- a/arch/x86/kvm/ioapic.c +++ b/arch/x86/kvm/ioapic.c @@ -96,7 +96,7 @@ static unsigned long ioapic_read_indirect(struct kvm_ioapic *ioapic, static void rtc_irq_eoi_tracking_reset(struct kvm_ioapic *ioapic) { ioapic->rtc_status.pending_eoi = 0; - bitmap_zero(ioapic->rtc_status.dest_map.map, KVM_MAX_VCPU_ID); + bitmap_zero(ioapic->rtc_status.dest_map.map, KVM_MAX_VCPU_ID + 1); } static void kvm_rtc_eoi_tracking_restore_all(struct kvm_ioapic *ioapic); diff --git a/arch/x86/kvm/ioapic.h b/arch/x86/kvm/ioapic.h index 660401700075..bbd4a5d18b5d 100644 --- a/arch/x86/kvm/ioapic.h +++ b/arch/x86/kvm/ioapic.h @@ -35,21 +35,17 @@ struct kvm_vcpu; #define IOAPIC_INIT 0x5 #define IOAPIC_EXTINT 0x7 -#ifdef CONFIG_X86 #define RTC_GSI 8 -#else -#define RTC_GSI -1U -#endif struct dest_map { /* vcpu bitmap where IRQ has been sent */ - DECLARE_BITMAP(map, KVM_MAX_VCPU_ID); + DECLARE_BITMAP(map, KVM_MAX_VCPU_ID + 1); /* * Vector sent to a given vcpu, only valid when * the vcpu's bit in map is set */ - u8 vectors[KVM_MAX_VCPU_ID]; + u8 vectors[KVM_MAX_VCPU_ID + 1]; }; diff --git a/arch/x86/kvm/irq.h b/arch/x86/kvm/irq.h index 9b64abf9b3f1..650642b18d15 100644 --- a/arch/x86/kvm/irq.h +++ b/arch/x86/kvm/irq.h @@ -55,7 +55,7 @@ struct kvm_pic { int output; /* intr from master PIC */ struct kvm_io_device dev_master; struct kvm_io_device dev_slave; - struct kvm_io_device dev_eclr; + struct kvm_io_device dev_elcr; void (*ack_notifier)(void *opaque, int irq); unsigned long irq_states[PIC_NUM_PINS]; }; diff --git a/arch/x86/kvm/lapic.c b/arch/x86/kvm/lapic.c index ba5a27879f1d..76fb00921203 100644 --- a/arch/x86/kvm/lapic.c +++ b/arch/x86/kvm/lapic.c @@ -192,6 +192,9 @@ void kvm_recalculate_apic_map(struct kvm *kvm) if (atomic_read_acquire(&kvm->arch.apic_map_dirty) == CLEAN) return; + WARN_ONCE(!irqchip_in_kernel(kvm), + "Dirty APIC map without an in-kernel local APIC"); + mutex_lock(&kvm->arch.apic_map_lock); /* * Read kvm->arch.apic_map_dirty before kvm->arch.apic_map @@ -2265,9 +2268,6 @@ void kvm_lapic_set_base(struct kvm_vcpu *vcpu, u64 value) u64 old_value = vcpu->arch.apic_base; struct kvm_lapic *apic = vcpu->arch.apic; - if (!apic) - value |= MSR_IA32_APICBASE_BSP; - vcpu->arch.apic_base = value; if ((old_value ^ value) & MSR_IA32_APICBASE_ENABLE) @@ -2323,6 +2323,13 @@ void kvm_lapic_reset(struct kvm_vcpu *vcpu, bool init_event) struct kvm_lapic *apic = vcpu->arch.apic; int i; + if (!init_event) { + vcpu->arch.apic_base = APIC_DEFAULT_PHYS_BASE | + MSR_IA32_APICBASE_ENABLE; + if (kvm_vcpu_is_reset_bsp(vcpu)) + vcpu->arch.apic_base |= MSR_IA32_APICBASE_BSP; + } + if (!apic) return; @@ -2330,8 +2337,8 @@ void kvm_lapic_reset(struct kvm_vcpu *vcpu, bool init_event) hrtimer_cancel(&apic->lapic_timer.timer); if (!init_event) { - kvm_lapic_set_base(vcpu, APIC_DEFAULT_PHYS_BASE | - MSR_IA32_APICBASE_ENABLE); + apic->base_address = APIC_DEFAULT_PHYS_BASE; + kvm_apic_set_xapic_id(apic, vcpu->vcpu_id); } kvm_apic_set_version(apic->vcpu); @@ -2364,9 +2371,7 @@ void kvm_lapic_reset(struct kvm_vcpu *vcpu, bool init_event) apic->highest_isr_cache = -1; update_divide_count(apic); atomic_set(&apic->lapic_timer.pending, 0); - if (kvm_vcpu_is_bsp(vcpu)) - kvm_lapic_set_base(vcpu, - vcpu->arch.apic_base | MSR_IA32_APICBASE_BSP); + vcpu->arch.pv_eoi.msr_val = 0; apic_update_ppr(apic); if (vcpu->arch.apicv_active) { @@ -2476,11 +2481,6 @@ int kvm_create_lapic(struct kvm_vcpu *vcpu, int timer_advance_ns) lapic_timer_advance_dynamic = false; } - /* - * APIC is created enabled. This will prevent kvm_lapic_set_base from - * thinking that APIC state has changed. - */ - vcpu->arch.apic_base = MSR_IA32_APICBASE_ENABLE; static_branch_inc(&apic_sw_disabled.key); /* sw disabled at reset */ kvm_iodevice_init(&apic->dev, &apic_mmio_ops); diff --git a/arch/x86/kvm/mmu.h b/arch/x86/kvm/mmu.h index 83e6c6965f1e..e9688a9f7b57 100644 --- a/arch/x86/kvm/mmu.h +++ b/arch/x86/kvm/mmu.h @@ -240,4 +240,29 @@ static inline bool kvm_memslots_have_rmaps(struct kvm *kvm) return smp_load_acquire(&kvm->arch.memslots_have_rmaps); } +static inline gfn_t gfn_to_index(gfn_t gfn, gfn_t base_gfn, int level) +{ + /* KVM_HPAGE_GFN_SHIFT(PG_LEVEL_4K) must be 0. */ + return (gfn >> KVM_HPAGE_GFN_SHIFT(level)) - + (base_gfn >> KVM_HPAGE_GFN_SHIFT(level)); +} + +static inline unsigned long +__kvm_mmu_slot_lpages(struct kvm_memory_slot *slot, unsigned long npages, + int level) +{ + return gfn_to_index(slot->base_gfn + npages - 1, + slot->base_gfn, level) + 1; +} + +static inline unsigned long +kvm_mmu_slot_lpages(struct kvm_memory_slot *slot, int level) +{ + return __kvm_mmu_slot_lpages(slot, slot->npages, level); +} + +static inline void kvm_update_page_stats(struct kvm *kvm, int level, int count) +{ + atomic64_add(count, &kvm->stat.pages[level - 1]); +} #endif diff --git a/arch/x86/kvm/mmu/mmu.c b/arch/x86/kvm/mmu/mmu.c index 845d114ae075..2d7e61122af8 100644 --- a/arch/x86/kvm/mmu/mmu.c +++ b/arch/x86/kvm/mmu/mmu.c @@ -53,6 +53,8 @@ #include <asm/kvm_page_track.h> #include "trace.h" +#include "paging.h" + extern bool itlb_multihit_kvm_mitigation; int __read_mostly nx_huge_pages = -1; @@ -95,6 +97,7 @@ module_param_named(flush_on_reuse, force_flush_and_sync_on_reuse, bool, 0644); bool tdp_enabled = false; static int max_huge_page_level __read_mostly; +static int tdp_root_level __read_mostly; static int max_tdp_level __read_mostly; enum { @@ -135,12 +138,22 @@ module_param(dbg, bool, 0644); #include <trace/events/kvm.h> -/* make pte_list_desc fit well in cache line */ -#define PTE_LIST_EXT 3 +/* make pte_list_desc fit well in cache lines */ +#define PTE_LIST_EXT 14 +/* + * Slight optimization of cacheline layout, by putting `more' and `spte_count' + * at the start; then accessing it will only use one single cacheline for + * either full (entries==PTE_LIST_EXT) case or entries<=6. + */ struct pte_list_desc { - u64 *sptes[PTE_LIST_EXT]; struct pte_list_desc *more; + /* + * Stores number of entries stored in the pte_list_desc. No need to be + * u64 but just for easier alignment. When PTE_LIST_EXT, means full. + */ + u64 spte_count; + u64 *sptes[PTE_LIST_EXT]; }; struct kvm_shadow_walk_iterator { @@ -191,7 +204,7 @@ struct kvm_mmu_role_regs { * the single source of truth for the MMU's state. */ #define BUILD_MMU_ROLE_REGS_ACCESSOR(reg, name, flag) \ -static inline bool ____is_##reg##_##name(struct kvm_mmu_role_regs *regs)\ +static inline bool __maybe_unused ____is_##reg##_##name(struct kvm_mmu_role_regs *regs)\ { \ return !!(regs->reg & flag); \ } @@ -213,7 +226,7 @@ BUILD_MMU_ROLE_REGS_ACCESSOR(efer, lma, EFER_LMA); * and the vCPU may be incorrect/irrelevant. */ #define BUILD_MMU_ROLE_ACCESSOR(base_or_ext, reg, name) \ -static inline bool is_##reg##_##name(struct kvm_mmu *mmu) \ +static inline bool __maybe_unused is_##reg##_##name(struct kvm_mmu *mmu) \ { \ return !!(mmu->mmu_role. base_or_ext . reg##_##name); \ } @@ -321,12 +334,6 @@ static bool check_mmio_spte(struct kvm_vcpu *vcpu, u64 spte) static gpa_t translate_gpa(struct kvm_vcpu *vcpu, gpa_t gpa, u32 access, struct x86_exception *exception) { - /* Check if guest physical address doesn't exceed guest maximum */ - if (kvm_vcpu_is_illegal_gpa(vcpu, gpa)) { - exception->error_code |= PFERR_RSVD_MASK; - return UNMAPPED_GVA; - } - return gpa; } @@ -590,12 +597,13 @@ static bool mmu_spte_update(u64 *sptep, u64 new_spte) * Rules for using mmu_spte_clear_track_bits: * It sets the sptep from present to nonpresent, and track the * state bits, it is used to clear the last level sptep. - * Returns non-zero if the PTE was previously valid. + * Returns the old PTE. */ -static int mmu_spte_clear_track_bits(u64 *sptep) +static int mmu_spte_clear_track_bits(struct kvm *kvm, u64 *sptep) { kvm_pfn_t pfn; u64 old_spte = *sptep; + int level = sptep_to_sp(sptep)->role.level; if (!spte_has_volatile_bits(old_spte)) __update_clear_spte_fast(sptep, 0ull); @@ -603,7 +611,9 @@ static int mmu_spte_clear_track_bits(u64 *sptep) old_spte = __update_clear_spte_slow(sptep, 0ull); if (!is_shadow_present_pte(old_spte)) - return 0; + return old_spte; + + kvm_update_page_stats(kvm, level, -1); pfn = spte_to_pfn(old_spte); @@ -620,7 +630,7 @@ static int mmu_spte_clear_track_bits(u64 *sptep) if (is_dirty_spte(old_spte)) kvm_set_pfn_dirty(pfn); - return 1; + return old_spte; } /* @@ -684,28 +694,36 @@ static bool mmu_spte_age(u64 *sptep) static void walk_shadow_page_lockless_begin(struct kvm_vcpu *vcpu) { - /* - * Prevent page table teardown by making any free-er wait during - * kvm_flush_remote_tlbs() IPI to all active vcpus. - */ - local_irq_disable(); + if (is_tdp_mmu(vcpu->arch.mmu)) { + kvm_tdp_mmu_walk_lockless_begin(); + } else { + /* + * Prevent page table teardown by making any free-er wait during + * kvm_flush_remote_tlbs() IPI to all active vcpus. + */ + local_irq_disable(); - /* - * Make sure a following spte read is not reordered ahead of the write - * to vcpu->mode. - */ - smp_store_mb(vcpu->mode, READING_SHADOW_PAGE_TABLES); + /* + * Make sure a following spte read is not reordered ahead of the write + * to vcpu->mode. + */ + smp_store_mb(vcpu->mode, READING_SHADOW_PAGE_TABLES); + } } static void walk_shadow_page_lockless_end(struct kvm_vcpu *vcpu) { - /* - * Make sure the write to vcpu->mode is not reordered in front of - * reads to sptes. If it does, kvm_mmu_commit_zap_page() can see us - * OUTSIDE_GUEST_MODE and proceed to free the shadow page table. - */ - smp_store_release(&vcpu->mode, OUTSIDE_GUEST_MODE); - local_irq_enable(); + if (is_tdp_mmu(vcpu->arch.mmu)) { + kvm_tdp_mmu_walk_lockless_end(); + } else { + /* + * Make sure the write to vcpu->mode is not reordered in front of + * reads to sptes. If it does, kvm_mmu_commit_zap_page() can see us + * OUTSIDE_GUEST_MODE and proceed to free the shadow page table. + */ + smp_store_release(&vcpu->mode, OUTSIDE_GUEST_MODE); + local_irq_enable(); + } } static int mmu_topup_memory_caches(struct kvm_vcpu *vcpu, bool maybe_indirect) @@ -784,7 +802,7 @@ static struct kvm_lpage_info *lpage_info_slot(gfn_t gfn, return &slot->arch.lpage_info[level - 2][idx]; } -static void update_gfn_disallow_lpage_count(struct kvm_memory_slot *slot, +static void update_gfn_disallow_lpage_count(const struct kvm_memory_slot *slot, gfn_t gfn, int count) { struct kvm_lpage_info *linfo; @@ -797,12 +815,12 @@ static void update_gfn_disallow_lpage_count(struct kvm_memory_slot *slot, } } -void kvm_mmu_gfn_disallow_lpage(struct kvm_memory_slot *slot, gfn_t gfn) +void kvm_mmu_gfn_disallow_lpage(const struct kvm_memory_slot *slot, gfn_t gfn) { update_gfn_disallow_lpage_count(slot, gfn, 1); } -void kvm_mmu_gfn_allow_lpage(struct kvm_memory_slot *slot, gfn_t gfn) +void kvm_mmu_gfn_allow_lpage(const struct kvm_memory_slot *slot, gfn_t gfn) { update_gfn_disallow_lpage_count(slot, gfn, -1); } @@ -891,7 +909,7 @@ static int pte_list_add(struct kvm_vcpu *vcpu, u64 *spte, struct kvm_rmap_head *rmap_head) { struct pte_list_desc *desc; - int i, count = 0; + int count = 0; if (!rmap_head->val) { rmap_printk("%p %llx 0->1\n", spte, *spte); @@ -901,24 +919,24 @@ static int pte_list_add(struct kvm_vcpu *vcpu, u64 *spte, desc = mmu_alloc_pte_list_desc(vcpu); desc->sptes[0] = (u64 *)rmap_head->val; desc->sptes[1] = spte; + desc->spte_count = 2; rmap_head->val = (unsigned long)desc | 1; ++count; } else { 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]) { + while (desc->spte_count == PTE_LIST_EXT) { count += PTE_LIST_EXT; - if (!desc->more) { desc->more = mmu_alloc_pte_list_desc(vcpu); desc = desc->more; + desc->spte_count = 0; break; } desc = desc->more; } - for (i = 0; desc->sptes[i]; ++i) - ++count; - desc->sptes[i] = spte; + count += desc->spte_count; + desc->sptes[desc->spte_count++] = spte; } return count; } @@ -928,13 +946,12 @@ pte_list_desc_remove_entry(struct kvm_rmap_head *rmap_head, struct pte_list_desc *desc, int i, struct pte_list_desc *prev_desc) { - int j; + int j = desc->spte_count - 1; - for (j = PTE_LIST_EXT - 1; !desc->sptes[j] && j > i; --j) - ; desc->sptes[i] = desc->sptes[j]; desc->sptes[j] = NULL; - if (j != 0) + desc->spte_count--; + if (desc->spte_count) return; if (!prev_desc && !desc->more) rmap_head->val = 0; @@ -967,7 +984,7 @@ static void __pte_list_remove(u64 *spte, struct kvm_rmap_head *rmap_head) desc = (struct pte_list_desc *)(rmap_head->val & ~1ul); prev_desc = NULL; while (desc) { - for (i = 0; i < PTE_LIST_EXT && desc->sptes[i]; ++i) { + for (i = 0; i < desc->spte_count; ++i) { if (desc->sptes[i] == spte) { pte_list_desc_remove_entry(rmap_head, desc, i, prev_desc); @@ -982,30 +999,68 @@ static void __pte_list_remove(u64 *spte, struct kvm_rmap_head *rmap_head) } } -static void pte_list_remove(struct kvm_rmap_head *rmap_head, u64 *sptep) +static void pte_list_remove(struct kvm *kvm, struct kvm_rmap_head *rmap_head, + u64 *sptep) { - mmu_spte_clear_track_bits(sptep); + mmu_spte_clear_track_bits(kvm, sptep); __pte_list_remove(sptep, rmap_head); } -static struct kvm_rmap_head *__gfn_to_rmap(gfn_t gfn, int level, - struct kvm_memory_slot *slot) +/* Return true if rmap existed, false otherwise */ +static bool pte_list_destroy(struct kvm *kvm, struct kvm_rmap_head *rmap_head) { - unsigned long idx; + struct pte_list_desc *desc, *next; + int i; - idx = gfn_to_index(gfn, slot->base_gfn, level); - return &slot->arch.rmap[level - PG_LEVEL_4K][idx]; + if (!rmap_head->val) + return false; + + if (!(rmap_head->val & 1)) { + mmu_spte_clear_track_bits(kvm, (u64 *)rmap_head->val); + goto out; + } + + desc = (struct pte_list_desc *)(rmap_head->val & ~1ul); + + for (; desc; desc = next) { + for (i = 0; i < desc->spte_count; i++) + mmu_spte_clear_track_bits(kvm, desc->sptes[i]); + next = desc->more; + mmu_free_pte_list_desc(desc); + } +out: + /* rmap_head is meaningless now, remember to reset it */ + rmap_head->val = 0; + return true; } -static struct kvm_rmap_head *gfn_to_rmap(struct kvm *kvm, gfn_t gfn, - struct kvm_mmu_page *sp) +unsigned int pte_list_count(struct kvm_rmap_head *rmap_head) { - struct kvm_memslots *slots; - struct kvm_memory_slot *slot; + struct pte_list_desc *desc; + unsigned int count = 0; - slots = kvm_memslots_for_spte_role(kvm, sp->role); - slot = __gfn_to_memslot(slots, gfn); - return __gfn_to_rmap(gfn, sp->role.level, slot); + if (!rmap_head->val) + return 0; + else if (!(rmap_head->val & 1)) + return 1; + + desc = (struct pte_list_desc *)(rmap_head->val & ~1ul); + + while (desc) { + count += desc->spte_count; + desc = desc->more; + } + + return count; +} + +static struct kvm_rmap_head *gfn_to_rmap(gfn_t gfn, int level, + const struct kvm_memory_slot *slot) +{ + unsigned long idx; + + idx = gfn_to_index(gfn, slot->base_gfn, level); + return &slot->arch.rmap[level - PG_LEVEL_4K][idx]; } static bool rmap_can_add(struct kvm_vcpu *vcpu) @@ -1018,24 +1073,39 @@ static bool rmap_can_add(struct kvm_vcpu *vcpu) static int rmap_add(struct kvm_vcpu *vcpu, u64 *spte, gfn_t gfn) { + struct kvm_memory_slot *slot; struct kvm_mmu_page *sp; struct kvm_rmap_head *rmap_head; sp = sptep_to_sp(spte); kvm_mmu_page_set_gfn(sp, spte - sp->spt, gfn); - rmap_head = gfn_to_rmap(vcpu->kvm, gfn, sp); + slot = kvm_vcpu_gfn_to_memslot(vcpu, gfn); + rmap_head = gfn_to_rmap(gfn, sp->role.level, slot); return pte_list_add(vcpu, spte, rmap_head); } + static void rmap_remove(struct kvm *kvm, u64 *spte) { + struct kvm_memslots *slots; + struct kvm_memory_slot *slot; struct kvm_mmu_page *sp; gfn_t gfn; struct kvm_rmap_head *rmap_head; sp = sptep_to_sp(spte); gfn = kvm_mmu_page_get_gfn(sp, spte - sp->spt); - rmap_head = gfn_to_rmap(kvm, gfn, sp); + + /* + * Unlike rmap_add and rmap_recycle, rmap_remove does not run in the + * context of a vCPU so have to determine which memslots to use based + * on context information in sp->role. + */ + slots = kvm_memslots_for_spte_role(kvm, sp->role); + + slot = __gfn_to_memslot(slots, gfn); + rmap_head = gfn_to_rmap(gfn, sp->role.level, slot); + __pte_list_remove(spte, rmap_head); } @@ -1117,7 +1187,9 @@ out: static void drop_spte(struct kvm *kvm, u64 *sptep) { - if (mmu_spte_clear_track_bits(sptep)) + u64 old_spte = mmu_spte_clear_track_bits(kvm, sptep); + + if (is_shadow_present_pte(old_spte)) rmap_remove(kvm, sptep); } @@ -1127,7 +1199,6 @@ static bool __drop_large_spte(struct kvm *kvm, u64 *sptep) if (is_large_pte(*sptep)) { WARN_ON(sptep_to_sp(sptep)->role.level == PG_LEVEL_4K); drop_spte(kvm, sptep); - --kvm->stat.lpages; return true; } @@ -1216,7 +1287,7 @@ static bool spte_wrprot_for_clear_dirty(u64 *sptep) * Returns true iff any D or W bits were cleared. */ static bool __rmap_clear_dirty(struct kvm *kvm, struct kvm_rmap_head *rmap_head, - struct kvm_memory_slot *slot) + const struct kvm_memory_slot *slot) { u64 *sptep; struct rmap_iterator iter; @@ -1254,8 +1325,8 @@ static void kvm_mmu_write_protect_pt_masked(struct kvm *kvm, return; while (mask) { - rmap_head = __gfn_to_rmap(slot->base_gfn + gfn_offset + __ffs(mask), - PG_LEVEL_4K, slot); + rmap_head = gfn_to_rmap(slot->base_gfn + gfn_offset + __ffs(mask), + PG_LEVEL_4K, slot); __rmap_write_protect(kvm, rmap_head, false); /* clear the first set bit */ @@ -1287,8 +1358,8 @@ static void kvm_mmu_clear_dirty_pt_masked(struct kvm *kvm, return; while (mask) { - rmap_head = __gfn_to_rmap(slot->base_gfn + gfn_offset + __ffs(mask), - PG_LEVEL_4K, slot); + rmap_head = gfn_to_rmap(slot->base_gfn + gfn_offset + __ffs(mask), + PG_LEVEL_4K, slot); __rmap_clear_dirty(kvm, rmap_head, slot); /* clear the first set bit */ @@ -1354,7 +1425,7 @@ bool kvm_mmu_slot_gfn_write_protect(struct kvm *kvm, if (kvm_memslots_have_rmaps(kvm)) { for (i = min_level; i <= KVM_MAX_HUGEPAGE_LEVEL; ++i) { - rmap_head = __gfn_to_rmap(gfn, i, slot); + rmap_head = gfn_to_rmap(gfn, i, slot); write_protected |= __rmap_write_protect(kvm, rmap_head, true); } } @@ -1375,20 +1446,9 @@ static bool rmap_write_protect(struct kvm_vcpu *vcpu, u64 gfn) } static bool kvm_zap_rmapp(struct kvm *kvm, struct kvm_rmap_head *rmap_head, - struct kvm_memory_slot *slot) + const struct kvm_memory_slot *slot) { - u64 *sptep; - struct rmap_iterator iter; - bool flush = false; - - while ((sptep = rmap_get_first(rmap_head, &iter))) { - rmap_printk("spte %p %llx.\n", sptep, *sptep); - - pte_list_remove(rmap_head, sptep); - flush = true; - } - - return flush; + return pte_list_destroy(kvm, rmap_head); } static bool kvm_unmap_rmapp(struct kvm *kvm, struct kvm_rmap_head *rmap_head, @@ -1419,13 +1479,13 @@ restart: need_flush = 1; if (pte_write(pte)) { - pte_list_remove(rmap_head, sptep); + pte_list_remove(kvm, rmap_head, sptep); goto restart; } else { new_spte = kvm_mmu_changed_pte_notifier_make_spte( *sptep, new_pfn); - mmu_spte_clear_track_bits(sptep); + mmu_spte_clear_track_bits(kvm, sptep); mmu_spte_set(sptep, new_spte); } } @@ -1440,7 +1500,7 @@ restart: struct slot_rmap_walk_iterator { /* input fields. */ - struct kvm_memory_slot *slot; + const struct kvm_memory_slot *slot; gfn_t start_gfn; gfn_t end_gfn; int start_level; @@ -1460,14 +1520,13 @@ rmap_walk_init_level(struct slot_rmap_walk_iterator *iterator, int level) { iterator->level = level; iterator->gfn = iterator->start_gfn; - iterator->rmap = __gfn_to_rmap(iterator->gfn, level, iterator->slot); - iterator->end_rmap = __gfn_to_rmap(iterator->end_gfn, level, - iterator->slot); + iterator->rmap = gfn_to_rmap(iterator->gfn, level, iterator->slot); + iterator->end_rmap = gfn_to_rmap(iterator->end_gfn, level, iterator->slot); } static void slot_rmap_walk_init(struct slot_rmap_walk_iterator *iterator, - struct kvm_memory_slot *slot, int start_level, + const struct kvm_memory_slot *slot, int start_level, int end_level, gfn_t start_gfn, gfn_t end_gfn) { iterator->slot = slot; @@ -1582,12 +1641,13 @@ static bool kvm_test_age_rmapp(struct kvm *kvm, struct kvm_rmap_head *rmap_head, static void rmap_recycle(struct kvm_vcpu *vcpu, u64 *spte, gfn_t gfn) { + struct kvm_memory_slot *slot; struct kvm_rmap_head *rmap_head; struct kvm_mmu_page *sp; sp = sptep_to_sp(spte); - - rmap_head = gfn_to_rmap(vcpu->kvm, gfn, sp); + slot = kvm_vcpu_gfn_to_memslot(vcpu, gfn); + rmap_head = gfn_to_rmap(gfn, sp->role.level, slot); kvm_unmap_rmapp(vcpu->kvm, rmap_head, NULL, gfn, sp->role.level, __pte(0)); kvm_flush_remote_tlbs_with_address(vcpu->kvm, sp->gfn, @@ -1642,7 +1702,7 @@ static int is_empty_shadow_page(u64 *spt) * aggregate version in order to make the slab shrinker * faster */ -static inline void kvm_mod_used_mmu_pages(struct kvm *kvm, unsigned long nr) +static inline void kvm_mod_used_mmu_pages(struct kvm *kvm, long nr) { kvm->arch.n_used_mmu_pages += nr; percpu_counter_add(&kvm_total_used_mmu_pages, nr); @@ -2230,8 +2290,6 @@ static int mmu_page_zap_pte(struct kvm *kvm, struct kvm_mmu_page *sp, if (is_shadow_present_pte(pte)) { if (is_last_spte(pte, sp->role.level)) { drop_spte(kvm, spte); - if (is_large_pte(pte)) - --kvm->stat.lpages; } else { child = to_shadow_page(pte & PT64_BASE_ADDR_MASK); drop_parent_pte(child, spte); @@ -2533,6 +2591,7 @@ static void kvm_unsync_page(struct kvm_vcpu *vcpu, struct kvm_mmu_page *sp) int mmu_try_to_unsync_pages(struct kvm_vcpu *vcpu, gfn_t gfn, bool can_unsync) { struct kvm_mmu_page *sp; + bool locked = false; /* * Force write-protection if the page is being tracked. Note, the page @@ -2555,9 +2614,34 @@ int mmu_try_to_unsync_pages(struct kvm_vcpu *vcpu, gfn_t gfn, bool can_unsync) if (sp->unsync) continue; + /* + * TDP MMU page faults require an additional spinlock as they + * run with mmu_lock held for read, not write, and the unsync + * logic is not thread safe. Take the spinklock regardless of + * the MMU type to avoid extra conditionals/parameters, there's + * no meaningful penalty if mmu_lock is held for write. + */ + if (!locked) { + locked = true; + spin_lock(&vcpu->kvm->arch.mmu_unsync_pages_lock); + + /* + * Recheck after taking the spinlock, a different vCPU + * may have since marked the page unsync. A false + * positive on the unprotected check above is not + * possible as clearing sp->unsync _must_ hold mmu_lock + * for write, i.e. unsync cannot transition from 0->1 + * while this CPU holds mmu_lock for read (or write). + */ + if (READ_ONCE(sp->unsync)) + continue; + } + WARN_ON(sp->role.level != PG_LEVEL_4K); kvm_unsync_page(vcpu, sp); } + if (locked) + spin_unlock(&vcpu->kvm->arch.mmu_unsync_pages_lock); /* * We need to ensure that the marking of unsync pages is visible @@ -2688,15 +2772,12 @@ static int mmu_set_spte(struct kvm_vcpu *vcpu, u64 *sptep, pgprintk("%s: setting spte %llx\n", __func__, *sptep); trace_kvm_mmu_set_spte(level, gfn, sptep); - if (!was_rmapped && is_large_pte(*sptep)) - ++vcpu->kvm->stat.lpages; - if (is_shadow_present_pte(*sptep)) { - if (!was_rmapped) { - rmap_count = rmap_add(vcpu, sptep, gfn); - if (rmap_count > RMAP_RECYCLE_THRESHOLD) - rmap_recycle(vcpu, sptep, gfn); - } + if (!was_rmapped) { + kvm_update_page_stats(vcpu->kvm, level, 1); + rmap_count = rmap_add(vcpu, sptep, gfn); + if (rmap_count > RMAP_RECYCLE_THRESHOLD) + rmap_recycle(vcpu, sptep, gfn); } return ret; @@ -2824,6 +2905,7 @@ int kvm_mmu_max_mapping_level(struct kvm *kvm, kvm_pfn_t pfn, int max_level) { struct kvm_lpage_info *linfo; + int host_level; max_level = min(max_level, max_huge_page_level); for ( ; max_level > PG_LEVEL_4K; max_level--) { @@ -2835,7 +2917,8 @@ int kvm_mmu_max_mapping_level(struct kvm *kvm, if (max_level == PG_LEVEL_4K) return PG_LEVEL_4K; - return host_pfn_mapping_level(kvm, gfn, pfn, slot); + host_level = host_pfn_mapping_level(kvm, gfn, pfn, slot); + return min(host_level, max_level); } int kvm_mmu_hugepage_adjust(struct kvm_vcpu *vcpu, gfn_t gfn, @@ -2859,17 +2942,12 @@ int kvm_mmu_hugepage_adjust(struct kvm_vcpu *vcpu, gfn_t gfn, if (!slot) return PG_LEVEL_4K; - level = kvm_mmu_max_mapping_level(vcpu->kvm, slot, gfn, pfn, max_level); - if (level == PG_LEVEL_4K) - return level; - - *req_level = level = min(level, max_level); - /* * Enforce the iTLB multihit workaround after capturing the requested * level, which will be used to do precise, accurate accounting. */ - if (huge_page_disallowed) + *req_level = level = kvm_mmu_max_mapping_level(vcpu->kvm, slot, gfn, pfn, max_level); + if (level == PG_LEVEL_4K || huge_page_disallowed) return PG_LEVEL_4K; /* @@ -2937,15 +3015,16 @@ static int __direct_map(struct kvm_vcpu *vcpu, gpa_t gpa, u32 error_code, break; drop_large_spte(vcpu, it.sptep); - if (!is_shadow_present_pte(*it.sptep)) { - sp = kvm_mmu_get_page(vcpu, base_gfn, it.addr, - it.level - 1, true, ACC_ALL); - - link_shadow_page(vcpu, it.sptep, sp); - if (is_tdp && huge_page_disallowed && - req_level >= it.level) - account_huge_nx_page(vcpu->kvm, sp); - } + if (is_shadow_present_pte(*it.sptep)) + continue; + + sp = kvm_mmu_get_page(vcpu, base_gfn, it.addr, + it.level - 1, true, ACC_ALL); + + link_shadow_page(vcpu, it.sptep, sp); + if (is_tdp && huge_page_disallowed && + req_level >= it.level) + account_huge_nx_page(vcpu->kvm, sp); } ret = mmu_set_spte(vcpu, it.sptep, ACC_ALL, @@ -3094,15 +3173,40 @@ static bool is_access_allowed(u32 fault_err_code, u64 spte) } /* - * Returns one of RET_PF_INVALID, RET_PF_FIXED or RET_PF_SPURIOUS. + * Returns the last level spte pointer of the shadow page walk for the given + * gpa, and sets *spte to the spte value. This spte may be non-preset. If no + * walk could be performed, returns NULL and *spte does not contain valid data. + * + * Contract: + * - Must be called between walk_shadow_page_lockless_{begin,end}. + * - The returned sptep must not be used after walk_shadow_page_lockless_end. */ -static int fast_page_fault(struct kvm_vcpu *vcpu, gpa_t cr2_or_gpa, - u32 error_code) +static u64 *fast_pf_get_last_sptep(struct kvm_vcpu *vcpu, gpa_t gpa, u64 *spte) { struct kvm_shadow_walk_iterator iterator; + u64 old_spte; + u64 *sptep = NULL; + + for_each_shadow_entry_lockless(vcpu, gpa, iterator, old_spte) { + sptep = iterator.sptep; + *spte = old_spte; + + if (!is_shadow_present_pte(old_spte)) + break; + } + + return sptep; +} + +/* + * Returns one of RET_PF_INVALID, RET_PF_FIXED or RET_PF_SPURIOUS. + */ +static int fast_page_fault(struct kvm_vcpu *vcpu, gpa_t gpa, u32 error_code) +{ struct kvm_mmu_page *sp; int ret = RET_PF_INVALID; u64 spte = 0ull; + u64 *sptep = NULL; uint retry_count = 0; if (!page_fault_can_be_fast(error_code)) @@ -3113,14 +3217,15 @@ static int fast_page_fault(struct kvm_vcpu *vcpu, gpa_t cr2_or_gpa, do { u64 new_spte; - for_each_shadow_entry_lockless(vcpu, cr2_or_gpa, iterator, spte) - if (!is_shadow_present_pte(spte)) - break; + if (is_tdp_mmu(vcpu->arch.mmu)) + sptep = kvm_tdp_mmu_fast_pf_get_last_sptep(vcpu, gpa, &spte); + else + sptep = fast_pf_get_last_sptep(vcpu, gpa, &spte); if (!is_shadow_present_pte(spte)) break; - sp = sptep_to_sp(iterator.sptep); + sp = sptep_to_sp(sptep); if (!is_last_spte(spte, sp->role.level)) break; @@ -3178,8 +3283,7 @@ static int fast_page_fault(struct kvm_vcpu *vcpu, gpa_t cr2_or_gpa, * since the gfn is not stable for indirect shadow page. See * Documentation/virt/kvm/locking.rst to get more detail. */ - if (fast_pf_fix_direct_spte(vcpu, sp, iterator.sptep, spte, - new_spte)) { + if (fast_pf_fix_direct_spte(vcpu, sp, sptep, spte, new_spte)) { ret = RET_PF_FIXED; break; } @@ -3192,8 +3296,7 @@ static int fast_page_fault(struct kvm_vcpu *vcpu, gpa_t cr2_or_gpa, } while (true); - trace_fast_page_fault(vcpu, cr2_or_gpa, error_code, iterator.sptep, - spte, ret); + trace_fast_page_fault(vcpu, gpa, error_code, sptep, spte, ret); walk_shadow_page_lockless_end(vcpu); return ret; @@ -3427,15 +3530,22 @@ static int mmu_alloc_shadow_roots(struct kvm_vcpu *vcpu) * the shadow page table may be a PAE or a long mode page table. */ pm_mask = PT_PRESENT_MASK | shadow_me_mask; - if (mmu->shadow_root_level == PT64_ROOT_4LEVEL) { + if (mmu->shadow_root_level >= PT64_ROOT_4LEVEL) { pm_mask |= PT_ACCESSED_MASK | PT_WRITABLE_MASK | PT_USER_MASK; if (WARN_ON_ONCE(!mmu->pml4_root)) { r = -EIO; goto out_unlock; } - mmu->pml4_root[0] = __pa(mmu->pae_root) | pm_mask; + + if (mmu->shadow_root_level == PT64_ROOT_5LEVEL) { + if (WARN_ON_ONCE(!mmu->pml5_root)) { + r = -EIO; + goto out_unlock; + } + mmu->pml5_root[0] = __pa(mmu->pml4_root) | pm_mask; + } } for (i = 0; i < 4; ++i) { @@ -3454,7 +3564,9 @@ static int mmu_alloc_shadow_roots(struct kvm_vcpu *vcpu) mmu->pae_root[i] = root | pm_mask; } - if (mmu->shadow_root_level == PT64_ROOT_4LEVEL) + if (mmu->shadow_root_level == PT64_ROOT_5LEVEL) + mmu->root_hpa = __pa(mmu->pml5_root); + else if (mmu->shadow_root_level == PT64_ROOT_4LEVEL) mmu->root_hpa = __pa(mmu->pml4_root); else mmu->root_hpa = __pa(mmu->pae_root); @@ -3470,7 +3582,10 @@ out_unlock: static int mmu_alloc_special_roots(struct kvm_vcpu *vcpu) { struct kvm_mmu *mmu = vcpu->arch.mmu; - u64 *pml4_root, *pae_root; + bool need_pml5 = mmu->shadow_root_level > PT64_ROOT_4LEVEL; + u64 *pml5_root = NULL; + u64 *pml4_root = NULL; + u64 *pae_root; /* * When shadowing 32-bit or PAE NPT with 64-bit NPT, the PML4 and PDP @@ -3483,20 +3598,21 @@ static int mmu_alloc_special_roots(struct kvm_vcpu *vcpu) return 0; /* - * This mess only works with 4-level paging and needs to be updated to - * work with 5-level paging. + * NPT, the only paging mode that uses this horror, uses a fixed number + * of levels for the shadow page tables, e.g. all MMUs are 4-level or + * all MMus are 5-level. Thus, this can safely require that pml5_root + * is allocated if the other roots are valid and pml5 is needed, as any + * prior MMU would also have required pml5. */ - if (WARN_ON_ONCE(mmu->shadow_root_level != PT64_ROOT_4LEVEL)) - return -EIO; - - if (mmu->pae_root && mmu->pml4_root) + if (mmu->pae_root && mmu->pml4_root && (!need_pml5 || mmu->pml5_root)) return 0; /* * The special roots should always be allocated in concert. Yell and * bail if KVM ends up in a state where only one of the roots is valid. */ - if (WARN_ON_ONCE(!tdp_enabled || mmu->pae_root || mmu->pml4_root)) + if (WARN_ON_ONCE(!tdp_enabled || mmu->pae_root || mmu->pml4_root || + (need_pml5 && mmu->pml5_root))) return -EIO; /* @@ -3507,16 +3623,31 @@ static int mmu_alloc_special_roots(struct kvm_vcpu *vcpu) if (!pae_root) return -ENOMEM; +#ifdef CONFIG_X86_64 pml4_root = (void *)get_zeroed_page(GFP_KERNEL_ACCOUNT); - if (!pml4_root) { - free_page((unsigned long)pae_root); - return -ENOMEM; + if (!pml4_root) + goto err_pml4; + + if (need_pml5) { + pml5_root = (void *)get_zeroed_page(GFP_KERNEL_ACCOUNT); + if (!pml5_root) + goto err_pml5; } +#endif mmu->pae_root = pae_root; mmu->pml4_root = pml4_root; + mmu->pml5_root = pml5_root; return 0; + +#ifdef CONFIG_X86_64 +err_pml5: + free_page((unsigned long)pml4_root); +err_pml4: + free_page((unsigned long)pae_root); + return -ENOMEM; +#endif } void kvm_mmu_sync_roots(struct kvm_vcpu *vcpu) @@ -3612,6 +3743,8 @@ static bool mmio_info_in_cache(struct kvm_vcpu *vcpu, u64 addr, bool direct) /* * Return the level of the lowest level SPTE added to sptes. * That SPTE may be non-present. + * + * Must be called between walk_shadow_page_lockless_{begin,end}. */ static int get_walk(struct kvm_vcpu *vcpu, u64 addr, u64 *sptes, int *root_level) { @@ -3619,8 +3752,6 @@ static int get_walk(struct kvm_vcpu *vcpu, u64 addr, u64 *sptes, int *root_level int leaf = -1; u64 spte; - walk_shadow_page_lockless_begin(vcpu); - for (shadow_walk_init(&iterator, vcpu, addr), *root_level = iterator.level; shadow_walk_okay(&iterator); @@ -3634,8 +3765,6 @@ static int get_walk(struct kvm_vcpu *vcpu, u64 addr, u64 *sptes, int *root_level break; } - walk_shadow_page_lockless_end(vcpu); - return leaf; } @@ -3647,11 +3776,15 @@ static bool get_mmio_spte(struct kvm_vcpu *vcpu, u64 addr, u64 *sptep) int root, leaf, level; bool reserved = false; + walk_shadow_page_lockless_begin(vcpu); + if (is_tdp_mmu(vcpu->arch.mmu)) leaf = kvm_tdp_mmu_get_walk(vcpu, addr, sptes, &root); else leaf = get_walk(vcpu, addr, sptes, &root); + walk_shadow_page_lockless_end(vcpu); + if (unlikely(leaf < 0)) { *sptep = 0ull; return reserved; @@ -3767,9 +3900,9 @@ static bool kvm_arch_setup_async_pf(struct kvm_vcpu *vcpu, gpa_t cr2_or_gpa, kvm_vcpu_gfn_to_hva(vcpu, gfn), &arch); } -static bool try_async_pf(struct kvm_vcpu *vcpu, bool prefault, gfn_t gfn, +static bool kvm_faultin_pfn(struct kvm_vcpu *vcpu, bool prefault, gfn_t gfn, gpa_t cr2_or_gpa, kvm_pfn_t *pfn, hva_t *hva, - bool write, bool *writable) + bool write, bool *writable, int *r) { struct kvm_memory_slot *slot = kvm_vcpu_gfn_to_memslot(vcpu, gfn); bool async; @@ -3780,13 +3913,26 @@ static bool try_async_pf(struct kvm_vcpu *vcpu, bool prefault, gfn_t gfn, * be zapped before KVM inserts a new MMIO SPTE for the gfn. */ if (slot && (slot->flags & KVM_MEMSLOT_INVALID)) - return true; - - /* Don't expose private memslots to L2. */ - if (is_guest_mode(vcpu) && !kvm_is_visible_memslot(slot)) { - *pfn = KVM_PFN_NOSLOT; - *writable = false; - return false; + goto out_retry; + + if (!kvm_is_visible_memslot(slot)) { + /* Don't expose private memslots to L2. */ + if (is_guest_mode(vcpu)) { + *pfn = KVM_PFN_NOSLOT; + *writable = false; + return false; + } + /* + * If the APIC access page exists but is disabled, go directly + * to emulation without caching the MMIO access or creating a + * MMIO SPTE. That way the cache doesn't need to be purged + * when the AVIC is re-enabled. + */ + if (slot && slot->id == APIC_ACCESS_PAGE_PRIVATE_MEMSLOT && + !kvm_apicv_activated(vcpu->kvm)) { + *r = RET_PF_EMULATE; + return true; + } } async = false; @@ -3800,14 +3946,17 @@ static bool try_async_pf(struct kvm_vcpu *vcpu, bool prefault, gfn_t gfn, if (kvm_find_async_pf_gfn(vcpu, gfn)) { trace_kvm_async_pf_doublefault(cr2_or_gpa, gfn); kvm_make_request(KVM_REQ_APF_HALT, vcpu); - return true; + goto out_retry; } else if (kvm_arch_setup_async_pf(vcpu, cr2_or_gpa, gfn)) - return true; + goto out_retry; } *pfn = __gfn_to_pfn_memslot(slot, gfn, false, NULL, write, writable, hva); - return false; + +out_retry: + *r = RET_PF_RETRY; + return true; } static int direct_page_fault(struct kvm_vcpu *vcpu, gpa_t gpa, u32 error_code, @@ -3826,11 +3975,9 @@ static int direct_page_fault(struct kvm_vcpu *vcpu, gpa_t gpa, u32 error_code, if (page_fault_handle_page_track(vcpu, error_code, gfn)) return RET_PF_EMULATE; - if (!is_tdp_mmu_fault) { - r = fast_page_fault(vcpu, gpa, error_code); - if (r != RET_PF_INVALID) - return r; - } + r = fast_page_fault(vcpu, gpa, error_code); + if (r != RET_PF_INVALID) + return r; r = mmu_topup_memory_caches(vcpu, false); if (r) @@ -3839,9 +3986,9 @@ 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, &hva, - write, &map_writable)) - return RET_PF_RETRY; + if (kvm_faultin_pfn(vcpu, prefault, gfn, gpa, &pfn, &hva, + write, &map_writable, &r)) + return r; if (handle_abnormal_pfn(vcpu, is_tdp ? 0 : gpa, gfn, pfn, ACC_ALL, &r)) return r; @@ -4560,6 +4707,10 @@ static union kvm_mmu_role kvm_calc_mmu_role_common(struct kvm_vcpu *vcpu, static inline int kvm_mmu_get_tdp_level(struct kvm_vcpu *vcpu) { + /* tdp_root_level is architecture forced level, use it if nonzero */ + if (tdp_root_level) + return tdp_root_level; + /* Use 5-level TDP if and only if it's useful/necessary. */ if (max_tdp_level == 5 && cpuid_maxphyaddr(vcpu) <= 48) return 4; @@ -5132,7 +5283,7 @@ int kvm_mmu_page_fault(struct kvm_vcpu *vcpu, gpa_t cr2_or_gpa, u64 error_code, if (r == RET_PF_INVALID) { r = kvm_mmu_do_page_fault(vcpu, cr2_or_gpa, lower_32_bits(error_code), false); - if (WARN_ON_ONCE(r == RET_PF_INVALID)) + if (KVM_BUG_ON(r == RET_PF_INVALID, vcpu->kvm)) return -EIO; } @@ -5251,10 +5402,11 @@ void kvm_mmu_invpcid_gva(struct kvm_vcpu *vcpu, gva_t gva, unsigned long pcid) */ } -void kvm_configure_mmu(bool enable_tdp, int tdp_max_root_level, - int tdp_huge_page_level) +void kvm_configure_mmu(bool enable_tdp, int tdp_forced_root_level, + int tdp_max_root_level, int tdp_huge_page_level) { tdp_enabled = enable_tdp; + tdp_root_level = tdp_forced_root_level; max_tdp_level = tdp_max_root_level; /* @@ -5274,12 +5426,13 @@ 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, - struct kvm_memory_slot *slot); +typedef bool (*slot_level_handler) (struct kvm *kvm, + struct kvm_rmap_head *rmap_head, + const struct kvm_memory_slot *slot); /* The caller should hold mmu-lock before calling this function. */ static __always_inline bool -slot_handle_level_range(struct kvm *kvm, struct kvm_memory_slot *memslot, +slot_handle_level_range(struct kvm *kvm, const struct kvm_memory_slot *memslot, slot_level_handler fn, int start_level, int end_level, gfn_t start_gfn, gfn_t end_gfn, bool flush_on_yield, bool flush) @@ -5306,7 +5459,7 @@ slot_handle_level_range(struct kvm *kvm, struct kvm_memory_slot *memslot, } static __always_inline bool -slot_handle_level(struct kvm *kvm, struct kvm_memory_slot *memslot, +slot_handle_level(struct kvm *kvm, const struct kvm_memory_slot *memslot, slot_level_handler fn, int start_level, int end_level, bool flush_on_yield) { @@ -5317,7 +5470,7 @@ slot_handle_level(struct kvm *kvm, struct kvm_memory_slot *memslot, } static __always_inline bool -slot_handle_leaf(struct kvm *kvm, struct kvm_memory_slot *memslot, +slot_handle_leaf(struct kvm *kvm, const struct kvm_memory_slot *memslot, slot_level_handler fn, bool flush_on_yield) { return slot_handle_level(kvm, memslot, fn, PG_LEVEL_4K, @@ -5330,6 +5483,7 @@ static void free_mmu_pages(struct kvm_mmu *mmu) set_memory_encrypted((unsigned long)mmu->pae_root, 1); free_page((unsigned long)mmu->pae_root); free_page((unsigned long)mmu->pml4_root); + free_page((unsigned long)mmu->pml5_root); } static int __kvm_mmu_create(struct kvm_vcpu *vcpu, struct kvm_mmu *mmu) @@ -5535,6 +5689,8 @@ void kvm_mmu_init_vm(struct kvm *kvm) { struct kvm_page_track_notifier_node *node = &kvm->arch.mmu_sp_tracker; + spin_lock_init(&kvm->arch.mmu_unsync_pages_lock); + if (!kvm_mmu_init_tdp_mmu(kvm)) /* * No smp_load/store wrappers needed here as we are in @@ -5557,6 +5713,10 @@ void kvm_mmu_uninit_vm(struct kvm *kvm) kvm_mmu_uninit_tdp_mmu(kvm); } +/* + * Invalidate (zap) SPTEs that cover GFNs from gfn_start and up to gfn_end + * (not including it) + */ void kvm_zap_gfn_range(struct kvm *kvm, gfn_t gfn_start, gfn_t gfn_end) { struct kvm_memslots *slots; @@ -5564,8 +5724,11 @@ void kvm_zap_gfn_range(struct kvm *kvm, gfn_t gfn_start, gfn_t gfn_end) int i; bool flush = false; + write_lock(&kvm->mmu_lock); + + kvm_inc_notifier_count(kvm, gfn_start, gfn_end); + if (kvm_memslots_have_rmaps(kvm)) { - 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) { @@ -5576,41 +5739,44 @@ void kvm_zap_gfn_range(struct kvm *kvm, gfn_t gfn_start, gfn_t gfn_end) if (start >= end) continue; - flush = slot_handle_level_range(kvm, memslot, + flush = slot_handle_level_range(kvm, + (const struct kvm_memory_slot *) memslot, kvm_zap_rmapp, PG_LEVEL_4K, KVM_MAX_HUGEPAGE_LEVEL, start, end - 1, true, flush); } } if (flush) - kvm_flush_remote_tlbs_with_address(kvm, gfn_start, gfn_end); - write_unlock(&kvm->mmu_lock); + kvm_flush_remote_tlbs_with_address(kvm, gfn_start, + gfn_end - gfn_start); } if (is_tdp_mmu_enabled(kvm)) { - flush = false; - - read_lock(&kvm->mmu_lock); for (i = 0; i < KVM_ADDRESS_SPACE_NUM; i++) flush = kvm_tdp_mmu_zap_gfn_range(kvm, i, gfn_start, - gfn_end, flush, true); + gfn_end, flush); if (flush) kvm_flush_remote_tlbs_with_address(kvm, gfn_start, - gfn_end); - - read_unlock(&kvm->mmu_lock); + gfn_end - gfn_start); } + + if (flush) + kvm_flush_remote_tlbs_with_address(kvm, gfn_start, gfn_end); + + kvm_dec_notifier_count(kvm, gfn_start, gfn_end); + + write_unlock(&kvm->mmu_lock); } static bool slot_rmap_write_protect(struct kvm *kvm, struct kvm_rmap_head *rmap_head, - struct kvm_memory_slot *slot) + const struct kvm_memory_slot *slot) { return __rmap_write_protect(kvm, rmap_head, false); } void kvm_mmu_slot_remove_write_access(struct kvm *kvm, - struct kvm_memory_slot *memslot, + const struct kvm_memory_slot *memslot, int start_level) { bool flush = false; @@ -5646,7 +5812,7 @@ 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_memory_slot *slot) + const struct kvm_memory_slot *slot) { u64 *sptep; struct rmap_iterator iter; @@ -5669,7 +5835,7 @@ restart: if (sp->role.direct && !kvm_is_reserved_pfn(pfn) && sp->role.level < kvm_mmu_max_mapping_level(kvm, slot, sp->gfn, pfn, PG_LEVEL_NUM)) { - pte_list_remove(rmap_head, sptep); + pte_list_remove(kvm, rmap_head, sptep); if (kvm_available_flush_tlb_with_range()) kvm_flush_remote_tlbs_with_address(kvm, sp->gfn, @@ -5685,10 +5851,8 @@ restart: } void kvm_mmu_zap_collapsible_sptes(struct kvm *kvm, - const struct kvm_memory_slot *memslot) + const struct kvm_memory_slot *slot) { - /* FIXME: const-ify all uses of struct kvm_memory_slot. */ - struct kvm_memory_slot *slot = (struct kvm_memory_slot *)memslot; bool flush = false; if (kvm_memslots_have_rmaps(kvm)) { @@ -5724,7 +5888,7 @@ void kvm_arch_flush_remote_tlbs_memslot(struct kvm *kvm, } void kvm_mmu_slot_leaf_clear_dirty(struct kvm *kvm, - struct kvm_memory_slot *memslot) + const struct kvm_memory_slot *memslot) { bool flush = false; diff --git a/arch/x86/kvm/mmu/mmu_audit.c b/arch/x86/kvm/mmu/mmu_audit.c index cedc17b2f60e..9e7dcf999f08 100644 --- a/arch/x86/kvm/mmu/mmu_audit.c +++ b/arch/x86/kvm/mmu/mmu_audit.c @@ -147,7 +147,7 @@ static void inspect_spte_has_rmap(struct kvm *kvm, u64 *sptep) return; } - rmap_head = __gfn_to_rmap(gfn, rev_sp->role.level, slot); + rmap_head = gfn_to_rmap(gfn, rev_sp->role.level, slot); if (!rmap_head->val) { if (!__ratelimit(&ratelimit_state)) return; @@ -200,7 +200,7 @@ static void audit_write_protection(struct kvm *kvm, struct kvm_mmu_page *sp) slots = kvm_memslots_for_spte_role(kvm, sp->role); slot = __gfn_to_memslot(slots, sp->gfn); - rmap_head = __gfn_to_rmap(sp->gfn, PG_LEVEL_4K, slot); + rmap_head = gfn_to_rmap(sp->gfn, PG_LEVEL_4K, slot); for_each_rmap_spte(rmap_head, &iter, sptep) { if (is_writable_pte(*sptep)) diff --git a/arch/x86/kvm/mmu/mmu_internal.h b/arch/x86/kvm/mmu/mmu_internal.h index 35567293c1fd..bf2bdbf333c2 100644 --- a/arch/x86/kvm/mmu/mmu_internal.h +++ b/arch/x86/kvm/mmu/mmu_internal.h @@ -31,13 +31,16 @@ extern bool dbg; #define IS_VALID_PAE_ROOT(x) (!!(x)) struct kvm_mmu_page { + /* + * Note, "link" through "spt" fit in a single 64 byte cache line on + * 64-bit kernels, keep it that way unless there's a reason not to. + */ struct list_head link; struct hlist_node hash_link; - struct list_head lpage_disallowed_link; + bool tdp_mmu_page; bool unsync; u8 mmu_valid_gen; - bool mmio_cached; bool lpage_disallowed; /* Can't be replaced by an equiv large page */ /* @@ -59,6 +62,7 @@ struct kvm_mmu_page { struct kvm_rmap_head parent_ptes; /* rmap pointers to parent sptes */ DECLARE_BITMAP(unsync_child_bitmap, 512); + struct list_head lpage_disallowed_link; #ifdef CONFIG_X86_32 /* * Used out of the mmu-lock to avoid reading spte values while an @@ -71,8 +75,6 @@ struct kvm_mmu_page { atomic_t write_flooding_count; #ifdef CONFIG_X86_64 - bool tdp_mmu_page; - /* Used for freeing the page asynchronously if it is a TDP MMU page. */ struct rcu_head rcu_head; #endif @@ -124,13 +126,14 @@ static inline bool is_nx_huge_page_enabled(void) int mmu_try_to_unsync_pages(struct kvm_vcpu *vcpu, gfn_t gfn, bool can_unsync); -void kvm_mmu_gfn_disallow_lpage(struct kvm_memory_slot *slot, gfn_t gfn); -void kvm_mmu_gfn_allow_lpage(struct kvm_memory_slot *slot, gfn_t gfn); +void kvm_mmu_gfn_disallow_lpage(const struct kvm_memory_slot *slot, gfn_t gfn); +void kvm_mmu_gfn_allow_lpage(const struct kvm_memory_slot *slot, gfn_t gfn); bool kvm_mmu_slot_gfn_write_protect(struct kvm *kvm, struct kvm_memory_slot *slot, u64 gfn, int min_level); void kvm_flush_remote_tlbs_with_address(struct kvm *kvm, u64 start_gfn, u64 pages); +unsigned int pte_list_count(struct kvm_rmap_head *rmap_head); /* * Return values of handle_mmio_page_fault, mmu.page_fault, and fast_page_fault(). @@ -140,6 +143,9 @@ void kvm_flush_remote_tlbs_with_address(struct kvm *kvm, * RET_PF_INVALID: the spte is invalid, let the real page fault path update it. * RET_PF_FIXED: The faulting entry has been fixed. * RET_PF_SPURIOUS: The faulting entry was already fixed, e.g. by another vCPU. + * + * Any names added to this enum should be exported to userspace for use in + * tracepoints via TRACE_DEFINE_ENUM() in mmutrace.h */ enum { RET_PF_RETRY = 0, diff --git a/arch/x86/kvm/mmu/mmutrace.h b/arch/x86/kvm/mmu/mmutrace.h index efbad33a0645..2924a4081a19 100644 --- a/arch/x86/kvm/mmu/mmutrace.h +++ b/arch/x86/kvm/mmu/mmutrace.h @@ -54,6 +54,12 @@ { PFERR_RSVD_MASK, "RSVD" }, \ { PFERR_FETCH_MASK, "F" } +TRACE_DEFINE_ENUM(RET_PF_RETRY); +TRACE_DEFINE_ENUM(RET_PF_EMULATE); +TRACE_DEFINE_ENUM(RET_PF_INVALID); +TRACE_DEFINE_ENUM(RET_PF_FIXED); +TRACE_DEFINE_ENUM(RET_PF_SPURIOUS); + /* * A pagetable walk has started */ diff --git a/arch/x86/kvm/mmu/page_track.c b/arch/x86/kvm/mmu/page_track.c index 91a9f7e0fd91..269f11f92fd0 100644 --- a/arch/x86/kvm/mmu/page_track.c +++ b/arch/x86/kvm/mmu/page_track.c @@ -16,6 +16,7 @@ #include <asm/kvm_page_track.h> +#include "mmu.h" #include "mmu_internal.h" void kvm_page_track_free_memslot(struct kvm_memory_slot *slot) diff --git a/arch/x86/kvm/mmu/paging.h b/arch/x86/kvm/mmu/paging.h new file mode 100644 index 000000000000..de8ab323bb70 --- /dev/null +++ b/arch/x86/kvm/mmu/paging.h @@ -0,0 +1,14 @@ +/* SPDX-License-Identifier: GPL-2.0-only */ +/* Shadow paging constants/helpers that don't need to be #undef'd. */ +#ifndef __KVM_X86_PAGING_H +#define __KVM_X86_PAGING_H + +#define GUEST_PT64_BASE_ADDR_MASK (((1ULL << 52) - 1) & ~(u64)(PAGE_SIZE-1)) +#define PT64_LVL_ADDR_MASK(level) \ + (GUEST_PT64_BASE_ADDR_MASK & ~((1ULL << (PAGE_SHIFT + (((level) - 1) \ + * PT64_LEVEL_BITS))) - 1)) +#define PT64_LVL_OFFSET_MASK(level) \ + (GUEST_PT64_BASE_ADDR_MASK & ((1ULL << (PAGE_SHIFT + (((level) - 1) \ + * PT64_LEVEL_BITS))) - 1)) +#endif /* __KVM_X86_PAGING_H */ + diff --git a/arch/x86/kvm/mmu/paging_tmpl.h b/arch/x86/kvm/mmu/paging_tmpl.h index 490a028ddabe..7d03e9b7ccfa 100644 --- a/arch/x86/kvm/mmu/paging_tmpl.h +++ b/arch/x86/kvm/mmu/paging_tmpl.h @@ -24,7 +24,7 @@ #define pt_element_t u64 #define guest_walker guest_walker64 #define FNAME(name) paging##64_##name - #define PT_BASE_ADDR_MASK PT64_BASE_ADDR_MASK + #define PT_BASE_ADDR_MASK GUEST_PT64_BASE_ADDR_MASK #define PT_LVL_ADDR_MASK(lvl) PT64_LVL_ADDR_MASK(lvl) #define PT_LVL_OFFSET_MASK(lvl) PT64_LVL_OFFSET_MASK(lvl) #define PT_INDEX(addr, level) PT64_INDEX(addr, level) @@ -57,7 +57,7 @@ #define pt_element_t u64 #define guest_walker guest_walkerEPT #define FNAME(name) ept_##name - #define PT_BASE_ADDR_MASK PT64_BASE_ADDR_MASK + #define PT_BASE_ADDR_MASK GUEST_PT64_BASE_ADDR_MASK #define PT_LVL_ADDR_MASK(lvl) PT64_LVL_ADDR_MASK(lvl) #define PT_LVL_OFFSET_MASK(lvl) PT64_LVL_OFFSET_MASK(lvl) #define PT_INDEX(addr, level) PT64_INDEX(addr, level) @@ -881,9 +881,9 @@ 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, &hva, - write_fault, &map_writable)) - return RET_PF_RETRY; + if (kvm_faultin_pfn(vcpu, prefault, walker.gfn, addr, &pfn, &hva, + write_fault, &map_writable, &r)) + return r; if (handle_abnormal_pfn(vcpu, addr, walker.gfn, pfn, walker.pte_access, &r)) return r; diff --git a/arch/x86/kvm/mmu/spte.h b/arch/x86/kvm/mmu/spte.h index 7a5ce9314107..eb7b227fc6cf 100644 --- a/arch/x86/kvm/mmu/spte.h +++ b/arch/x86/kvm/mmu/spte.h @@ -38,12 +38,6 @@ static_assert(SPTE_TDP_AD_ENABLED_MASK == 0); #else #define PT64_BASE_ADDR_MASK (((1ULL << 52) - 1) & ~(u64)(PAGE_SIZE-1)) #endif -#define PT64_LVL_ADDR_MASK(level) \ - (PT64_BASE_ADDR_MASK & ~((1ULL << (PAGE_SHIFT + (((level) - 1) \ - * PT64_LEVEL_BITS))) - 1)) -#define PT64_LVL_OFFSET_MASK(level) \ - (PT64_BASE_ADDR_MASK & ((1ULL << (PAGE_SHIFT + (((level) - 1) \ - * PT64_LEVEL_BITS))) - 1)) #define PT64_PERM_MASK (PT_PRESENT_MASK | PT_WRITABLE_MASK | shadow_user_mask \ | shadow_x_mask | shadow_nx_mask | shadow_me_mask) diff --git a/arch/x86/kvm/mmu/tdp_mmu.c b/arch/x86/kvm/mmu/tdp_mmu.c index 0853370bd811..64ccfc1fa553 100644 --- a/arch/x86/kvm/mmu/tdp_mmu.c +++ b/arch/x86/kvm/mmu/tdp_mmu.c @@ -10,7 +10,7 @@ #include <asm/cmpxchg.h> #include <trace/events/kvm.h> -static bool __read_mostly tdp_mmu_enabled = false; +static bool __read_mostly tdp_mmu_enabled = true; module_param_named(tdp_mmu, tdp_mmu_enabled, bool, 0644); /* Initializes the TDP MMU for the VM, if enabled. */ @@ -43,6 +43,7 @@ void kvm_mmu_uninit_tdp_mmu(struct kvm *kvm) if (!kvm->arch.tdp_mmu_enabled) return; + WARN_ON(!list_empty(&kvm->arch.tdp_mmu_pages)); WARN_ON(!list_empty(&kvm->arch.tdp_mmu_roots)); /* @@ -81,8 +82,6 @@ static void tdp_mmu_free_sp_rcu_callback(struct rcu_head *head) void kvm_tdp_mmu_put_root(struct kvm *kvm, struct kvm_mmu_page *root, bool shared) { - gfn_t max_gfn = 1ULL << (shadow_phys_bits - PAGE_SHIFT); - kvm_lockdep_assert_mmu_lock_held(kvm, shared); if (!refcount_dec_and_test(&root->tdp_mmu_root_count)) @@ -94,7 +93,7 @@ void kvm_tdp_mmu_put_root(struct kvm *kvm, struct kvm_mmu_page *root, list_del_rcu(&root->link); spin_unlock(&kvm->arch.tdp_mmu_pages_lock); - zap_gfn_range(kvm, root, 0, max_gfn, false, false, shared); + zap_gfn_range(kvm, root, 0, -1ull, false, false, shared); call_rcu(&root->rcu_head, tdp_mmu_free_sp_rcu_callback); } @@ -256,26 +255,17 @@ static void handle_changed_spte_dirty_log(struct kvm *kvm, int as_id, gfn_t gfn, * * @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) + bool account_nx) { - if (shared) - spin_lock(&kvm->arch.tdp_mmu_pages_lock); - else - lockdep_assert_held_write(&kvm->mmu_lock); - + spin_lock(&kvm->arch.tdp_mmu_pages_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); + spin_unlock(&kvm->arch.tdp_mmu_pages_lock); } /** @@ -446,13 +436,6 @@ static void __handle_changed_spte(struct kvm *kvm, int as_id, gfn_t gfn, trace_kvm_tdp_mmu_spte_changed(as_id, gfn, level, old_spte, new_spte); - if (is_large_pte(old_spte) != is_large_pte(new_spte)) { - if (is_large_pte(old_spte)) - atomic64_sub(1, (atomic64_t*)&kvm->stat.lpages); - else - atomic64_add(1, (atomic64_t*)&kvm->stat.lpages); - } - /* * The only times a SPTE should be changed from a non-present to * non-present state is when an MMIO entry is installed/modified/ @@ -478,6 +461,8 @@ static void __handle_changed_spte(struct kvm *kvm, int as_id, gfn_t gfn, return; } + if (is_leaf != was_leaf) + kvm_update_page_stats(kvm, level, is_leaf ? 