diff options
Diffstat (limited to 'arch')
308 files changed, 8163 insertions, 3977 deletions
diff --git a/arch/Kconfig b/arch/Kconfig index a08999dfcf16..78c6f05b10f9 100644 --- a/arch/Kconfig +++ b/arch/Kconfig @@ -976,16 +976,16 @@ config VMAP_STACK default y bool "Use a virtually-mapped stack" depends on HAVE_ARCH_VMAP_STACK - depends on !KASAN || KASAN_VMALLOC + depends on !KASAN || KASAN_HW_TAGS || KASAN_VMALLOC help Enable this if you want the use virtually-mapped kernel stacks with guard pages. This causes kernel stack overflows to be caught immediately rather than causing difficult-to-diagnose corruption. - To use this with KASAN, the architecture must support backing - virtual mappings with real shadow memory, and KASAN_VMALLOC must - be enabled. + To use this with software KASAN modes, the architecture must support + backing virtual mappings with real shadow memory, and KASAN_VMALLOC + must be enabled. config ARCH_OPTIONAL_KERNEL_RWX def_bool n diff --git a/arch/alpha/kernel/rtc.c b/arch/alpha/kernel/rtc.c index 1b1d5963ac55..ce3077946e1d 100644 --- a/arch/alpha/kernel/rtc.c +++ b/arch/alpha/kernel/rtc.c @@ -216,6 +216,6 @@ alpha_rtc_init(void) rtc->ops = &remote_rtc_ops; #endif - return rtc_register_device(rtc); + return devm_rtc_register_device(rtc); } device_initcall(alpha_rtc_init); diff --git a/arch/alpha/kernel/syscalls/syscall.tbl b/arch/alpha/kernel/syscalls/syscall.tbl index ee7b01bb7346..a6617067dbe6 100644 --- a/arch/alpha/kernel/syscalls/syscall.tbl +++ b/arch/alpha/kernel/syscalls/syscall.tbl @@ -480,3 +480,4 @@ 548 common pidfd_getfd sys_pidfd_getfd 549 common faccessat2 sys_faccessat2 550 common process_madvise sys_process_madvise +551 common epoll_pwait2 sys_epoll_pwait2 diff --git a/arch/arm/Kconfig b/arch/arm/Kconfig index ba937d85cb6c..138248999df7 100644 --- a/arch/arm/Kconfig +++ b/arch/arm/Kconfig @@ -5,7 +5,6 @@ config ARM select ARCH_32BIT_OFF_T select ARCH_HAS_BINFMT_FLAT select ARCH_HAS_DEBUG_VIRTUAL if MMU - select ARCH_HAS_DEVMEM_IS_ALLOWED select ARCH_HAS_DMA_WRITE_COMBINE if !ARM_DMA_MEM_BUFFERABLE select ARCH_HAS_ELF_RANDOMIZE select ARCH_HAS_FORTIFY_SOURCE @@ -57,6 +56,7 @@ config ARM select GENERIC_IRQ_PROBE select GENERIC_IRQ_SHOW select GENERIC_IRQ_SHOW_LEVEL + select GENERIC_LIB_DEVMEM_IS_ALLOWED select GENERIC_PCI_IOMAP select GENERIC_SCHED_CLOCK select GENERIC_SMP_IDLE_THREAD @@ -68,6 +68,7 @@ config ARM select HAVE_ARCH_BITREVERSE if (CPU_32v7M || CPU_32v7) && !CPU_32v6 select HAVE_ARCH_JUMP_LABEL if !XIP_KERNEL && !CPU_ENDIAN_BE32 && MMU select HAVE_ARCH_KGDB if !CPU_ENDIAN_BE32 && MMU + select HAVE_ARCH_KASAN if MMU && !XIP_KERNEL select HAVE_ARCH_MMAP_RND_BITS if MMU select HAVE_ARCH_PFN_VALID select HAVE_ARCH_SECCOMP @@ -245,7 +246,7 @@ config ARM_PATCH_PHYS_VIRT kernel in system memory. This can only be used with non-XIP MMU kernels where the base - of physical memory is at a 16MB boundary. + of physical memory is at a 2 MiB boundary. Only disable this option if you know that you do not require this feature (eg, building a kernel for a single machine) and @@ -1298,6 +1299,15 @@ config PAGE_OFFSET default 0xB0000000 if VMSPLIT_3G_OPT default 0xC0000000 +config KASAN_SHADOW_OFFSET + hex + depends on KASAN + default 0x1f000000 if PAGE_OFFSET=0x40000000 + default 0x5f000000 if PAGE_OFFSET=0x80000000 + default 0x9f000000 if PAGE_OFFSET=0xC0000000 + default 0x8f000000 if PAGE_OFFSET=0xB0000000 + default 0xffffffff + config NR_CPUS int "Maximum number of CPUs (2-32)" range 2 32 diff --git a/arch/arm/Makefile b/arch/arm/Makefile index 4a066c687cec..4aaec9599e8a 100644 --- a/arch/arm/Makefile +++ b/arch/arm/Makefile @@ -10,7 +10,7 @@ # # Copyright (C) 1995-2001 by Russell King -LDFLAGS_vmlinux := --no-undefined -X --pic-veneer +LDFLAGS_vmlinux := --no-undefined -X --pic-veneer -z norelro ifeq ($(CONFIG_CPU_ENDIAN_BE8),y) LDFLAGS_vmlinux += --be8 KBUILD_LDFLAGS_MODULE += --be8 diff --git a/arch/arm/boot/compressed/Makefile b/arch/arm/boot/compressed/Makefile index e1567418a2b1..fb521efcc6c2 100644 --- a/arch/arm/boot/compressed/Makefile +++ b/arch/arm/boot/compressed/Makefile @@ -24,6 +24,7 @@ OBJS += hyp-stub.o endif GCOV_PROFILE := n +KASAN_SANITIZE := n # Prevents link failures: __sanitizer_cov_trace_pc() is not linked in. KCOV_INSTRUMENT := n diff --git a/arch/arm/boot/compressed/head.S b/arch/arm/boot/compressed/head.S index caa27322a0ab..d9cce7238a36 100644 --- a/arch/arm/boot/compressed/head.S +++ b/arch/arm/boot/compressed/head.S @@ -11,6 +11,12 @@ #include "efi-header.S" +#ifdef __ARMEB__ +#define OF_DT_MAGIC 0xd00dfeed +#else +#define OF_DT_MAGIC 0xedfe0dd0 +#endif + AR_CLASS( .arch armv7-a ) M_CLASS( .arch armv7-m ) @@ -116,7 +122,7 @@ /* * Debug print of the final appended DTB location */ - .macro dbgadtb, begin, end + .macro dbgadtb, begin, size #ifdef DEBUG kputc #'D' kputc #'T' @@ -129,7 +135,7 @@ kputc #'(' kputc #'0' kputc #'x' - kphex \end, 8 /* End of appended DTB */ + kphex \size, 8 /* Size of appended DTB */ kputc #')' kputc #'\n' #endif @@ -165,6 +171,16 @@ orr \res, \res, \tmp1, lsl #24 .endm + .macro be32tocpu, val, tmp +#ifndef __ARMEB__ + /* convert to little endian */ + eor \tmp, \val, \val, ror #16 + bic \tmp, \tmp, #0x00ff0000 + mov \val, \val, ror #8 + eor \val, \val, \tmp, lsr #8 +#endif + .endm + .section ".start", "ax" /* * sort out different calling conventions @@ -325,11 +341,7 @@ restart: adr r0, LC1 */ ldr lr, [r6, #0] -#ifndef __ARMEB__ - ldr r1, =0xedfe0dd0 @ sig is 0xd00dfeed big endian -#else - ldr r1, =0xd00dfeed -#endif + ldr r1, =OF_DT_MAGIC cmp lr, r1 bne dtb_check_done @ not found @@ -345,13 +357,7 @@ restart: adr r0, LC1 /* Get the initial DTB size */ ldr r5, [r6, #4] -#ifndef __ARMEB__ - /* convert to little endian */ - eor r1, r5, r5, ror #16 - bic r1, r1, #0x00ff0000 - mov r5, r5, ror #8 - eor r5, r5, r1, lsr #8 -#endif + be32tocpu r5, r1 dbgadtb r6, r5 /* 50% DTB growth should be good enough */ add r5, r5, r5, lsr #1 @@ -403,13 +409,7 @@ restart: adr r0, LC1 /* Get the current DTB size */ ldr r5, [r6, #4] -#ifndef __ARMEB__ - /* convert r5 (dtb size) to little endian */ - eor r1, r5, r5, ror #16 - bic r1, r1, #0x00ff0000 - mov r5, r5, ror #8 - eor r5, r5, r1, lsr #8 -#endif + be32tocpu r5, r1 /* preserve 64-bit alignment */ add r5, r5, #7 @@ -468,15 +468,10 @@ dtb_check_done: /* * Compute the address of the hyp vectors after relocation. - * This requires some arithmetic since we cannot directly - * reference __hyp_stub_vectors in a PC-relative way. * Call __hyp_set_vectors with the new address so that we * can HVC again after the copy. */ -0: adr r0, 0b - movw r1, #:lower16:__hyp_stub_vectors - 0b - movt r1, #:upper16:__hyp_stub_vectors - 0b - add r0, r0, r1 + adr_l r0, __hyp_stub_vectors sub r0, r0, r5 add r0, r0, r10 bl __hyp_set_vectors @@ -627,17 +622,11 @@ not_relocated: mov r0, #0 cmp r0, #HYP_MODE @ if not booted in HYP mode... bne __enter_kernel @ boot kernel directly - adr r12, .L__hyp_reentry_vectors_offset - ldr r0, [r12] - add r0, r0, r12 - + adr_l r0, __hyp_reentry_vectors bl __hyp_set_vectors __HVC(0) @ otherwise bounce to hyp mode b . @ should never be reached - - .align 2 -.L__hyp_reentry_vectors_offset: .long __hyp_reentry_vectors - . #else b __enter_kernel #endif @@ -1440,8 +1429,7 @@ ENTRY(efi_enter_kernel) mov r4, r0 @ preserve image base mov r8, r1 @ preserve DT pointer - ARM( adrl r0, call_cache_fn ) - THUMB( adr r0, call_cache_fn ) + adr_l r0, call_cache_fn adr r1, 0f @ clean the region of code we bl cache_clean_flush @ may run with the MMU off diff --git a/arch/arm/boot/compressed/string.c b/arch/arm/boot/compressed/string.c index ade5079bebbf..8c0fa276d994 100644 --- a/arch/arm/boot/compressed/string.c +++ b/arch/arm/boot/compressed/string.c @@ -7,6 +7,25 @@ #include <linux/string.h> +/* + * The decompressor is built without KASan but uses the same redirects as the + * rest of the kernel when CONFIG_KASAN is enabled, defining e.g. memcpy() + * to __memcpy() but since we are not linking with the main kernel string + * library in the decompressor, that will lead to link failures. + * + * Undefine KASan's versions, define the wrapped functions and alias them to + * the right names so that when e.g. __memcpy() appear in the code, it will + * still be linked to this local version of memcpy(). + */ +#ifdef CONFIG_KASAN +#undef memcpy +#undef memmove +#undef memset +void *__memcpy(void *__dest, __const void *__src, size_t __n) __alias(memcpy); +void *__memmove(void *__dest, __const void *__src, size_t count) __alias(memmove); +void *__memset(void *s, int c, size_t count) __alias(memset); +#endif + void *memcpy(void *__dest, __const void *__src, size_t __n) { int i = 0; diff --git a/arch/arm/include/asm/assembler.h b/arch/arm/include/asm/assembler.h index feac2c8b86f2..6ed30421f697 100644 --- a/arch/arm/include/asm/assembler.h +++ b/arch/arm/include/asm/assembler.h @@ -259,7 +259,7 @@ */ #define ALT_UP(instr...) \ .pushsection ".alt.smp.init", "a" ;\ - .long 9998b ;\ + .long 9998b - . ;\ 9997: instr ;\ .if . - 9997b == 2 ;\ nop ;\ @@ -270,7 +270,7 @@ .popsection #define ALT_UP_B(label) \ .pushsection ".alt.smp.init", "a" ;\ - .long 9998b ;\ + .long 9998b - . ;\ W(b) . + (label - 9998b) ;\ .popsection #else @@ -494,4 +494,88 @@ THUMB( orr \reg , \reg , #PSR_T_BIT ) #define _ASM_NOKPROBE(entry) #endif + .macro __adldst_l, op, reg, sym, tmp, c + .if __LINUX_ARM_ARCH__ < 7 + ldr\c \tmp, .La\@ + .subsection 1 + .align 2 +.La\@: .long \sym - .Lpc\@ + .previous + .else + .ifnb \c + THUMB( ittt \c ) + .endif + movw\c \tmp, #:lower16:\sym - .Lpc\@ + movt\c \tmp, #:upper16:\sym - .Lpc\@ + .endif + +#ifndef CONFIG_THUMB2_KERNEL + .set .Lpc\@, . + 8 // PC bias + .ifc \op, add + add\c \reg, \tmp, pc + .else + \op\c \reg, [pc, \tmp] + .endif +#else +.Lb\@: add\c \tmp, \tmp, pc + /* + * In Thumb-2 builds, the PC bias depends on whether we are currently + * emitting into a .arm or a .thumb section. The size of the add opcode + * above will be 2 bytes when emitting in Thumb mode and 4 bytes when + * emitting in ARM mode, so let's use this to account for the bias. + */ + .set .Lpc\@, . + (. - .Lb\@) + + .ifnc \op, add + \op\c \reg, [\tmp] + .endif +#endif + .endm + + /* + * mov_l - move a constant value or [relocated] address into a register + */ + .macro mov_l, dst:req, imm:req + .if __LINUX_ARM_ARCH__ < 7 + ldr \dst, =\imm + .else + movw \dst, #:lower16:\imm + movt \dst, #:upper16:\imm + .endif + .endm + + /* + * adr_l - adr pseudo-op with unlimited range + * + * @dst: destination register + * @sym: name of the symbol + * @cond: conditional opcode suffix + */ + .macro adr_l, dst:req, sym:req, cond + __adldst_l add, \dst, \sym, \dst, \cond + .endm + + /* + * ldr_l - ldr <literal> pseudo-op with unlimited range + * + * @dst: destination register + * @sym: name of the symbol + * @cond: conditional opcode suffix + */ + .macro ldr_l, dst:req, sym:req, cond + __adldst_l ldr, \dst, \sym, \dst, \cond + .endm + + /* + * str_l - str <literal> pseudo-op with unlimited range + * + * @src: source register + * @sym: name of the symbol + * @tmp: mandatory scratch register + * @cond: conditional opcode suffix + */ + .macro str_l, src:req, sym:req, tmp:req, cond + __adldst_l str, \src, \sym, \tmp, \cond + .endm + #endif /* __ASM_ASSEMBLER_H__ */ diff --git a/arch/arm/include/asm/div64.h b/arch/arm/include/asm/div64.h index 898e9c78a7e7..595e538f5bfb 100644 --- a/arch/arm/include/asm/div64.h +++ b/arch/arm/include/asm/div64.h @@ -21,29 +21,20 @@ * assembly implementation with completely non standard calling convention * for arguments and results (beware). */ - -#ifdef __ARMEB__ -#define __xh "r0" -#define __xl "r1" -#else -#define __xl "r0" -#define __xh "r1" -#endif - static inline uint32_t __div64_32(uint64_t *n, uint32_t base) { register unsigned int __base asm("r4") = base; register unsigned long long __n asm("r0") = *n; register unsigned long long __res asm("r2"); - register unsigned int __rem asm(__xh); - asm( __asmeq("%0", __xh) + unsigned int __rem; + asm( __asmeq("%0", "r0") __asmeq("%1", "r2") - __asmeq("%2", "r0") - __asmeq("%3", "r4") + __asmeq("%2", "r4") "bl __do_div64" - : "=r" (__rem), "=r" (__res) - : "r" (__n), "r" (__base) + : "+r" (__n), "=r" (__res) + : "r" (__base) : "ip", "lr", "cc"); + __rem = __n >> 32; *n = __res; return __rem; } diff --git a/arch/arm/include/asm/elf.h b/arch/arm/include/asm/elf.h index 61941f369861..b8102a6ddf16 100644 --- a/arch/arm/include/asm/elf.h +++ b/arch/arm/include/asm/elf.h @@ -51,6 +51,7 @@ typedef struct user_fp elf_fpregset_t; #define R_ARM_NONE 0 #define R_ARM_PC24 1 #define R_ARM_ABS32 2 +#define R_ARM_REL32 3 #define R_ARM_CALL 28 #define R_ARM_JUMP24 29 #define R_ARM_TARGET1 38 @@ -58,11 +59,15 @@ typedef struct user_fp elf_fpregset_t; #define R_ARM_PREL31 42 #define R_ARM_MOVW_ABS_NC 43 #define R_ARM_MOVT_ABS 44 +#define R_ARM_MOVW_PREL_NC 45 +#define R_ARM_MOVT_PREL 46 #define R_ARM_THM_CALL 10 #define R_ARM_THM_JUMP24 30 #define R_ARM_THM_MOVW_ABS_NC 47 #define R_ARM_THM_MOVT_ABS 48 +#define R_ARM_THM_MOVW_PREL_NC 49 +#define R_ARM_THM_MOVT_PREL 50 /* * These are used to set parameters in the core dumps. diff --git a/arch/arm/include/asm/fixmap.h b/arch/arm/include/asm/fixmap.h index c279a8a463a2..707068f852c2 100644 --- a/arch/arm/include/asm/fixmap.h +++ b/arch/arm/include/asm/fixmap.h @@ -2,7 +2,7 @@ #ifndef _ASM_FIXMAP_H #define _ASM_FIXMAP_H -#define FIXADDR_START 0xffc00000UL +#define FIXADDR_START 0xffc80000UL #define FIXADDR_END 0xfff00000UL #define FIXADDR_TOP (FIXADDR_END - PAGE_SIZE) diff --git a/arch/arm/include/asm/io.h b/arch/arm/include/asm/io.h index ab2b654084fa..fc748122f1e0 100644 --- a/arch/arm/include/asm/io.h +++ b/arch/arm/include/asm/io.h @@ -441,7 +441,6 @@ extern void pci_iounmap(struct pci_dev *dev, void __iomem *addr); #define ARCH_HAS_VALID_PHYS_ADDR_RANGE extern int valid_phys_addr_range(phys_addr_t addr, size_t size); extern int valid_mmap_phys_addr_range(unsigned long pfn, size_t size); -extern int devmem_is_allowed(unsigned long pfn); #endif /* diff --git a/arch/arm/include/asm/kasan.h b/arch/arm/include/asm/kasan.h new file mode 100644 index 000000000000..303c35df3135 --- /dev/null +++ b/arch/arm/include/asm/kasan.h @@ -0,0 +1,33 @@ +/* SPDX-License-Identifier: GPL-2.0 */ +/* + * arch/arm/include/asm/kasan.h + * + * Copyright (c) 2015 Samsung Electronics Co., Ltd. + * Author: Andrey Ryabinin <ryabinin.a.a@gmail.com> + * + */ + +#ifndef __ASM_KASAN_H +#define __ASM_KASAN_H + +#ifdef CONFIG_KASAN + +#include <asm/kasan_def.h> + +#define KASAN_SHADOW_SCALE_SHIFT 3 + +/* + * The compiler uses a shadow offset assuming that addresses start + * from 0. Kernel addresses don't start from 0, so shadow + * for kernel really starts from 'compiler's shadow offset' + + * ('kernel address space start' >> KASAN_SHADOW_SCALE_SHIFT) + */ + +asmlinkage void kasan_early_init(void); +extern void kasan_init(void); + +#else +static inline void kasan_init(void) { } +#endif + +#endif diff --git a/arch/arm/include/asm/kasan_def.h b/arch/arm/include/asm/kasan_def.h new file mode 100644 index 000000000000..5739605aa7cf --- /dev/null +++ b/arch/arm/include/asm/kasan_def.h @@ -0,0 +1,81 @@ +/* SPDX-License-Identifier: GPL-2.0 */ +/* + * arch/arm/include/asm/kasan_def.h + * + * Copyright (c) 2018 Huawei Technologies Co., Ltd. + * + * Author: Abbott Liu <liuwenliang@huawei.com> + */ + +#ifndef __ASM_KASAN_DEF_H +#define __ASM_KASAN_DEF_H + +#ifdef CONFIG_KASAN + +/* + * Define KASAN_SHADOW_OFFSET,KASAN_SHADOW_START and KASAN_SHADOW_END for + * the Arm kernel address sanitizer. We are "stealing" lowmem (the 4GB + * addressable by a 32bit architecture) out of the virtual address + * space to use as shadow memory for KASan as follows: + * + * +----+ 0xffffffff + * | | \ + * | | |-> Static kernel image (vmlinux) BSS and page table + * | |/ + * +----+ PAGE_OFFSET + * | | \ + * | | |-> Loadable kernel modules virtual address space area + * | |/ + * +----+ MODULES_VADDR = KASAN_SHADOW_END + * | | \ + * | | |-> The shadow area of kernel virtual address. + * | |/ + * +----+-> TASK_SIZE (start of kernel space) = KASAN_SHADOW_START the + * | |\ shadow address of MODULES_VADDR + * | | | + * | | | + * | | |-> The user space area in lowmem. The kernel address + * | | | sanitizer do not use this space, nor does it map it. + * | | | + * | | | + * | | | + * | | | + * | |/ + * ------ 0 + * + * 1) KASAN_SHADOW_START + * This value begins with the MODULE_VADDR's shadow address. It is the + * start of kernel virtual space. Since we have modules to load, we need + * to cover also that area with shadow memory so we can find memory + * bugs in modules. + * + * 2) KASAN_SHADOW_END + * This value is the 0x100000000's shadow address: the mapping that would + * be after the end of the kernel memory at 0xffffffff. It is the end of + * kernel address sanitizer shadow area. It is also the start of the + * module area. + * + * 3) KASAN_SHADOW_OFFSET: + * This value is used to map an address to the corresponding shadow + * address by the following formula: + * + * shadow_addr = (address >> 3) + KASAN_SHADOW_OFFSET; + * + * As you would expect, >> 3 is equal to dividing by 8, meaning each + * byte in the shadow memory covers 8 bytes of kernel memory, so one + * bit shadow memory per byte of kernel memory is used. + * + * The KASAN_SHADOW_OFFSET is provided in a Kconfig option depending + * on the VMSPLIT layout of the system: the kernel and userspace can + * split up lowmem in different ways according to needs, so we calculate + * the shadow offset depending on this. + */ + +#define KASAN_SHADOW_SCALE_SHIFT 3 +#define KASAN_SHADOW_OFFSET _AC(CONFIG_KASAN_SHADOW_OFFSET, UL) +#define KASAN_SHADOW_END ((UL(1) << (32 - KASAN_SHADOW_SCALE_SHIFT)) \ + + KASAN_SHADOW_OFFSET) +#define KASAN_SHADOW_START ((KASAN_SHADOW_END >> 3) + KASAN_SHADOW_OFFSET) + +#endif +#endif diff --git a/arch/arm/include/asm/memory.h b/arch/arm/include/asm/memory.h index 99035b5891ef..2f841cb65c30 100644 --- a/arch/arm/include/asm/memory.h +++ b/arch/arm/include/asm/memory.h @@ -18,6 +18,7 @@ #ifdef CONFIG_NEED_MACH_MEMORY_H #include <mach/memory.h> #endif +#include <asm/kasan_def.h> /* PAGE_OFFSET - the virtual address of the start of the kernel image */ #define PAGE_OFFSET UL(CONFIG_PAGE_OFFSET) @@ -28,7 +29,11 @@ * TASK_SIZE - the maximum size of a user space task. * TASK_UNMAPPED_BASE - the lower boundary of the mmap VM area */ +#ifndef CONFIG_KASAN #define TASK_SIZE (UL(CONFIG_PAGE_OFFSET) - UL(SZ_16M)) +#else +#define TASK_SIZE (KASAN_SHADOW_START) +#endif #define TASK_UNMAPPED_BASE ALIGN(TASK_SIZE / 3, SZ_16M) /* @@ -67,6 +72,10 @@ */ #define XIP_VIRT_ADDR(physaddr) (MODULES_VADDR + ((physaddr) & 0x000fffff)) +#define FDT_FIXED_BASE UL(0xff800000) +#define FDT_FIXED_SIZE (2 * SECTION_SIZE) +#define FDT_VIRT_BASE(physbase) ((void *)(FDT_FIXED_BASE | (physbase) % SECTION_SIZE)) + #if !defined(CONFIG_SMP) && !defined(CONFIG_ARM_LPAE) /* * Allow 16MB-aligned ioremap pages @@ -107,6 +116,7 @@ extern unsigned long vectors_base; #define MODULES_VADDR PAGE_OFFSET #define XIP_VIRT_ADDR(physaddr) (physaddr) +#define FDT_VIRT_BASE(physbase) ((void *)(physbase)) #endif /* !CONFIG_MMU */ @@ -173,6 +183,7 @@ extern unsigned long vectors_base; * so that all we need to do is modify the 8-bit constant field. */ #define __PV_BITS_31_24 0x81000000 +#define __PV_BITS_23_16 0x810000 #define __PV_BITS_7_0 0x81 extern unsigned long __pv_phys_pfn_offset; @@ -183,43 +194,65 @@ extern const void *__pv_table_begin, *__pv_table_end; #define PHYS_OFFSET ((phys_addr_t)__pv_phys_pfn_offset << PAGE_SHIFT) #define PHYS_PFN_OFFSET (__pv_phys_pfn_offset) -#define __pv_stub(from,to,instr,type) \ +#ifndef CONFIG_THUMB2_KERNEL +#define __pv_stub(from,to,instr) \ __asm__("@ __pv_stub\n" \ "1: " instr " %0, %1, %2\n" \ + "2: " instr " %0, %0, %3\n" \ " .pushsection .pv_table,\"a\"\n" \ - " .long 1b\n" \ + " .long 1b - ., 2b - .\n" \ " .popsection\n" \ : "=r" (to) \ - : "r" (from), "I" (type)) + : "r" (from), "I" (__PV_BITS_31_24), \ + "I"(__PV_BITS_23_16)) -#define __pv_stub_mov_hi(t) \ - __asm__ volatile("@ __pv_stub_mov\n" \ - "1: mov %R0, %1\n" \ +#define __pv_add_carry_stub(x, y) \ + __asm__("@ __pv_add_carry_stub\n" \ + "0: movw %R0, #0\n" \ + " adds %Q0, %1, %R0, lsl #20\n" \ + "1: mov %R0, %2\n" \ + " adc %R0, %R0, #0\n" \ " .pushsection .pv_table,\"a\"\n" \ - " .long 1b\n" \ + " .long 0b - ., 1b - .\n" \ " .popsection\n" \ - : "=r" (t) \ - : "I" (__PV_BITS_7_0)) + : "=&r" (y) \ + : "r" (x), "I" (__PV_BITS_7_0) \ + : "cc") + +#else +#define __pv_stub(from,to,instr) \ + __asm__("@ __pv_stub\n" \ + "0: movw %0, #0\n" \ + " lsl %0, #21\n" \ + " " instr " %0, %1, %0\n" \ + " .pushsection .pv_table,\"a\"\n" \ + " .long 0b - .\n" \ + " .popsection\n" \ + : "=&r" (to) \ + : "r" (from)) #define __pv_add_carry_stub(x, y) \ - __asm__ volatile("@ __pv_add_carry_stub\n" \ - "1: adds %Q0, %1, %2\n" \ + __asm__("@ __pv_add_carry_stub\n" \ + "0: movw %R0, #0\n" \ + " lsls %R0, #21\n" \ + " adds %Q0, %1, %R0\n" \ + "1: mvn %R0, #0\n" \ " adc %R0, %R0, #0\n" \ " .pushsection .pv_table,\"a\"\n" \ - " .long 1b\n" \ + " .long 0b - ., 1b - .\n" \ " .popsection\n" \ - : "+r" (y) \ - : "r" (x), "I" (__PV_BITS_31_24) \ + : "=&r" (y) \ + : "r" (x) \ : "cc") +#endif static inline phys_addr_t __virt_to_phys_nodebug(unsigned long x) { phys_addr_t t; if (sizeof(phys_addr_t) == 4) { - __pv_stub(x, t, "add", __PV_BITS_31_24); + __pv_stub(x, t, "add"); } else { - __pv_stub_mov_hi(t); __pv_add_carry_stub(x, t); } return t; @@ -235,7 +268,7 @@ static inline unsigned long __phys_to_virt(phys_addr_t x) * assembler expression receives 32 bit argument * in place where 'r' 32 bit operand is expected. */ - __pv_stub((unsigned long) x, t, "sub", __PV_BITS_31_24); + __pv_stub((unsigned long) x, t, "sub"); return t; } diff --git a/arch/arm/include/asm/pgalloc.h b/arch/arm/include/asm/pgalloc.h index 15f4674715f8..fdee1f04f4f3 100644 --- a/arch/arm/include/asm/pgalloc.h +++ b/arch/arm/include/asm/pgalloc.h @@ -21,6 +21,7 @@ #define _PAGE_KERNEL_TABLE (PMD_TYPE_TABLE | PMD_BIT4 | PMD_DOMAIN(DOMAIN_KERNEL)) #ifdef CONFIG_ARM_LPAE +#define PGD_SIZE (PTRS_PER_PGD * sizeof(pgd_t)) static inline void pud_populate(struct mm_struct *mm, pud_t *pud, pmd_t *pmd) { @@ -28,14 +29,19 @@ static inline void pud_populate(struct mm_struct *mm, pud_t *pud, pmd_t *pmd) } #else /* !CONFIG_ARM_LPAE */ +#define PGD_SIZE (PAGE_SIZE << 2) /* * Since we have only two-level page tables, these are trivial */ #define pmd_alloc_one(mm,addr) ({ BUG(); ((pmd_t *)2); }) #define pmd_free(mm, pmd) do { } while (0) +#ifdef CONFIG_KASAN +/* The KASan core unconditionally calls pud_populate() on all architectures */ +#define pud_populate(mm,pmd,pte) do { } while (0) +#else #define pud_populate(mm,pmd,pte) BUG() - +#endif #endif /* CONFIG_ARM_LPAE */ extern pgd_t *pgd_alloc(struct mm_struct *mm); diff --git a/arch/arm/include/asm/pgtable-2level.h b/arch/arm/include/asm/pgtable-2level.h index baf7d0204eb5..70fe69bdcce2 100644 --- a/arch/arm/include/asm/pgtable-2level.h +++ b/arch/arm/include/asm/pgtable-2level.h @@ -179,11 +179,28 @@ * the pud: the pud entry is never bad, always exists, and can't be set or * cleared. */ -#define pud_none(pud) (0) -#define pud_bad(pud) (0) -#define pud_present(pud) (1) -#define pud_clear(pudp) do { } while (0) -#define set_pud(pud,pudp) do { } while (0) +static inline int pud_none(pud_t pud) +{ + return 0; +} + +static inline int pud_bad(pud_t pud) +{ + return 0; +} + +static inline int pud_present(pud_t pud) +{ + return 1; +} + +static inline void pud_clear(pud_t *pudp) +{ +} + +static inline void set_pud(pud_t *pudp, pud_t pud) +{ +} static inline pmd_t *pmd_offset(pud_t *pud, unsigned long addr) { diff --git a/arch/arm/include/asm/processor.h b/arch/arm/include/asm/processor.h index b9241051e5cb..9e6b97286307 100644 --- a/arch/arm/include/asm/processor.h +++ b/arch/arm/include/asm/processor.h @@ -96,7 +96,7 @@ unsigned long get_wchan(struct task_struct *p); #define __ALT_SMP_ASM(smp, up) \ "9998: " smp "\n" \ " .pushsection \".alt.smp.init\", \"a\"\n" \ - " .long 9998b\n" \ + " .long 9998b - .\n" \ " " up "\n" \ " .popsection\n" #else diff --git a/arch/arm/include/asm/prom.h b/arch/arm/include/asm/prom.h index 1e36c40533c1..402e3f34c7ed 100644 --- a/arch/arm/include/asm/prom.h +++ b/arch/arm/include/asm/prom.h @@ -9,12 +9,12 @@ #ifdef CONFIG_OF -extern const struct machine_desc *setup_machine_fdt(unsigned int dt_phys); +extern const struct machine_desc *setup_machine_fdt(void *dt_virt); extern void __init arm_dt_init_cpu_maps(void); #else /* CONFIG_OF */ -static inline const struct machine_desc *setup_machine_fdt(unsigned int dt_phys) +static inline const struct machine_desc *setup_machine_fdt(void *dt_virt) { return NULL; } diff --git a/arch/arm/include/asm/string.h b/arch/arm/include/asm/string.h index 111a1d8a41dd..6c607c68f3ad 100644 --- a/arch/arm/include/asm/string.h +++ b/arch/arm/include/asm/string.h @@ -5,6 +5,9 @@ /* * We don't do inline string functions, since the * optimised inline asm versions are not small. + * + * The __underscore versions of some functions are for KASan to be able + * to replace them with instrumented versions. */ #define __HAVE_ARCH_STRRCHR @@ -15,15 +18,18 @@ extern char * strchr(const char * s, int c); #define __HAVE_ARCH_MEMCPY extern void * memcpy(void *, const void *, __kernel_size_t); +extern void *__memcpy(void *dest, const void *src, __kernel_size_t n); #define __HAVE_ARCH_MEMMOVE extern void * memmove(void *, const void *, __kernel_size_t); +extern void *__memmove(void *dest, const void *src, __kernel_size_t n); #define __HAVE_ARCH_MEMCHR extern void * memchr(const void *, int, __kernel_size_t); #define __HAVE_ARCH_MEMSET extern void * memset(void *, int, __kernel_size_t); +extern void *__memset(void *s, int c, __kernel_size_t n); #define __HAVE_ARCH_MEMSET32 extern void *__memset32(uint32_t *, uint32_t v, __kernel_size_t); @@ -39,4 +45,24 @@ static inline void *memset64(uint64_t *p, uint64_t v, __kernel_size_t n) return __memset64(p, v, n * 8, v >> 32); } +/* + * For files that are not instrumented (e.g. mm/slub.c) we + * must use non-instrumented versions of the mem* + * functions named __memcpy() etc. All such kernel code has + * been tagged with KASAN_SANITIZE_file.o = n, which means + * that the address sanitization argument isn't passed to the + * compiler, and __SANITIZE_ADDRESS__ is not set. As a result + * these defines kick in. + */ +#if defined(CONFIG_KASAN) && !defined(__SANITIZE_ADDRESS__) +#define memcpy(dst, src, len) __memcpy(dst, src, len) +#define memmove(dst, src, len) __memmove(dst, src, len) +#define memset(s, c, n) __memset(s, c, n) + +#ifndef __NO_FORTIFY +#define __NO_FORTIFY /* FORTIFY_SOURCE uses __builtin_memcpy, etc. */ +#endif + +#endif + #endif diff --git a/arch/arm/include/asm/thread_info.h b/arch/arm/include/asm/thread_info.h index eb7ce2747eb0..70d4cbc49ae1 100644 --- a/arch/arm/include/asm/thread_info.h +++ b/arch/arm/include/asm/thread_info.h @@ -13,7 +13,15 @@ #include <asm/fpstate.h> #include <asm/page.h> +#ifdef CONFIG_KASAN +/* + * KASan uses a lot of extra stack space so the thread size order needs to + * be increased. + */ +#define THREAD_SIZE_ORDER 2 +#else #define THREAD_SIZE_ORDER 1 +#endif #define THREAD_SIZE (PAGE_SIZE << THREAD_SIZE_ORDER) #define THREAD_START_SP (THREAD_SIZE - 8) diff --git a/arch/arm/include/asm/uaccess-asm.h b/arch/arm/include/asm/uaccess-asm.h index 907571fd05c6..e6eb7a2aaf1e 100644 --- a/arch/arm/include/asm/uaccess-asm.h +++ b/arch/arm/include/asm/uaccess-asm.h @@ -85,7 +85,7 @@ */ .macro uaccess_entry, tsk, tmp0, tmp1, tmp2, disable ldr \tmp1, [\tsk, #TI_ADDR_LIMIT] - mov \tmp2, #TASK_SIZE + ldr \tmp2, =TASK_SIZE str \tmp2, [\tsk, #TI_ADDR_LIMIT] DACR( mrc p15, 0, \tmp0, c3, c0, 0) DACR( str \tmp0, [sp, #SVC_DACR]) diff --git a/arch/arm/kernel/Makefile b/arch/arm/kernel/Makefile index 09e67cb02b20..ae295a3bcfef 100644 --- a/arch/arm/kernel/Makefile +++ b/arch/arm/kernel/Makefile @@ -21,6 +21,9 @@ obj-y := elf.o entry-common.o irq.o opcodes.o \ setup.o signal.o sigreturn_codes.o \ stacktrace.o sys_arm.o time.o traps.o +KASAN_SANITIZE_stacktrace.o := n +KASAN_SANITIZE_traps.o := n + ifneq ($(CONFIG_ARM_UNWIND),y) obj-$(CONFIG_FRAME_POINTER) += return_address.o endif @@ -88,6 +91,7 @@ obj-$(CONFIG_PARAVIRT) += paravirt.o head-y := head$(MMUEXT).o obj-$(CONFIG_DEBUG_LL) += debug.o obj-$(CONFIG_EARLY_PRINTK) += early_printk.o +obj-$(CONFIG_ARM_PATCH_PHYS_VIRT) += phys2virt.o # This is executed very early using a temporary stack when no memory allocator # nor global data is available. Everything has to be allocated on the stack. diff --git a/arch/arm/kernel/atags.h b/arch/arm/kernel/atags.h index 067e12edc341..f2819c25b602 100644 --- a/arch/arm/kernel/atags.h +++ b/arch/arm/kernel/atags.h @@ -2,11 +2,11 @@ void convert_to_tag_list(struct tag *tags); #ifdef CONFIG_ATAGS -const struct machine_desc *setup_machine_tags(phys_addr_t __atags_pointer, +const struct machine_desc *setup_machine_tags(void *__atags_vaddr, unsigned int machine_nr); #else static inline const struct machine_desc * __init __noreturn -setup_machine_tags(phys_addr_t __atags_pointer, unsigned int machine_nr) +setup_machine_tags(void *__atags_vaddr, unsigned int machine_nr) { early_print("no ATAGS support: can't continue\n"); while (true); diff --git a/arch/arm/kernel/atags_parse.c b/arch/arm/kernel/atags_parse.c index 6c12d9fe694e..373b61f9a4f0 100644 --- a/arch/arm/kernel/atags_parse.c +++ b/arch/arm/kernel/atags_parse.c @@ -174,7 +174,7 @@ static void __init squash_mem_tags(struct tag *tag) } const struct machine_desc * __init -setup_machine_tags(phys_addr_t __atags_pointer, unsigned int machine_nr) +setup_machine_tags(void *atags_vaddr, unsigned int machine_nr) { struct tag *tags = (struct tag *)&default_tags; const struct machine_desc *mdesc = NULL, *p; @@ -195,8 +195,8 @@ setup_machine_tags(phys_addr_t __atags_pointer, unsigned int machine_nr) if (!mdesc) return NULL; - if (__atags_pointer) - tags = phys_to_virt(__atags_pointer); + if (atags_vaddr) + tags = atags_vaddr; else if (mdesc->atag_offset) tags = (void *)(PAGE_OFFSET + mdesc->atag_offset); diff --git a/arch/arm/kernel/devtree.c b/arch/arm/kernel/devtree.c index 7f0745a97e20..28311dd0fee6 100644 --- a/arch/arm/kernel/devtree.c +++ b/arch/arm/kernel/devtree.c @@ -203,12 +203,12 @@ static const void * __init arch_get_next_mach(const char *const **match) /** * setup_machine_fdt - Machine setup when an dtb was passed to the kernel - * @dt_phys: physical address of dt blob + * @dt_virt: virtual address of dt blob * * If a dtb was passed to the kernel in r2, then use it to choose the * correct machine_desc and to setup the system. */ -const struct machine_desc * __init setup_machine_fdt(unsigned int dt_phys) +const struct machine_desc * __init setup_machine_fdt(void *dt_virt) { const struct machine_desc *mdesc, *mdesc_best = NULL; @@ -221,7 +221,7 @@ const struct machine_desc * __init setup_machine_fdt(unsigned int dt_phys) mdesc_best = &__mach_desc_GENERIC_DT; #endif - if (!dt_phys || !early_init_dt_verify(phys_to_virt(dt_phys))) + if (!dt_virt || !early_init_dt_verify(dt_virt)) return NULL; mdesc = of_flat_dt_match_machine(mdesc_best, arch_get_next_mach); diff --git a/arch/arm/kernel/entry-armv.S b/arch/arm/kernel/entry-armv.S index 55a47df04773..0ea8529a4872 100644 --- a/arch/arm/kernel/entry-armv.S +++ b/arch/arm/kernel/entry-armv.S @@ -252,31 +252,10 @@ __und_svc: #else svc_entry #endif - @ - @ call emulation code, which returns using r9 if it has emulated - @ the instruction, or the more conventional lr if we are to treat - @ this as a real undefined instruction - @ - @ r0 - instruction - @ -#ifndef CONFIG_THUMB2_KERNEL - ldr r0, [r4, #-4] -#else - mov r1, #2 - ldrh r0, [r4, #-2] @ Thumb instruction at LR - 2 - cmp r0, #0xe800 @ 32-bit instruction if xx >= 0 - blo __und_svc_fault - ldrh r9, [r4] @ bottom 16 bits - add r4, r4, #2 - str r4, [sp, #S_PC] - orr r0, r9, r0, lsl #16 -#endif - badr r9, __und_svc_finish - mov r2, r4 - bl call_fpe mov r1, #4 @ PC correction to apply -__und_svc_fault: + THUMB( tst r5, #PSR_T_BIT ) @ exception taken in Thumb mode? + THUMB( movne r1, #2 ) @ if so, fix up PC correction mov r0, sp @ struct pt_regs *regs bl __und_fault @@ -427,7 +406,8 @@ ENDPROC(__fiq_abt) @ if it was interrupted in a critical region. Here we @ perform a quick test inline since it should be false @ 99.9999% of the time. The rest is done out of line. - cmp r4, #TASK_SIZE + ldr r0, =TASK_SIZE + cmp r4, r0 blhs kuser_cmpxchg64_fixup #endif #endif diff --git a/arch/arm/kernel/entry-common.S b/arch/arm/kernel/entry-common.S index 77d16390a524..e0d7833a1827 100644 --- a/arch/arm/kernel/entry-common.S +++ b/arch/arm/kernel/entry-common.S @@ -50,7 +50,8 @@ __ret_fast_syscall: UNWIND(.cantunwind ) disable_irq_notrace @ disable interrupts ldr r2, [tsk, #TI_ADDR_LIMIT] - cmp r2, #TASK_SIZE + ldr r1, =TASK_SIZE + cmp r2, r1 blne addr_limit_check_failed ldr r1, [tsk, #TI_FLAGS] @ re-check for syscall tracing movs r1, r1, lsl #16 @@ -87,7 +88,8 @@ __ret_fast_syscall: #endif disable_irq_notrace @ disable interrupts ldr r2, [tsk, #TI_ADDR_LIMIT] - cmp r2, #TASK_SIZE + ldr r1, =TASK_SIZE + cmp r2, r1 blne addr_limit_check_failed ldr r1, [tsk, #TI_FLAGS] @ re-check for syscall tracing movs r1, r1, lsl #16 @@ -128,7 +130,8 @@ ret_slow_syscall: disable_irq_notrace @ disable interrupts ENTRY(ret_to_user_from_irq) ldr r2, [tsk, #TI_ADDR_LIMIT] - cmp r2, #TASK_SIZE + ldr r1, =TASK_SIZE + cmp r2, r1 blne addr_limit_check_failed ldr r1, [tsk, #TI_FLAGS] movs r1, r1, lsl #16 diff --git a/arch/arm/kernel/head-common.S b/arch/arm/kernel/head-common.S index 4a3982812a40..29b2eda136bb 100644 --- a/arch/arm/kernel/head-common.S +++ b/arch/arm/kernel/head-common.S @@ -95,7 +95,7 @@ __mmap_switched: THUMB( ldmia r4!, {r0, r1, r2, r3} ) THUMB( mov sp, r3 ) sub r2, r2, r1 - bl memcpy @ copy .data to RAM + bl __memcpy @ copy .data to RAM #endif ARM( ldmia r4!, {r0, r1, sp} ) @@ -103,7 +103,7 @@ __mmap_switched: THUMB( mov sp, r3 ) sub r2, r1, r0 mov r1, #0 - bl memset @ clear .bss + bl __memset @ clear .bss ldmia r4, {r0, r1, r2, r3} str r9, [r0] @ Save processor ID @@ -111,6 +111,9 @@ __mmap_switched: str r8, [r2] @ Save atags pointer cmp r3, #0 strne r10, [r3] @ Save control register values +#ifdef CONFIG_KASAN + bl kasan_early_init +#endif mov lr, #0 b start_kernel ENDPROC(__mmap_switched) @@ -170,11 +173,12 @@ ENDPROC(lookup_processor_type) * r9 = cpuid (preserved) */ __lookup_processor_type: - adr r3, __lookup_processor_type_data - ldmia r3, {r4 - r6} - sub r3, r3, r4 @ get offset between virt&phys - add r5, r5, r3 @ convert virt addresses to - add r6, r6, r3 @ physical address space + /* + * Look in <asm/procinfo.h> for information about the __proc_info + * structure. + */ + adr_l r5, __proc_info_begin + adr_l r6, __proc_info_end 1: ldmia r5, {r3, r4} @ value, mask and r4, r4, r9 @ mask wanted bits teq r3, r4 @@ -186,17 +190,6 @@ __lookup_processor_type: 2: ret lr ENDPROC(__lookup_processor_type) -/* - * Look in <asm/procinfo.h> for information about the __proc_info structure. - */ - .align 2 - .type __lookup_processor_type_data, %object -__lookup_processor_type_data: - .long . - .long __proc_info_begin - .long __proc_info_end - .size __lookup_processor_type_data, . - __lookup_processor_type_data - __error_lpae: #ifdef CONFIG_DEBUG_LL adr r0, str_lpae diff --git a/arch/arm/kernel/head.S b/arch/arm/kernel/head.S index f8904227e7fd..7f62c5eccdf3 100644 --- a/arch/arm/kernel/head.S +++ b/arch/arm/kernel/head.S @@ -103,10 +103,8 @@ ENTRY(stext) #endif #ifndef CONFIG_XIP_KERNEL - adr r3, 2f - ldmia r3, {r4, r8} - sub r4, r3, r4 @ (PHYS_OFFSET - PAGE_OFFSET) - add r8, r8, r4 @ PHYS_OFFSET + adr_l r8, _text @ __pa(_text) + sub r8, r8, #TEXT_OFFSET @ PHYS_OFFSET #else ldr r8, =PLAT_PHYS_OFFSET @ always constant in this case #endif @@ -158,10 +156,6 @@ ENTRY(stext) 1: b __enable_mmu ENDPROC(stext) .ltorg -#ifndef CONFIG_XIP_KERNEL -2: .long . - .long PAGE_OFFSET -#endif /* * Setup the initial page tables. We only setup the barest @@ -224,11 +218,8 @@ __create_page_tables: * Create identity mapping to cater for __enable_mmu. * This identity mapping will be removed by paging_init(). */ - adr r0, __turn_mmu_on_loc - ldmia r0, {r3, r5, r6} - sub r0, r0, r3 @ virt->phys offset - add r5, r5, r0 @ phys __turn_mmu_on - add r6, r6, r0 @ phys __turn_mmu_on_end + adr_l r5, __turn_mmu_on @ _pa(__turn_mmu_on) + adr_l r6, __turn_mmu_on_end @ _pa(__turn_mmu_on_end) mov r5, r5, lsr #SECTION_SHIFT mov r6, r6, lsr #SECTION_SHIFT @@ -274,11 +265,10 @@ __create_page_tables: * We map 2 sections in case the ATAGs/DTB crosses a section boundary. */ mov r0, r2, lsr #SECTION_SHIFT - movs r0, r0, lsl #SECTION_SHIFT - subne r3, r0, r8 - addne r3, r3, #PAGE_OFFSET - addne r3, r4, r3, lsr #(SECTION_SHIFT - PMD_ORDER) - orrne r6, r7, r0 + cmp r2, #0 + ldrne r3, =FDT_FIXED_BASE >> (SECTION_SHIFT - PMD_ORDER) + addne r3, r3, r4 + orrne r6, r7, r0, lsl #SECTION_SHIFT strne r6, [r3], #1 << PMD_ORDER addne r6, r6, #1 << SECTION_SHIFT strne r6, [r3] @@ -351,11 +341,6 @@ __create_page_tables: ret lr ENDPROC(__create_page_tables) .ltorg - .align -__turn_mmu_on_loc: - .long . - .long __turn_mmu_on - .long __turn_mmu_on_end #if defined(CONFIG_SMP) .text @@ -391,10 +376,8 @@ ENTRY(secondary_startup) /* * Use the page tables supplied from __cpu_up. */ - adr r4, __secondary_data - ldmia r4, {r5, r7, r12} @ address to jump to after - sub lr, r4, r5 @ mmu has been enabled - add r3, r7, lr + adr_l r3, secondary_data + mov_l r12, __secondary_switched ldrd r4, r5, [r3, #0] @ get secondary_data.pgdir ARM_BE8(eor r4, r4, r5) @ Swap r5 and r4 in BE: ARM_BE8(eor r5, r4, r5) @ it can be done in 3 steps @@ -409,22 +392,13 @@ ARM_BE8(eor r4, r4, r5) @ without using a temp reg. ENDPROC(secondary_startup) ENDPROC(secondary_startup_arm) - /* - * r6 = &secondary_data - */ ENTRY(__secondary_switched) - ldr sp, [r7, #12] @ get secondary_data.stack + ldr_l r7, secondary_data + 12 @ get secondary_data.stack + mov sp, r7 mov fp, #0 b secondary_start_kernel ENDPROC(__secondary_switched) - .align - - .type __secondary_data, %object -__secondary_data: - .long . - .long secondary_data - .long __secondary_switched #endif /* defined(CONFIG_SMP) */ @@ -539,19 +513,11 @@ ARM_BE8(rev r0, r0) @ byteswap if big endian retne lr __fixup_smp_on_up: - adr r0, 1f - ldmia r0, {r3 - r5} - sub r3, r0, r3 - add r4, r4, r3 - add r5, r5, r3 + adr_l r4, __smpalt_begin + adr_l r5, __smpalt_end b __do_fixup_smp_on_up ENDPROC(__fixup_smp) - .align -1: .word . - .word __smpalt_begin - .word __smpalt_end - .pushsection .data .align 2 .globl smp_on_up @@ -565,14 +531,15 @@ smp_on_up: __do_fixup_smp_on_up: cmp r4, r5 reths lr - ldmia r4!, {r0, r6} - ARM( str r6, [r0, r3] ) - THUMB( add r0, r0, r3 ) + ldmia r4, {r0, r6} + ARM( str r6, [r0, r4] ) + THUMB( add r0, r0, r4 ) + add r4, r4, #8 #ifdef __ARMEB__ THUMB( mov r6, r6, ror #16 ) @ Convert word order for big-endian. #endif THUMB( strh r6, [r0], #2 ) @ For Thumb-2, store as two halfwords - THUMB( mov r6, r6, lsr #16 ) @ to be robust against misaligned r3. + THUMB( mov r6, r6, lsr #16 ) @ to be robust against misaligned r0. THUMB( strh r6, [r0] ) b __do_fixup_smp_on_up ENDPROC(__do_fixup_smp_on_up) @@ -581,151 +548,8 @@ ENTRY(fixup_smp) stmfd sp!, {r4 - r6, lr} mov r4, r0 add r5, r0, r1 - mov r3, #0 bl __do_fixup_smp_on_up ldmfd sp!, {r4 - r6, pc} ENDPROC(fixup_smp) -#ifdef __ARMEB__ -#define LOW_OFFSET 0x4 -#define HIGH_OFFSET 0x0 -#else -#define LOW_OFFSET 0x0 -#define HIGH_OFFSET 0x4 -#endif - -#ifdef CONFIG_ARM_PATCH_PHYS_VIRT - -/* __fixup_pv_table - patch the stub instructions with the delta between - * PHYS_OFFSET and PAGE_OFFSET, which is assumed to be 16MiB aligned and - * can be expressed by an immediate shifter operand. The stub instruction - * has a form of '(add|sub) rd, rn, #imm'. - */ - __HEAD -__fixup_pv_table: - adr r0, 1f - ldmia r0, {r3-r7} - mvn ip, #0 - subs r3, r0, r3 @ PHYS_OFFSET - PAGE_OFFSET - add r4, r4, r3 @ adjust table start address - add r5, r5, r3 @ adjust table end address - add r6, r6, r3 @ adjust __pv_phys_pfn_offset address - add r7, r7, r3 @ adjust __pv_offset address - mov r0, r8, lsr #PAGE_SHIFT @ convert to PFN - str r0, [r6] @ save computed PHYS_OFFSET to __pv_phys_pfn_offset - strcc ip, [r7, #HIGH_OFFSET] @ save to __pv_offset high bits - mov r6, r3, lsr #24 @ constant for add/sub instructions - teq r3, r6, lsl #24 @ must be 16MiB aligned -THUMB( it ne @ cross section branch ) - bne __error - str r3, [r7, #LOW_OFFSET] @ save to __pv_offset low bits - b __fixup_a_pv_table -ENDPROC(__fixup_pv_table) - - .align -1: .long . - .long __pv_table_begin - .long __pv_table_end -2: .long __pv_phys_pfn_offset - .long __pv_offset - - .text -__fixup_a_pv_table: - adr r0, 3f - ldr r6, [r0] - add r6, r6, r3 - ldr r0, [r6, #HIGH_OFFSET] @ pv_offset high word - ldr r6, [r6, #LOW_OFFSET] @ pv_offset low word - mov r6, r6, lsr #24 - cmn r0, #1 -#ifdef CONFIG_THUMB2_KERNEL - moveq r0, #0x200000 @ set bit 21, mov to mvn instruction - lsls r6, #24 - beq 2f - clz r7, r6 - lsr r6, #24 - lsl r6, r7 - bic r6, #0x0080 - lsrs r7, #1 - orrcs r6, #0x0080 - orr r6, r6, r7, lsl #12 - orr r6, #0x4000 - b 2f -1: add r7, r3 - ldrh ip, [r7, #2] -ARM_BE8(rev16 ip, ip) - tst ip, #0x4000 - and ip, #0x8f00 - orrne ip, r6 @ mask in offset bits 31-24 - orreq ip, r0 @ mask in offset bits 7-0 -ARM_BE8(rev16 ip, ip) - strh ip, [r7, #2] - bne 2f - ldrh ip, [r7] -ARM_BE8(rev16 ip, ip) - bic ip, #0x20 - orr ip, ip, r0, lsr #16 -ARM_BE8(rev16 ip, ip) - strh ip, [r7] -2: cmp r4, r5 - ldrcc r7, [r4], #4 @ use branch for delay slot - bcc 1b - bx lr -#else -#ifdef CONFIG_CPU_ENDIAN_BE8 - moveq r0, #0x00004000 @ set bit 22, mov to mvn instruction -#else - moveq r0, #0x400000 @ set bit 22, mov to mvn instruction -#endif - b 2f -1: ldr ip, [r7, r3] -#ifdef CONFIG_CPU_ENDIAN_BE8 - @ in BE8, we load data in BE, but instructions still in LE - bic ip, ip, #0xff000000 - tst ip, #0x000f0000 @ check the rotation field - orrne ip, ip, r6, lsl #24 @ mask in offset bits 31-24 - biceq ip, ip, #0x00004000 @ clear bit 22 - orreq ip, ip, r0 @ mask in offset bits 7-0 -#else - bic ip, ip, #0x000000ff - tst ip, #0xf00 @ check the rotation field - orrne ip, ip, r6 @ mask in offset bits 31-24 - biceq ip, ip, #0x400000 @ clear bit 22 - orreq ip, ip, r0 @ mask in offset bits 7-0 -#endif - str ip, [r7, r3] -2: cmp r4, r5 - ldrcc r7, [r4], #4 @ use branch for delay slot - bcc 1b - ret lr -#endif -ENDPROC(__fixup_a_pv_table) - - .align -3: .long __pv_offset - -ENTRY(fixup_pv_table) - stmfd sp!, {r4 - r7, lr} - mov r3, #0 @ no offset - mov r4, r0 @ r0 = table start - add r5, r0, r1 @ r1 = table size - bl __fixup_a_pv_table - ldmfd sp!, {r4 - r7, pc} -ENDPROC(fixup_pv_table) - - .data - .align 2 - .globl __pv_phys_pfn_offset - .type __pv_phys_pfn_offset, %object -__pv_phys_pfn_offset: - .word 0 - .size __pv_phys_pfn_offset, . -__pv_phys_pfn_offset - - .globl __pv_offset - .type __pv_offset, %object -__pv_offset: - .quad 0 - .size __pv_offset, . -__pv_offset -#endif - #include "head-common.S" diff --git a/arch/arm/kernel/hyp-stub.S b/arch/arm/kernel/hyp-stub.S index 26d8e03b1dd3..b699b22a4db1 100644 --- a/arch/arm/kernel/hyp-stub.S +++ b/arch/arm/kernel/hyp-stub.S @@ -24,41 +24,38 @@ ENTRY(__boot_cpu_mode) .text /* - * Save the primary CPU boot mode. Requires 3 scratch registers. + * Save the primary CPU boot mode. Requires 2 scratch registers. */ - .macro store_primary_cpu_mode reg1, reg2, reg3 + .macro store_primary_cpu_mode reg1, reg2 mrs \reg1, cpsr and \reg1, \reg1, #MODE_MASK - adr \reg2, .L__boot_cpu_mode_offset - ldr \reg3, [\reg2] - str \reg1, [\reg2, \reg3] + str_l \reg1, __boot_cpu_mode, \reg2 .endm /* * Compare the current mode with the one saved on the primary CPU. * If they don't match, record that fact. The Z bit indicates * if there's a match or not. - * Requires 3 additionnal scratch registers. + * Requires 2 additional scratch registers. */ - .macro compare_cpu_mode_with_primary mode, reg1, reg2, reg3 - adr \reg2, .L__boot_cpu_mode_offset - ldr \reg3, [\reg2] - ldr \reg1, [\reg2, \reg3] + .macro compare_cpu_mode_with_primary mode, reg1, reg2 + adr_l \reg2, __boot_cpu_mode + ldr \reg1, [\reg2] cmp \mode, \reg1 @ matches primary CPU boot mode? orrne \reg1, \reg1, #BOOT_CPU_MODE_MISMATCH - strne \reg1, [\reg2, \reg3] @ record what happened and give up + strne \reg1, [\reg2] @ record what happened and give up .endm #else /* ZIMAGE */ - .macro store_primary_cpu_mode reg1:req, reg2:req, reg3:req + .macro store_primary_cpu_mode reg1:req, reg2:req .endm /* * The zImage loader only runs on one CPU, so we don't bother with mult-CPU * consistency checking: */ - .macro compare_cpu_mode_with_primary mode, reg1, reg2, reg3 + .macro compare_cpu_mode_with_primary mode, reg1, reg2 cmp \mode, \mode .endm @@ -73,7 +70,7 @@ ENTRY(__boot_cpu_mode) */ @ Call this from the primary CPU ENTRY(__hyp_stub_install) - store_primary_cpu_mode r4, r5, r6 + store_primary_cpu_mode r4, r5 ENDPROC(__hyp_stub_install) @ fall through... @@ -87,7 +84,7 @@ ENTRY(__hyp_stub_install_secondary) * If the secondary has booted with a different mode, give up * immediately. */ - compare_cpu_mode_with_primary r4, r5, r6, r7 + compare_cpu_mode_with_primary r4, r5, r6 retne lr /* @@ -228,12 +225,6 @@ ENTRY(__hyp_soft_restart) ret lr ENDPROC(__hyp_soft_restart) -#ifndef ZIMAGE -.align 2 -.L__boot_cpu_mode_offset: - .long __boot_cpu_mode - . -#endif - .align 5 ENTRY(__hyp_stub_vectors) __hyp_stub_reset: W(b) . diff --git a/arch/arm/kernel/iwmmxt.S b/arch/arm/kernel/iwmmxt.S index 0dcae787b004..d2b4ac06e4ed 100644 --- a/arch/arm/kernel/iwmmxt.S +++ b/arch/arm/kernel/iwmmxt.S @@ -16,6 +16,7 @@ #include <asm/thread_info.h> #include <asm/asm-offsets.h> #include <asm/assembler.h> +#include "iwmmxt.h" #if defined(CONFIG_CPU_PJ4) || defined(CONFIG_CPU_PJ4B) #define PJ4(code...) code @@ -113,33 +114,33 @@ concan_save: concan_dump: - wstrw wCSSF, [r1, #MMX_WCSSF] - wstrw wCASF, [r1, #MMX_WCASF] - wstrw wCGR0, [r1, #MMX_WCGR0] - wstrw wCGR1, [r1, #MMX_WCGR1] - wstrw wCGR2, [r1, #MMX_WCGR2] - wstrw wCGR3, [r1, #MMX_WCGR3] + wstrw wCSSF, r1, MMX_WCSSF + wstrw wCASF, r1, MMX_WCASF + wstrw wCGR0, r1, MMX_WCGR0 + wstrw wCGR1, r1, MMX_WCGR1 + wstrw wCGR2, r1, MMX_WCGR2 + wstrw wCGR3, r1, MMX_WCGR3 1: @ MUP? wRn tst r2, #0x2 beq 2f - wstrd wR0, [r1, #MMX_WR0] - wstrd wR1, [r1, #MMX_WR1] - wstrd wR2, [r1, #MMX_WR2] - wstrd wR3, [r1, #MMX_WR3] - wstrd wR4, [r1, #MMX_WR4] - wstrd wR5, [r1, #MMX_WR5] - wstrd wR6, [r1, #MMX_WR6] - wstrd wR7, [r1, #MMX_WR7] - wstrd wR8, [r1, #MMX_WR8] - wstrd wR9, [r1, #MMX_WR9] - wstrd wR10, [r1, #MMX_WR10] - wstrd wR11, [r1, #MMX_WR11] - wstrd wR12, [r1, #MMX_WR12] - wstrd wR13, [r1, #MMX_WR13] - wstrd wR14, [r1, #MMX_WR14] - wstrd wR15, [r1, #MMX_WR15] + wstrd wR0, r1, MMX_WR0 + wstrd wR1, r1, MMX_WR1 + wstrd wR2, r1, MMX_WR2 + wstrd wR3, r1, MMX_WR3 + wstrd wR4, r1, MMX_WR4 + wstrd wR5, r1, MMX_WR5 + wstrd wR6, r1, MMX_WR6 + wstrd wR7, r1, MMX_WR7 + wstrd wR8, r1, MMX_WR8 + wstrd wR9, r1, MMX_WR9 + wstrd wR10, r1, MMX_WR10 + wstrd wR11, r1, MMX_WR11 + wstrd wR12, r1, MMX_WR12 + wstrd wR13, r1, MMX_WR13 + wstrd wR14, r1, MMX_WR14 + wstrd wR15, r1, MMX_WR15 2: teq r0, #0 @ anything to load? reteq lr @ if not, return @@ -147,30 +148,30 @@ concan_dump: concan_load: @ Load wRn - wldrd wR0, [r0, #MMX_WR0] - wldrd wR1, [r0, #MMX_WR1] - wldrd wR2, [r0, #MMX_WR2] - wldrd wR3, [r0, #MMX_WR3] - wldrd wR4, [r0, #MMX_WR4] - wldrd wR5, [r0, #MMX_WR5] - wldrd wR6, [r0, #MMX_WR6] - wldrd wR7, [r0, #MMX_WR7] - wldrd wR8, [r0, #MMX_WR8] - wldrd wR9, [r0, #MMX_WR9] - wldrd wR10, [r0, #MMX_WR10] - wldrd wR11, [r0, #MMX_WR11] - wldrd wR12, [r0, #MMX_WR12] - wldrd wR13, [r0, #MMX_WR13] - wldrd wR14, [r0, #MMX_WR14] - wldrd wR15, [r0, #MMX_WR15] + wldrd wR0, r0, MMX_WR0 + wldrd wR1, r0, MMX_WR1 + wldrd wR2, r0, MMX_WR2 + wldrd wR3, r0, MMX_WR3 + wldrd wR4, r0, MMX_WR4 + wldrd wR5, r0, MMX_WR5 + wldrd wR6, r0, MMX_WR6 + wldrd wR7, r0, MMX_WR7 + wldrd wR8, r0, MMX_WR8 + wldrd wR9, r0, MMX_WR9 + wldrd wR10, r0, MMX_WR10 + wldrd wR11, r0, MMX_WR11 + wldrd wR12, r0, MMX_WR12 + wldrd wR13, r0, MMX_WR13 + wldrd wR14, r0, MMX_WR14 + wldrd wR15, r0, MMX_WR15 @ Load wCx - wldrw wCSSF, [r0, #MMX_WCSSF] - wldrw wCASF, [r0, #MMX_WCASF] - wldrw wCGR0, [r0, #MMX_WCGR0] - wldrw wCGR1, [r0, #MMX_WCGR1] - wldrw wCGR2, [r0, #MMX_WCGR2] - wldrw wCGR3, [r0, #MMX_WCGR3] + wldrw wCSSF, r0, MMX_WCSSF + wldrw wCASF, r0, MMX_WCASF + wldrw wCGR0, r0, MMX_WCGR0 + wldrw wCGR1, r0, MMX_WCGR1 + wldrw wCGR2, r0, MMX_WCGR2 + wldrw wCGR3, r0, MMX_WCGR3 @ clear CUP/MUP (only if r1 != 0) teq r1, #0 diff --git a/arch/arm/kernel/iwmmxt.h b/arch/arm/kernel/iwmmxt.h new file mode 100644 index 000000000000..fb627286f5bb --- /dev/null +++ b/arch/arm/kernel/iwmmxt.h @@ -0,0 +1,47 @@ +/* SPDX-License-Identifier: GPL-2.0 */ + +#ifndef __IWMMXT_H__ +#define __IWMMXT_H__ + +.irp b, 0, 1, 2, 3, 4, 5, 6, 7, 8, 9, 10, 11, 12, 13, 14, 15 +.set .LwR\b, \b +.set .Lr\b, \b +.endr + +.set .LwCSSF, 0x2 +.set .LwCASF, 0x3 +.set .LwCGR0, 0x8 +.set .LwCGR1, 0x9 +.set .LwCGR2, 0xa +.set .LwCGR3, 0xb + +.macro wldrd, reg:req, base:req, offset:req +.inst 0xedd00100 | (.L\reg << 12) | (.L\base << 16) | (\offset >> 2) +.endm + +.macro wldrw, reg:req, base:req, offset:req +.inst 0xfd900100 | (.L\reg << 12) | (.L\base << 16) | (\offset >> 2) +.endm + +.macro wstrd, reg:req, base:req, offset:req +.inst 0xedc00100 | (.L\reg << 12) | (.L\base << 16) | (\offset >> 2) +.endm + +.macro wstrw, reg:req, base:req, offset:req +.inst 0xfd800100 | (.L\reg << 12) | (.L\base << 16) | (\offset >> 2) +.endm + +#ifdef __clang__ + +#define wCon c1 + +.macro tmrc, dest:req, control:req +mrc p1, 0, \dest, \control, c0, 0 +.endm + +.macro tmcr, control:req, src:req +mcr p1, 0, \src, \control, c0, 0 +.endm +#endif + +#endif diff --git a/arch/arm/kernel/module.c b/arch/arm/kernel/module.c index e15444b25ca0..beac45e89ba6 100644 --- a/arch/arm/kernel/module.c +++ b/arch/arm/kernel/module.c @@ -185,14 +185,24 @@ apply_relocate(Elf32_Shdr *sechdrs, const char *strtab, unsigned int symindex, *(u32 *)loc |= offset & 0x7fffffff; break; + case R_ARM_REL32: + *(u32 *)loc += sym->st_value - loc; + break; + case R_ARM_MOVW_ABS_NC: case R_ARM_MOVT_ABS: + case R_ARM_MOVW_PREL_NC: + case R_ARM_MOVT_PREL: offset = tmp = __mem_to_opcode_arm(*(u32 *)loc); offset = ((offset & 0xf0000) >> 4) | (offset & 0xfff); offset = (offset ^ 0x8000) - 0x8000; offset += sym->st_value; - if (ELF32_R_TYPE(rel->r_info) == R_ARM_MOVT_ABS) + if (ELF32_R_TYPE(rel->r_info) == R_ARM_MOVT_PREL || + ELF32_R_TYPE(rel->r_info) == R_ARM_MOVW_PREL_NC) + offset -= loc; + if (ELF32_R_TYPE(rel->r_info) == R_ARM_MOVT_ABS || + ELF32_R_TYPE(rel->r_info) == R_ARM_MOVT_PREL) offset >>= 16; tmp &= 0xfff0f000; @@ -283,6 +293,8 @@ apply_relocate(Elf32_Shdr *sechdrs, const char *strtab, unsigned int symindex, case R_ARM_THM_MOVW_ABS_NC: case R_ARM_THM_MOVT_ABS: + case R_ARM_THM_MOVW_PREL_NC: + case R_ARM_THM_MOVT_PREL: upper = __mem_to_opcode_thumb16(*(u16 *)loc); lower = __mem_to_opcode_thumb16(*(u16 *)(loc + 2)); @@ -302,7 +314,11 @@ apply_relocate(Elf32_Shdr *sechdrs, const char *strtab, unsigned int symindex, offset = (offset ^ 0x8000) - 0x8000; offset += sym->st_value; - if (ELF32_R_TYPE(rel->r_info) == R_ARM_THM_MOVT_ABS) + if (ELF32_R_TYPE(rel->r_info) == R_ARM_THM_MOVT_PREL || + ELF32_R_TYPE(rel->r_info) == R_ARM_THM_MOVW_PREL_NC) + offset -= loc; + if (ELF32_R_TYPE(rel->r_info) == R_ARM_THM_MOVT_ABS || + ELF32_R_TYPE(rel->r_info) == R_ARM_THM_MOVT_PREL) offset >>= 16; upper = (u16)((upper & 0xfbf0) | diff --git a/arch/arm/kernel/phys2virt.S b/arch/arm/kernel/phys2virt.S new file mode 100644 index 000000000000..fb53db78fe78 --- /dev/null +++ b/arch/arm/kernel/phys2virt.S @@ -0,0 +1,238 @@ +/* SPDX-License-Identifier: GPL-2.0-only */ +/* + * Copyright (C) 1994-2002 Russell King + * Copyright (c) 2003, 2020 ARM Limited + * All Rights Reserved + */ + +#include <linux/init.h> +#include <linux/linkage.h> +#include <asm/assembler.h> +#include <asm/page.h> + +#ifdef __ARMEB__ +#define LOW_OFFSET 0x4 +#define HIGH_OFFSET 0x0 +#else +#define LOW_OFFSET 0x0 +#define HIGH_OFFSET 0x4 +#endif + +/* + * __fixup_pv_table - patch the stub instructions with the delta between + * PHYS_OFFSET and PAGE_OFFSET, which is assumed to be + * 2 MiB aligned. + * + * Called from head.S, which expects the following registers to be preserved: + * r1 = machine no, r2 = atags or dtb, + * r8 = phys_offset, r9 = cpuid, r10 = procinfo + */ + __HEAD +ENTRY(__fixup_pv_table) + mov r0, r8, lsr #PAGE_SHIFT @ convert to PFN + str_l r0, __pv_phys_pfn_offset, r3 + + adr_l r0, __pv_offset + subs r3, r8, #PAGE_OFFSET @ PHYS_OFFSET - PAGE_OFFSET + mvn ip, #0 + strcc ip, [r0, #HIGH_OFFSET] @ save to __pv_offset high bits + str r3, [r0, #LOW_OFFSET] @ save to __pv_offset low bits + + mov r0, r3, lsr #21 @ constant for add/sub instructions + teq r3, r0, lsl #21 @ must be 2 MiB aligned + bne 0f + + adr_l r4, __pv_table_begin + adr_l r5, __pv_table_end + b __fixup_a_pv_table + +0: mov r0, r0 @ deadloop on error + b 0b +ENDPROC(__fixup_pv_table) + + .text +__fixup_a_pv_table: + adr_l r6, __pv_offset + ldr r0, [r6, #HIGH_OFFSET] @ pv_offset high word + ldr r6, [r6, #LOW_OFFSET] @ pv_offset low word + cmn r0, #1 +#ifdef CONFIG_THUMB2_KERNEL + @ + @ The Thumb-2 versions of the patchable sequences are + @ + @ phys-to-virt: movw <reg>, #offset<31:21> + @ lsl <reg>, #21 + @ sub <VA>, <PA>, <reg> + @ + @ virt-to-phys (non-LPAE): movw <reg>, #offset<31:21> + @ lsl <reg>, #21 + @ add <PA>, <VA>, <reg> + @ + @ virt-to-phys (LPAE): movw <reg>, #offset<31:21> + @ lsl <reg>, #21 + @ adds <PAlo>, <VA>, <reg> + @ mov <PAhi>, #offset<39:32> + @ adc <PAhi>, <PAhi>, #0 + @ + @ In the non-LPAE case, all patchable instructions are MOVW + @ instructions, where we need to patch in the offset into the + @ second halfword of the opcode (the 16-bit immediate is encoded + @ as imm4:i:imm3:imm8) + @ + @ 15 11 10 9 4 3 0 15 14 12 11 8 7 0 + @ +-----------+---+-------------+------++---+------+----+------+ + @ MOVW | 1 1 1 1 0 | i | 1 0 0 1 0 0 | imm4 || 0 | imm3 | Rd | imm8 | + @ +-----------+---+-------------+------++---+------+----+------+ + @ + @ In the LPAE case, we also need to patch in the high word of the + @ offset into the immediate field of the MOV instruction, or patch it + @ to a MVN instruction if the offset is negative. In this case, we + @ need to inspect the first halfword of the opcode, to check whether + @ it is MOVW or MOV/MVN, and to perform the MOV to MVN patching if + @ needed. The encoding of the immediate is rather complex for values + @ of i:imm3 != 0b0000, but fortunately, we never need more than 8 lower + @ order bits, which can be patched into imm8 directly (and i:imm3 + @ cleared) + @ + @ 15 11 10 9 5 0 15 14 12 11 8 7 0 + @ +-----------+---+---------------------++---+------+----+------+ + @ MOV | 1 1 1 1 0 | i | 0 0 0 1 0 0 1 1 1 1 || 0 | imm3 | Rd | imm8 | + @ MVN | 1 1 1 1 0 | i | 0 0 0 1 1 0 1 1 1 1 || 0 | imm3 | Rd | imm8 | + @ +-----------+---+---------------------++---+------+----+------+ + @ + moveq r0, #0x200000 @ set bit 21, mov to mvn instruction + lsrs r3, r6, #29 @ isolate top 3 bits of displacement + ubfx r6, r6, #21, #8 @ put bits 28:21 into the MOVW imm8 field + bfi r6, r3, #12, #3 @ put bits 31:29 into the MOVW imm3 field + b .Lnext +.Lloop: add r7, r4 + adds r4, #4 @ clears Z flag +#ifdef CONFIG_ARM_LPAE + ldrh ip, [r7] +ARM_BE8(rev16 ip, ip) + tst ip, #0x200 @ MOVW has bit 9 set, MVN has it clear + bne 0f @ skip to MOVW handling (Z flag is clear) + bic ip, #0x20 @ clear bit 5 (MVN -> MOV) + orr ip, ip, r0, lsr #16 @ MOV -> MVN if offset < 0 +ARM_BE8(rev16 ip, ip) + strh ip, [r7] + @ Z flag is set +0: +#endif + ldrh ip, [r7, #2] +ARM_BE8(rev16 ip, ip) + and ip, #0xf00 @ clear everything except Rd field + orreq ip, r0 @ Z flag set -> MOV/MVN -> patch in high bits + orrne ip, r6 @ Z flag clear -> MOVW -> patch in low bits +ARM_BE8(rev16 ip, ip) + strh ip, [r7, #2] +#else +#ifdef CONFIG_CPU_ENDIAN_BE8 +@ in BE8, we load data in BE, but instructions still in LE +#define PV_BIT24 0x00000001 +#define PV_IMM8_MASK 0xff000000 +#define PV_IMMR_MSB 0x00080000 +#else +#define PV_BIT24 0x01000000 +#define PV_IMM8_MASK 0x000000ff +#define PV_IMMR_MSB 0x00000800 +#endif + + @ + @ The ARM versions of the patchable sequences are + @ + @ phys-to-virt: sub <VA>, <PA>, #offset<31:24>, lsl #24 + @ sub <VA>, <PA>, #offset<23:16>, lsl #16 + @ + @ virt-to-phys (non-LPAE): add <PA>, <VA>, #offset<31:24>, lsl #24 + @ add <PA>, <VA>, #offset<23:16>, lsl #16 + @ + @ virt-to-phys (LPAE): movw <reg>, #offset<31:20> + @ adds <PAlo>, <VA>, <reg>, lsl #20 + @ mov <PAhi>, #offset<39:32> + @ adc <PAhi>, <PAhi>, #0 + @ + @ In the non-LPAE case, all patchable instructions are ADD or SUB + @ instructions, where we need to patch in the offset into the + @ immediate field of the opcode, which is emitted with the correct + @ rotation value. (The effective value of the immediate is imm12<7:0> + @ rotated right by [2 * imm12<11:8>] bits) + @ + @ 31 28 27 23 22 20 19 16 15 12 11 0 + @ +------+-----------------+------+------+-------+ + @ ADD | cond | 0 0 1 0 1 0 0 0 | Rn | Rd | imm12 | + @ SUB | cond | 0 0 1 0 0 1 0 0 | Rn | Rd | imm12 | + @ MOV | cond | 0 0 1 1 1 0 1 0 | Rn | Rd | imm12 | + @ MVN | cond | 0 0 1 1 1 1 1 0 | Rn | Rd | imm12 | + @ +------+-----------------+------+------+-------+ + @ + @ In the LPAE case, we use a MOVW instruction to carry the low offset + @ word, and patch in the high word of the offset into the immediate + @ field of the subsequent MOV instruction, or patch it to a MVN + @ instruction if the offset is negative. We can distinguish MOVW + @ instructions based on bits 23:22 of the opcode, and ADD/SUB can be + @ distinguished from MOV/MVN (all using the encodings above) using + @ bit 24. + @ + @ 31 28 27 23 22 20 19 16 15 12 11 0 + @ +------+-----------------+------+------+-------+ + @ MOVW | cond | 0 0 1 1 0 0 0 0 | imm4 | Rd | imm12 | + @ +------+-----------------+------+------+-------+ + @ + moveq r0, #0x400000 @ set bit 22, mov to mvn instruction + mov r3, r6, lsr #16 @ put offset bits 31-16 into r3 + mov r6, r6, lsr #24 @ put offset bits 31-24 into r6 + and r3, r3, #0xf0 @ only keep offset bits 23-20 in r3 + b .Lnext +.Lloop: ldr ip, [r7, r4] +#ifdef CONFIG_ARM_LPAE + tst ip, #PV_BIT24 @ ADD/SUB have bit 24 clear + beq 1f +ARM_BE8(rev ip, ip) + tst ip, #0xc00000 @ MOVW has bits 23:22 clear + bic ip, ip, #0x400000 @ clear bit 22 + bfc ip, #0, #12 @ clear imm12 field of MOV[W] instruction + orreq ip, ip, r6, lsl #4 @ MOVW -> mask in offset bits 31-24 + orreq ip, ip, r3, lsr #4 @ MOVW -> mask in offset bits 23-20 + orrne ip, ip, r0 @ MOV -> mask in offset bits 7-0 (or bit 22) +ARM_BE8(rev ip, ip) + b 2f +1: +#endif + tst ip, #PV_IMMR_MSB @ rotation value >= 16 ? + bic ip, ip, #PV_IMM8_MASK + orreq ip, ip, r6 ARM_BE8(, lsl #24) @ mask in offset bits 31-24 + orrne ip, ip, r3 ARM_BE8(, lsl #24) @ mask in offset bits 23-20 +2: + str ip, [r7, r4] + add r4, r4, #4 +#endif + +.Lnext: + cmp r4, r5 + ldrcc r7, [r4] @ use branch for delay slot + bcc .Lloop + ret lr +ENDPROC(__fixup_a_pv_table) + +ENTRY(fixup_pv_table) + stmfd sp!, {r4 - r7, lr} + mov r4, r0 @ r0 = table start + add r5, r0, r1 @ r1 = table size + bl __fixup_a_pv_table + ldmfd sp!, {r4 - r7, pc} +ENDPROC(fixup_pv_table) + + .data + .align 2 + .globl __pv_phys_pfn_offset + .type __pv_phys_pfn_offset, %object +__pv_phys_pfn_offset: + .word 0 + .size __pv_phys_pfn_offset, . -__pv_phys_pfn_offset + + .globl __pv_offset + .type __pv_offset, %object +__pv_offset: + .quad 0 + .size __pv_offset, . -__pv_offset diff --git a/arch/arm/kernel/setup.c b/arch/arm/kernel/setup.c index 3f65d0ac9f63..1a5edf562e85 100644 --- a/arch/arm/kernel/setup.c +++ b/arch/arm/kernel/setup.c @@ -18,6 +18,7 @@ #include <linux/of_platform.h> #include <linux/init.h> #include <linux/kexec.h> +#include <linux/libfdt.h> #include <linux/of_fdt.h> #include <linux/cpu.h> #include <linux/interrupt.h> @@ -58,6 +59,7 @@ #include <asm/unwind.h> #include <asm/memblock.h> #include <asm/virt.h> +#include <asm/kasan.h> #include "atags.h" @@ -763,7 +765,7 @@ int __init arm_add_memory(u64 start, u64 size) #ifndef CONFIG_PHYS_ADDR_T_64BIT if (aligned_start > ULONG_MAX) { pr_crit("Ignoring memory at 0x%08llx outside 32-bit physical address space\n", - (long long)start); + start); return -EINVAL; } @@ -1081,19 +1083,27 @@ void __init hyp_mode_check(void) void __init setup_arch(char **cmdline_p) { - const struct machine_desc *mdesc; + const struct machine_desc *mdesc = NULL; + void *atags_vaddr = NULL; + + if (__atags_pointer) + atags_vaddr = FDT_VIRT_BASE(__atags_pointer); setup_processor(); - mdesc = setup_machine_fdt(__atags_pointer); + if (atags_vaddr) { + mdesc = setup_machine_fdt(atags_vaddr); + if (mdesc) + memblock_reserve(__atags_pointer, + fdt_totalsize(atags_vaddr)); + } if (!mdesc) - mdesc = setup_machine_tags(__atags_pointer, __machine_arch_type); + mdesc = setup_machine_tags(atags_vaddr, __machine_arch_type); if (!mdesc) { early_print("\nError: invalid dtb and unrecognized/unsupported machine ID\n"); early_print(" r1=0x%08x, r2=0x%08x\n", __machine_arch_type, __atags_pointer); if (__atags_pointer) - early_print(" r2[]=%*ph\n", 16, - phys_to_virt(__atags_pointer)); + early_print(" r2[]=%*ph\n", 16, atags_vaddr); dump_machine_table(); } @@ -1126,7 +1136,7 @@ void __init setup_arch(char **cmdline_p) efi_init(); /* * Make sure the calculation for lowmem/highmem is set appropriately - * before reserving/allocating any mmeory + * before reserving/allocating any memory */ adjust_lowmem_bounds(); arm_memblock_init(mdesc); @@ -1136,6 +1146,7 @@ void __init setup_arch(char **cmdline_p) early_ioremap_reset(); paging_init(mdesc); + kasan_init(); request_standard_resources(mdesc); if (mdesc->restart) diff --git a/arch/arm/kernel/sleep.S b/arch/arm/kernel/sleep.S index 5dc8b80bb693..43077e11dafd 100644 --- a/arch/arm/kernel/sleep.S +++ b/arch/arm/kernel/sleep.S @@ -72,8 +72,9 @@ ENTRY(__cpu_suspend) ldr r3, =sleep_save_sp stmfd sp!, {r0, r1} @ save suspend func arg and pointer ldr r3, [r3, #SLEEP_SAVE_SP_VIRT] - ALT_SMP(ldr r0, =mpidr_hash) + ALT_SMP(W(nop)) @ don't use adr_l inside ALT_SMP() ALT_UP_B(1f) + adr_l r0, mpidr_hash /* This ldmia relies on the memory layout of the mpidr_hash struct */ ldmia r0, {r1, r6-r8} @ r1 = mpidr mask (r6,r7,r8) = l[0,1,2] shifts compute_mpidr_hash r0, r6, r7, r8, r2, r1 @@ -147,9 +148,8 @@ no_hyp: mov r1, #0 ALT_SMP(mrc p15, 0, r0, c0, c0, 5) ALT_UP_B(1f) - adr r2, mpidr_hash_ptr - ldr r3, [r2] - add r2, r2, r3 @ r2 = struct mpidr_hash phys address + adr_l r2, mpidr_hash @ r2 = struct mpidr_hash phys address + /* * This ldmia relies on the memory layout of the mpidr_hash * struct mpidr_hash. @@ -157,10 +157,7 @@ no_hyp: ldmia r2, { r3-r6 } @ r3 = mpidr mask (r4,r5,r6) = l[0,1,2] shifts compute_mpidr_hash r1, r4, r5, r6, r0, r3 1: - adr r0, _sleep_save_sp - ldr r2, [r0] - add r0, r0, r2 - ldr r0, [r0, #SLEEP_SAVE_SP_PHYS] + ldr_l r0, sleep_save_sp + SLEEP_SAVE_SP_PHYS ldr r0, [r0, r1, lsl #2] @ load phys pgd, stack, resume fn @@ -177,12 +174,6 @@ ENDPROC(cpu_resume_arm) ENDPROC(cpu_resume_no_hyp) #endif - .align 2 -_sleep_save_sp: - .long sleep_save_sp - . -mpidr_hash_ptr: - .long mpidr_hash - . @ mpidr_hash struct offset - .data .align 2 .type sleep_save_sp, #object diff --git a/arch/arm/kernel/smp.c b/arch/arm/kernel/smp.c index 48099c6e1e4a..6ab2b0ad5f40 100644 --- a/arch/arm/kernel/smp.c +++ b/arch/arm/kernel/smp.c @@ -524,14 +524,13 @@ void __init smp_prepare_cpus(unsigned int max_cpus) } static const char *ipi_types[NR_IPI] __tracepoint_string = { -#define S(x,s) [x] = s - S(IPI_WAKEUP, "CPU wakeup interrupts"), - S(IPI_TIMER, "Timer broadcast interrupts"), - S(IPI_RESCHEDULE, "Rescheduling interrupts"), - S(IPI_CALL_FUNC, "Function call interrupts"), - S(IPI_CPU_STOP, "CPU stop interrupts"), - S(IPI_IRQ_WORK, "IRQ work interrupts"), - S(IPI_COMPLETION, "completion interrupts"), + [IPI_WAKEUP] = "CPU wakeup interrupts", + [IPI_TIMER] = "Timer broadcast interrupts", + [IPI_RESCHEDULE] = "Rescheduling interrupts", + [IPI_CALL_FUNC] = "Function call interrupts", + [IPI_CPU_STOP] = "CPU stop interrupts", + [IPI_IRQ_WORK] = "IRQ work interrupts", + [IPI_COMPLETION] = "completion interrupts", }; static void smp_cross_call(const struct cpumask *target, unsigned int ipinr); diff --git a/arch/arm/kernel/unwind.c b/arch/arm/kernel/unwind.c index d2bd0df2318d..59fdf257bf8b 100644 --- a/arch/arm/kernel/unwind.c +++ b/arch/arm/kernel/unwind.c @@ -18,9 +18,6 @@ #warning Your compiler does not have EABI support. #warning ARM unwind is known to compile only with EABI compilers. #warning Change compiler or disable ARM_UNWIND option. -#elif (__GNUC__ == 4 && __GNUC_MINOR__ <= 2) && !defined(__clang__) -#warning Your compiler is too buggy; it is known to not compile ARM unwind support. -#warning Change compiler or disable ARM_UNWIND option. #endif #endif /* __CHECKER__ */ @@ -236,7 +233,11 @@ static int unwind_pop_register(struct unwind_ctrl_block *ctrl, if (*vsp >= (unsigned long *)ctrl->sp_high) return -URC_FAILURE; - ctrl->vrs[reg] = *(*vsp)++; + /* Use READ_ONCE_NOCHECK here to avoid this memory access + * from being tracked by KASAN. + */ + ctrl->vrs[reg] = READ_ONCE_NOCHECK(*(*vsp)); + (*vsp)++; return URC_OK; } diff --git a/arch/arm/lib/memcpy.S b/arch/arm/lib/memcpy.S index 09a333153dc6..e4caf48c089f 100644 --- a/arch/arm/lib/memcpy.S +++ b/arch/arm/lib/memcpy.S @@ -58,10 +58,12 @@ /* Prototype: void *memcpy(void *dest, const void *src, size_t n); */ +ENTRY(__memcpy) ENTRY(mmiocpy) -ENTRY(memcpy) +WEAK(memcpy) #include "copy_template.S" ENDPROC(memcpy) ENDPROC(mmiocpy) +ENDPROC(__memcpy) diff --git a/arch/arm/lib/memmove.S b/arch/arm/lib/memmove.S index b50e5770fb44..6fecc12a1f51 100644 --- a/arch/arm/lib/memmove.S +++ b/arch/arm/lib/memmove.S @@ -24,12 +24,13 @@ * occurring in the opposite direction. */ -ENTRY(memmove) +ENTRY(__memmove) +WEAK(memmove) UNWIND( .fnstart ) subs ip, r0, r1 cmphi r2, ip - bls memcpy + bls __memcpy stmfd sp!, {r0, r4, lr} UNWIND( .fnend ) @@ -222,3 +223,4 @@ ENTRY(memmove) 18: backward_copy_shift push=24 pull=8 ENDPROC(memmove) +ENDPROC(__memmove) diff --git a/arch/arm/lib/memset.S b/arch/arm/lib/memset.S index 6ca4535c47fb..9817cb258c1a 100644 --- a/arch/arm/lib/memset.S +++ b/arch/arm/lib/memset.S @@ -13,8 +13,9 @@ .text .align 5 +ENTRY(__memset) ENTRY(mmioset) -ENTRY(memset) +WEAK(memset) UNWIND( .fnstart ) ands r3, r0, #3 @ 1 unaligned? mov ip, r0 @ preserve r0 as return value @@ -132,6 +133,7 @@ UNWIND( .fnstart ) UNWIND( .fnend ) ENDPROC(memset) ENDPROC(mmioset) +ENDPROC(__memset) ENTRY(__memset32) UNWIND( .fnstart ) diff --git a/arch/arm/mach-s3c/mach-h1940.c b/arch/arm/mach-s3c/mach-h1940.c index 53d51aa83200..8a43ed1c4c4d 100644 --- a/arch/arm/mach-s3c/mach-h1940.c +++ b/arch/arm/mach-s3c/mach-h1940.c @@ -297,6 +297,15 @@ static const struct s3c_adc_bat_thresh bat_lut_acin[] = { { .volt = 3841, .cur = 0, .level = 0}, }; +static struct gpiod_lookup_table h1940_bat_gpio_table = { + .dev_id = "s3c-adc-battery", + .table = { + /* Charge status S3C2410_GPF(3) */ + GPIO_LOOKUP("GPIOF", 3, "charge-status", GPIO_ACTIVE_LOW), + { }, + }, +}; + static int h1940_bat_init(void) { int ret; @@ -330,8 +339,6 @@ static struct s3c_adc_bat_pdata h1940_bat_cfg = { .exit = h1940_bat_exit, .enable_charger = h1940_enable_charger, .disable_charger = h1940_disable_charger, - .gpio_charge_finished = S3C2410_GPF(3), - .gpio_inverted = 1, .lut_noac = bat_lut_noac, .lut_noac_cnt = ARRAY_SIZE(bat_lut_noac), .lut_acin = bat_lut_acin, @@ -720,6 +727,7 @@ static void __init h1940_init(void) s3c24xx_fb_set_platdata(&h1940_fb_info); gpiod_add_lookup_table(&h1940_mmc_gpio_table); gpiod_add_lookup_table(&h1940_audio_gpio_table); + gpiod_add_lookup_table(&h1940_bat_gpio_table); /* Configure the I2S pins (GPE0...GPE4) in correct mode */ s3c_gpio_cfgall_range(S3C2410_GPE(0), 5, S3C_GPIO_SFN(2), S3C_GPIO_PULL_NONE); diff --git a/arch/arm/mach-s3c/mach-rx1950.c b/arch/arm/mach-s3c/mach-rx1950.c index b9758f0a9a14..6e19add158