1 : -1); if (was_leaf && is_dirty_spte(old_spte) && (!is_present || !is_dirty_spte(new_spte) || pfn_changed)) @@ -527,6 +512,10 @@ static inline bool tdp_mmu_set_spte_atomic_no_dirty_log(struct kvm *kvm, if (is_removed_spte(iter->old_spte)) return false; + /* + * Note, fast_pf_fix_direct_spte() can also modify TDP MMU SPTEs and + * does not hold the mmu_lock. + */ if (cmpxchg64(rcu_dereference(iter->sptep), iter->old_spte, new_spte) != iter->old_spte) return false; @@ -538,15 +527,40 @@ static inline bool tdp_mmu_set_spte_atomic_no_dirty_log(struct kvm *kvm, return true; } -static inline bool tdp_mmu_set_spte_atomic(struct kvm *kvm, - struct tdp_iter *iter, - u64 new_spte) +/* + * tdp_mmu_map_set_spte_atomic - Set a leaf TDP MMU SPTE atomically to resolve a + * TDP page fault. + * + * @vcpu: The vcpu instance that took the TDP page fault. + * @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_map_set_spte_atomic(struct kvm_vcpu *vcpu, + struct tdp_iter *iter, + u64 new_spte) { + struct kvm *kvm = vcpu->kvm; + if (!tdp_mmu_set_spte_atomic_no_dirty_log(kvm, iter, new_spte)) return false; - handle_changed_spte_dirty_log(kvm, iter->as_id, iter->gfn, - iter->old_spte, new_spte, iter->level); + /* + * Use kvm_vcpu_gfn_to_memslot() instead of going through + * handle_changed_spte_dirty_log() to leverage vcpu->last_used_slot. + */ + if (is_writable_pte(new_spte)) { + struct kvm_memory_slot *slot = kvm_vcpu_gfn_to_memslot(vcpu, iter->gfn); + + if (slot && kvm_slot_dirty_track_enabled(slot)) { + /* Enforced by kvm_mmu_hugepage_adjust. */ + WARN_ON_ONCE(iter->level > PG_LEVEL_4K); + mark_page_dirty_in_slot(kvm, slot, iter->gfn); + } + } + return true; } @@ -559,7 +573,7 @@ static inline bool tdp_mmu_zap_spte_atomic(struct kvm *kvm, * immediately installing a present entry in its place * before the TLBs are flushed. */ - if (!tdp_mmu_set_spte_atomic(kvm, iter, REMOVED_SPTE)) + if (!tdp_mmu_set_spte_atomic_no_dirty_log(kvm, iter, REMOVED_SPTE)) return false; kvm_flush_remote_tlbs_with_address(kvm, iter->gfn, @@ -724,13 +738,29 @@ static bool zap_gfn_range(struct kvm *kvm, struct kvm_mmu_page *root, gfn_t start, gfn_t end, bool can_yield, bool flush, bool shared) { + gfn_t max_gfn_host = 1ULL << (shadow_phys_bits - PAGE_SHIFT); + bool zap_all = (start == 0 && end >= max_gfn_host); struct tdp_iter iter; + /* + * No need to try to step down in the iterator when zapping all SPTEs, + * zapping the top-level non-leaf SPTEs will recurse on their children. + */ + int min_level = zap_all ? root->role.level : PG_LEVEL_4K; + + /* + * Bound the walk at host.MAXPHYADDR, guest accesses beyond that will + * hit a #PF(RSVD) and never get to an EPT Violation/Misconfig / #NPF, + * and so KVM will never install a SPTE for such addresses. + */ + end = min(end, max_gfn_host); + kvm_lockdep_assert_mmu_lock_held(kvm, shared); rcu_read_lock(); - tdp_root_for_each_pte(iter, root, start, end) { + for_each_tdp_pte_min_level(iter, root->spt, root->role.level, + min_level, start, end) { retry: if (can_yield && tdp_mmu_iter_cond_resched(kvm, &iter, flush, shared)) { @@ -744,9 +774,10 @@ retry: /* * If this is a non-last-level SPTE that covers a larger range * than should be zapped, continue, and zap the mappings at a - * lower level. + * lower level, except when zapping all SPTEs. */ - if ((iter.gfn < start || + if (!zap_all && + (iter.gfn < start || iter.gfn + KVM_PAGES_PER_HPAGE(iter.level) > end) && !is_last_spte(iter.old_spte, iter.level)) continue; @@ -773,34 +804,26 @@ retry: * non-root pages mapping GFNs strictly within that range. Returns true if * SPTEs have been cleared and a TLB flush is needed before releasing the * MMU lock. - * - * If shared is true, this thread holds the MMU lock in read mode and must - * account for the possibility that other threads are modifying the paging - * structures concurrently. If shared is false, this thread should hold the - * MMU in write mode. */ bool __kvm_tdp_mmu_zap_gfn_range(struct kvm *kvm, int as_id, gfn_t start, - gfn_t end, bool can_yield, bool flush, - bool shared) + gfn_t end, bool can_yield, bool flush) { struct kvm_mmu_page *root; - for_each_tdp_mmu_root_yield_safe(kvm, root, as_id, shared) + for_each_tdp_mmu_root_yield_safe(kvm, root, as_id, false) flush = zap_gfn_range(kvm, root, start, end, can_yield, flush, - shared); + false); return flush; } void kvm_tdp_mmu_zap_all(struct kvm *kvm) { - gfn_t max_gfn = 1ULL << (shadow_phys_bits - PAGE_SHIFT); bool flush = false; int i; for (i = 0; i < KVM_ADDRESS_SPACE_NUM; i++) - flush = kvm_tdp_mmu_zap_gfn_range(kvm, i, 0, max_gfn, - flush, false); + flush = kvm_tdp_mmu_zap_gfn_range(kvm, i, 0, -1ull, flush); if (flush) kvm_flush_remote_tlbs(kvm); @@ -838,7 +861,6 @@ static struct kvm_mmu_page *next_invalidated_root(struct kvm *kvm, */ void kvm_tdp_mmu_zap_invalidated_roots(struct kvm *kvm) { - gfn_t max_gfn = 1ULL << (shadow_phys_bits - PAGE_SHIFT); struct kvm_mmu_page *next_root; struct kvm_mmu_page *root; bool flush = false; @@ -854,8 +876,7 @@ void kvm_tdp_mmu_zap_invalidated_roots(struct kvm *kvm) rcu_read_unlock(); - flush = zap_gfn_range(kvm, root, 0, max_gfn, true, flush, - true); + flush = zap_gfn_range(kvm, root, 0, -1ull, true, flush, true); /* * Put the reference acquired in @@ -927,7 +948,7 @@ static int tdp_mmu_map_handle_target_level(struct kvm_vcpu *vcpu, int write, if (new_spte == iter->old_spte) ret = RET_PF_SPURIOUS; - else if (!tdp_mmu_set_spte_atomic(vcpu->kvm, iter, new_spte)) + else if (!tdp_mmu_map_set_spte_atomic(vcpu, iter, new_spte)) return RET_PF_RETRY; /* @@ -1031,9 +1052,8 @@ int kvm_tdp_mmu_map(struct kvm_vcpu *vcpu, gpa_t gpa, u32 error_code, new_spte = make_nonleaf_spte(child_pt, !shadow_accessed_mask); - if (tdp_mmu_set_spte_atomic(vcpu->kvm, &iter, - new_spte)) { - tdp_mmu_link_page(vcpu->kvm, sp, true, + if (tdp_mmu_set_spte_atomic_no_dirty_log(vcpu->kvm, &iter, new_spte)) { + tdp_mmu_link_page(vcpu->kvm, sp, huge_page_disallowed && req_level >= iter.level); @@ -1242,8 +1262,8 @@ retry: * only affect leaf SPTEs down to min_level. * Returns true if an SPTE has been changed and the TLBs need to be flushed. */ -bool kvm_tdp_mmu_wrprot_slot(struct kvm *kvm, struct kvm_memory_slot *slot, - int min_level) +bool kvm_tdp_mmu_wrprot_slot(struct kvm *kvm, + const struct kvm_memory_slot *slot, int min_level) { struct kvm_mmu_page *root; bool spte_set = false; @@ -1313,7 +1333,8 @@ retry: * each SPTE. Returns true if an SPTE has been changed and the TLBs need to * be flushed. */ -bool kvm_tdp_mmu_clear_dirty_slot(struct kvm *kvm, struct kvm_memory_slot *slot) +bool kvm_tdp_mmu_clear_dirty_slot(struct kvm *kvm, + const struct kvm_memory_slot *slot) { struct kvm_mmu_page *root; bool spte_set = false; @@ -1516,6 +1537,8 @@ bool kvm_tdp_mmu_write_protect_gfn(struct kvm *kvm, /* * Return the level of the lowest level SPTE added to sptes. * That SPTE may be non-present. + * + * Must be called between kvm_tdp_mmu_walk_lockless_{begin,end}. */ int kvm_tdp_mmu_get_walk(struct kvm_vcpu *vcpu, u64 addr, u64 *sptes, int *root_level) @@ -1527,14 +1550,47 @@ 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; } + +/* + * Returns the last level spte pointer of the shadow page walk for the given + * gpa, and sets *spte to the spte value. This spte may be non-preset. If no + * walk could be performed, returns NULL and *spte does not contain valid data. + * + * Contract: + * - Must be called between kvm_tdp_mmu_walk_lockless_{begin,end}. + * - The returned sptep must not be used after kvm_tdp_mmu_walk_lockless_end. + * + * WARNING: This function is only intended to be called during fast_page_fault. + */ +u64 *kvm_tdp_mmu_fast_pf_get_last_sptep(struct kvm_vcpu *vcpu, u64 addr, + u64 *spte) +{ + struct tdp_iter iter; + struct kvm_mmu *mmu = vcpu->arch.mmu; + gfn_t gfn = addr >> PAGE_SHIFT; + tdp_ptep_t sptep = NULL; + + tdp_mmu_for_each_pte(iter, mmu, gfn, gfn + 1) { + *spte = iter.old_spte; + sptep = iter.sptep; + } + + /* + * Perform the rcu_dereference to get the raw spte pointer value since + * we are passing it up to fast_page_fault, which is shared with the + * legacy MMU and thus does not retain the TDP MMU-specific __rcu + * annotation. + * + * This is safe since fast_page_fault obeys the contracts of this + * function as well as all TDP MMU contracts around modifying SPTEs + * outside of mmu_lock. + */ + return rcu_dereference(sptep); +} diff --git a/arch/x86/kvm/mmu/tdp_mmu.h b/arch/x86/kvm/mmu/tdp_mmu.h index 1cae4485b3bc..358f447d4012 100644 --- a/arch/x86/kvm/mmu/tdp_mmu.h +++ b/arch/x86/kvm/mmu/tdp_mmu.h @@ -20,14 +20,11 @@ void kvm_tdp_mmu_put_root(struct kvm *kvm, struct kvm_mmu_page *root, bool shared); bool __kvm_tdp_mmu_zap_gfn_range(struct kvm *kvm, int as_id, gfn_t start, - gfn_t end, bool can_yield, bool flush, - bool shared); + gfn_t end, bool can_yield, bool flush); static inline bool kvm_tdp_mmu_zap_gfn_range(struct kvm *kvm, int as_id, - gfn_t start, gfn_t end, bool flush, - bool shared) + gfn_t start, gfn_t end, bool flush) { - return __kvm_tdp_mmu_zap_gfn_range(kvm, as_id, start, end, true, flush, - shared); + return __kvm_tdp_mmu_zap_gfn_range(kvm, as_id, start, end, true, flush); } static inline bool kvm_tdp_mmu_zap_sp(struct kvm *kvm, struct kvm_mmu_page *sp) { @@ -44,7 +41,7 @@ static inline bool kvm_tdp_mmu_zap_sp(struct kvm *kvm, struct kvm_mmu_page *sp) */ lockdep_assert_held_write(&kvm->mmu_lock); return __kvm_tdp_mmu_zap_gfn_range(kvm, kvm_mmu_page_as_id(sp), - sp->gfn, end, false, false, false); + sp->gfn, end, false, false); } void kvm_tdp_mmu_zap_all(struct kvm *kvm); @@ -61,10 +58,10 @@ bool kvm_tdp_mmu_age_gfn_range(struct kvm *kvm, struct kvm_gfn_range *range); bool kvm_tdp_mmu_test_age_gfn(struct kvm *kvm, struct kvm_gfn_range *range); bool kvm_tdp_mmu_set_spte_gfn(struct kvm *kvm, struct kvm_gfn_range *range); -bool kvm_tdp_mmu_wrprot_slot(struct kvm *kvm, struct kvm_memory_slot *slot, - int min_level); +bool kvm_tdp_mmu_wrprot_slot(struct kvm *kvm, + const struct kvm_memory_slot *slot, int min_level); bool kvm_tdp_mmu_clear_dirty_slot(struct kvm *kvm, - struct kvm_memory_slot *slot); + const struct kvm_memory_slot *slot); void kvm_tdp_mmu_clear_dirty_pt_masked(struct kvm *kvm, struct kvm_memory_slot *slot, gfn_t gfn, unsigned long mask, @@ -77,8 +74,20 @@ bool kvm_tdp_mmu_write_protect_gfn(struct kvm *kvm, struct kvm_memory_slot *slot, gfn_t gfn, int min_level); +static inline void kvm_tdp_mmu_walk_lockless_begin(void) +{ + rcu_read_lock(); +} + +static inline void kvm_tdp_mmu_walk_lockless_end(void) +{ + rcu_read_unlock(); +} + int kvm_tdp_mmu_get_walk(struct kvm_vcpu *vcpu, u64 addr, u64 *sptes, int *root_level); +u64 *kvm_tdp_mmu_fast_pf_get_last_sptep(struct kvm_vcpu *vcpu, u64 addr, + u64 *spte); #ifdef CONFIG_X86_64 bool kvm_mmu_init_tdp_mmu(struct kvm *kvm); diff --git a/arch/x86/kvm/pmu.c b/arch/x86/kvm/pmu.c index 827886c12c16..0772bad9165c 100644 --- a/arch/x86/kvm/pmu.c +++ b/arch/x86/kvm/pmu.c @@ -137,18 +137,20 @@ static void pmc_reprogram_counter(struct kvm_pmc *pmc, u32 type, pmc->perf_event = event; pmc_to_pmu(pmc)->event_count++; clear_bit(pmc->idx, pmc_to_pmu(pmc)->reprogram_pmi); + pmc->is_paused = false; } static void pmc_pause_counter(struct kvm_pmc *pmc) { u64 counter = pmc->counter; - if (!pmc->perf_event) + if (!pmc->perf_event || pmc->is_paused) return; /* update counter, reset event value to avoid redundant accumulation */ counter += perf_event_pause(pmc->perf_event, true); pmc->counter = counter & pmc_bitmask(pmc); + pmc->is_paused = true; } static bool pmc_resume_counter(struct kvm_pmc *pmc) @@ -163,6 +165,7 @@ static bool pmc_resume_counter(struct kvm_pmc *pmc) /* reuse perf_event to serve as pmc_reprogram_counter() does*/ perf_event_enable(pmc->perf_event); + pmc->is_paused = false; clear_bit(pmc->idx, (unsigned long *)&pmc_to_pmu(pmc)->reprogram_pmi); return true; diff --git a/arch/x86/kvm/pmu.h b/arch/x86/kvm/pmu.h index 67e753edfa22..0e4f2b1fa9fb 100644 --- a/arch/x86/kvm/pmu.h +++ b/arch/x86/kvm/pmu.h @@ -55,7 +55,7 @@ static inline u64 pmc_read_counter(struct kvm_pmc *pmc) u64 counter, enabled, running; counter = pmc->counter; - if (pmc->perf_event) + if (pmc->perf_event && !pmc->is_paused) counter += perf_event_read_value(pmc->perf_event, &enabled, &running); /* FIXME: Scaling needed? */ diff --git a/arch/x86/kvm/svm/avic.c b/arch/x86/kvm/svm/avic.c index 1d01da64c333..8052d92069e0 100644 --- a/arch/x86/kvm/svm/avic.c +++ b/arch/x86/kvm/svm/avic.c @@ -197,6 +197,8 @@ void avic_init_vmcb(struct vcpu_svm *svm) vmcb->control.avic_logical_id = lpa & AVIC_HPA_MASK; vmcb->control.avic_physical_id = ppa & AVIC_HPA_MASK; vmcb->control.avic_physical_id |= AVIC_MAX_PHYSICAL_ID_COUNT; + vmcb->control.avic_vapic_bar = APIC_DEFAULT_PHYS_BASE & VMCB_AVIC_APIC_BAR_MASK; + if (kvm_apicv_activated(svm->vcpu.kvm)) vmcb->control.int_ctl |= AVIC_ENABLE_MASK; else @@ -225,31 +227,26 @@ static u64 *avic_get_physical_id_entry(struct kvm_vcpu *vcpu, * field of the VMCB. Therefore, we set up the * APIC_ACCESS_PAGE_PRIVATE_MEMSLOT (4KB) here. */ -static int avic_update_access_page(struct kvm *kvm, bool activate) +static int avic_alloc_access_page(struct kvm *kvm) { void __user *ret; int r = 0; mutex_lock(&kvm->slots_lock); - /* - * During kvm_destroy_vm(), kvm_pit_set_reinject() could trigger - * APICv mode change, which update APIC_ACCESS_PAGE_PRIVATE_MEMSLOT - * memory region. So, we need to ensure that kvm->mm == current->mm. - */ - if ((kvm->arch.apic_access_memslot_enabled == activate) || - (kvm->mm != current->mm)) + + if (kvm->arch.apic_access_memslot_enabled) goto out; ret = __x86_set_memory_region(kvm, APIC_ACCESS_PAGE_PRIVATE_MEMSLOT, APIC_DEFAULT_PHYS_BASE, - activate ? PAGE_SIZE : 0); + PAGE_SIZE); if (IS_ERR(ret)) { r = PTR_ERR(ret); goto out; } - kvm->arch.apic_access_memslot_enabled = activate; + kvm->arch.apic_access_memslot_enabled = true; out: mutex_unlock(&kvm->slots_lock); return r; @@ -270,7 +267,7 @@ static int avic_init_backing_page(struct kvm_vcpu *vcpu) if (kvm_apicv_activated(vcpu->kvm)) { int ret; - ret = avic_update_access_page(vcpu->kvm, true); + ret = avic_alloc_access_page(vcpu->kvm); if (ret) return ret; } @@ -587,17 +584,6 @@ void avic_post_state_restore(struct kvm_vcpu *vcpu) avic_handle_ldr_update(vcpu); } -void svm_toggle_avic_for_irq_window(struct kvm_vcpu *vcpu, bool activate) -{ - if (!enable_apicv || !lapic_in_kernel(vcpu)) - return; - - srcu_read_unlock(&vcpu->kvm->srcu, vcpu->srcu_idx); - kvm_request_apicv_update(vcpu->kvm, activate, - APICV_INHIBIT_REASON_IRQWIN); - vcpu->srcu_idx = srcu_read_lock(&vcpu->kvm->srcu); -} - void svm_set_virtual_apic_mode(struct kvm_vcpu *vcpu) { return; @@ -646,7 +632,7 @@ out: void svm_refresh_apicv_exec_ctrl(struct kvm_vcpu *vcpu) { struct vcpu_svm *svm = to_svm(vcpu); - struct vmcb *vmcb = svm->vmcb; + struct vmcb *vmcb = svm->vmcb01.ptr; bool activated = kvm_vcpu_apicv_active(vcpu); if (!enable_apicv) @@ -667,6 +653,11 @@ void svm_refresh_apicv_exec_ctrl(struct kvm_vcpu *vcpu) } vmcb_mark_dirty(vmcb, VMCB_AVIC); + if (activated) + avic_vcpu_load(vcpu, vcpu->cpu); + else + avic_vcpu_put(vcpu); + svm_set_pi_irte_mode(vcpu, activated); } @@ -918,10 +909,6 @@ bool svm_check_apicv_inhibit_reasons(ulong bit) return supported & BIT(bit); } -void svm_pre_update_apicv_exec_ctrl(struct kvm *kvm, bool activate) -{ - avic_update_access_page(kvm, activate); -} static inline int avic_update_iommu_vcpu_affinity(struct kvm_vcpu *vcpu, int cpu, bool r) @@ -960,9 +947,6 @@ void avic_vcpu_load(struct kvm_vcpu *vcpu, int cpu) int h_physical_id = kvm_cpu_get_apicid(cpu); struct vcpu_svm *svm = to_svm(vcpu); - if (!kvm_vcpu_apicv_active(vcpu)) - return; - /* * Since the host physical APIC id is 8 bits, * we can support host APIC ID upto 255. @@ -990,9 +974,6 @@ void avic_vcpu_put(struct kvm_vcpu *vcpu) u64 entry; struct vcpu_svm *svm = to_svm(vcpu); - if (!kvm_vcpu_apicv_active(vcpu)) - return; - entry = READ_ONCE(*(svm->avic_physical_id_cache)); if (entry & AVIC_PHYSICAL_ID_ENTRY_IS_RUNNING_MASK) avic_update_iommu_vcpu_affinity(vcpu, -1, 0); @@ -1009,6 +990,10 @@ static void avic_set_running(struct kvm_vcpu *vcpu, bool is_run) struct vcpu_svm *svm = to_svm(vcpu); svm->avic_is_running = is_run; + + if (!kvm_vcpu_apicv_active(vcpu)) + return; + if (is_run) avic_vcpu_load(vcpu, vcpu->cpu); else diff --git a/arch/x86/kvm/svm/nested.c b/arch/x86/kvm/svm/nested.c index 21d03e3a5dfd..2545d0c61985 100644 --- a/arch/x86/kvm/svm/nested.c +++ b/arch/x86/kvm/svm/nested.c @@ -154,6 +154,13 @@ void recalc_intercepts(struct vcpu_svm *svm) for (i = 0; i < MAX_INTERCEPT; i++) c->intercepts[i] |= g->intercepts[i]; + + /* If SMI is not intercepted, ignore guest SMI intercept as well */ + if (!intercept_smi) + vmcb_clr_intercept(c, INTERCEPT_SMI); + + vmcb_set_intercept(c, INTERCEPT_VMLOAD); + vmcb_set_intercept(c, INTERCEPT_VMSAVE); } static void copy_vmcb_control_area(struct vmcb_control_area *dst, @@ -304,8 +311,8 @@ static bool nested_vmcb_valid_sregs(struct kvm_vcpu *vcpu, return true; } -static void nested_load_control_from_vmcb12(struct vcpu_svm *svm, - struct vmcb_control_area *control) +void nested_load_control_from_vmcb12(struct vcpu_svm *svm, + struct vmcb_control_area *control) { copy_vmcb_control_area(&svm->nested.ctl, control); @@ -499,7 +506,11 @@ static void nested_vmcb02_prepare_save(struct vcpu_svm *svm, struct vmcb *vmcb12 static void nested_vmcb02_prepare_control(struct vcpu_svm *svm) { - const u32 mask = V_INTR_MASKING_MASK | V_GIF_ENABLE_MASK | V_GIF_MASK; + const u32 int_ctl_vmcb01_bits = + V_INTR_MASKING_MASK | V_GIF_MASK | V_GIF_ENABLE_MASK; + + const u32 int_ctl_vmcb12_bits = V_TPR_MASK | V_IRQ_INJECTION_BITS_MASK; + struct kvm_vcpu *vcpu = &svm->vcpu; /* @@ -511,7 +522,7 @@ static void nested_vmcb02_prepare_control(struct vcpu_svm *svm) * Also covers avic_vapic_bar, avic_backing_page, avic_logical_id, * avic_physical_id. */ - WARN_ON(svm->vmcb01.ptr->control.int_ctl & AVIC_ENABLE_MASK); + WARN_ON(kvm_apicv_activated(svm->vcpu.kvm)); /* Copied from vmcb01. msrpm_base can be overwritten later. */ svm->vmcb->control.nested_ctl = svm->vmcb01.ptr->control.nested_ctl; @@ -531,8 +542,8 @@ static void nested_vmcb02_prepare_control(struct vcpu_svm *svm) vcpu->arch.l1_tsc_offset + svm->nested.ctl.tsc_offset; svm->vmcb->control.int_ctl = - (svm->nested.ctl.int_ctl & ~mask) | - (svm->vmcb01.ptr->control.int_ctl & mask); + (svm->nested.ctl.int_ctl & int_ctl_vmcb12_bits) | + (svm->vmcb01.ptr->control.int_ctl & int_ctl_vmcb01_bits); svm->vmcb->control.virt_ext = svm->nested.ctl.virt_ext; svm->vmcb->control.int_vector = svm->nested.ctl.int_vector; @@ -618,6 +629,11 @@ int nested_svm_vmrun(struct kvm_vcpu *vcpu) struct kvm_host_map map; u64 vmcb12_gpa; + if (!svm->nested.hsave_msr) { + kvm_inject_gp(vcpu, 0); + return 1; + } + if (is_smm(vcpu)) { kvm_queue_exception(vcpu, UD_VECTOR); return 1; @@ -650,11 +666,6 @@ int nested_svm_vmrun(struct kvm_vcpu *vcpu) goto out; } - - /* Clear internal status */ - kvm_clear_exception_queue(vcpu); - kvm_clear_interrupt_queue(vcpu); - /* * Since vmcb01 is not in use, we can use it to store some of the L1 * state. @@ -692,7 +703,28 @@ out: return ret; } -void nested_svm_vmloadsave(struct vmcb *from_vmcb, struct vmcb *to_vmcb) +/* Copy state save area fields which are handled by VMRUN */ +void svm_copy_vmrun_state(struct vmcb_save_area *to_save, + struct vmcb_save_area *from_save) +{ + to_save->es = from_save->es; + to_save->cs = from_save->cs; + to_save->ss = from_save->ss; + to_save->ds = from_save->ds; + to_save->gdtr = from_save->gdtr; + to_save->idtr = from_save->idtr; + to_save->rflags = from_save->rflags | X86_EFLAGS_FIXED; + to_save->efer = from_save->efer; + to_save->cr0 = from_save->cr0; + to_save->cr3 = from_save->cr3; + to_save->cr4 = from_save->cr4; + to_save->rax = from_save->rax; + to_save->rsp = from_save->rsp; + to_save->rip = from_save->rip; + to_save->cpl = 0; +} + +void svm_copy_vmloadsave_state(struct vmcb *to_vmcb, struct vmcb *from_vmcb) { to_vmcb->save.fs = from_vmcb->save.fs; to_vmcb->save.gs = from_vmcb->save.gs; @@ -1355,28 +1387,11 @@ static int svm_set_nested_state(struct kvm_vcpu *vcpu, svm->nested.vmcb12_gpa = kvm_state->hdr.svm.vmcb_pa; - svm->vmcb01.ptr->save.es = save->es; - svm->vmcb01.ptr->save.cs = save->cs; - svm->vmcb01.ptr->save.ss = save->ss; - svm->vmcb01.ptr->save.ds = save->ds; - svm->vmcb01.ptr->save.gdtr = save->gdtr; - svm->vmcb01.ptr->save.idtr = save->idtr; - svm->vmcb01.ptr->save.rflags = save->rflags | X86_EFLAGS_FIXED; - svm->vmcb01.ptr->save.efer = save->efer; - svm->vmcb01.ptr->save.cr0 = save->cr0; - svm->vmcb01.ptr->save.cr3 = save->cr3; - svm->vmcb01.ptr->save.cr4 = save->cr4; - svm->vmcb01.ptr->save.rax = save->rax; - svm->vmcb01.ptr->save.rsp = save->rsp; - svm->vmcb01.ptr->save.rip = save->rip; - svm->vmcb01.ptr->save.cpl = 0; - + svm_copy_vmrun_state(&svm->vmcb01.ptr->save, save); nested_load_control_from_vmcb12(svm, ctl); svm_switch_vmcb(svm, &svm->nested.vmcb02); - nested_vmcb02_prepare_control(svm); - kvm_make_request(KVM_REQ_GET_NESTED_STATE_PAGES, vcpu); ret = 0; out_free: diff --git a/arch/x86/kvm/svm/sev.c b/arch/x86/kvm/svm/sev.c index 62926f1a5f7b..75e0b21ad07c 100644 --- a/arch/x86/kvm/svm/sev.c +++ b/arch/x86/kvm/svm/sev.c @@ -28,8 +28,6 @@ #include "cpuid.h" #include "trace.h" -#define __ex(x) __kvm_handle_fault_on_reboot(x) - #ifndef CONFIG_KVM_AMD_SEV /* * When this config is not defined, SEV feature is not supported and APIs in @@ -64,6 +62,7 @@ static DEFINE_MUTEX(sev_bitmap_lock); unsigned int max_sev_asid; static unsigned int min_sev_asid; static unsigned long sev_me_mask; +static unsigned int nr_asids; static unsigned long *sev_asid_bitmap; static unsigned long *sev_reclaim_asid_bitmap; @@ -78,11 +77,11 @@ struct enc_region { /* Called with the sev_bitmap_lock held, or on shutdown */ static int sev_flush_asids(int min_asid, int max_asid) { - int ret, pos, error = 0; + int ret, asid, error = 0; /* Check if there are any ASIDs to reclaim before performing a flush */ - pos = find_next_bit(sev_reclaim_asid_bitmap, max_asid, min_asid); - if (pos >= max_asid) + asid = find_next_bit(sev_reclaim_asid_bitmap, nr_asids, min_asid); + if (asid > max_asid) return -EBUSY; /* @@ -115,15 +114,15 @@ static bool __sev_recycle_asids(int min_asid, int max_asid) /* The flush process will flush all reclaimable SEV and SEV-ES ASIDs */ bitmap_xor(sev_asid_bitmap, sev_asid_bitmap, sev_reclaim_asid_bitmap, - max_sev_asid); - bitmap_zero(sev_reclaim_asid_bitmap, max_sev_asid); + nr_asids); + bitmap_zero(sev_reclaim_asid_bitmap, nr_asids); return true; } static int sev_asid_new(struct kvm_sev_info *sev) { - int pos, min_asid, max_asid, ret; + int asid, min_asid, max_asid, ret; bool retry = true; enum misc_res_type type; @@ -143,11 +142,11 @@ static int sev_asid_new(struct kvm_sev_info *sev) * SEV-enabled guests must use asid from min_sev_asid to max_sev_asid. * SEV-ES-enabled guest can use from 1 to min_sev_asid - 1. */ - min_asid = sev->es_active ? 0 : min_sev_asid - 1; + min_asid = sev->es_active ? 1 : min_sev_asid; max_asid = sev->es_active ? min_sev_asid - 1 : max_sev_asid; again: - pos = find_next_zero_bit(sev_asid_bitmap, max_sev_asid, min_asid); - if (pos >= max_asid) { + asid = find_next_zero_bit(sev_asid_bitmap, max_asid + 1, min_asid); + if (asid > max_asid) { if (retry && __sev_recycle_asids(min_asid, max_asid)) { retry = false; goto again; @@ -157,11 +156,11 @@ again: goto e_uncharge; } - __set_bit(pos, sev_asid_bitmap); + __set_bit(asid, sev_asid_bitmap); mutex_unlock(&sev_bitmap_lock); - return pos + 1; + return asid; e_uncharge: misc_cg_uncharge(type, sev->misc_cg, 1); put_misc_cg(sev->misc_cg); @@ -179,17 +178,16 @@ static int sev_get_asid(struct kvm *kvm) static void sev_asid_free(struct kvm_sev_info *sev) { struct svm_cpu_data *sd; - int cpu, pos; + int cpu; enum misc_res_type type; mutex_lock(&sev_bitmap_lock); - pos = sev->asid - 1; - __set_bit(pos, sev_reclaim_asid_bitmap); + __set_bit(sev->asid, sev_reclaim_asid_bitmap); for_each_possible_cpu(cpu) { sd = per_cpu(svm_data, cpu); - sd->sev_vmcbs[pos] = NULL; + sd->sev_vmcbs[sev->asid] = NULL; } mutex_unlock(&sev_bitmap_lock); @@ -584,6 +582,7 @@ static int sev_es_sync_vmsa(struct vcpu_svm *svm) save->xcr0 = svm->vcpu.arch.xcr0; save->pkru = svm->vcpu.arch.pkru; save->xss = svm->vcpu.arch.ia32_xss; + save->dr6 = svm->vcpu.arch.dr6; /* * SEV-ES will use a VMSA that is pointed to by the VMCB, not @@ -1272,8 +1271,8 @@ static int sev_send_update_data(struct kvm *kvm, struct kvm_sev_cmd *argp) /* Pin guest memory */ guest_page = sev_pin_memory(kvm, params.guest_uaddr & PAGE_MASK, PAGE_SIZE, &n, 0); - if (!guest_page) - return -EFAULT; + if (IS_ERR(guest_page)) + return PTR_ERR(guest_page); /* allocate memory for header and transport buffer */ ret = -ENOMEM; @@ -1310,8 +1309,9 @@ static int sev_send_update_data(struct kvm *kvm, struct kvm_sev_cmd *argp) } /* Copy packet header to userspace. */ - ret = copy_to_user((void __user *)(uintptr_t)params.hdr_uaddr, hdr, - params.hdr_len); + if (copy_to_user((void __user *)(uintptr_t)params.hdr_uaddr, hdr, + params.hdr_len)) + ret = -EFAULT; e_free_trans_data: kfree(trans_data); @@ -1463,11 +1463,12 @@ static int sev_receive_update_data(struct kvm *kvm, struct kvm_sev_cmd *argp) data.trans_len = params.trans_len; /* Pin guest memory */ - ret = -EFAULT; guest_page = sev_pin_memory(kvm, params.guest_uaddr & PAGE_MASK, PAGE_SIZE, &n, 0); - if (!guest_page) + if (IS_ERR(guest_page)) { + ret = PTR_ERR(guest_page); goto e_free_trans; + } /* The RECEIVE_UPDATE_DATA command requires C-bit to be always set. */ data.guest_address = (page_to_pfn(guest_page[0]) << PAGE_SHIFT) + offset; @@ -1855,12 +1856,17 @@ void __init sev_hardware_setup(void) min_sev_asid = edx; sev_me_mask = 1UL << (ebx & 0x3f); - /* Initialize SEV ASID bitmaps */ - sev_asid_bitmap = bitmap_zalloc(max_sev_asid, GFP_KERNEL); + /* + * Initialize SEV ASID bitmaps. Allocate space for ASID 0 in the bitmap, + * even though it's never used, so that the bitmap is indexed by the + * actual ASID. + */ + nr_asids = max_sev_asid + 1; + sev_asid_bitmap = bitmap_zalloc(nr_asids, GFP_KERNEL); if (!sev_asid_bitmap) goto out; - sev_reclaim_asid_bitmap = bitmap_zalloc(max_sev_asid, GFP_KERNEL); + sev_reclaim_asid_bitmap = bitmap_zalloc(nr_asids, GFP_KERNEL); if (!sev_reclaim_asid_bitmap) { bitmap_free(sev_asid_bitmap); sev_asid_bitmap = NULL; @@ -1905,7 +1911,7 @@ void sev_hardware_teardown(void) return; /* No need to take sev_bitmap_lock, all VMs have been destroyed. */ - sev_flush_asids(0, max_sev_asid); + sev_flush_asids(1, max_sev_asid); bitmap_free(sev_asid_bitmap); bitmap_free(sev_reclaim_asid_bitmap); @@ -1919,7 +1925,7 @@ int sev_cpu_init(struct svm_cpu_data *sd) if (!sev_enabled) return 0; - sd->sev_vmcbs = kcalloc(max_sev_asid + 1, sizeof(void *), GFP_KERNEL); + sd->sev_vmcbs = kcalloc(nr_asids, sizeof(void *), GFP_KERNEL); if (!sd->sev_vmcbs) return -ENOMEM; diff --git a/arch/x86/kvm/svm/svm.c b/arch/x86/kvm/svm/svm.c index 8834822c00cd..05e8d4d27969 100644 --- a/arch/x86/kvm/svm/svm.c +++ b/arch/x86/kvm/svm/svm.c @@ -46,8 +46,6 @@ #include "kvm_onhyperv.h" #include "svm_onhyperv.h" -#define __ex(x) __kvm_handle_fault_on_reboot(x) - MODULE_AUTHOR("Qumranet"); MODULE_LICENSE("GPL"); @@ -198,6 +196,11 @@ module_param(avic, bool, 0444); bool __read_mostly dump_invalid_vmcb; module_param(dump_invalid_vmcb, bool, 0644); + +bool intercept_smi = true; +module_param(intercept_smi, bool, 0444); + + static bool svm_gp_erratum_intercept = true; static u8 rsm_ins_bytes[] = "\x0f\xaa"; @@ -256,7 +259,7 @@ u32 svm_msrpm_offset(u32 msr) static int get_max_npt_level(void) { #ifdef CONFIG_X86_64 - return PT64_ROOT_4LEVEL; + return pgtable_l5_enabled() ? PT64_ROOT_5LEVEL : PT64_ROOT_4LEVEL; #else return PT32E_ROOT_LEVEL; #endif @@ -457,11 +460,6 @@ static int has_svm(void) return 0; } - if (pgtable_l5_enabled()) { - pr_info("KVM doesn't yet support 5-level paging on AMD SVM\n"); - return 0; - } - return 1; } @@ -1010,7 +1008,9 @@ static __init int svm_hardware_setup(void) if (!boot_cpu_has(X86_FEATURE_NPT)) npt_enabled = false; - kvm_configure_mmu(npt_enabled, get_max_npt_level(), PG_LEVEL_1G); + /* Force VM NPT level equal to the host's max NPT level */ + kvm_configure_mmu(npt_enabled, get_max_npt_level(), + get_max_npt_level(), PG_LEVEL_1G); pr_info("kvm: Nested Paging %sabled\n", npt_enabled ? "en" : "dis"); /* Note, SEV setup consumes npt_enabled. */ @@ -1156,8 +1156,6 @@ static void init_vmcb(struct kvm_vcpu *vcpu) struct vmcb_control_area *control = &svm->vmcb->control; struct vmcb_save_area *save = &svm->vmcb->save; - vcpu->arch.hflags = 0; - svm_set_intercept(svm, INTERCEPT_CR0_READ); svm_set_intercept(svm, INTERCEPT_CR3_READ); svm_set_intercept(svm, INTERCEPT_CR4_READ); @@ -1185,7 +1183,10 @@ static void init_vmcb(struct kvm_vcpu *vcpu) svm_set_intercept(svm, INTERCEPT_INTR); svm_set_intercept(svm, INTERCEPT_NMI); - svm_set_intercept(svm, INTERCEPT_SMI); + + if (intercept_smi) + svm_set_intercept(svm, INTERCEPT_SMI); + svm_set_intercept(svm, INTERCEPT_SELECTIVE_CR0); svm_set_intercept(svm, INTERCEPT_RDPMC); svm_set_intercept(svm, INTERCEPT_CPUID); @@ -1233,29 +1234,14 @@ static void init_vmcb(struct kvm_vcpu *vcpu) SVM_SELECTOR_S_MASK | SVM_SELECTOR_CODE_MASK; save->cs.limit = 0xffff; + save->gdtr.base = 0; save->gdtr.limit = 0xffff; + save->idtr.base = 0; save->idtr.limit = 0xffff; init_sys_seg(&save->ldtr, SEG_TYPE_LDT); init_sys_seg(&save->tr, SEG_TYPE_BUSY_TSS16); - svm_set_cr4(vcpu, 0); - svm_set_efer(vcpu, 0); - save->dr6 = 0xffff0ff0; - kvm_set_rflags(vcpu, X86_EFLAGS_FIXED); - save->rip = 0x0000fff0; - vcpu->arch.regs[VCPU_REGS_RIP] = save->rip; - - /* - * svm_set_cr0() sets PG and WP and clears NW and CD on save->cr0. - * It also updates the guest-visible cr0 value. - */ - svm_set_cr0(vcpu, X86_CR0_NW | X86_CR0_CD | X86_CR0_ET); - kvm_mmu_reset_context(vcpu); - - save->cr4 = X86_CR4_PAE; - /* rdx = ?? */ - if (npt_enabled) { /* Setup VMCB for Nested Paging */ control->nested_ctl |= SVM_NESTED_CTL_NP_ENABLE; @@ -1265,14 +1251,12 @@ static void init_vmcb(struct kvm_vcpu *vcpu) svm_clr_intercept(svm, INTERCEPT_CR3_WRITE); save->g_pat = vcpu->arch.pat; save->cr3 = 0; - save->cr4 = 0; } svm->current_vmcb->asid_generation = 0; svm->asid = 0; svm->nested.vmcb12_gpa = INVALID_GPA; svm->nested.last_vmcb12_gpa = INVALID_GPA; - vcpu->arch.hflags = 0; if (!kvm_pause_in_guest(vcpu->kvm)) { control->pause_filter_count = pause_filter_count; @@ -1322,25 +1306,11 @@ static void init_vmcb(struct kvm_vcpu *vcpu) static void svm_vcpu_reset(struct kvm_vcpu *vcpu, bool init_event) { struct vcpu_svm *svm = to_svm(vcpu); - u32 dummy; - u32 eax = 1; svm->spec_ctrl = 0; svm->virt_spec_ctrl = 0; - if (!init_event) { - vcpu->arch.apic_base = APIC_DEFAULT_PHYS_BASE | - MSR_IA32_APICBASE_ENABLE; - if (kvm_vcpu_is_reset_bsp(vcpu)) - vcpu->arch.apic_base |= MSR_IA32_APICBASE_BSP; - } init_vmcb(vcpu); - - kvm_cpuid(vcpu, &eax, &dummy, &dummy, &dummy, false); - kvm_rdx_write(vcpu, eax); - - if (kvm_vcpu_apicv_active(vcpu) && !init_event) - avic_update_vapic_bar(svm, APIC_DEFAULT_PHYS_BASE); } void svm_switch_vmcb(struct vcpu_svm *svm, struct kvm_vmcb_info *target_vmcb) @@ -1398,8 +1368,6 @@ static int svm_create_vcpu(struct kvm_vcpu *vcpu) goto error_free_vmsa_page; } - svm_vcpu_init_msrpm(vcpu, svm->msrpm); - svm->vmcb01.ptr = page_address(vmcb01_page); svm->vmcb01.pa = __sme_set(page_to_pfn(vmcb01_page) << PAGE_SHIFT); @@ -1411,6 +1379,8 @@ static int svm_create_vcpu(struct kvm_vcpu *vcpu) svm_switch_vmcb(svm, &svm->vmcb01); init_vmcb(vcpu); + svm_vcpu_init_msrpm(vcpu, svm->msrpm); + svm_init_osvw(vcpu); vcpu->arch.microcode_version = 0x01000065; @@ -1505,12 +1475,15 @@ static void svm_vcpu_load(struct kvm_vcpu *vcpu, int cpu) sd->current_vmcb = svm->vmcb; indirect_branch_prediction_barrier(); } - avic_vcpu_load(vcpu, cpu); + if (kvm_vcpu_apicv_active(vcpu)) + avic_vcpu_load(vcpu, cpu); } static void svm_vcpu_put(struct kvm_vcpu *vcpu) { - avic_vcpu_put(vcpu); + if (kvm_vcpu_apicv_active(vcpu)) + avic_vcpu_put(vcpu); + svm_prepare_host_switch(vcpu); ++vcpu->stat.host_state_reload; @@ -1552,7 +1525,7 @@ static void svm_cache_reg(struct kvm_vcpu *vcpu, enum kvm_reg reg) load_pdptrs(vcpu, vcpu->arch.walk_mmu, kvm_read_cr3(vcpu)); break; default: - WARN_ON_ONCE(1); + KVM_BUG_ON(1, vcpu->kvm); } } @@ -1560,8 +1533,11 @@ static void svm_set_vintr(struct vcpu_svm *svm) { struct vmcb_control_area *control; - /* The following fields are ignored when AVIC is enabled */ - WARN_ON(kvm_vcpu_apicv_active(&svm->vcpu)); + /* + * The following fields are ignored when AVIC is enabled + */ + WARN_ON(kvm_apicv_activated(svm->vcpu.kvm)); + svm_set_intercept(svm, INTERCEPT_VINTR); /* @@ -1578,17 +1554,18 @@ static void svm_set_vintr(struct vcpu_svm *svm) static void svm_clear_vintr(struct vcpu_svm *svm) { - const u32 mask = V_TPR_MASK | V_GIF_ENABLE_MASK | V_GIF_MASK | V_INTR_MASKING_MASK; svm_clr_intercept(svm, INTERCEPT_VINTR); /* Drop int_ctl fields related to VINTR injection. */ - svm->vmcb->control.int_ctl &= mask; + svm->vmcb->control.int_ctl &= ~V_IRQ_INJECTION_BITS_MASK; if (is_guest_mode(&svm->vcpu)) { - svm->vmcb01.ptr->control.int_ctl &= mask; + svm->vmcb01.ptr->control.int_ctl &= ~V_IRQ_INJECTION_BITS_MASK; WARN_ON((svm->vmcb->control.int_ctl & V_TPR_MASK) != (svm->nested.ctl.int_ctl & V_TPR_MASK)); - svm->vmcb->control.int_ctl |= svm->nested.ctl.int_ctl & ~mask; + + svm->vmcb->control.int_ctl |= svm->nested.ctl.int_ctl & + V_IRQ_INJECTION_BITS_MASK; } vmcb_mark_dirty(svm->vmcb, VMCB_INTR); @@ -1923,7 +1900,7 @@ static int npf_interception(struct kvm_vcpu *vcpu) { struct vcpu_svm *svm = to_svm(vcpu); - u64 fault_address = __sme_clr(svm->vmcb->control.exit_info_2); + u64 fault_address = svm->vmcb->control.exit_info_2; u64 error_code = svm->vmcb->control.exit_info_1; trace_kvm_page_fault(fault_address, error_code); @@ -2066,11 +2043,15 @@ static int shutdown_interception(struct kvm_vcpu *vcpu) return -EINVAL; /* - * VMCB is undefined after a SHUTDOWN intercept - * so reinitialize it. + * VMCB is undefined after a SHUTDOWN intercept. INIT the vCPU to put + * the VMCB in a known good state. Unfortuately, KVM doesn't have + * KVM_MP_STATE_SHUTDOWN and can't add it without potentially breaking + * userspace. At a platform view, INIT is acceptable behavior as + * there exist bare metal platforms that automatically INIT the CPU + * in response to shutdown. */ clear_page(svm->vmcb); - init_vmcb(vcpu); + kvm_vcpu_reset(vcpu, true); kvm_run->exit_reason = KVM_EXIT_SHUTDOWN; return 0; @@ -2106,6 +2087,11 @@ static int nmi_interception(struct kvm_vcpu *vcpu) return 1; } +static int smi_interception(struct kvm_vcpu *vcpu) +{ + return 1; +} + static int intr_interception(struct kvm_vcpu *vcpu) { ++vcpu->stat.irq_exits; @@ -2134,11 +2120,12 @@ static int vmload_vmsave_interception(struct kvm_vcpu *vcpu, bool vmload) ret = kvm_skip_emulated_instruction(vcpu); if (vmload) { - nested_svm_vmloadsave(vmcb12, svm->vmcb); + svm_copy_vmloadsave_state(svm->vmcb, vmcb12); svm->sysenter_eip_hi = 0; svm->sysenter_esp_hi = 0; - } else - nested_svm_vmloadsave(svm->vmcb, vmcb12); + } else { + svm_copy_vmloadsave_state(vmcb12, svm->vmcb); + } kvm_vcpu_unmap(vcpu, &map, true); @@ -2941,7 +2928,16 @@ static int svm_set_msr(struct kvm_vcpu *vcpu, struct msr_data *msr) svm_disable_lbrv(vcpu); break; case MSR_VM_HSAVE_PA: - svm->nested.hsave_msr = data; + /* + * Old kernels did not validate the value written to + * MSR_VM_HSAVE_PA. Allow KVM_SET_MSR to set an invalid + * value to allow live migrating buggy or malicious guests + * originating from those kernels. + */ + if (!msr->host_initiated && !page_address_valid(vcpu, data)) + return 1; + + svm->nested.hsave_msr = data & PAGE_MASK; break; case MSR_VM_CR: return svm_set_vm_cr(vcpu, data); @@ -2966,10 +2962,6 @@ static int svm_set_msr(struct kvm_vcpu *vcpu, struct msr_data *msr) svm->msr_decfg = data; break; } - case MSR_IA32_APICBASE: - if (kvm_vcpu_apicv_active(vcpu)) - avic_update_vapic_bar(to_svm(vcpu), data); - fallthrough; default: return kvm_set_msr_common(vcpu, msr); } @@ -2994,7 +2986,7 @@ static int interrupt_window_interception(struct kvm_vcpu *vcpu) * In this case AVIC was temporarily disabled for * requesting the IRQ window and we have to re-enable it. */ - svm_toggle_avic_for_irq_window(vcpu, true); + kvm_request_apicv_update(vcpu->kvm, true, APICV_INHIBIT_REASON_IRQWIN); ++vcpu->stat.irq_window_exits; return 1; @@ -3080,8 +3072,7 @@ static int (*const svm_exit_handlers[])(struct kvm_vcpu *vcpu) = { [SVM_EXIT_EXCP_BASE + GP_VECTOR] = gp_interception, [SVM_EXIT_INTR] = intr_interception, [SVM_EXIT_NMI] = nmi_interception, - [SVM_EXIT_SMI] = kvm_emulate_as_nop, - [SVM_EXIT_INIT] = kvm_emulate_as_nop, + [SVM_EXIT_SMI] = smi_interception, [SVM_EXIT_VINTR] = interrupt_window_interception, [SVM_EXIT_RDPMC] = kvm_emulate_rdpmc, [SVM_EXIT_CPUID] = kvm_emulate_cpuid, @@ -3243,12 +3234,14 @@ static void dump_vmcb(struct kvm_vcpu *vcpu) "excp_to:", save->last_excp_to); } -static int svm_handle_invalid_exit(struct kvm_vcpu *vcpu, u64 exit_code) +static bool svm_check_exit_valid(struct kvm_vcpu *vcpu, u64 exit_code) { - if (exit_code < ARRAY_SIZE(svm_exit_handlers) && - svm_exit_handlers[exit_code]) - return 0; + return (exit_code < ARRAY_SIZE(svm_exit_handlers) && + svm_exit_handlers[exit_code]); +} +static int svm_handle_invalid_exit(struct kvm_vcpu *vcpu, u64 exit_code) +{ vcpu_unimpl(vcpu, "svm: unexpected exit reason 0x%llx\n", exit_code); dump_vmcb(vcpu); vcpu->run->exit_reason = KVM_EXIT_INTERNAL_ERROR; @@ -3256,14 +3249,13 @@ static int svm_handle_invalid_exit(struct kvm_vcpu *vcpu, u64 exit_code) vcpu->run->internal.ndata = 2; vcpu->run->internal.data[0] = exit_code; vcpu->run->internal.data[1] = vcpu->arch.last_vmentry_cpu; - - return -EINVAL; + return 0; } int svm_invoke_exit_handler(struct kvm_vcpu *vcpu, u64 exit_code) { - if (svm_handle_invalid_exit(vcpu, exit_code)) - return 0; + if (!svm_check_exit_valid(vcpu, exit_code)) + return svm_handle_invalid_exit(vcpu, exit_code); #ifdef CONFIG_RETPOLINE if (exit_code == SVM_EXIT_MSR) @@ -3547,7 +3539,7 @@ static void svm_enable_irq_window(struct kvm_vcpu *vcpu) * via AVIC. In such case, we need to temporarily disable AVIC, * and fallback to injecting IRQ via V_IRQ. */ - svm_toggle_avic_for_irq_window(vcpu, false); + kvm_request_apicv_update(vcpu->kvm, false, APICV_INHIBIT_REASON_IRQWIN); svm_set_vintr(svm); } } @@ -3782,6 +3774,8 @@ static __no_kcsan fastpath_t svm_vcpu_run(struct kvm_vcpu *vcpu) pre_svm_run(vcpu); + WARN_ON_ONCE(kvm_apicv_activated(vcpu->kvm) != kvm_vcpu_apicv_active(vcpu)); + sync_lapic_to_cr8(vcpu); if (unlikely(svm->asid != svm->vmcb->control.asid)) { @@ -4288,6 +4282,7 @@ static int svm_smi_allowed(struct kvm_vcpu *vcpu, bool for_injection) static int svm_enter_smm(struct kvm_vcpu *vcpu, char *smstate) { struct vcpu_svm *svm = to_svm(vcpu); + struct kvm_host_map map_save; int ret; if (is_guest_mode(vcpu)) { @@ -4303,6 +4298,29 @@ static int svm_enter_smm(struct kvm_vcpu *vcpu, char *smstate) ret = nested_svm_vmexit(svm); if (ret) return ret; + + /* + * KVM uses VMCB01 to store L1 host state while L2 runs but + * VMCB01 is going to be used during SMM and thus the state will + * be lost. Temporary save non-VMLOAD/VMSAVE state to the host save + * area pointed to by MSR_VM_HSAVE_PA. APM guarantees that the + * format of the area is identical to guest save area offsetted + * by 0x400 (matches the offset of 'struct vmcb_save_area' + * within 'struct vmcb'). Note: HSAVE area may also be used by + * L1 hypervisor to save additional host context (e.g. KVM does + * that, see svm_prepare_guest_switch()) which must be + * preserved. + */ + if (kvm_vcpu_map(vcpu, gpa_to_gfn(svm->nested.hsave_msr), + &map_save) == -EINVAL) + return 1; + + BUILD_BUG_ON(offsetof(struct vmcb, save) != 0x400); + + svm_copy_vmrun_state(map_save.hva + 0x400, + &svm->vmcb01.ptr->save); + + kvm_vcpu_unmap(vcpu, &map_save, true); } return 0; } @@ -4310,13 +4328,14 @@ static int svm_enter_smm(struct kvm_vcpu *vcpu, char *smstate) static int svm_leave_smm(struct kvm_vcpu *vcpu, const char *smstate) { struct vcpu_svm *svm = to_svm(vcpu); - struct kvm_host_map map; + struct kvm_host_map map, map_save; int ret = 0; if (guest_cpuid_has(vcpu, X86_FEATURE_LM)) { u64 saved_efer = GET_SMSTATE(u64, smstate, 0x7ed0); u64 guest = GET_SMSTATE(u64, smstate, 0x7ed8); u64 vmcb12_gpa = GET_SMSTATE(u64, smstate, 0x7ee0); + struct vmcb *vmcb12; if (guest) { if (!guest_cpuid_has(vcpu, X86_FEATURE_SVM)) @@ -4332,8 +4351,25 @@ static int svm_leave_smm(struct kvm_vcpu *vcpu, const char *smstate) if (svm_allocate_nested(svm)) return 1; - ret = enter_svm_guest_mode(vcpu, vmcb12_gpa, map.hva); + vmcb12 = map.hva; + + nested_load_control_from_vmcb12(svm, &vmcb12->control); + + ret = enter_svm_guest_mode(vcpu, vmcb12_gpa, vmcb12); kvm_vcpu_unmap(vcpu, &map, true); + + /* + * Restore L1 host state from L1 HSAVE area as VMCB01 was + * used during SMM (see svm_enter_smm()) + */ + if (kvm_vcpu_map(vcpu, gpa_to_gfn(svm->nested.hsave_msr), + &map_save) == -EINVAL) + return 1; + + svm_copy_vmrun_state(&svm->vmcb01.ptr->save, + map_save.hva + 0x400); + + kvm_vcpu_unmap(vcpu, &map_save, true); } } @@ -4542,7 +4578,6 @@ static struct kvm_x86_ops svm_x86_ops __initdata = { .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, - .pre_update_apicv_exec_ctrl = svm_pre_update_apicv_exec_ctrl, .load_eoi_exitmap = svm_load_eoi_exitmap, .hwapic_irr_update = svm_hwapic_irr_update, .hwapic_isr_update = svm_hwapic_isr_update, diff --git a/arch/x86/kvm/svm/svm.h b/arch/x86/kvm/svm/svm.h index f89b623bb591..524d943f3efc 100644 --- a/arch/x86/kvm/svm/svm.h +++ b/arch/x86/kvm/svm/svm.h @@ -31,6 +31,7 @@ #define MSRPM_OFFSETS 16 extern u32 msrpm_offsets[MSRPM_OFFSETS] __read_mostly; extern bool npt_enabled; +extern bool intercept_smi; /* * Clean bits in VMCB. @@ -463,7 +464,9 @@ void svm_leave_nested(struct vcpu_svm *svm); void svm_free_nested(struct vcpu_svm *svm); int svm_allocate_nested(struct vcpu_svm *svm); int nested_svm_vmrun(struct kvm_vcpu *vcpu); -void nested_svm_vmloadsave(struct vmcb *from_vmcb, struct vmcb *to_vmcb); +void svm_copy_vmrun_state(struct vmcb_save_area *to_save, + struct vmcb_save_area *from_save); +void svm_copy_vmloadsave_state(struct vmcb *to_vmcb, struct vmcb *from_vmcb); int nested_svm_vmexit(struct vcpu_svm *svm); static inline int nested_svm_simple_vmexit(struct vcpu_svm *svm, u32 exit_code) @@ -479,6 +482,8 @@ int nested_svm_check_permissions(struct kvm_vcpu *vcpu); int nested_svm_check_exception(struct vcpu_svm *svm, unsigned nr, bool has_error_code, u32 error_code); int nested_svm_exit_special(struct vcpu_svm *svm); +void nested_load_control_from_vmcb12(struct vcpu_svm *svm, + struct vmcb_control_area *control); void nested_sync_control_from_vmcb02(struct vcpu_svm *svm); void nested_vmcb02_compute_g_pat(struct vcpu_svm *svm); void svm_switch_vmcb(struct vcpu_svm *svm, struct kvm_vmcb_info *target_vmcb); @@ -498,12 +503,6 @@ extern struct kvm_x86_nested_ops svm_nested_ops; #define VMCB_AVIC_APIC_BAR_MASK 0xFFFFFFFFFF000ULL -static inline void avic_update_vapic_bar(struct vcpu_svm *svm, u64 data) -{ - svm->vmcb->control.avic_vapic_bar = data & VMCB_AVIC_APIC_BAR_MASK; - vmcb_mark_dirty(svm->vmcb, VMCB_AVIC); -} - static inline bool avic_vcpu_is_running(struct kvm_vcpu *vcpu) { struct vcpu_svm *svm = to_svm(vcpu); @@ -519,7 +518,6 @@ int avic_ga_log_notifier(u32 ga_tag); void avic_vm_destroy(struct kvm *kvm); int avic_vm_init(struct kvm *kvm); void avic_init_vmcb(struct vcpu_svm *svm); -void svm_toggle_avic_for_irq_window(struct kvm_vcpu *vcpu, bool activate); int avic_incomplete_ipi_interception(struct kvm_vcpu *vcpu); int avic_unaccelerated_access_interception(struct kvm_vcpu *vcpu); int avic_init_vcpu(struct vcpu_svm *svm); @@ -529,7 +527,6 @@ void avic_post_state_restore(struct kvm_vcpu *vcpu); void svm_set_virtual_apic_mode(struct kvm_vcpu *vcpu); void svm_refresh_apicv_exec_ctrl(struct kvm_vcpu *vcpu); bool svm_check_apicv_inhibit_reasons(ulong bit); -void svm_pre_update_apicv_exec_ctrl(struct kvm *kvm, bool activate); void svm_load_eoi_exitmap(struct kvm_vcpu *vcpu, u64 *eoi_exit_bitmap); void svm_hwapic_irr_update(struct kvm_vcpu *vcpu, int max_irr); void svm_hwapic_isr_update(struct kvm_vcpu *vcpu, int max_isr); diff --git a/arch/x86/kvm/svm/svm_onhyperv.h b/arch/x86/kvm/svm/svm_onhyperv.h index 9b9a55abc29f..c53b8bf8d013 100644 --- a/arch/x86/kvm/svm/svm_onhyperv.h +++ b/arch/x86/kvm/svm/svm_onhyperv.h @@ -89,7 +89,7 @@ static inline void svm_hv_vmcb_dirty_nested_enlightenments( * as we mark it dirty unconditionally towards end of vcpu * init phase. */ - if (vmcb && vmcb_is_clean(vmcb, VMCB_HV_NESTED_ENLIGHTENMENTS) && + if (vmcb_is_clean(vmcb, VMCB_HV_NESTED_ENLIGHTENMENTS) && hve->hv_enlightenments_control.msr_bitmap) vmcb_mark_dirty(vmcb, VMCB_HV_NESTED_ENLIGHTENMENTS); } diff --git a/arch/x86/kvm/svm/svm_ops.h b/arch/x86/kvm/svm/svm_ops.h index 8170f2a5a16f..22e2b019de37 100644 --- a/arch/x86/kvm/svm/svm_ops.h +++ b/arch/x86/kvm/svm/svm_ops.h @@ -4,7 +4,7 @@ #include <linux/compiler_types.h> -#include <asm/kvm_host.h> +#include "x86.h" #define svm_asm(insn, clobber...) \ do { \ diff --git a/arch/x86/kvm/trace.h b/arch/x86/kvm/trace.h index b484141ea15b..03ebe368333e 100644 --- a/arch/x86/kvm/trace.h +++ b/arch/x86/kvm/trace.h @@ -92,6 +92,21 @@ TRACE_EVENT(kvm_hv_hypercall, __entry->outgpa) ); +TRACE_EVENT(kvm_hv_hypercall_done, + TP_PROTO(u64 result), + TP_ARGS(result), + + TP_STRUCT__entry( + __field(__u64, result) + ), + + TP_fast_assign( + __entry->result = result; + ), + + TP_printk("result 0x%llx", __entry->result) +); + /* * Tracepoint for Xen hypercall. */ diff --git a/arch/x86/kvm/vmx/evmcs.c b/arch/x86/kvm/vmx/evmcs.c index 896b2a50b4aa..0dab1b7b529f 100644 --- a/arch/x86/kvm/vmx/evmcs.c +++ b/arch/x86/kvm/vmx/evmcs.c @@ -14,7 +14,6 @@ DEFINE_STATIC_KEY_FALSE(enable_evmcs); #if IS_ENABLED(CONFIG_HYPERV) -#define ROL16(val, n) ((u16)(((u16)(val) << (n)) | ((u16)(val) >> (16 - (n))))) #define EVMCS1_OFFSET(x) offsetof(struct hv_enlightened_vmcs, x) #define EVMCS1_FIELD(number, name, clean_field)[ROL16(number, 6)] = \ {EVMCS1_OFFSET(name), clean_field} diff --git a/arch/x86/kvm/vmx/evmcs.h b/arch/x86/kvm/vmx/evmcs.h index 2ec9b46f0d0c..152ab0aa82cf 100644 --- a/arch/x86/kvm/vmx/evmcs.h +++ b/arch/x86/kvm/vmx/evmcs.h @@ -73,8 +73,6 @@ struct evmcs_field { extern const struct evmcs_field vmcs_field_to_evmcs_1[]; extern const unsigned int nr_evmcs_1_fields; -#define ROL16(val, n) ((u16)(((u16)(val) << (n)) | ((u16)(val) >> (16 - (n))))) - static __always_inline int get_evmcs_offset(unsigned long field, u16 *clean_field) { @@ -95,8 +93,6 @@ static __always_inline int get_evmcs_offset(unsigned long field, return evmcs_field->offset; } -#undef ROL16 - static inline void evmcs_write64(unsigned long field, u64 value) { u16 clean_field; diff --git a/arch/x86/kvm/vmx/nested.c b/arch/x86/kvm/vmx/nested.c index 1a52134b0c42..ccb03d69546c 100644 --- a/arch/x86/kvm/vmx/nested.c +++ b/arch/x86/kvm/vmx/nested.c @@ -330,6 +330,31 @@ void nested_vmx_free_vcpu(struct kvm_vcpu *vcpu) vcpu_put(vcpu); } +#define EPTP_PA_MASK GENMASK_ULL(51, 12) + +static bool nested_ept_root_matches(hpa_t root_hpa, u64 root_eptp, u64 eptp) +{ + return VALID_PAGE(root_hpa) && + ((root_eptp & EPTP_PA_MASK) == (eptp & EPTP_PA_MASK)); +} + +static void nested_ept_invalidate_addr(struct kvm_vcpu *vcpu, gpa_t eptp, + gpa_t addr) +{ + uint i; + struct kvm_mmu_root_info *cached_root; + + WARN_ON_ONCE(!mmu_is_nested(vcpu)); + + for (i = 0; i < KVM_MMU_NUM_PREV_ROOTS; i++) { + cached_root = &vcpu->arch.mmu->prev_roots[i]; + + if (nested_ept_root_matches(cached_root->hpa, cached_root->pgd, + eptp)) + vcpu->arch.mmu->invlpg(vcpu, addr, cached_root->hpa); + } +} + static void nested_ept_inject_page_fault(struct kvm_vcpu *vcpu, struct x86_exception *fault) { @@ -342,10 +367,22 @@ static void nested_ept_inject_page_fault(struct kvm_vcpu *vcpu, vm_exit_reason = EXIT_REASON_PML_FULL; vmx->nested.pml_full = false; exit_qualification &= INTR_INFO_UNBLOCK_NMI; - } else if (fault->error_code & PFERR_RSVD_MASK) - vm_exit_reason = EXIT_REASON_EPT_MISCONFIG; - else - vm_exit_reason = EXIT_REASON_EPT_VIOLATION; + } else { + if (fault->error_code & PFERR_RSVD_MASK) + vm_exit_reason = EXIT_REASON_EPT_MISCONFIG; + else + vm_exit_reason = EXIT_REASON_EPT_VIOLATION; + + /* + * Although the caller (kvm_inject_emulated_page_fault) would + * have already synced the faulting address in the shadow EPT + * tables for the current EPTP12, we also need to sync it for + * any other cached EPTP02s based on the same EP4TA, since the + * TLB associates mappings to the EP4TA rather than the full EPTP. + */ + nested_ept_invalidate_addr(vcpu, vmcs12->ept_pointer, + fault->address); + } nested_vmx_vmexit(vcpu, vm_exit_reason, 0, exit_qualification); vmcs12->guest_physical_address = fault->address; @@ -2170,7 +2207,8 @@ static void prepare_vmcs02_early_rare(struct vcpu_vmx *vmx, } } -static void prepare_vmcs02_early(struct vcpu_vmx *vmx, struct vmcs12 *vmcs12) +static void prepare_vmcs02_early(struct vcpu_vmx *vmx, struct loaded_vmcs *vmcs01, + struct vmcs12 *vmcs12) { u32 exec_control; u64 guest_efer = nested_vmx_calc_efer(vmx, vmcs12); @@ -2181,23 +2219,22 @@ static void prepare_vmcs02_early(struct vcpu_vmx *vmx, struct vmcs12 *vmcs12) /* * PIN CONTROLS */ - exec_control = vmx_pin_based_exec_ctrl(vmx); + exec_control = __pin_controls_get(vmcs01); exec_control |= (vmcs12->pin_based_vm_exec_control & ~PIN_BASED_VMX_PREEMPTION_TIMER); /* Posted interrupts setting is only taken from vmcs12. */ - if (nested_cpu_has_posted_intr(vmcs12)) { + vmx->nested.pi_pending = false; + if (nested_cpu_has_posted_intr(vmcs12)) vmx->nested.posted_intr_nv = vmcs12->posted_intr_nv; - vmx->nested.pi_pending = false; - } else { + else exec_control &= ~PIN_BASED_POSTED_INTR; - } pin_controls_set(vmx, exec_control); /* * EXEC CONTROLS */ - exec_control = vmx_exec_control(vmx); /* L0's desires */ + exec_control = __exec_controls_get(vmcs01); /* L0's desires */ exec_control &= ~CPU_BASED_INTR_WINDOW_EXITING; exec_control &= ~CPU_BASED_NMI_WINDOW_EXITING; exec_control &= ~CPU_BASED_TPR_SHADOW; @@ -2234,10 +2271,11 @@ static void prepare_vmcs02_early(struct vcpu_vmx *vmx, struct vmcs12 *vmcs12) * SECONDARY EXEC CONTROLS */ if (cpu_has_secondary_exec_ctrls()) { - exec_control = vmx->secondary_exec_control; + exec_control = __secondary_exec_controls_get(vmcs01); /* Take the following fields only from vmcs12 */ exec_control &= ~(SECONDARY_EXEC_VIRTUALIZE_APIC_ACCESSES | + SECONDARY_EXEC_VIRTUALIZE_X2APIC_MODE | SECONDARY_EXEC_ENABLE_INVPCID | SECONDARY_EXEC_ENABLE_RDTSCP | SECONDARY_EXEC_XSAVES | @@ -2245,7 +2283,9 @@ static void prepare_vmcs02_early(struct vcpu_vmx *vmx, struct vmcs12 *vmcs12) SECONDARY_EXEC_VIRTUAL_INTR_DELIVERY | SECONDARY_EXEC_APIC_REGISTER_VIRT | SECONDARY_EXEC_ENABLE_VMFUNC | - SECONDARY_EXEC_TSC_SCALING); + SECONDARY_EXEC_TSC_SCALING | + SECONDARY_EXEC_DESC); + if (nested_cpu_has(vmcs12, CPU_BASED_ACTIVATE_SECONDARY_CONTROLS)) exec_control |= vmcs12->secondary_vm_exec_control; @@ -2285,8 +2325,9 @@ static void prepare_vmcs02_early(struct vcpu_vmx *vmx, struct vmcs12 *vmcs12) * on the related bits (if supported by the CPU) in the hope that * we can avoid VMWrites during vmx_set_efer(). */ - exec_control = (vmcs12->vm_entry_controls | vmx_vmentry_ctrl()) & - ~VM_ENTRY_IA32E_MODE & ~VM_ENTRY_LOAD_IA32_EFER; + exec_control = __vm_entry_controls_get(vmcs01); + exec_control |= vmcs12->vm_entry_controls; + exec_control &= ~(VM_ENTRY_IA32E_MODE | VM_ENTRY_LOAD_IA32_EFER); if (cpu_has_load_ia32_efer()) { if (guest_efer & EFER_LMA) exec_control |= VM_ENTRY_IA32E_MODE; @@ -2302,9 +2343,11 @@ static void prepare_vmcs02_early(struct vcpu_vmx *vmx, struct vmcs12 *vmcs12) * we should use its exit controls. Note that VM_EXIT_LOAD_IA32_EFER * bits may be modified by vmx_set_efer() in prepare_vmcs02(). */ - exec_control = vmx_vmexit_ctrl(); + exec_control = __vm_exit_controls_get(vmcs01); if (cpu_has_load_ia32_efer() && guest_efer != host_efer) exec_control |= VM_EXIT_LOAD_IA32_EFER; + else + exec_control &= ~VM_EXIT_LOAD_IA32_EFER; vm_exit_controls_set(vmx, exec_control); /* @@ -3347,7 +3390,7 @@ enum nvmx_vmentry_status nested_vmx_enter_non_root_mode(struct kvm_vcpu *vcpu, vmx_switch_vmcs(vcpu, &vmx->nested.vmcs02); - prepare_vmcs02_early(vmx, vmcs12); + prepare_vmcs02_early(vmx, &vmx->vmcs01, vmcs12); if (from_vmentry) { if (unlikely(!nested_get_vmcs12_pages(vcpu))) { @@ -4267,7 +4310,7 @@ static void load_vmcs12_host_state(struct kvm_vcpu *vcpu, seg.l = 1; else seg.db = 1; - vmx_set_segment(vcpu, &seg, VCPU_SREG_CS); + __vmx_set_segment(vcpu, &seg, VCPU_SREG_CS); seg = (struct kvm_segment) { .base = 0, .limit = 0xFFFFFFFF, @@ -4278,17 +4321,17 @@ static void load_vmcs12_host_state(struct kvm_vcpu *vcpu, .g = 1 }; seg.selector = vmcs12->host_ds_selector; - vmx_set_segment(vcpu, &seg, VCPU_SREG_DS); + __vmx_set_segment(vcpu, &seg, VCPU_SREG_DS); seg.selector = vmcs12->host_es_selector; - vmx_set_segment(vcpu, &seg, VCPU_SREG_ES); + __vmx_set_segment(vcpu, &seg, VCPU_SREG_ES); seg.selector = vmcs12->host_ss_selector; - vmx_set_segment(vcpu, &seg, VCPU_SREG_SS); + __vmx_set_segment(vcpu, &seg, VCPU_SREG_SS); seg.selector = vmcs12->host_fs_selector; seg.base = vmcs12->host_fs_base; - vmx_set_segment(vcpu, &seg, VCPU_SREG_FS); + __vmx_set_segment(vcpu, &seg, VCPU_SREG_FS); seg.selector = vmcs12->host_gs_selector; seg.base = vmcs12->host_gs_base; - vmx_set_segment(vcpu, &seg, VCPU_SREG_GS); + __vmx_set_segment(vcpu, &seg, VCPU_SREG_GS); seg = (struct kvm_segment) { .base = vmcs12->host_tr_base, .limit = 0x67, @@ -4296,14 +4339,15 @@ static void load_vmcs12_host_state(struct kvm_vcpu *vcpu, .type = 11, .present = 1 }; - vmx_set_segment(vcpu, &seg, VCPU_SREG_TR); + __vmx_set_segment(vcpu, &seg, VCPU_SREG_TR); + + memset(&seg, 0, sizeof(seg)); + seg.unusable = 1; + __vmx_set_segment(vcpu, &seg, VCPU_SREG_LDTR); kvm_set_dr(vcpu, 7, 0x400); vmcs_write64(GUEST_IA32_DEBUGCTL, 0); - if (cpu_has_vmx_msr_bitmap()) - vmx_update_msr_bitmap(vcpu); - if (nested_vmx_load_msr(vcpu, vmcs12->vm_exit_msr_load_addr, vmcs12->vm_exit_msr_load_count)) nested_vmx_abort(vcpu, VMX_ABORT_LOAD_HOST_MSR_FAIL); @@ -4382,9 +4426,6 @@ static void nested_vmx_restore_host_state(struct kvm_vcpu *vcpu) kvm_mmu_reset_context(vcpu); - if (cpu_has_vmx_msr_bitmap()) - vmx_update_msr_bitmap(vcpu); - /* * This nasty bit of open coding is a compromise between blindly * loading L1's MSRs using the exit load lists (incorrect emulation @@ -5325,14 +5366,6 @@ static int handle_vmptrst(struct kvm_vcpu *vcpu) return nested_vmx_succeed(vcpu); } -#define EPTP_PA_MASK GENMASK_ULL(51, 12) - -static bool nested_ept_root_matches(hpa_t root_hpa, u64 root_eptp, u64 eptp) -{ - return VALID_PAGE(root_hpa) && - ((root_eptp & EPTP_PA_MASK) == (eptp & EPTP_PA_MASK)); -} - /* Emulate the INVEPT instruction */ static int handle_invept(struct kvm_vcpu *vcpu) { @@ -5826,7 +5859,8 @@ static bool nested_vmx_l0_wants_exit(struct kvm_vcpu *vcpu, if (is_nmi(intr_info)) return true; else if (is_page_fault(intr_info)) - return vcpu->arch.apf.host_apf_flags || !enable_ept; + return vcpu->arch.apf.host_apf_flags || + vmx_need_pf_intercept(vcpu); else if (is_debug(intr_info) && vcpu->guest_debug & (KVM_GUESTDBG_SINGLESTEP | KVM_GUESTDBG_USE_HW_BP)) diff --git a/arch/x86/kvm/vmx/pmu_intel.c b/arch/x86/kvm/vmx/pmu_intel.c index 9efc1a6b8693..10cc4f65c4ef 100644 --- a/arch/x86/kvm/vmx/pmu_intel.c +++ b/arch/x86/kvm/vmx/pmu_intel.c @@ -437,13 +437,13 @@ static int intel_pmu_set_msr(struct kvm_vcpu *vcpu, struct msr_data *msr_info) !(msr & MSR_PMC_FULL_WIDTH_BIT)) data = (s64)(s32)data; pmc->counter += data - pmc_read_counter(pmc); - if (pmc->perf_event) + if (pmc->perf_event && !pmc->is_paused) perf_event_period(pmc->perf_event, get_sample_period(pmc, data)); return 0; } else if ((pmc = get_fixed_pmc(pmu, msr))) { pmc->counter += data - pmc_read_counter(pmc); - if (pmc->perf_event) + if (pmc->perf_event && !pmc->is_paused) perf_event_period(pmc->perf_event, get_sample_period(pmc, data)); return 0; diff --git a/arch/x86/kvm/vmx/vmcs.h b/arch/x86/kvm/vmx/vmcs.h index 4b9957e2bf5b..6e5de2e2b0da 100644 --- a/arch/x86/kvm/vmx/vmcs.h +++ b/arch/x86/kvm/vmx/vmcs.h @@ -11,6 +11,8 @@ #include "capabilities.h" +#define ROL16(val, n) ((u16)(((u16)(val) << (n)) | ((u16)(val) >> (16 - (n))))) + struct vmcs_hdr { u32 revision_id:31; u32 shadow_vmcs:1; diff --git a/arch/x86/kvm/vmx/vmcs12.c b/arch/x86/kvm/vmx/vmcs12.c index d9f5d7c56ae3..cab6ba7a5005 100644 --- a/arch/x86/kvm/vmx/vmcs12.c +++ b/arch/x86/kvm/vmx/vmcs12.c @@ -2,7 +2,6 @@ #include "vmcs12.h" -#define ROL16(val, n) ((u16)(((u16)(val) << (n)) | ((u16)(val) >> (16 - (n))))) #define VMCS12_OFFSET(x) offsetof(struct vmcs12, x) #define FIELD(number, name) [ROL16(number, 6)] = VMCS12_OFFSET(name) #define FIELD64(number, name) \ diff --git a/arch/x86/kvm/vmx/vmcs12.h b/arch/x86/kvm/vmx/vmcs12.h index 5e0e1b39f495..2a45f026ee11 100644 --- a/arch/x86/kvm/vmx/vmcs12.h +++ b/arch/x86/kvm/vmx/vmcs12.h @@ -364,8 +364,6 @@ static inline void vmx_check_vmcs12_offsets(void) extern const unsigned short vmcs_field_to_offset_table[]; extern const unsigned int nr_vmcs12_fields; -#define ROL16(val, n) ((u16)(((u16)(val) << (n)) | ((u16)(val) >> (16 - (n))))) - static inline short vmcs_field_to_offset(unsigned long field) { unsigned short offset; @@ -385,8 +383,6 @@ static inline short vmcs_field_to_offset(unsigned long field) return offset; } -#undef ROL16 - static inline u64 vmcs12_read_any(struct vmcs12 *vmcs12, unsigned long field, u16 offset) { diff --git a/arch/x86/kvm/vmx/vmx.c b/arch/x86/kvm/vmx/vmx.c index 927a552393b9..0c2c0d5ae873 100644 --- a/arch/x86/kvm/vmx/vmx.c +++ b/arch/x86/kvm/vmx/vmx.c @@ -136,8 +136,7 @@ module_param(allow_smaller_maxphyaddr, bool, S_IRUGO); #define KVM_VM_CR0_ALWAYS_OFF (X86_CR0_NW | X86_CR0_CD) #define KVM_VM_CR0_ALWAYS_ON_UNRESTRICTED_GUEST X86_CR0_NE #define KVM_VM_CR0_ALWAYS_ON \ - (KVM_VM_CR0_ALWAYS_ON_UNRESTRICTED_GUEST | \ - X86_CR0_WP | X86_CR0_PG | X86_CR0_PE) + (KVM_VM_CR0_ALWAYS_ON_UNRESTRICTED_GUEST | X86_CR0_PG | X86_CR0_PE) #define KVM_VM_CR4_ALWAYS_ON_UNRESTRICTED_GUEST X86_CR4_VMXE #define KVM_PMODE_VM_CR4_ALWAYS_ON (X86_CR4_PAE | X86_CR4_VMXE) @@ -1648,11 +1647,12 @@ static void vmx_setup_uret_msr(struct vcpu_vmx *vmx, unsigned int msr, } /* - * Set up the vmcs to automatically save and restore system - * msrs. Don't touch the 64-bit msrs if the guest is in legacy - * mode, as fiddling with msrs is very expensive. + * Configuring user return MSRs to automatically save, load, and restore MSRs + * that need to be shoved into hardware when running the guest. Note, omitting + * an MSR here does _NOT_ mean it's not emulated, only that it will not be + * loaded into hardware when running the guest. */ -static void setup_msrs(struct vcpu_vmx *vmx) +static void vmx_setup_uret_msrs(struct vcpu_vmx *vmx) { #ifdef CONFIG_X86_64 bool load_syscall_msrs; @@ -1682,9 +1682,6 @@ static void setup_msrs(struct vcpu_vmx *vmx) */ vmx_setup_uret_msr(vmx, MSR_IA32_TSX_CTRL, boot_cpu_has(X86_FEATURE_RTM)); - if (cpu_has_vmx_msr_bitmap()) - vmx_update_msr_bitmap(&vmx->vcpu); - /* * The set of MSRs to load may have changed, reload MSRs before the * next VM-Enter. @@ -2263,8 +2260,11 @@ static void vmx_cache_reg(struct kvm_vcpu *vcpu, enum kvm_reg reg) vcpu->arch.cr0 |= vmcs_readl(GUEST_CR0) & guest_owned_bits; break; case VCPU_EXREG_CR3: - if (is_unrestricted_guest(vcpu) || - (enable_ept && is_paging(vcpu))) + /* + * When intercepting CR3 loads, e.g. for shadowing paging, KVM's + * CR3 is loaded into hardware, not the guest's CR3. + */ + if (!(exec_controls_get(to_vmx(vcpu)) & CPU_BASED_CR3_LOAD_EXITING)) vcpu->arch.cr3 = vmcs_readl(GUEST_CR3); break; case VCPU_EXREG_CR4: @@ -2274,7 +2274,7 @@ static void vmx_cache_reg(struct kvm_vcpu *vcpu, enum kvm_reg reg) vcpu->arch.cr4 |= vmcs_readl(GUEST_CR4) & guest_owned_bits; break; default: - WARN_ON_ONCE(1); + KVM_BUG_ON(1, vcpu->kvm); break; } } @@ -2733,7 +2733,7 @@ static void fix_pmode_seg(struct kvm_vcpu *vcpu, int seg, save->dpl = save->selector & SEGMENT_RPL_MASK; save->s = 1; } - vmx_set_segment(vcpu, save, seg); + __vmx_set_segment(vcpu, save, seg); } static void enter_pmode(struct kvm_vcpu *vcpu) @@ -2754,7 +2754,7 @@ static void enter_pmode(struct kvm_vcpu *vcpu) vmx->rmode.vm86_active = 0; - vmx_set_segment(vcpu, &vmx->rmode.segs[VCPU_SREG_TR], VCPU_SREG_TR); + __vmx_set_segment(vcpu, &vmx->rmode.segs[VCPU_SREG_TR], VCPU_SREG_TR); flags = vmcs_readl(GUEST_RFLAGS); flags &= RMODE_GUEST_OWNED_EFLAGS_BITS; @@ -2852,8 +2852,6 @@ static void enter_rmode(struct kvm_vcpu *vcpu) fix_rmode_seg(VCPU_SREG_DS, &vmx->rmode.segs[VCPU_SREG_DS]); fix_rmode_seg(VCPU_SREG_GS, &vmx->rmode.segs[VCPU_SREG_GS]); fix_rmode_seg(VCPU_SREG_FS, &vmx->rmode.segs[VCPU_SREG_FS]); - - kvm_mmu_reset_context(vcpu); } int vmx_set_efer(struct kvm_vcpu *vcpu, u64 efer) @@ -2874,7 +2872,7 @@ int vmx_set_efer(struct kvm_vcpu *vcpu, u64 efer) msr->data = efer & ~EFER_LME; } - setup_msrs(vmx); + vmx_setup_uret_msrs(vmx); return 0; } @@ -2997,42 +2995,24 @@ void ept_save_pdptrs(struct kvm_vcpu *vcpu) kvm_register_mark_dirty(vcpu, VCPU_EXREG_PDPTR); } -static void ept_update_paging_mode_cr0(unsigned long *hw_cr0, - unsigned long cr0, - struct kvm_vcpu *vcpu) -{ - struct vcpu_vmx *vmx = to_vmx(vcpu); - - if (!kvm_register_is_available(vcpu, VCPU_EXREG_CR3)) - vmx_cache_reg(vcpu, VCPU_EXREG_CR3); - if (!(cr0 & X86_CR0_PG)) { - /* From paging/starting to nonpaging */ - exec_controls_setbit(vmx, CPU_BASED_CR3_LOAD_EXITING | - CPU_BASED_CR3_STORE_EXITING); - vcpu->arch.cr0 = cr0; - vmx_set_cr4(vcpu, kvm_read_cr4(vcpu)); - } else if (!is_paging(vcpu)) { - /* From nonpaging to paging */ - exec_controls_clearbit(vmx, CPU_BASED_CR3_LOAD_EXITING | - CPU_BASED_CR3_STORE_EXITING); - vcpu->arch.cr0 = cr0; - vmx_set_cr4(vcpu, kvm_read_cr4(vcpu)); - } - - if (!(cr0 & X86_CR0_WP)) - *hw_cr0 &= ~X86_CR0_WP; -} +#define CR3_EXITING_BITS (CPU_BASED_CR3_LOAD_EXITING | \ + CPU_BASED_CR3_STORE_EXITING) void vmx_set_cr0(struct kvm_vcpu *vcpu, unsigned long cr0) { struct vcpu_vmx *vmx = to_vmx(vcpu); - unsigned long hw_cr0; + unsigned long hw_cr0, old_cr0_pg; + u32 tmp; + + old_cr0_pg = kvm_read_cr0_bits(vcpu, X86_CR0_PG); hw_cr0 = (cr0 & ~KVM_VM_CR0_ALWAYS_OFF); if (is_unrestricted_guest(vcpu)) hw_cr0 |= KVM_VM_CR0_ALWAYS_ON_UNRESTRICTED_GUEST; else { hw_cr0 |= KVM_VM_CR0_ALWAYS_ON; + if (!enable_ept) + hw_cr0 |= X86_CR0_WP; if (vmx->rmode.vm86_active && (cr0 & X86_CR0_PE)) enter_pmode(vcpu); @@ -3041,22 +3021,60 @@ void vmx_set_cr0(struct kvm_vcpu *vcpu, unsigned long cr0) enter_rmode(vcpu); } + vmcs_writel(CR0_READ_SHADOW, cr0); + vmcs_writel(GUEST_CR0, hw_cr0); + vcpu->arch.cr0 = cr0; + kvm_register_mark_available(vcpu, VCPU_EXREG_CR0); + #ifdef CONFIG_X86_64 if (vcpu->arch.efer & EFER_LME) { - if (!is_paging(vcpu) && (cr0 & X86_CR0_PG)) + if (!old_cr0_pg && (cr0 & X86_CR0_PG)) enter_lmode(vcpu); - if (is_paging(vcpu) && !(cr0 & X86_CR0_PG)) + else if (old_cr0_pg && !(cr0 & X86_CR0_PG)) exit_lmode(vcpu); } #endif - if (enable_ept && !is_unrestricted_guest(vcpu)) - ept_update_paging_mode_cr0(&hw_cr0, cr0, vcpu); + if (enable_ept && !is_unrestricted_guest(vcpu)) { + /* + * Ensure KVM has an up-to-date snapshot of the guest's CR3. If + * the below code _enables_ CR3 exiting, vmx_cache_reg() will + * (correctly) stop reading vmcs.GUEST_CR3 because it thinks + * KVM's CR3 is installed. + */ + if (!kvm_register_is_available(vcpu, VCPU_EXREG_CR3)) + vmx_cache_reg(vcpu, VCPU_EXREG_CR3); - vmcs_writel(CR0_READ_SHADOW, cr0); - vmcs_writel(GUEST_CR0, hw_cr0); - vcpu->arch.cr0 = cr0; - kvm_register_mark_available(vcpu, VCPU_EXREG_CR0); + /* + * When running with EPT but not unrestricted guest, KVM must + * intercept CR3 accesses when paging is _disabled_. This is + * necessary because restricted guests can't actually run with + * paging disabled, and so KVM stuffs its own CR3 in order to + * run the guest when identity mapped page tables. + * + * Do _NOT_ check the old CR0.PG, e.g. to optimize away the + * update, it may be stale with respect to CR3 interception, + * e.g. after nested VM-Enter. + * + * Lastly, honor L1's desires, i.e. intercept CR3 loads and/or + * stores to forward them to L1, even if KVM does not need to + * intercept them to preserve its identity mapped page tables. + */ + if (!(cr0 & X86_CR0_PG)) { + exec_controls_setbit(vmx, CR3_EXITING_BITS); + } else if (!is_guest_mode(vcpu)) { + exec_controls_clearbit(vmx, CR3_EXITING_BITS); + } else { + tmp = exec_controls_get(vmx); + tmp &= ~CR3_EXITING_BITS; + tmp |= get_vmcs12(vcpu)->cpu_based_vm_exec_control & CR3_EXITING_BITS; + exec_controls_set(vmx, tmp); + } + + /* Note, vmx_set_cr4() consumes the new vcpu->arch.cr0. */ + if ((old_cr0_pg ^ cr0) & X86_CR0_PG) + vmx_set_cr4(vcpu, kvm_read_cr4(vcpu)); + } /* depends on vcpu->arch.cr0 to be set to a new value */ vmx->emulation_required = emulation_required(vcpu); @@ -3271,7 +3289,7 @@ static u32 vmx_segment_access_rights(struct kvm_segment *var) return ar; } -void vmx_set_segment(struct kvm_vcpu *vcpu, struct kvm_segment *var, int seg) +void __vmx_set_segment(struct kvm_vcpu *vcpu, struct kvm_segment *var, int seg) { struct vcpu_vmx *vmx = to_vmx(vcpu); const struct kvm_vmx_segment_field *sf = &kvm_vmx_segment_fields[seg]; @@ -3284,7 +3302,7 @@ void vmx_set_segment(struct kvm_vcpu *vcpu, struct kvm_segment *var, int seg) vmcs_write16(sf->selector, var->selector); else if (var->s) fix_rmode_seg(seg, &vmx->rmode.segs[seg]); - goto out; + return; } vmcs_writel(sf->base, var->base); @@ -3306,9 +3324,13 @@ void vmx_set_segment(struct kvm_vcpu *vcpu, struct kvm_segment *var, int seg) var->type |= 0x1; /* Accessed */ vmcs_write32(sf->ar_bytes, vmx_segment_access_rights(var)); +} -out: - vmx->emulation_required = emulation_required(vcpu); +static void vmx_set_segment(struct kvm_vcpu *vcpu, struct kvm_segment *var, int seg) +{ + __vmx_set_segment(vcpu, var, seg); + + to_vmx(vcpu)->emulation_required = emulation_required(vcpu); } static void vmx_get_cs_db_l_bits(struct kvm_vcpu *vcpu, int *db, int *l) @@ -3790,21 +3812,6 @@ void vmx_enable_intercept_for_msr(struct kvm_vcpu *vcpu, u32 msr, int type) vmx_set_msr_bitmap_write(msr_bitmap, msr); } -static u8 vmx_msr_bitmap_mode(struct kvm_vcpu *vcpu) -{ - u8 mode = 0; - - if (cpu_has_secondary_exec_ctrls() && - (secondary_exec_controls_get(to_vmx(vcpu)) & - SECONDARY_EXEC_VIRTUALIZE_X2APIC_MODE)) { - mode |= MSR_BITMAP_MODE_X2APIC; - if (enable_apicv && kvm_vcpu_apicv_active(vcpu)) - mode |= MSR_BITMAP_MODE_X2APIC_APICV; - } - - return mode; -} - static void vmx_reset_x2apic_msrs(struct kvm_vcpu *vcpu, u8 mode) { unsigned long *msr_bitmap = to_vmx(vcpu)->vmcs01.msr_bitmap; @@ -3822,11 +3829,29 @@ static void vmx_reset_x2apic_msrs(struct kvm_vcpu *vcpu, u8 mode) } } -static void vmx_update_msr_bitmap_x2apic(struct kvm_vcpu *vcpu, u8 mode) +static void vmx_update_msr_bitmap_x2apic(struct kvm_vcpu *vcpu) { + struct vcpu_vmx *vmx = to_vmx(vcpu); + u8 mode; + if (!cpu_has_vmx_msr_bitmap()) return; + if (cpu_has_secondary_exec_ctrls() && + (secondary_exec_controls_get(vmx) & + SECONDARY_EXEC_VIRTUALIZE_X2APIC_MODE)) { + mode = MSR_BITMAP_MODE_X2APIC; + if (enable_apicv && kvm_vcpu_apicv_active(vcpu)) + mode |= MSR_BITMAP_MODE_X2APIC_APICV; + } else { + mode = 0; + } + + if (mode == vmx->x2apic_msr_bitmap_mode) + return; + + vmx->x2apic_msr_bitmap_mode = mode; + vmx_reset_x2apic_msrs(vcpu, mode); /* @@ -3843,21 +3868,6 @@ static void vmx_update_msr_bitmap_x2apic(struct kvm_vcpu *vcpu, u8 mode) } } -void vmx_update_msr_bitmap(struct kvm_vcpu *vcpu) -{ - struct vcpu_vmx *vmx = to_vmx(vcpu); - u8 mode = vmx_msr_bitmap_mode(vcpu); - u8 changed = mode ^ vmx->msr_bitmap_mode; - - if (!changed) - return; - - if (changed & (MSR_BITMAP_MODE_X2APIC | MSR_BITMAP_MODE_X2APIC_APICV)) - vmx_update_msr_bitmap_x2apic(vcpu, mode); - - vmx->msr_bitmap_mode = mode; -} - void pt_update_intercept_for_msr(struct kvm_vcpu *vcpu) { struct vcpu_vmx *vmx = to_vmx(vcpu); @@ -3914,7 +3924,6 @@ static void vmx_msr_filter_changed(struct kvm_vcpu *vcpu) } pt_update_intercept_for_msr(vcpu); - vmx_update_msr_bitmap_x2apic(vcpu, vmx_msr_bitmap_mode(vcpu)); } static inline bool kvm_vcpu_trigger_posted_interrupt(struct kvm_vcpu *vcpu, @@ -4086,7 +4095,7 @@ void set_cr4_guest_host_mask(struct vcpu_vmx *vmx) vmcs_writel(CR4_GUEST_HOST_MASK, ~vcpu->arch.cr4_guest_owned_bits); } -u32 vmx_pin_based_exec_ctrl(struct vcpu_vmx *vmx) +static u32 vmx_pin_based_exec_ctrl(struct vcpu_vmx *vmx) { u32 pin_based_exec_ctrl = vmcs_config.pin_based_exec_ctrl; @@ -4102,6 +4111,30 @@ u32 vmx_pin_based_exec_ctrl(struct vcpu_vmx *vmx) return pin_based_exec_ctrl; } +static u32 vmx_vmentry_ctrl(void) +{ + u32 vmentry_ctrl = vmcs_config.vmentry_ctrl; + + if (vmx_pt_mode_is_system()) + vmentry_ctrl &= ~(VM_ENTRY_PT_CONCEAL_PIP | + VM_ENTRY_LOAD_IA32_RTIT_CTL); + /* Loading of EFER and PERF_GLOBAL_CTRL are toggled dynamically */ + return vmentry_ctrl & + ~(VM_ENTRY_LOAD_IA32_PERF_GLOBAL_CTRL | VM_ENTRY_LOAD_IA32_EFER); +} + +static u32 vmx_vmexit_ctrl(void) +{ + u32 vmexit_ctrl = vmcs_config.vmexit_ctrl; + + if (vmx_pt_mode_is_system()) + vmexit_ctrl &= ~(VM_EXIT_PT_CONCEAL_PIP | + VM_EXIT_CLEAR_IA32_RTIT_CTL); + /* Loading of EFER and PERF_GLOBAL_CTRL are toggled dynamically */ + return vmexit_ctrl & + ~(VM_EXIT_LOAD_IA32_PERF_GLOBAL_CTRL | VM_EXIT_LOAD_IA32_EFER); +} + static void vmx_refresh_apicv_exec_ctrl(struct kvm_vcpu *vcpu) { struct vcpu_vmx *vmx = to_vmx(vcpu); @@ -4118,11 +4151,10 @@ static void vmx_refresh_apicv_exec_ctrl(struct kvm_vcpu *vcpu) SECONDARY_EXEC_VIRTUAL_INTR_DELIVERY); } - if (cpu_has_vmx_msr_bitmap()) - vmx_update_msr_bitmap(vcpu); + vmx_update_msr_bitmap_x2apic(vcpu); } -u32 vmx_exec_control(struct vcpu_vmx *vmx) +static u32 vmx_exec_control(struct vcpu_vmx *vmx) { u32 exec_control = vmcs_config.cpu_based_exec_ctrl; @@ -4204,7 +4236,7 @@ vmx_adjust_secondary_exec_control(struct vcpu_vmx *vmx, u32 *exec_control, #define vmx_adjust_sec_exec_exiting(vmx, exec_control, lname, uname) \ vmx_adjust_sec_exec_control(vmx, exec_control, lname, uname, uname##_EXITING, true) -static void vmx_compute_secondary_exec_control(struct vcpu_vmx *vmx) +static u32 vmx_secondary_exec_control(struct vcpu_vmx *vmx) { struct kvm_vcpu *vcpu = &vmx->vcpu; @@ -4290,7 +4322,7 @@ static void vmx_compute_secondary_exec_control(struct vcpu_vmx *vmx) if (!vcpu->kvm->arch.bus_lock_detection_enabled) exec_control &= ~SECONDARY_EXEC_BUS_LOCK_DETECTION; - vmx->secondary_exec_control = exec_control; + return exec_control; } #define VMX_XSS_EXIT_BITMAP 0 @@ -4314,10 +4346,8 @@ static void init_vmcs(struct vcpu_vmx *vmx) exec_controls_set(vmx, vmx_exec_control(vmx)); - if (cpu_has_secondary_exec_ctrls()) { - vmx_compute_secondary_exec_control(vmx); - secondary_exec_controls_set(vmx, vmx->secondary_exec_control); - } + if (cpu_has_secondary_exec_ctrls()) + secondary_exec_controls_set(vmx, vmx_secondary_exec_control(vmx)); if (kvm_vcpu_apicv_active(&vmx->vcpu)) { vmcs_write64(EOI_EXIT_BITMAP0, 0); @@ -4388,32 +4418,35 @@ static void init_vmcs(struct vcpu_vmx *vmx) vmx->pt_desc.guest.output_mask = 0x7F; vmcs_write64(GUEST_IA32_RTIT_CTL, 0); } + + vmcs_write32(GUEST_SYSENTER_CS, 0); + vmcs_writel(GUEST_SYSENTER_ESP, 0); + vmcs_writel(GUEST_SYSENTER_EIP, 0); + vmcs_write64(GUEST_IA32_DEBUGCTL, 0); + + if (cpu_has_vmx_tpr_shadow()) { + vmcs_write64(VIRTUAL_APIC_PAGE_ADDR, 0); + if (cpu_need_tpr_shadow(&vmx->vcpu)) + vmcs_write64(VIRTUAL_APIC_PAGE_ADDR, + __pa(vmx->vcpu.arch.apic->regs)); + vmcs_write32(TPR_THRESHOLD, 0); + } + + vmx_setup_uret_msrs(vmx); } static void vmx_vcpu_reset(struct kvm_vcpu *vcpu, bool init_event) { struct vcpu_vmx *vmx = to_vmx(vcpu); - struct msr_data apic_base_msr; - u64 cr0; vmx->rmode.vm86_active = 0; vmx->spec_ctrl = 0; vmx->msr_ia32_umwait_control = 0; - vmx->vcpu.arch.regs[VCPU_REGS_RDX] = get_rdx_init_val(); vmx->hv_deadline_tsc = -1; kvm_set_cr8(vcpu, 0); - if (!init_event) { - apic_base_msr.data = APIC_DEFAULT_PHYS_BASE | - MSR_IA32_APICBASE_ENABLE; - if (kvm_vcpu_is_reset_bsp(vcpu)) - apic_base_msr.data |= MSR_IA32_APICBASE_BSP; - apic_base_msr.host_initiated = true; - kvm_set_apic_base(vcpu, &apic_base_msr); - } - vmx_segment_cache_clear(vmx); seg_setup(VCPU_SREG_CS); @@ -4436,16 +4469,6 @@ static void vmx_vcpu_reset(struct kvm_vcpu *vcpu, bool init_event) vmcs_write32(GUEST_LDTR_LIMIT, 0xffff); vmcs_write32(GUEST_LDTR_AR_BYTES, 0x00082); - if (!init_event) { - vmcs_write32(GUEST_SYSENTER_CS, 0); - vmcs_writel(GUEST_SYSENTER_ESP, 0); - vmcs_writel(GUEST_SYSENTER_EIP, 0); - vmcs_write64(GUEST_IA32_DEBUGCTL, 0); - } - - kvm_set_rflags(vcpu, X86_EFLAGS_FIXED); - kvm_rip_write(vcpu, 0xfff0); - vmcs_writel(GUEST_GDTR_BASE, 0); vmcs_write32(GUEST_GDTR_LIMIT, 0xffff); @@ -4458,31 +4481,11 @@ static void vmx_vcpu_reset(struct kvm_vcpu *vcpu, bool init_event) if (kvm_mpx_supported()) vmcs_write64(GUEST_BNDCFGS, 0); - setup_msrs(vmx); - vmcs_write32(VM_ENTRY_INTR_INFO_FIELD, 0); /* 22.2.1 */ - if (cpu_has_vmx_tpr_shadow() && !init_event) { - vmcs_write64(VIRTUAL_APIC_PAGE_ADDR, 0); - if (cpu_need_tpr_shadow(vcpu)) - vmcs_write64(VIRTUAL_APIC_PAGE_ADDR, - __pa(vcpu->arch.apic->regs)); - vmcs_write32(TPR_THRESHOLD, 0); - } - kvm_make_request(KVM_REQ_APIC_PAGE_RELOAD, vcpu); - cr0 = X86_CR0_NW | X86_CR0_CD | X86_CR0_ET; - vmx->vcpu.arch.cr0 = cr0; - vmx_set_cr0(vcpu, cr0); /* enter rmode */ - vmx_set_cr4(vcpu, 0); - vmx_set_efer(vcpu, 0); - - vmx_update_exception_bitmap(vcpu); - vpid_sync_context(vmx->vpid); - if (init_event) - vmx_clear_hlt(vcpu); } static void vmx_enable_irq_window(struct kvm_vcpu *vcpu) @@ -4996,6 +4999,7 @@ static int handle_cr(struct kvm_vcpu *vcpu) return kvm_complete_insn_gp(vcpu, err); case 3: WARN_ON_ONCE(enable_unrestricted_guest); + err = kvm_set_cr3(vcpu, val); return kvm_complete_insn_gp(vcpu, err); case 4: @@ -5021,14 +5025,13 @@ static int handle_cr(struct kvm_vcpu *vcpu) } break; case 2: /* clts */ - WARN_ONCE(1, "Guest should always own CR0.TS"); - vmx_set_cr0(vcpu, kvm_read_cr0_bits(vcpu, ~X86_CR0_TS)); - trace_kvm_cr_write(0, kvm_read_cr0(vcpu)); - return kvm_skip_emulated_instruction(vcpu); + KVM_BUG(1, vcpu->kvm, "Guest always owns CR0.TS"); + return -EIO; case 1: /*mov from cr*/ switch (cr) { case 3: WARN_ON_ONCE(enable_unrestricted_guest); + val = kvm_read_cr3(vcpu); kvm_register_write(vcpu, reg, val); trace_kvm_cr_read(cr, val); @@ -5129,6 +5132,12 @@ static void vmx_sync_dirty_debug_regs(struct kvm_vcpu *vcpu) vcpu->arch.switch_db_regs &= ~KVM_DEBUGREG_WONT_EXIT; exec_controls_setbit(to_vmx(vcpu), CPU_BASED_MOV_DR_EXITING); + + /* + * exc_debug expects dr6 to be cleared after it runs, avoid that it sees + * a stale dr6 from the guest. + */ + set_debugreg(DR6_RESERVED, 6); } static void vmx_set_dr7(struct kvm_vcpu *vcpu, unsigned long val) @@ -5338,7 +5347,9 @@ static int handle_ept_misconfig(struct kvm_vcpu *vcpu) static int handle_nmi_window(struct kvm_vcpu *vcpu) { - WARN_ON_ONCE(!enable_vnmi); + if (KVM_BUG_ON(!enable_vnmi, vcpu->kvm)) + return -EIO; + exec_controls_clearbit(to_vmx(vcpu), CPU_BASED_NMI_WINDOW_EXITING); ++vcpu->stat.nmi_window_exits; kvm_make_request(KVM_REQ_EVENT, vcpu); @@ -5896,7 +5907,8 @@ static int __vmx_handle_exit(struct kvm_vcpu *vcpu, fastpath_t exit_fastpath) * below) should never happen as that means we incorrectly allowed a * nested VM-Enter with an invalid vmcs12. */ - WARN_ON_ONCE(vmx->nested.nested_run_pending); + if (KVM_BUG_ON(vmx->nested.nested_run_pending, vcpu->kvm)) + return -EIO; /* If guest state is invalid, start emulating */ if (vmx->emulation_required) @@ -6189,7 +6201,7 @@ void vmx_set_virtual_apic_mode(struct kvm_vcpu *vcpu) } secondary_exec_controls_set(vmx, sec_exec_control); - vmx_update_msr_bitmap(vcpu); + vmx_update_msr_bitmap_x2apic(vcpu); } static void vmx_set_apic_access_page_addr(struct kvm_vcpu *vcpu) @@ -6274,7 +6286,9 @@ static int vmx_sync_pir_to_irr(struct kvm_vcpu *vcpu) int max_irr; bool max_irr_updated; - WARN_ON(!vcpu->arch.apicv_active); + if (KVM_BUG_ON(!vcpu->arch.apicv_active, vcpu->kvm)) + return -EIO; + if (pi_test_on(&vmx->pi_desc)) { pi_clear_on(&vmx->pi_desc); /* @@ -6357,7 +6371,7 @@ static void handle_external_interrupt_irqoff(struct kvm_vcpu *vcpu) unsigned int vector = intr_info & INTR_INFO_VECTOR_MASK; gate_desc *desc = (gate_desc *)host_idt_base + vector; - if (WARN_ONCE(!is_external_intr(intr_info), + if (KVM_BUG(!is_external_intr(intr_info), vcpu->kvm, "KVM: unexpected VM-Exit interrupt info: 0x%x", intr_info)) return; @@ -6368,6 +6382,9 @@ static void vmx_handle_exit_irqoff(struct kvm_vcpu *vcpu) { struct vcpu_vmx *vmx = to_vmx(vcpu); + if (vmx->emulation_required) + return; + if (vmx->exit_reason.basic == EXIT_REASON_EXTERNAL_INTERRUPT) handle_external_interrupt_irqoff(vcpu); else if (vmx->exit_reason.basic == EXIT_REASON_EXCEPTION_NMI) @@ -6639,6 +6656,10 @@ static fastpath_t vmx_vcpu_run(struct kvm_vcpu *vcpu) vmx->loaded_vmcs->host_state.cr4 = cr4; } + /* When KVM_DEBUGREG_WONT_EXIT, dr6 is accessible in guest. */ + if (unlikely(vcpu->arch.switch_db_regs & KVM_DEBUGREG_WONT_EXIT)) + set_debugreg(vcpu->arch.dr6, 6); + /* When single-stepping over STI and MOV SS, we must clear the * corresponding interruptibility bits in the guest state. Otherwise * vmentry fails as it then expects bit 14 (BS) in pending debug @@ -6838,7 +6859,6 @@ static int vmx_create_vcpu(struct kvm_vcpu *vcpu) vmx_disable_intercept_for_msr(vcpu, MSR_CORE_C6_RESIDENCY, MSR_TYPE_R); vmx_disable_intercept_for_msr(vcpu, MSR_CORE_C7_RESIDENCY, MSR_TYPE_R); } - vmx->msr_bitmap_mode = 0; vmx->loaded_vmcs = &vmx->vmcs01; cpu = get_cpu(); @@ -6997,7 +7017,7 @@ exit: return (cache << VMX_EPT_MT_EPTE_SHIFT) | ipat; } -static void vmcs_set_secondary_exec_control(struct vcpu_vmx *vmx) +static void vmcs_set_secondary_exec_control(struct vcpu_vmx *vmx, u32 new_ctl) { /* * These bits in the secondary execution controls field @@ -7011,7 +7031,6 @@ static void vmcs_set_secondary_exec_control(struct vcpu_vmx *vmx) SECONDARY_EXEC_VIRTUALIZE_APIC_ACCESSES | SECONDARY_EXEC_DESC; - u32 new_ctl = vmx->secondary_exec_control; u32 cur_ctl = secondary_exec_controls_get(vmx); secondary_exec_controls_set(vmx, (new_ctl & ~mask) | (cur_ctl & mask)); @@ -7154,10 +7173,11 @@ static void vmx_vcpu_after_set_cpuid(struct kvm_vcpu *vcpu) /* xsaves_enabled is recomputed in vmx_compute_secondary_exec_control(). */ vcpu->arch.xsaves_enabled = false; - if (cpu_has_secondary_exec_ctrls()) { - vmx_compute_secondary_exec_control(vmx); - vmcs_set_secondary_exec_control(vmx); - } + vmx_setup_uret_msrs(vmx); + + if (cpu_has_secondary_exec_ctrls()) + vmcs_set_secondary_exec_control(vmx, + vmx_secondary_exec_control(vmx)); if (nested_vmx_allowed(vcpu)) to_vmx(vcpu)->msr_ia32_feature_control_valid_bits |= @@ -7803,7 +7823,8 @@ static __init int hardware_setup(void) ept_lpage_level = PG_LEVEL_2M; else ept_lpage_level = PG_LEVEL_4K; - kvm_configure_mmu(enable_ept, vmx_get_max_tdp_level(), ept_lpage_level); + kvm_configure_mmu(enable_ept, 0, vmx_get_max_tdp_level(), + ept_lpage_level); /* * Only enable PML when hardware supports PML feature, and both EPT diff --git a/arch/x86/kvm/vmx/vmx.h b/arch/x86/kvm/vmx/vmx.h index 3979a947933a..4858c5fd95f2 100644 --- a/arch/x86/kvm/vmx/vmx.h +++ b/arch/x86/kvm/vmx/vmx.h @@ -14,8 +14,6 @@ #include "vmx_ops.h" #include "cpuid.h" -extern const u32 vmx_msr_index[]; - #define MSR_TYPE_R 1 #define MSR_TYPE_W 2 #define MSR_TYPE_RW 3 @@ -229,7 +227,7 @@ struct nested_vmx { struct vcpu_vmx { struct kvm_vcpu vcpu; u8 fail; - u8 msr_bitmap_mode; + u8 x2apic_msr_bitmap_mode; /* * If true, host state has been stored in vmx->loaded_vmcs for @@ -265,8 +263,6 @@ struct vcpu_vmx { u64 spec_ctrl; u32 msr_ia32_umwait_control; - u32 secondary_exec_control; - /* * loaded_vmcs points to the VMCS currently used in this vcpu. For a * non-nested (L1) guest, it always points to vmcs01. For a nested @@ -373,12 +369,11 @@ void vmx_set_cr4(struct kvm_vcpu *vcpu, unsigned long cr4); void set_cr4_guest_host_mask(struct vcpu_vmx *vmx); void ept_save_pdptrs(struct kvm_vcpu *vcpu); void vmx_get_segment(struct kvm_vcpu *vcpu, struct kvm_segment *var, int seg); -void vmx_set_segment(struct kvm_vcpu *vcpu, struct kvm_segment *var, int seg); +void __vmx_set_segment(struct kvm_vcpu *vcpu, struct kvm_segment *var, int seg); u64 construct_eptp(struct kvm_vcpu *vcpu, hpa_t root_hpa, int root_level); bool vmx_guest_inject_ac(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); bool vmx_get_nmi_mask(struct kvm_vcpu *vcpu); @@ -421,9 +416,13 @@ static inline void lname##_controls_set(struct vcpu_vmx *vmx, u32 val) \ vmx->loaded_vmcs->controls_shadow.lname = val; \ } \ } \ +static inline u32 __##lname##_controls_get(struct loaded_vmcs *vmcs) \ +{ \ + return vmcs->controls_shadow.lname; \ +} \ static inline u32 lname##_controls_get(struct vcpu_vmx *vmx) \ { \ - return vmx->loaded_vmcs->controls_shadow.lname; \ + return __##lname##_controls_get(vmx->loaded_vmcs); \ } \ static inline void lname##_controls_setbit(struct vcpu_vmx *vmx, u32 val) \ { \ @@ -453,31 +452,6 @@ static inline void vmx_register_cache_reset(struct kvm_vcpu *vcpu) vcpu->arch.regs_dirty = 0; } -static inline u32 vmx_vmentry_ctrl(void) -{ - u32 vmentry_ctrl = vmcs_config.vmentry_ctrl; - if (vmx_pt_mode_is_system()) - vmentry_ctrl &= ~(VM_ENTRY_PT_CONCEAL_PIP | - VM_ENTRY_LOAD_IA32_RTIT_CTL); - /* Loading of EFER and PERF_GLOBAL_CTRL are toggled dynamically */ - return vmentry_ctrl & - ~(VM_ENTRY_LOAD_IA32_PERF_GLOBAL_CTRL | VM_ENTRY_LOAD_IA32_EFER); -} - -static inline u32 vmx_vmexit_ctrl(void) -{ - u32 vmexit_ctrl = vmcs_config.vmexit_ctrl; - if (vmx_pt_mode_is_system()) - vmexit_ctrl &= ~(VM_EXIT_PT_CONCEAL_PIP | - VM_EXIT_CLEAR_IA32_RTIT_CTL); - /* Loading of EFER and PERF_GLOBAL_CTRL are toggled dynamically */ - return vmexit_ctrl & - ~(VM_EXIT_LOAD_IA32_PERF_GLOBAL_CTRL | VM_EXIT_LOAD_IA32_EFER); -} - -u32 vmx_exec_control(struct vcpu_vmx *vmx); -u32 vmx_pin_based_exec_ctrl(struct vcpu_vmx *vmx); - static inline struct kvm_vmx *to_kvm_vmx(struct kvm *kvm) { return container_of(kvm, struct kvm_vmx, kvm); @@ -524,7 +498,7 @@ static inline struct vmcs *alloc_vmcs(bool shadow) static inline bool vmx_has_waitpkg(struct vcpu_vmx *vmx) { - return vmx->secondary_exec_control & + return secondary_exec_controls_get(vmx) & SECONDARY_EXEC_ENABLE_USR_WAIT_PAUSE; } diff --git a/arch/x86/kvm/vmx/vmx_ops.h b/arch/x86/kvm/vmx/vmx_ops.h index 164b64f65a8f..9e9ef47e988c 100644 --- a/arch/x86/kvm/vmx/vmx_ops.h +++ b/arch/x86/kvm/vmx/vmx_ops.h @@ -4,13 +4,11 @@ #include <linux/nospec.h> -#include <asm/kvm_host.h> #include <asm/vmx.h> #include "evmcs.h" #include "vmcs.h" - -#define __ex(x) __kvm_handle_fault_on_reboot(x) +#include "x86.h" asmlinkage void vmread_error(unsigned long field, bool fault); __attribute__((regparm(0))) void vmread_error_trampoline(unsigned long field, diff --git a/arch/x86/kvm/x86.c b/arch/x86/kvm/x86.c index c6dc1b445231..28ef14155726 100644 --- a/arch/x86/kvm/x86.c +++ b/arch/x86/kvm/x86.c @@ -233,12 +233,13 @@ const struct _kvm_stats_desc kvm_vm_stats_desc[] = { STATS_DESC_COUNTER(VM, mmu_recycled), STATS_DESC_COUNTER(VM, mmu_cache_miss), STATS_DESC_ICOUNTER(VM, mmu_unsync), - STATS_DESC_ICOUNTER(VM, lpages), + STATS_DESC_ICOUNTER(VM, pages_4k), + STATS_DESC_ICOUNTER(VM, pages_2m), + STATS_DESC_ICOUNTER(VM, pages_1g), STATS_DESC_ICOUNTER(VM, nx_lpage_splits), + STATS_DESC_PCOUNTER(VM, max_mmu_rmap_size), STATS_DESC_PCOUNTER(VM, max_mmu_page_hash_collisions) }; -static_assert(ARRAY_SIZE(kvm_vm_stats_desc) == - sizeof(struct kvm_vm_stat) / sizeof(u64)); const struct kvm_stats_header kvm_vm_stats_header = { .name_size = KVM_STATS_NAME_SIZE, @@ -278,8 +279,6 @@ const struct _kvm_stats_desc kvm_vcpu_stats_desc[] = { STATS_DESC_COUNTER(VCPU, directed_yield_successful), STATS_DESC_ICOUNTER(VCPU, guest_mode) }; -static_assert(ARRAY_SIZE(kvm_vcpu_stats_desc) == - sizeof(struct kvm_vcpu_stat) / sizeof(u64)); const struct kvm_stats_header kvm_vcpu_stats_header = { .name_size = KVM_STATS_NAME_SIZE, @@ -485,7 +484,14 @@ int kvm_set_apic_base(struct kvm_vcpu *vcpu, struct msr_data *msr_info) } EXPORT_SYMBOL_GPL(kvm_set_apic_base); -asmlinkage __visible noinstr void kvm_spurious_fault(void) +/* + * Handle a fault on a hardware virtualization (VMX or SVM) instruction. + * + * Hardware virtualization extension instructions may fault if a reboot turns + * off virtualization while processes are running. Usually after catching the + * fault we just panic; during reboot instead the instruction is ignored. + */ +noinstr void kvm_spurious_fault(void) { /* Fault while not rebooting. We want the trace. */ BUG_ON(!kvm_rebooting); @@ -1180,7 +1186,6 @@ static void kvm_update_dr0123(struct kvm_vcpu *vcpu) if (!(vcpu->guest_debug & KVM_GUESTDBG_USE_HW_BP)) { for (i = 0; i < KVM_NR_DB_REGS; i++) vcpu->arch.eff_db[i] = vcpu->arch.db[i]; - vcpu->arch.switch_db_regs |= KVM_DEBUGREG_RELOAD; } } @@ -3316,6 +3321,10 @@ int kvm_set_msr_common(struct kvm_vcpu *vcpu, struct msr_data *msr_info) if (!msr_info->host_initiated) { s64 adj = data - vcpu->arch.ia32_tsc_adjust_msr; adjust_tsc_offset_guest(vcpu, adj); + /* Before back to guest, tsc_timestamp must be adjusted + * as well, otherwise guest's percpu pvclock time could jump. + */ + kvm_make_request(KVM_REQ_CLOCK_UPDATE, vcpu); } vcpu->arch.ia32_tsc_adjust_msr = data; } @@ -3407,7 +3416,7 @@ int kvm_set_msr_common(struct kvm_vcpu *vcpu, struct msr_data *msr_info) return 1; break; case MSR_KVM_ASYNC_PF_ACK: - if (!guest_pv_has(vcpu, KVM_FEATURE_ASYNC_PF)) + if (!guest_pv_has(vcpu, KVM_FEATURE_ASYNC_PF_INT)) return 1; if (data & 0x1) { vcpu->arch.apf.pageready_pending = false; @@ -3746,7 +3755,7 @@ int kvm_get_msr_common(struct kvm_vcpu *vcpu, struct msr_data *msr_info) msr_info->data = vcpu->arch.apf.msr_int_val; break; case MSR_KVM_ASYNC_PF_ACK: - if (!guest_pv_has(vcpu, KVM_FEATURE_ASYNC_PF)) + if (!guest_pv_has(vcpu, KVM_FEATURE_ASYNC_PF_INT)) return 1; msr_info->data = 0; @@ -4310,12 +4319,6 @@ void kvm_arch_vcpu_put(struct kvm_vcpu *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 - * on every vmexit, but if not, we might have a stale dr6 from the - * guest. do_debug expects dr6 to be cleared after it runs, do the same. - */ - set_debugreg(0, 6); } static int kvm_vcpu_ioctl_get_lapic(struct kvm_vcpu *vcpu, @@ -4358,8 +4361,17 @@ static int kvm_cpu_accept_dm_intr(struct kvm_vcpu *vcpu) static int kvm_vcpu_ready_for_interrupt_injection(struct kvm_vcpu *vcpu) { - return kvm_arch_interrupt_allowed(vcpu) && - kvm_cpu_accept_dm_intr(vcpu); + /* + * Do not cause an interrupt window exit if an exception + * is pending or an event needs reinjection; userspace + * might want to inject the interrupt manually using KVM_SET_REGS + * or KVM_SET_SREGS. For that to work, we must be at an + * instruction boundary and with no events half-injected. + */ + return (kvm_arch_interrupt_allowed(vcpu) && + kvm_cpu_accept_dm_intr(vcpu) && + !kvm_event_needs_reinjection(vcpu) && + !vcpu->arch.exception.pending); } static int kvm_vcpu_ioctl_interrupt(struct kvm_vcpu *vcpu, @@ -6558,9 +6570,9 @@ static int vcpu_mmio_gva_to_gpa(struct kvm_vcpu *vcpu, unsigned long gva, * there is no pkey in EPT page table for L1 guest or EPT * shadow page table for L2 guest. */ - if (vcpu_match_mmio_gva(vcpu, gva) - && !permission_fault(vcpu, vcpu->arch.walk_mmu, - vcpu->arch.mmio_access, 0, access)) { + if (vcpu_match_mmio_gva(vcpu, gva) && (!is_paging(vcpu) || + !permission_fault(vcpu, vcpu->arch.walk_mmu, + vcpu->arch.mmio_access, 0, access))) { *gpa = vcpu->arch.mmio_gfn << PAGE_SHIFT | (gva & (PAGE_SIZE - 1)); trace_vcpu_match_mmio(gva, *gpa, write, false); @@ -8569,6 +8581,8 @@ EXPORT_SYMBOL_GPL(kvm_apicv_activated); static void kvm_apicv_init(struct kvm *kvm) { + mutex_init(&kvm->arch.apicv_update_lock); + if (enable_apicv) clear_bit(APICV_INHIBIT_REASON_DISABLE, &kvm->arch.apicv_inhibit_reasons); @@ -8882,6 +8896,10 @@ static int inject_pending_event(struct kvm_vcpu *vcpu, bool *req_immediate_exit) can_inject = false; } + /* Don't inject interrupts if the user asked to avoid doing so */ + if (vcpu->guest_debug & KVM_GUESTDBG_BLOCKIRQ) + return 0; + /* * Finally, inject interrupt events. If an event cannot be injected * due to architectural conditions (e.g. IF=0) a window-open exit @@ -9227,10 +9245,18 @@ void kvm_make_scan_ioapic_request(struct kvm *kvm) void kvm_vcpu_update_apicv(struct kvm_vcpu *vcpu) { + bool activate; + if (!lapic_in_kernel(vcpu)) return; - vcpu->arch.apicv_active = kvm_apicv_activated(vcpu->kvm); + mutex_lock(&vcpu->kvm->arch.apicv_update_lock); + + activate = kvm_apicv_activated(vcpu->kvm); + if (vcpu->arch.apicv_active == activate) + goto out; + + vcpu->arch.apicv_active = activate; kvm_apic_update_apicv(vcpu); static_call(kvm_x86_refresh_apicv_exec_ctrl)(vcpu); @@ -9242,54 +9268,45 @@ void kvm_vcpu_update_apicv(struct kvm_vcpu *vcpu) */ if (!vcpu->arch.apicv_active) kvm_make_request(KVM_REQ_EVENT, vcpu); + +out: + mutex_unlock(&vcpu->kvm->arch.apicv_update_lock); } EXPORT_SYMBOL_GPL(kvm_vcpu_update_apicv); -/* - * NOTE: Do not hold any lock prior to calling this. - * - * In particular, kvm_request_apicv_update() expects kvm->srcu not to be - * locked, because it calls __x86_set_memory_region() which does - * synchronize_srcu(&kvm->srcu). - */ -void kvm_request_apicv_update(struct kvm *kvm, bool activate, ulong bit) +void __kvm_request_apicv_update(struct kvm *kvm, bool activate, ulong bit) { - struct kvm_vcpu *except; - unsigned long old, new, expected; + unsigned long old, new; if (!kvm_x86_ops.check_apicv_inhibit_reasons || !static_call(kvm_x86_check_apicv_inhibit_reasons)(bit)) return; - old = READ_ONCE(kvm->arch.apicv_inhibit_reasons); - do { - expected = new = old; - if (activate) - __clear_bit(bit, &new); - else - __set_bit(bit, &new); - if (new == old) - break; - old = cmpxchg(&kvm->arch.apicv_inhibit_reasons, expected, new); - } while (old != expected); - - if (!!old == !!new) - return; + old = new = kvm->arch.apicv_inhibit_reasons; - trace_kvm_apicv_update_request(activate, bit); - if (kvm_x86_ops.pre_update_apicv_exec_ctrl) - static_call(kvm_x86_pre_update_apicv_exec_ctrl)(kvm, activate); + if (activate) + __clear_bit(bit, &new); + else + __set_bit(bit, &new); + + if (!!old != !!new) { + trace_kvm_apicv_update_request(activate, bit); + kvm_make_all_cpus_request(kvm, KVM_REQ_APICV_UPDATE); + kvm->arch.apicv_inhibit_reasons = new; + if (new) { + unsigned long gfn = gpa_to_gfn(APIC_DEFAULT_PHYS_BASE); + kvm_zap_gfn_range(kvm, gfn, gfn+1); + } + } else + kvm->arch.apicv_inhibit_reasons = new; +} +EXPORT_SYMBOL_GPL(__kvm_request_apicv_update); - /* - * Sending request to update APICV for all other vcpus, - * while update the calling vcpu immediately instead of - * waiting for another #VMEXIT to handle the request. - */ - except = kvm_get_running_vcpu(); - kvm_make_all_cpus_request_except(kvm, KVM_REQ_APICV_UPDATE, - except); - if (except) - kvm_vcpu_update_apicv(except); +void kvm_request_apicv_update(struct kvm *kvm, bool activate, ulong bit) +{ + mutex_lock(&kvm->arch.apicv_update_lock); + __kvm_request_apicv_update(kvm, activate, bit); + mutex_unlock(&kvm->arch.apicv_update_lock); } EXPORT_SYMBOL_GPL(kvm_request_apicv_update); @@ -9386,6 +9403,10 @@ static int vcpu_enter_guest(struct kvm_vcpu *vcpu) } if (kvm_request_pending(vcpu)) { + if (kvm_check_request(KVM_REQ_VM_BUGGED, vcpu)) { + r = -EIO; + goto out; + } if (kvm_check_request(KVM_REQ_GET_NESTED_STATE_PAGES, vcpu)) { if (unlikely(!kvm_x86_ops.nested_ops->get_nested_state_pages(vcpu))) { r = 0; @@ -9599,8 +9620,8 @@ static int vcpu_enter_guest(struct kvm_vcpu *vcpu) set_debugreg(vcpu->arch.eff_db[1], 1); set_debugreg(vcpu->arch.eff_db[2], 2); set_debugreg(vcpu->arch.eff_db[3], 3); - set_debugreg(vcpu->arch.dr6, 6); - vcpu->arch.switch_db_regs &= ~KVM_DEBUGREG_RELOAD; + } else if (unlikely(hw_breakpoint_active())) { + set_debugreg(0, 7); } for (;;) { @@ -9628,7 +9649,6 @@ static int vcpu_enter_guest(struct kvm_vcpu *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; } /* @@ -9965,7 +9985,8 @@ int kvm_arch_vcpu_ioctl_run(struct kvm_vcpu *vcpu) goto out; } - if (kvm_run->kvm_valid_regs & ~KVM_SYNC_X86_VALID_FIELDS) { + if ((kvm_run->kvm_valid_regs & ~KVM_SYNC_X86_VALID_FIELDS) || + (kvm_run->kvm_dirty_regs & ~KVM_SYNC_X86_VALID_FIELDS)) { r = -EINVAL; goto out; } @@ -10570,9 +10591,6 @@ static void store_regs(struct kvm_vcpu *vcpu) static int sync_regs(struct kvm_vcpu *vcpu) { - if (vcpu->run->kvm_dirty_regs & ~KVM_SYNC_X86_VALID_FIELDS) - return -EINVAL; - if (vcpu->run->kvm_dirty_regs & KVM_SYNC_X86_REGS) { __set_regs(vcpu, &vcpu->run->s.regs.regs); vcpu->run->kvm_dirty_regs &= ~KVM_SYNC_X86_REGS; @@ -10788,6 +10806,8 @@ void kvm_arch_vcpu_destroy(struct kvm_vcpu *vcpu) void kvm_vcpu_reset(struct kvm_vcpu *vcpu, bool init_event) { unsigned long old_cr0 = kvm_read_cr0(vcpu); + unsigned long new_cr0; + u32 eax, dummy; kvm_lapic_reset(vcpu, init_event); @@ -10854,10 +10874,41 @@ void kvm_vcpu_reset(struct kvm_vcpu *vcpu, bool init_event) vcpu->arch.regs_avail = ~0; vcpu->arch.regs_dirty = ~0; + /* + * Fall back to KVM's default Family/Model/Stepping of 0x600 (P6/Athlon) + * if no CPUID match is found. Note, it's impossible to get a match at + * RESET since KVM emulates RESET before exposing the vCPU to userspace, + * i.e. it'simpossible for kvm_cpuid() to find a valid entry on RESET. + * But, go through the motions in case that's ever remedied. + */ + eax = 1; + if (!kvm_cpuid(vcpu, &eax, &dummy, &dummy, &dummy, true)) + eax = 0x600; + kvm_rdx_write(vcpu, eax); + vcpu->arch.ia32_xss = 0; static_call(kvm_x86_vcpu_reset)(vcpu, init_event); + kvm_set_rflags(vcpu, X86_EFLAGS_FIXED); + kvm_rip_write(vcpu, 0xfff0); + + /* + * CR0.CD/NW are set on RESET, preserved on INIT. Note, some versions + * of Intel's SDM list CD/NW as being set on INIT, but they contradict + * (or qualify) that with a footnote stating that CD/NW are preserved. + */ + new_cr0 = X86_CR0_ET; + if (init_event) + new_cr0 |= (old_cr0 & (X86_CR0_NW | X86_CR0_CD)); + else + new_cr0 |= X86_CR0_NW | X86_CR0_CD; + + static_call(kvm_x86_set_cr0)(vcpu, new_cr0); + static_call(kvm_x86_set_cr4)(vcpu, 0); + static_call(kvm_x86_set_efer)(vcpu, 0); + static_call(kvm_x86_update_exception_bitmap)(vcpu); + /* * Reset the MMU context if paging was enabled prior to INIT (which is * implied if CR0.PG=1 as CR0 will be '0' prior to RESET). Unlike the @@ -10868,7 +10919,20 @@ void kvm_vcpu_reset(struct kvm_vcpu *vcpu, bool init_event) */ if (old_cr0 & X86_CR0_PG) kvm_mmu_reset_context(vcpu); + + /* + * Intel's SDM states that all TLB entries are flushed on INIT. AMD's + * APM states the TLBs are untouched by INIT, but it also states that + * the TLBs are flushed on "External initialization of the processor." + * Flush the guest TLB regardless of vendor, there is no meaningful + * benefit in relying on the guest to flush the TLB immediately after + * INIT. A spurious TLB flush is benign and likely negligible from a + * performance perspective. + */ + if (init_event) + kvm_make_request(KVM_REQ_TLB_FLUSH_GUEST, vcpu); } +EXPORT_SYMBOL_GPL(kvm_vcpu_reset); void kvm_vcpu_deliver_sipi_vector(struct kvm_vcpu *vcpu, u8 vector) { @@ -10985,9 +11049,6 @@ int kvm_arch_hardware_setup(void *opaque) int r; rdmsrl_safe(MSR_EFER, &host_efer); - if (WARN_ON_ONCE(boot_cpu_has(X86_FEATURE_NX) && - !(host_efer & EFER_NX))) - return -EIO; if (boot_cpu_has(X86_FEATURE_XSAVES)) rdmsrl(MSR_IA32_XSS, host_xss); @@ -11115,6 +11176,7 @@ int kvm_arch_init_vm(struct kvm *kvm, unsigned long type) kvm_hv_init_vm(kvm); kvm_page_track_init(kvm); kvm_mmu_init_vm(kvm); + kvm_xen_init_vm(kvm); return static_call(kvm_x86_vm_init)(kvm); } @@ -11304,8 +11366,7 @@ static int memslot_rmap_alloc(struct kvm_memory_slot *slot, for (i = 0; i < KVM_NR_PAGE_SIZES; ++i) { int level = i + 1; - int lpages = gfn_to_index(slot->base_gfn + npages - 1, - slot->base_gfn, level) + 1; + int lpages = __kvm_mmu_slot_lpages(slot, npages, level); WARN_ON(slot->arch.rmap[i]); @@ -11388,8 +11449,7 @@ static int kvm_alloc_memslot_metadata(struct kvm *kvm, int lpages; int level = i + 1; - lpages = gfn_to_index(slot->base_gfn + npages - 1, - slot->base_gfn, level) + 1; + lpages = __kvm_mmu_slot_lpages(slot, npages, level); linfo = kvcalloc(lpages, sizeof(*linfo), GFP_KERNEL_ACCOUNT); if (!linfo) @@ -11473,7 +11533,7 @@ static void kvm_mmu_update_cpu_dirty_logging(struct kvm *kvm, bool enable) static void kvm_mmu_slot_apply_flags(struct kvm *kvm, struct kvm_memory_slot *old, - struct kvm_memory_slot *new, + const struct kvm_memory_slot *new, enum kvm_mr_change change) { bool log_dirty_pages = new->flags & KVM_MEM_LOG_DIRTY_PAGES; @@ -11553,10 +11613,7 @@ void kvm_arch_commit_memory_region(struct kvm *kvm, kvm_mmu_change_mmu_pages(kvm, kvm_mmu_calculate_default_mmu_pages(kvm)); - /* - * FIXME: const-ify all uses of struct kvm_memory_slot. - */ - kvm_mmu_slot_apply_flags(kvm, old, (struct kvm_memory_slot *) new, change); + kvm_mmu_slot_apply_flags(kvm, old, new, change); /* Free the arrays associated with the old memslot. */ if (change == KVM_MR_MOVE) diff --git a/arch/x86/kvm/x86.h b/arch/x86/kvm/x86.h index 44ae10312740..7d66d63dc55a 100644 --- a/arch/x86/kvm/x86.h +++ b/arch/x86/kvm/x86.h @@ -8,6 +8,8 @@ #include "kvm_cache_regs.h" #include "kvm_emulate.h" +void kvm_spurious_fault(void); + static __always_inline void kvm_guest_enter_irqoff(void) { /* diff --git a/arch/x86/kvm/xen.c b/arch/x86/kvm/xen.c index ae17250e1efe..9ea9c3dabe37 100644 --- a/arch/x86/kvm/xen.c +++ b/arch/x86/kvm/xen.c @@ -25,15 +25,14 @@ 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 ret = 0; 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) + if (kvm_is_error_hva(gfn_to_hva(kvm, gfn))) { + ret = -EFAULT; goto out; - - kvm->arch.xen.shinfo_set = true; + } + kvm->arch.xen.shinfo_gfn = gfn; /* Paranoia checks on the 32-bit struct layout */ BUILD_BUG_ON(offsetof(struct compat_shared_info, wc) != 0x900); @@ -245,7 +244,7 @@ int kvm_xen_hvm_set_attr(struct kvm *kvm, struct kvm_xen_hvm_attr *data) case KVM_XEN_ATTR_TYPE_SHARED_INFO: if (data->u.shared_info.gfn == GPA_INVALID) { - kvm->arch.xen.shinfo_set = false; + kvm->arch.xen.shinfo_gfn = GPA_INVALID; r = 0; break; } @@ -283,10 +282,7 @@ int kvm_xen_hvm_get_attr(struct kvm *kvm, struct kvm_xen_hvm_attr *data) 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; + data->u.shared_info.gfn = gpa_to_gfn(kvm->arch.xen.shinfo_gfn); r = 0; break; @@ -646,6 +642,11 @@ int kvm_xen_hvm_config(struct kvm *kvm, struct kvm_xen_hvm_config *xhc) return 0; } +void kvm_xen_init_vm(struct kvm *kvm) +{ + kvm->arch.xen.shinfo_gfn = GPA_INVALID; +} + void kvm_xen_destroy_vm(struct kvm *kvm) { if (kvm->arch.xen_hvm_config.msr) diff --git a/arch/x86/kvm/xen.h b/arch/x86/kvm/xen.h index 463a7844a8ca..cc0cf5f37450 100644 --- a/arch/x86/kvm/xen.h +++ b/arch/x86/kvm/xen.h @@ -21,6 +21,7 @@ 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_init_vm(struct kvm *kvm); void kvm_xen_destroy_vm(struct kvm *kvm); static inline bool kvm_xen_msr_enabled(struct kvm *kvm) @@ -50,6 +51,10 @@ static inline int kvm_xen_write_hypercall_page(struct kvm_vcpu *vcpu, u64 data) return 1; } +static inline void kvm_xen_init_vm(struct kvm *kvm) +{ +} + static inline void kvm_xen_destroy_vm(struct kvm *kvm) { } diff --git a/arch/x86/lib/Makefile b/arch/x86/lib/Makefile index bad4dee4f0e4..c6506c6a7092 100644 --- a/arch/x86/lib/Makefile +++ b/arch/x86/lib/Makefile @@ -44,6 +44,7 @@ obj-$(CONFIG_SMP) += msr-smp.o cache-smp.o lib-y := delay.o misc.o cmdline.o cpu.o lib-y += usercopy_$(BITS).o usercopy.o getuser.o putuser.o lib-y += memcpy_$(BITS).o +lib-y += pc-conf-reg.o lib-$(CONFIG_ARCH_HAS_COPY_MC) += copy_mc.o copy_mc_64.o lib-$(CONFIG_INSTRUCTION_DECODER) += insn.o inat.o insn-eval.o lib-$(CONFIG_RANDOMIZE_BASE) += kaslr.o diff --git a/arch/x86/lib/pc-conf-reg.c b/arch/x86/lib/pc-conf-reg.c new file mode 100644 index 000000000000..febb52749e8d --- /dev/null +++ b/arch/x86/lib/pc-conf-reg.c @@ -0,0 +1,13 @@ +// SPDX-License-Identifier: GPL-2.0 +/* + * Support for the configuration register space at port I/O locations + * 0x22 and 0x23 variously used by PC architectures, e.g. the MP Spec, + * Cyrix CPUs, numerous chipsets. As the space is indirectly addressed + * it may have to be protected with a spinlock, depending on the context. + */ + +#include <linux/spinlock.h> + +#include <asm/pc-conf-reg.h> + +DEFINE_RAW_SPINLOCK(pc_conf_lock); diff --git a/arch/x86/mm/init.c b/arch/x86/mm/init.c index 75ef19aa8903..23a14d82e783 100644 --- a/arch/x86/mm/init.c +++ b/arch/x86/mm/init.c @@ -127,14 +127,12 @@ __ref void *alloc_low_pages(unsigned int num) unsigned long ret = 0; if (min_pfn_mapped < max_pfn_mapped) { - ret = memblock_find_in_range( + ret = memblock_phys_alloc_range( + PAGE_SIZE * num, PAGE_SIZE, min_pfn_mapped << PAGE_SHIFT, - max_pfn_mapped << PAGE_SHIFT, - PAGE_SIZE * num , PAGE_SIZE); + max_pfn_mapped << PAGE_SHIFT); } - if (ret) - memblock_reserve(ret, PAGE_SIZE * num); - else if (can_use_brk_pgt) + if (!ret && can_use_brk_pgt) ret = __pa(extend_brk(PAGE_SIZE * num, PAGE_SIZE)); if (!ret) @@ -610,8 +608,17 @@ static void __init memory_map_top_down(unsigned long map_start, unsigned long addr; unsigned long mapped_ram_size = 0; - /* xen has big range in reserved near end of ram, skip it at first.*/ - addr = memblock_find_in_range(map_start, map_end, PMD_SIZE, PMD_SIZE); + /* + * Systems that have many reserved areas near top of the memory, + * e.g. QEMU with less than 1G RAM and EFI enabled, or Xen, will + * require lots of 4K mappings which may exhaust pgt_buf. + * Start with top-most PMD_SIZE range aligned at PMD_SIZE to ensure + * there is enough mapped memory that can be allocated from + * memblock. + */ + addr = memblock_phys_alloc_range(PMD_SIZE, PMD_SIZE, map_start, + map_end); + memblock_free(addr, PMD_SIZE); real_end = addr + PMD_SIZE; /* step_size need to be small so pgt_buf from BRK could cover it */ diff --git a/arch/x86/mm/init_32.c b/arch/x86/mm/init_32.c index 74b78840182d..bd90b8fe81e4 100644 --- a/arch/x86/mm/init_32.c +++ b/arch/x86/mm/init_32.c @@ -801,8 +801,7 @@ int arch_add_memory(int nid, u64 start, u64 size, return __add_pages(nid, start_pfn, nr_pages, params); } -void arch_remove_memory(int nid, u64 start, u64 size, - struct vmem_altmap *altmap) +void arch_remove_memory(u64 start, u64 size, struct vmem_altmap *altmap) { unsigned long start_pfn = start >> PAGE_SHIFT; unsigned long nr_pages = size >> PAGE_SHIFT; diff --git a/arch/x86/mm/init_64.c b/arch/x86/mm/init_64.c index ddeaba947eb3..a6e11763763f 100644 --- a/arch/x86/mm/init_64.c +++ b/arch/x86/mm/init_64.c @@ -1255,8 +1255,7 @@ kernel_physical_mapping_remove(unsigned long start, unsigned long end) remove_pagetable(start, end, true, NULL); } -void __ref arch_remove_memory(int nid, u64 start, u64 size, - struct vmem_altmap *altmap) +void __ref arch_remove_memory(u64 start, u64 size, struct vmem_altmap *altmap) { unsigned long start_pfn = start >> PAGE_SHIFT; unsigned long nr_pages = size >> PAGE_SHIFT; diff --git a/arch/x86/mm/mmio-mod.c b/arch/x86/mm/mmio-mod.c index cd768dafca9e..933a2ebad471 100644 --- a/arch/x86/mm/mmio-mod.c +++ b/arch/x86/mm/mmio-mod.c @@ -376,12 +376,12 @@ static void enter_uniprocessor(void) goto out; } - get_online_cpus(); + cpus_read_lock(); cpumask_copy(downed_cpus, cpu_online_mask); cpumask_clear_cpu(cpumask_first(cpu_online_mask), downed_cpus); if (num_online_cpus() > 1) pr_notice("Disabling non-boot CPUs...\n"); - put_online_cpus(); + cpus_read_unlock(); for_each_cpu(cpu, downed_cpus) { err = remove_cpu(cpu); diff --git a/arch/x86/mm/numa.c b/arch/x86/mm/numa.c index e94da744386f..a1b5c71099e6 100644 --- a/arch/x86/mm/numa.c +++ b/arch/x86/mm/numa.c @@ -376,15 +376,14 @@ static int __init numa_alloc_distance(void) cnt++; size = cnt * cnt * sizeof(numa_distance[0]); - phys = memblock_find_in_range(0, PFN_PHYS(max_pfn_mapped), - size, PAGE_SIZE); + phys = memblock_phys_alloc_range(size, PAGE_SIZE, 0, + PFN_PHYS(max_pfn_mapped)); if (!phys) { pr_warn("Warning: can't allocate distance table!\n"); /* don't retry until explicitly reset */ numa_distance = (void *)1LU; return -ENOMEM; } - memblock_reserve(phys, size); numa_distance = __va(phys); numa_distance_cnt = cnt; diff --git a/arch/x86/mm/numa_emulation.c b/arch/x86/mm/numa_emulation.c index 87d77cc52f86..737491b13728 100644 --- a/arch/x86/mm/numa_emulation.c +++ b/arch/x86/mm/numa_emulation.c @@ -447,13 +447,12 @@ void __init numa_emulation(struct numa_meminfo *numa_meminfo, int numa_dist_cnt) if (numa_dist_cnt) { u64 phys; - phys = memblock_find_in_range(0, PFN_PHYS(max_pfn_mapped), - phys_size, PAGE_SIZE); + phys = memblock_phys_alloc_range(phys_size, PAGE_SIZE, 0, + PFN_PHYS(max_pfn_mapped)); if (!phys) { pr_warn("NUMA: Warning: can't allocate copy of distance table, disabling emulation\n"); goto no_emu; } - memblock_reserve(phys, phys_size); phys_dist = __va(phys); for (i = 0; i < numa_dist_cnt; i++) diff --git a/arch/x86/mm/pgtable.c b/arch/x86/mm/pgtable.c index 3364fe62b903..3481b35cb4ec 100644 --- a/arch/x86/mm/pgtable.c +++ b/arch/x86/mm/pgtable.c @@ -682,7 +682,6 @@ int p4d_clear_huge(p4d_t *p4d) } #endif -#if CONFIG_PGTABLE_LEVELS > 3 /** * pud_set_huge - setup kernel PUD mapping * @@ -722,23 +721,6 @@ int pud_set_huge(pud_t *pud, phys_addr_t addr, pgprot_t prot) } /** - * pud_clear_huge - clear kernel PUD mapping when it is set - * - * Returns 1 on success and 0 on failure (no PUD map is found). - */ -int pud_clear_huge(pud_t *pud) -{ - if (pud_large(*pud)) { - pud_clear(pud); - return 1; - } - - return 0; -} -#endif - -#if CONFIG_PGTABLE_LEVELS > 2 -/** * pmd_set_huge - setup kernel PMD mapping * * See text over pud_set_huge() above. @@ -769,6 +751,21 @@ int pmd_set_huge(pmd_t *pmd, phys_addr_t addr, pgprot_t prot) } /** + * pud_clear_huge - clear kernel PUD mapping when it is set + * + * Returns 1 on success and 0 on failure (no PUD map is found). + */ +int pud_clear_huge(pud_t *pud) +{ + if (pud_large(*pud)) { + pud_clear(pud); + return 1; + } + + return 0; +} + +/** * pmd_clear_huge - clear kernel PMD mapping when it is set * * Returns 1 on success and 0 on failure (no PMD map is found). @@ -782,7 +779,6 @@ int pmd_clear_huge(pmd_t *pmd) return 0; } -#endif #ifdef CONFIG_X86_64 /** diff --git a/arch/x86/mm/tlb.c b/arch/x86/mm/tlb.c index cfe6b1e85fa6..59ba2968af1b 100644 --- a/arch/x86/mm/tlb.c +++ b/arch/x86/mm/tlb.c @@ -8,11 +8,13 @@ #include <linux/export.h> #include <linux/cpu.h> #include <linux/debugfs.h> +#include <linux/sched/smt.h> #include <asm/tlbflush.h> #include <asm/mmu_context.h> #include <asm/nospec-branch.h> #include <asm/cache.h> +#include <asm/cacheflush.h> #include <asm/apic.h> #include <asm/perf_event.h> @@ -43,10 +45,15 @@ */ /* - * Use bit 0 to mangle the TIF_SPEC_IB state into the mm pointer which is - * stored in cpu_tlb_state.last_user_mm_ibpb. + * Bits to mangle the TIF_SPEC_* state into the mm pointer which is + * stored in cpu_tlb_state.last_user_mm_spec. */ #define LAST_USER_MM_IBPB 0x1UL +#define LAST_USER_MM_L1D_FLUSH 0x2UL +#define LAST_USER_MM_SPEC_MASK (LAST_USER_MM_IBPB | LAST_USER_MM_L1D_FLUSH) + +/* Bits to set when tlbstate and flush is (re)initialized */ +#define LAST_USER_MM_INIT LAST_USER_MM_IBPB /* * The x86 feature is called PCID (Process Context IDentifier). It is similar @@ -317,20 +324,70 @@ void switch_mm(struct mm_struct *prev, struct mm_struct *next, local_irq_restore(flags); } -static unsigned long mm_mangle_tif_spec_ib(struct task_struct *next) +/* + * Invoked from return to user/guest by a task that opted-in to L1D + * flushing but ended up running on an SMT enabled core due to wrong + * affinity settings or CPU hotplug. This is part of the paranoid L1D flush + * contract which this task requested. + */ +static void l1d_flush_force_sigbus(struct callback_head *ch) +{ + force_sig(SIGBUS); +} + +static void l1d_flush_evaluate(unsigned long prev_mm, unsigned long next_mm, + struct task_struct *next) +{ + /* Flush L1D if the outgoing task requests it */ + if (prev_mm & LAST_USER_MM_L1D_FLUSH) + wrmsrl(MSR_IA32_FLUSH_CMD, L1D_FLUSH); + + /* Check whether the incoming task opted in for L1D flush */ + if (likely(!(next_mm & LAST_USER_MM_L1D_FLUSH))) + return; + + /* + * Validate that it is not running on an SMT sibling as this would + * make the excercise pointless because the siblings share L1D. If + * it runs on a SMT sibling, notify it with SIGBUS on return to + * user/guest + */ + if (this_cpu_read(cpu_info.smt_active)) { + clear_ti_thread_flag(&next->thread_info, TIF_SPEC_L1D_FLUSH); + next->l1d_flush_kill.func = l1d_flush_force_sigbus; + task_work_add(next, &next->l1d_flush_kill, TWA_RESUME); + } +} + +static unsigned long mm_mangle_tif_spec_bits(struct task_struct *next) { unsigned long next_tif = task_thread_info(next)->flags; - unsigned long ibpb = (next_tif >> TIF_SPEC_IB) & LAST_USER_MM_IBPB; + unsigned long spec_bits = (next_tif >> TIF_SPEC_IB) & LAST_USER_MM_SPEC_MASK; - return (unsigned long)next->mm | ibpb; + /* + * Ensure that the bit shift above works as expected and the two flags + * end up in bit 0 and 1. + */ + BUILD_BUG_ON(TIF_SPEC_L1D_FLUSH != TIF_SPEC_IB + 1); + + return (unsigned long)next->mm | spec_bits; } -static void cond_ibpb(struct task_struct *next) +static void cond_mitigation(struct task_struct *next) { + unsigned long prev_mm, next_mm; + if (!next || !next->mm) return; + next_mm = mm_mangle_tif_spec_bits(next); + prev_mm = this_cpu_read(cpu_tlbstate.last_user_mm_spec); + /* + * Avoid user/user BTB poisoning by flushing the branch predictor + * when switching between processes. This stops one process from + * doing Spectre-v2 attacks on another. + * * Both, the conditional and the always IBPB mode use the mm * pointer to avoid the IBPB when switching between tasks of the * same process. Using the mm pointer instead of mm->context.ctx_id @@ -340,8 +397,6 @@ static void cond_ibpb(struct task_struct *next) * exposed data is not really interesting. */ if (static_branch_likely(&switch_mm_cond_ibpb)) { - unsigned long prev_mm, next_mm; - /* * This is a bit more complex than the always mode because * it has to handle two cases: @@ -371,20 +426,14 @@ static void cond_ibpb(struct task_struct *next) * Optimize this with reasonably small overhead for the * above cases. Mangle the TIF_SPEC_IB bit into the mm * pointer of the incoming task which is stored in - * cpu_tlbstate.last_user_mm_ibpb for comparison. - */ - next_mm = mm_mangle_tif_spec_ib(next); - prev_mm = this_cpu_read(cpu_tlbstate.last_user_mm_ibpb); - - /* + * cpu_tlbstate.last_user_mm_spec for comparison. + * * Issue IBPB only if the mm's are different and one or * both have the IBPB bit set. */ if (next_mm != prev_mm && (next_mm | prev_mm) & LAST_USER_MM_IBPB) indirect_branch_prediction_barrier(); - - this_cpu_write(cpu_tlbstate.last_user_mm_ibpb, next_mm); } if (static_branch_unlikely(&switch_mm_always_ibpb)) { @@ -393,11 +442,22 @@ static void cond_ibpb(struct task_struct *next) * different context than the user space task which ran * last on this CPU. */ - if (this_cpu_read(cpu_tlbstate.last_user_mm) != next->mm) { + if ((prev_mm & ~LAST_USER_MM_SPEC_MASK) != + (unsigned long)next->mm) indirect_branch_prediction_barrier(); - this_cpu_write(cpu_tlbstate.last_user_mm, next->mm); - } } + + if (static_branch_unlikely(&switch_mm_cond_l1d_flush)) { + /* + * Flush L1D when the outgoing task requested it and/or + * check whether the incoming task requested L1D flushing + * and ended up on an SMT sibling. + */ + if (unlikely((prev_mm | next_mm) & LAST_USER_MM_L1D_FLUSH)) + l1d_flush_evaluate(prev_mm, next_mm, next); + } + + this_cpu_write(cpu_tlbstate.last_user_mm_spec, next_mm); } #ifdef CONFIG_PERF_EVENTS @@ -531,11 +591,10 @@ void switch_mm_irqs_off(struct mm_struct *prev, struct mm_struct *next, need_flush = true; } else { /* - * Avoid user/user BTB poisoning by flushing the branch - * predictor when switching between processes. This stops - * one process from doing Spectre-v2 attacks on another. + * Apply process to process speculation vulnerability + * mitigations if applicable. */ - cond_ibpb(tsk); + cond_mitigation(tsk); /* * Stop remote flushes for the previous mm. @@ -643,7 +702,7 @@ void initialize_tlbstate_and_flush(void) write_cr3(build_cr3(mm->pgd, 0)); /* Reinitialize tlbstate. */ - this_cpu_write(cpu_tlbstate.last_user_mm_ibpb, LAST_USER_MM_IBPB); + this_cpu_write(cpu_tlbstate.last_user_mm_spec, LAST_USER_MM_INIT); this_cpu_write(cpu_tlbstate.loaded_mm_asid, 0); this_cpu_write(cpu_tlbstate.next_asid, 1); this_cpu_write(cpu_tlbstate.ctxs[0].ctx_id, mm->context.ctx_id); diff --git a/arch/x86/net/bpf_jit_comp.c b/arch/x86/net/bpf_jit_comp.c index e835164189f1..0fe6aacef3db 100644 --- a/arch/x86/net/bpf_jit_comp.c +++ b/arch/x86/net/bpf_jit_comp.c @@ -570,6 +570,9 @@ static void bpf_tail_call_direct_fixup(struct bpf_prog *prog) for (i = 0; i < prog->aux->size_poke_tab; i++) { poke = &prog->aux->poke_tab[i]; + if (poke->aux && poke->aux != prog->aux) + continue; + WARN_ON_ONCE(READ_ONCE(poke->tailcall_target_stable)); if (poke->reason != BPF_POKE_REASON_TAIL_CALL) @@ -1216,6 +1219,13 @@ static int do_jit(struct bpf_prog *bpf_prog, int *addrs, u8 *image, } break; + /* speculation barrier */ + case BPF_ST | BPF_NOSPEC: + if (boot_cpu_has(X86_FEATURE_XMM2)) + /* Emit 'lfence' */ + EMIT3(0x0F, 0xAE, 0xE8); + break; + /* ST: *(u8*)(dst_reg + off) = imm */ case BPF_ST | BPF_MEM | BPF_B: if (is_ereg(dst_reg)) @@ -1951,6 +1961,9 @@ int arch_prepare_bpf_trampoline(struct bpf_tramp_image *im, void *image, void *i if (flags & BPF_TRAMP_F_CALL_ORIG) stack_size += 8; /* room for return value of orig_call */ + if (flags & BPF_TRAMP_F_IP_ARG) + stack_size += 8; /* room for IP address argument */ + if (flags & BPF_TRAMP_F_SKIP_FRAME) /* skip patched call instruction and point orig_call to actual * body of the kernel function. @@ -1964,6 +1977,22 @@ int arch_prepare_bpf_trampoline(struct bpf_tramp_image *im, void *image, void *i EMIT4(0x48, 0x83, 0xEC, stack_size); /* sub rsp, stack_size */ EMIT1(0x53); /* push rbx */ + if (flags & BPF_TRAMP_F_IP_ARG) { + /* Store IP address of the traced function: + * mov rax, QWORD PTR [rbp + 8] + * sub rax, X86_PATCH_SIZE + * mov QWORD PTR [rbp - stack_size], rax + */ + emit_ldx(&prog, BPF_DW, BPF_REG_0, BPF_REG_FP, 8); + EMIT4(0x48, 0x83, 0xe8, X86_PATCH_SIZE); + emit_stx(&prog, BPF_DW, BPF_REG_FP, BPF_REG_0, -stack_size); + + /* Continue with stack_size for regs storage, stack will + * be correctly restored with 'leave' instruction. + */ + stack_size -= 8; + } + save_regs(m, &prog, nr_args, stack_size); if (flags & BPF_TRAMP_F_CALL_ORIG) { diff --git a/arch/x86/net/bpf_jit_comp32.c b/arch/x86/net/bpf_jit_comp32.c index 3da88ded6ee3..3bfda5f502cb 100644 --- a/arch/x86/net/bpf_jit_comp32.c +++ b/arch/x86/net/bpf_jit_comp32.c @@ -1886,6 +1886,12 @@ static int do_jit(struct bpf_prog *bpf_prog, int *addrs, u8 *image, i++; break; } + /* speculation barrier */ + case BPF_ST | BPF_NOSPEC: + if (boot_cpu_has(X86_FEATURE_XMM2)) + /* Emit 'lfence' */ + EMIT3(0x0F, 0xAE, 0xE8); + break; /* ST: *(u8*)(dst_reg + off) = imm */ case BPF_ST | BPF_MEM | BPF_H: case BPF_ST | BPF_MEM | BPF_B: diff --git a/arch/x86/pci/irq.c b/arch/x86/pci/irq.c index d3a73f9335e1..97b63e35e152 100644 --- a/arch/x86/pci/irq.c +++ b/arch/x86/pci/irq.c @@ -13,9 +13,13 @@ #include <linux/dmi.h> #include <linux/io.h> #include <linux/smp.h> +#include <linux/spinlock.h> #include <asm/io_apic.h> #include <linux/irq.h> #include <linux/acpi.h> + +#include <asm/i8259.h> +#include <asm/pc-conf-reg.h> #include <asm/pci_x86.h> #define PIRQ_SIGNATURE (('$' << 0) + ('P' << 8) + ('I' << 16) + ('R' << 24)) @@ -47,6 +51,8 @@ struct irq_router { int (*get)(struct pci_dev *router, struct pci_dev *dev, int pirq); int (*set)(struct pci_dev *router, struct pci_dev *dev, int pirq, int new); + int (*lvl)(struct pci_dev *router, struct pci_dev *dev, int pirq, + int irq); }; struct irq_router_handler { @@ -153,7 +159,7 @@ static void __init pirq_peer_trick(void) void elcr_set_level_irq(unsigned int irq) { unsigned char mask = 1 << (irq & 7); - unsigned int port = 0x4d0 + (irq >> 3); + unsigned int port = PIC_ELCR1 + (irq >> 3); unsigned char val; static u16 elcr_irq_mask; @@ -170,6 +176,139 @@ void elcr_set_level_irq(unsigned int irq) } /* + * PIRQ routing for the M1487 ISA Bus Controller (IBC) ASIC used + * with the ALi FinALi 486 chipset. The IBC is not decoded in the + * PCI configuration space, so we identify it by the accompanying + * M1489 Cache-Memory PCI Controller (CMP) ASIC. + * + * There are four 4-bit mappings provided, spread across two PCI + * INTx Routing Table Mapping Registers, available in the port I/O + * space accessible indirectly via the index/data register pair at + * 0x22/0x23, located at indices 0x42 and 0x43 for the INT1/INT2 + * and INT3/INT4 lines respectively. The INT1/INT3 and INT2/INT4 + * lines are mapped in the low and the high 4-bit nibble of the + * corresponding register as follows: + * + * 0000 : Disabled + * 0001 : IRQ9 + * 0010 : IRQ3 + * 0011 : IRQ10 + * 0100 : IRQ4 + * 0101 : IRQ5 + * 0110 : IRQ7 + * 0111 : IRQ6 + * 1000 : Reserved + * 1001 : IRQ11 + * 1010 : Reserved + * 1011 : IRQ12 + * 1100 : Reserved + * 1101 : IRQ14 + * 1110 : Reserved + * 1111 : IRQ15 + * + * In addition to the usual ELCR register pair there is a separate + * PCI INTx Sensitivity Register at index 0x44 in the same port I/O + * space, whose bits 3:0 select the trigger mode for INT[4:1] lines + * respectively. Any bit set to 1 causes interrupts coming on the + * corresponding line to be passed to ISA as edge-triggered and + * otherwise they are passed as level-triggered. Manufacturer's + * documentation says this register has to be set consistently with + * the relevant ELCR register. + * + * Accesses to the port I/O space concerned here need to be unlocked + * by writing the value of 0xc5 to the Lock Register at index 0x03 + * beforehand. Any other value written to said register prevents + * further accesses from reaching the register file, except for the + * Lock Register being written with 0xc5 again. + * + * References: + * + * "M1489/M1487: 486 PCI Chip Set", Version 1.2, Acer Laboratories + * Inc., July 1997 + */ + +#define PC_CONF_FINALI_LOCK 0x03u +#define PC_CONF_FINALI_PCI_INTX_RT1 0x42u +#define PC_CONF_FINALI_PCI_INTX_RT2 0x43u +#define PC_CONF_FINALI_PCI_INTX_SENS 0x44u + +#define PC_CONF_FINALI_LOCK_KEY 0xc5u + +static u8 read_pc_conf_nybble(u8 base, u8 index) +{ + u8 reg = base + (index >> 1); + u8 x; + + x = pc_conf_get(reg); + return index & 1 ? x >> 4 : x & 0xf; +} + +static void write_pc_conf_nybble(u8 base, u8 index, u8 val) +{ + u8 reg = base + (index >> 1); + u8 x; + + x = pc_conf_get(reg); + x = index & 1 ? (x & 0x0f) | (val << 4) : (x & 0xf0) | val; + pc_conf_set(reg, x); +} + +static int pirq_finali_get(struct pci_dev *router, struct pci_dev *dev, + int pirq) +{ + static const u8 irqmap[16] = { + 0, 9, 3, 10, 4, 5, 7, 6, 0, 11, 0, 12, 0, 14, 0, 15 + }; + unsigned long flags; + u8 x; + + raw_spin_lock_irqsave(&pc_conf_lock, flags); + pc_conf_set(PC_CONF_FINALI_LOCK, PC_CONF_FINALI_LOCK_KEY); + x = irqmap[read_pc_conf_nybble(PC_CONF_FINALI_PCI_INTX_RT1, pirq - 1)]; + pc_conf_set(PC_CONF_FINALI_LOCK, 0); + raw_spin_unlock_irqrestore(&pc_conf_lock, flags); + return x; +} + +static int pirq_finali_set(struct pci_dev *router, struct pci_dev *dev, + int pirq, int irq) +{ + static const u8 irqmap[16] = { + 0, 0, 0, 2, 4, 5, 7, 6, 0, 1, 3, 9, 11, 0, 13, 15 + }; + u8 val = irqmap[irq]; + unsigned long flags; + + if (!val) + return 0; + + raw_spin_lock_irqsave(&pc_conf_lock, flags); + pc_conf_set(PC_CONF_FINALI_LOCK, PC_CONF_FINALI_LOCK_KEY); + write_pc_conf_nybble(PC_CONF_FINALI_PCI_INTX_RT1, pirq - 1, val); + pc_conf_set(PC_CONF_FINALI_LOCK, 0); + raw_spin_unlock_irqrestore(&pc_conf_lock, flags); + return 1; +} + +static int pirq_finali_lvl(struct pci_dev *router, struct pci_dev *dev, + int pirq, int irq) +{ + u8 mask = ~(1u << (pirq - 1)); + unsigned long flags; + u8 trig; + + elcr_set_level_irq(irq); + raw_spin_lock_irqsave(&pc_conf_lock, flags); + pc_conf_set(PC_CONF_FINALI_LOCK, PC_CONF_FINALI_LOCK_KEY); + trig = pc_conf_get(PC_CONF_FINALI_PCI_INTX_SENS); + trig &= mask; + pc_conf_set(PC_CONF_FINALI_PCI_INTX_SENS, trig); + pc_conf_set(PC_CONF_FINALI_LOCK, 0); + raw_spin_unlock_irqrestore(&pc_conf_lock, flags); + return 1; +} + +/* * Common IRQ routing practice: nibbles in config space, * offset by some magic constant. */ @@ -220,6 +359,74 @@ static int pirq_ali_set(struct pci_dev *router, struct pci_dev *dev, int pirq, i } /* + * PIRQ routing for the 82374EB/82374SB EISA System Component (ESC) + * ASIC used with the Intel 82420 and 82430 PCIsets. The ESC is not + * decoded in the PCI configuration space, so we identify it by the + * accompanying 82375EB/82375SB PCI-EISA Bridge (PCEB) ASIC. + * + * There are four PIRQ Route Control registers, available in the + * port I/O space accessible indirectly via the index/data register + * pair at 0x22/0x23, located at indices 0x60/0x61/0x62/0x63 for the + * PIRQ0/1/2/3# lines respectively. The semantics is the same as + * with the PIIX router. + * + * Accesses to the port I/O space concerned here need to be unlocked + * by writing the value of 0x0f to the ESC ID Register at index 0x02 + * beforehand. Any other value written to said register prevents + * further accesses from reaching the register file, except for the + * ESC ID Register being written with 0x0f again. + * + * References: + * + * "82374EB/82374SB EISA System Component (ESC)", Intel Corporation, + * Order Number: 290476-004, March 1996 + * + * "82375EB/82375SB PCI-EISA Bridge (PCEB)", Intel Corporation, Order + * Number: 290477-004, March 1996 + */ + +#define PC_CONF_I82374_ESC_ID 0x02u +#define PC_CONF_I82374_PIRQ_ROUTE_CONTROL 0x60u + +#define PC_CONF_I82374_ESC_ID_KEY 0x0fu + +static int pirq_esc_get(struct pci_dev *router, struct pci_dev *dev, int pirq) +{ + unsigned long flags; + int reg; + u8 x; + + reg = pirq; + if (reg >= 1 && reg <= 4) + reg += PC_CONF_I82374_PIRQ_ROUTE_CONTROL - 1; + + raw_spin_lock_irqsave(&pc_conf_lock, flags); + pc_conf_set(PC_CONF_I82374_ESC_ID, PC_CONF_I82374_ESC_ID_KEY); + x = pc_conf_get(reg); + pc_conf_set(PC_CONF_I82374_ESC_ID, 0); + raw_spin_unlock_irqrestore(&pc_conf_lock, flags); + return (x < 16) ? x : 0; +} + +static int pirq_esc_set(struct pci_dev *router, struct pci_dev *dev, int pirq, + int irq) +{ + unsigned long flags; + int reg; + + reg = pirq; + if (reg >= 1 && reg <= 4) + reg += PC_CONF_I82374_PIRQ_ROUTE_CONTROL - 1; + + raw_spin_lock_irqsave(&pc_conf_lock, flags); + pc_conf_set(PC_CONF_I82374_ESC_ID, PC_CONF_I82374_ESC_ID_KEY); + pc_conf_set(reg, irq); + pc_conf_set(PC_CONF_I82374_ESC_ID, 0); + raw_spin_unlock_irqrestore(&pc_conf_lock, flags); + return 1; +} + +/* * The Intel PIIX4 pirq rules are fairly simple: "pirq" is * just a pointer to the config space. */ @@ -238,6 +445,50 @@ static int pirq_piix_set(struct pci_dev *router, struct pci_dev *dev, int pirq, } /* + * PIRQ routing for the 82426EX ISA Bridge (IB) ASIC used with the + * Intel 82420EX PCIset. + * + * There are only two PIRQ Route Control registers, available in the + * combined 82425EX/82426EX PCI configuration space, at 0x66 and 0x67 + * for the PIRQ0# and PIRQ1# lines respectively. The semantics is + * the same as with the PIIX router. + * + * References: + * + * "82420EX PCIset Data Sheet, 82425EX PCI System Controller (PSC) + * and 82426EX ISA Bridge (IB)", Intel Corporation, Order Number: + * 290488-004, December 1995 + */ + +#define PCI_I82426EX_PIRQ_ROUTE_CONTROL 0x66u + +static int pirq_ib_get(struct pci_dev *router, struct pci_dev *dev, int pirq) +{ + int reg; + u8 x; + + reg = pirq; + if (reg >= 1 && reg <= 2) + reg += PCI_I82426EX_PIRQ_ROUTE_CONTROL - 1; + + pci_read_config_byte(router, reg, &x); + return (x < 16) ? x : 0; +} + +static int pirq_ib_set(struct pci_dev *router, struct pci_dev *dev, int pirq, + int irq) +{ + int reg; + + reg = pirq; + if (reg >= 1 && reg <= 2) + reg += PCI_I82426EX_PIRQ_ROUTE_CONTROL - 1; + + pci_write_config_byte(router, reg, irq); + return 1; +} + +/* * The VIA pirq rules are nibble-based, like ALI, * but without the ugly irq number munging. * However, PIRQD is in the upper instead of lower 4 bits. @@ -549,6 +800,11 @@ static __init int intel_router_probe(struct irq_router *r, struct pci_dev *route return 0; switch (device) { + case PCI_DEVICE_ID_INTEL_82375: + r->name = "PCEB/ESC"; + r->get = pirq_esc_get; + r->set = pirq_esc_set; + return 1; case PCI_DEVICE_ID_INTEL_82371FB_0: case PCI_DEVICE_ID_INTEL_82371SB_0: case PCI_DEVICE_ID_INTEL_82371AB_0: @@ -594,6 +850,11 @@ static __init int intel_router_probe(struct irq_router *r, struct pci_dev *route r->get = pirq_piix_get; r->set = pirq_piix_set; return 1; + case PCI_DEVICE_ID_INTEL_82425: + r->name = "PSC/IB"; + r->get = pirq_ib_get; + r->set = pirq_ib_set; + return 1; } if ((device >= PCI_DEVICE_ID_INTEL_5_3400_SERIES_LPC_MIN && @@ -745,6 +1006,12 @@ static __init int ite_router_probe(struct irq_router *r, struct pci_dev *router, static __init int ali_router_probe(struct irq_router *r, struct pci_dev *router, u16 device) { switch (device) { + case PCI_DEVICE_ID_AL_M1489: + r->name = "FinALi"; + r->get = pirq_finali_get; + r->set = pirq_finali_set; + r->lvl = pirq_finali_lvl; + return 1; case PCI_DEVICE_ID_AL_M1533: case PCI_DEVICE_ID_AL_M1563: r->name = "ALI"; @@ -968,11 +1235,17 @@ static int pcibios_lookup_irq(struct pci_dev *dev, int assign) } else if (r->get && (irq = r->get(pirq_router_dev, dev, pirq)) && \ ((!(pci_probe & PCI_USE_PIRQ_MASK)) || ((1 << irq) & mask))) { msg = "found"; - elcr_set_level_irq(irq); + if (r->lvl) + r->lvl(pirq_router_dev, dev, pirq, irq); + else + elcr_set_level_irq(irq); } else if (newirq && r->set && (dev->class >> 8) != PCI_CLASS_DISPLAY_VGA) { if (r->set(pirq_router_dev, dev, pirq, newirq)) { - elcr_set_level_irq(newirq); + if (r->lvl) + r->lvl(pirq_router_dev, dev, pirq, newirq); + else + elcr_set_level_irq(newirq); msg = "assigned"; irq = newirq; } diff --git a/arch/x86/pci/numachip.c b/arch/x86/pci/numachip.c index 01a085d9135a..4f0147d4e225 100644 --- a/arch/x86/pci/numachip.c +++ b/arch/x86/pci/numachip.c @@ -12,6 +12,7 @@ #include <linux/pci.h> #include <asm/pci_x86.h> +#include <asm/numachip/numachip.h> static u8 limit __read_mostly; diff --git a/arch/x86/pci/sta2x11-fixup.c b/arch/x86/pci/sta2x11-fixup.c index 7d2525691854..101081ad64b6 100644 --- a/arch/x86/pci/sta2x11-fixup.c +++ b/arch/x86/pci/sta2x11-fixup.c @@ -146,8 +146,7 @@ static void sta2x11_map_ep(struct pci_dev *pdev) dev_err(dev, "sta2x11: could not set DMA offset\n"); dev->bus_dma_limit = max_amba_addr; - pci_set_consistent_dma_mask(pdev, max_amba_addr); - pci_set_dma_mask(pdev, max_amba_addr); + dma_set_mask_and_coherent(&pdev->dev, max_amba_addr); /* Configure AHB mapping */ pci_write_config_dword(pdev, AHB_PEXLBASE(0), 0); diff --git a/arch/x86/power/cpu.c b/arch/x86/power/cpu.c index 3a070e7cdb8b..6665f8802098 100644 --- a/arch/x86/power/cpu.c +++ b/arch/x86/power/cpu.c @@ -58,19 +58,20 @@ static void msr_restore_context(struct saved_context *ctxt) } /** - * __save_processor_state - save CPU registers before creating a - * hibernation image and before restoring the memory state from it - * @ctxt - structure to store the registers contents in + * __save_processor_state() - Save CPU registers before creating a + * hibernation image and before restoring + * the memory state from it + * @ctxt: Structure to store the registers contents in. * - * NOTE: If there is a CPU register the modification of which by the - * boot kernel (ie. the kernel used for loading the hibernation image) - * might affect the operations of the restored target kernel (ie. the one - * saved in the hibernation image), then its contents must be saved by this - * function. In other words, if kernel A is hibernated and different - * kernel B is used for loading the hibernation image into memory, the - * kernel A's __save_processor_state() function must save all registers - * needed by kernel A, so that it can operate correctly after the resume - * regardless of what kernel B does in the meantime. + * NOTE: If there is a CPU register the modification of which by the + * boot kernel (ie. the kernel used for loading the hibernation image) + * might affect the operations of the restored target kernel (ie. the one + * saved in the hibernation image), then its contents must be saved by this + * function. In other words, if kernel A is hibernated and different + * kernel B is used for loading the hibernation image into memory, the + * kernel A's __save_processor_state() function must save all registers + * needed by kernel A, so that it can operate correctly after the resume + * regardless of what kernel B does in the meantime. */ static void __save_processor_state(struct saved_context *ctxt) { @@ -181,9 +182,9 @@ static void fix_processor_context(void) } /** - * __restore_processor_state - restore the contents of CPU registers saved - * by __save_processor_state() - * @ctxt - structure to load the registers contents from + * __restore_processor_state() - Restore the contents of CPU registers saved + * by __save_processor_state() + * @ctxt: Structure to load the registers contents from. * * The asm code that gets us here will have restored a usable GDT, although * it will be pointing to the wrong alias. diff --git a/arch/x86/realmode/init.c b/arch/x86/realmode/init.c index 6534c92d0f83..31b5856010cb 100644 --- a/arch/x86/realmode/init.c +++ b/arch/x86/realmode/init.c @@ -28,7 +28,7 @@ void __init reserve_real_mode(void) WARN_ON(slab_is_available()); /* Has to be under 1M so we can execute real-mode AP code. */ - mem = memblock_find_in_range(0, 1<<20, size, PAGE_SIZE); + mem = memblock_phys_alloc_range(size, PAGE_SIZE, 0, 1<<20); if (!mem) pr_info("No sub-1M memory is available for the trampoline\n"); else diff --git a/arch/x86/tools/chkobjdump.awk b/arch/x86/tools/chkobjdump.awk index fd1ab80be0de..a4cf678cf5c8 100644 --- a/arch/x86/tools/chkobjdump.awk +++ b/arch/x86/tools/chkobjdump.awk @@ -10,6 +10,7 @@ BEGIN { /^GNU objdump/ { verstr = "" + gsub(/\(.*\)/, ""); for (i = 3; i <= NF; i++) if (match($(i), "^[0-9]")) { verstr = $(i); diff --git a/arch/x86/tools/relocs.c b/arch/x86/tools/relocs.c index 04c5a44b9682..27c82207d387 100644 --- a/arch/x86/tools/relocs.c +++ b/arch/x86/tools/relocs.c @@ -26,6 +26,9 @@ static struct relocs relocs32; #if ELF_BITS == 64 static struct relocs relocs32neg; static struct relocs relocs64; +#define FMT PRIu64 +#else +#define FMT PRIu32 #endif struct section { @@ -57,12 +60,12 @@ static const char * const sym_regex_kernel[S_NSYMTYPES] = { [S_REL] = "^(__init_(begin|end)|" "__x86_cpu_dev_(start|end)|" - "(__parainstructions|__alt_instructions)(|_end)|" - "(__iommu_table|__apicdrivers|__smp_locks)(|_end)|" + "(__parainstructions|__alt_instructions)(_end)?|" + "(__iommu_table|__apicdrivers|__smp_locks)(_end)?|" "__(start|end)_pci_.*|" "__(start|end)_builtin_fw|" - "__(start|stop)___ksymtab(|_gpl)|" - "__(start|stop)___kcrctab(|_gpl)|" + "__(start|stop)___ksymtab(_gpl)?|" + "__(start|stop)___kcrctab(_gpl)?|" "__(start|stop)___param|" "__(start|stop)___modver|" "__(start|stop)___bug_table|" @@ -389,7 +392,7 @@ static void read_ehdr(FILE *fp) Elf_Shdr shdr; if (fseek(fp, ehdr.e_shoff, SEEK_SET) < 0) - die("Seek to %d failed: %s\n", ehdr.e_shoff, strerror(errno)); + die("Seek to %" FMT " failed: %s\n", ehdr.e_shoff, strerror(errno)); if (fread(&shdr, sizeof(shdr), 1, fp) != 1) die("Cannot read initial ELF section header: %s\n", strerror(errno)); @@ -412,17 +415,17 @@ static void read_shdrs(FILE *fp) secs = calloc(shnum, sizeof(struct section)); if (!secs) { - die("Unable to allocate %d section headers\n", + die("Unable to allocate %ld section headers\n", shnum); } if (fseek(fp, ehdr.e_shoff, SEEK_SET) < 0) { - die("Seek to %d failed: %s\n", - ehdr.e_shoff, strerror(errno)); + die("Seek to %" FMT " failed: %s\n", + ehdr.e_shoff, strerror(errno)); } for (i = 0; i < shnum; i++) { struct section *sec = &secs[i]; if (fread(&shdr, sizeof(shdr), 1, fp) != 1) - die("Cannot read ELF section headers %d/%d: %s\n", + die("Cannot read ELF section headers %d/%ld: %s\n", i, shnum, strerror(errno)); sec->shdr.sh_name = elf_word_to_cpu(shdr.sh_name); sec->shdr.sh_type = elf_word_to_cpu(shdr.sh_type); @@ -450,12 +453,12 @@ static void read_strtabs(FILE *fp) } sec->strtab = malloc(sec->shdr.sh_size); if (!sec->strtab) { - die("malloc of %d bytes for strtab failed\n", - sec->shdr.sh_size); + die("malloc of %" FMT " bytes for strtab failed\n", + sec->shdr.sh_size); } if (fseek(fp, sec->shdr.sh_offset, SEEK_SET) < 0) { - die("Seek to %d failed: %s\n", - sec->shdr.sh_offset, strerror(errno)); + die("Seek to %" FMT " failed: %s\n", + sec->shdr.sh_offset, strerror(errno)); } if (fread(sec->strtab, 1, sec->shdr.sh_size, fp) != sec->shdr.sh_size) { @@ -475,12 +478,12 @@ static void read_symtabs(FILE *fp) } sec->symtab = malloc(sec->shdr.sh_size); if (!sec->symtab) { - die("malloc of %d bytes for symtab failed\n", - sec->shdr.sh_size); + die("malloc of %" FMT " bytes for symtab failed\n", + sec->shdr.sh_size); } if (fseek(fp, sec->shdr.sh_offset, SEEK_SET) < 0) { - die("Seek to %d failed: %s\n", - sec->shdr.sh_offset, strerror(errno)); + die("Seek to %" FMT " failed: %s\n", + sec->shdr.sh_offset, strerror(errno)); } if (fread(sec->symtab, 1, sec->shdr.sh_size, fp) != sec->shdr.sh_size) { @@ -508,12 +511,12 @@ static void read_relocs(FILE *fp) } sec->reltab = malloc(sec->shdr.sh_size); if (!sec->reltab) { - die("malloc of %d bytes for relocs failed\n", - sec->shdr.sh_size); + die("malloc of %" FMT " bytes for relocs failed\n", + sec->shdr.sh_size); } if (fseek(fp, sec->shdr.sh_offset, SEEK_SET) < 0) { - die("Seek to %d failed: %s\n", - sec->shdr.sh_offset, strerror(errno)); + die("Seek to %" FMT " failed: %s\n", + sec->shdr.sh_offset, strerror(errno)); } if (fread(sec->reltab, 1, sec->shdr.sh_size, fp) != sec->shdr.sh_size) { diff --git a/arch/x86/tools/relocs.h b/arch/x86/tools/relocs.h index 43c83c0fd22c..4c49c82446eb 100644 --- a/arch/x86/tools/relocs.h +++ b/arch/x86/tools/relocs.h @@ -17,6 +17,7 @@ #include <regex.h> #include <tools/le_byteshift.h> +__attribute__((__format__(printf, 1, 2))) void die(char *fmt, ...) __attribute__((noreturn)); #define ARRAY_SIZE(x) (sizeof(x) / sizeof((x)[0])) diff --git a/arch/x86/xen/enlighten_pv.c b/arch/x86/xen/enlighten_pv.c index 03149422dce2..753f63734c13 100644 --- a/arch/x86/xen/enlighten_pv.c +++ b/arch/x86/xen/enlighten_pv.c @@ -116,9 +116,8 @@ static void __init xen_banner(void) HYPERVISOR_xen_version(XENVER_extraversion, &extra); pr_info("Booting paravirtualized kernel on %s\n", pv_info.name); - printk(KERN_INFO "Xen version: %d.%d%s%s\n", - version >> 16, version & 0xffff, extra.extraversion, - xen_feature(XENFEAT_mmu_pt_update_preserve_ad) ? " (preserve-AD)" : ""); + pr_info("Xen version: %d.%d%s (preserve-AD)\n", + version >> 16, version & 0xffff, extra.extraversion); } static void __init xen_pv_init_platform(void) @@ -1302,13 +1301,6 @@ asmlinkage __visible void __init xen_start_kernel(void) xen_init_apic(); #endif - if (xen_feature(XENFEAT_mmu_pt_update_preserve_ad)) { - pv_ops.mmu.ptep_modify_prot_start = - xen_ptep_modify_prot_start; - pv_ops.mmu.ptep_modify_prot_commit = - xen_ptep_modify_prot_commit; - } - machine_ops = xen_machine_ops; /* diff --git a/arch/x86/xen/mmu_pv.c b/arch/x86/xen/mmu_pv.c index ade789e73ee4..1df5f01529e5 100644 --- a/arch/x86/xen/mmu_pv.c +++ b/arch/x86/xen/mmu_pv.c @@ -2099,8 +2099,8 @@ static const struct pv_mmu_ops xen_mmu_ops __initconst = { .set_pte = xen_set_pte_init, .set_pmd = xen_set_pmd_hyper, - .ptep_modify_prot_start = __ptep_modify_prot_start, - .ptep_modify_prot_commit = __ptep_modify_prot_commit, + .ptep_modify_prot_start = xen_ptep_modify_prot_start, + .ptep_modify_prot_commit = xen_ptep_modify_prot_commit, .pte_val = PV_CALLEE_SAVE(xen_pte_val), .pgd_val = PV_CALLEE_SAVE(xen_pgd_val), diff --git a/arch/x86/xen/p2m.c b/arch/x86/xen/p2m.c index ac06ca32e9ef..5e6e236977c7 100644 --- a/arch/x86/xen/p2m.c +++ b/arch/x86/xen/p2m.c @@ -618,8 +618,8 @@ int xen_alloc_p2m_entry(unsigned long pfn) } /* Expanded the p2m? */ - if (pfn > xen_p2m_last_pfn) { - xen_p2m_last_pfn = pfn; + if (pfn >= xen_p2m_last_pfn) { + xen_p2m_last_pfn = ALIGN(pfn + 1, P2M_PER_PAGE); HYPERVISOR_shared_info->arch.max_pfn = xen_p2m_last_pfn; } diff --git a/arch/x86/xen/platform-pci-unplug.c b/arch/x86/xen/platform-pci-unplug.c index 96d7f7d39cb9..62ac4898df1a 100644 --- a/arch/x86/xen/platform-pci-unplug.c +++ b/arch/x86/xen/platform-pci-unplug.c @@ -7,6 +7,8 @@ * Copyright (c) 2010, Citrix */ +#define pr_fmt(fmt) KBUILD_MODNAME ": " fmt + #include <linux/init.h> #include <linux/io.h> #include <linux/export.h> @@ -30,13 +32,13 @@ static int check_platform_magic(void) magic = inw(XEN_IOPORT_MAGIC); if (magic != XEN_IOPORT_MAGIC_VAL) { - printk(KERN_ERR "Xen Platform PCI: unrecognised magic value\n"); + pr_err("Xen Platform PCI: unrecognised magic value\n"); return XEN_PLATFORM_ERR_MAGIC; } protocol = inb(XEN_IOPORT_PROTOVER); - printk(KERN_DEBUG "Xen Platform PCI: I/O protocol version %d\n", + pr_debug("Xen Platform PCI: I/O protocol version %d\n", protocol); switch (protocol) { @@ -44,12 +46,12 @@ static int check_platform_magic(void) outw(XEN_IOPORT_LINUX_PRODNUM, XEN_IOPORT_PRODNUM); outl(XEN_IOPORT_LINUX_DRVVER, XEN_IOPORT_DRVVER); if (inw(XEN_IOPORT_MAGIC) != XEN_IOPORT_MAGIC_VAL) { - printk(KERN_ERR "Xen Platform: blacklisted by host\n"); + pr_err("Xen Platform: blacklisted by host\n"); return XEN_PLATFORM_ERR_BLACKLIST; } break; default: - printk(KERN_WARNING "Xen Platform PCI: unknown I/O protocol version\n"); + pr_warn("Xen Platform PCI: unknown I/O protocol version\n"); return XEN_PLATFORM_ERR_PROTOCOL; } @@ -155,12 +157,12 @@ void xen_unplug_emulated_devices(void) * been compiled for this kernel (modules or built-in are both OK). */ if (!xen_emul_unplug) { if (xen_must_unplug_nics()) { - printk(KERN_INFO "Netfront and the Xen platform PCI driver have " + pr_info("Netfront and the Xen platform PCI driver have " "been compiled for this kernel: unplug emulated NICs.\n"); xen_emul_unplug |= XEN_UNPLUG_ALL_NICS; } if (xen_must_unplug_disks()) { - printk(KERN_INFO "Blkfront and the Xen platform PCI driver have " + pr_info("Blkfront and the Xen platform PCI driver have " "been compiled for this kernel: unplug emulated disks.\n" "You might have to change the root device\n" "from /dev/hd[a-d] to /dev/xvd[a-d]\n" @@ -200,7 +202,7 @@ static int __init parse_xen_emul_unplug(char *arg) else if (!strncmp(p, "never", l)) xen_emul_unplug |= XEN_UNPLUG_NEVER; else - printk(KERN_WARNING "unrecognised option '%s' " + pr_warn("unrecognised option '%s' " "in parameter 'xen_emul_unplug'\n", p); } return 0; diff --git a/arch/x86/xen/smp_pv.c b/arch/x86/xen/smp_pv.c index c2ac319f11a4..96afadf9878e 100644 --- a/arch/x86/xen/smp_pv.c +++ b/arch/x86/xen/smp_pv.c @@ -64,7 +64,6 @@ static void cpu_bringup(void) cr4_init(); cpu_init(); touch_softlockup_watchdog(); - preempt_disable(); /* PVH runs in ring 0 and allows us to do native syscalls. Yay! */ if (!xen_feature(XENFEAT_supervisor_mode_kernel)) { |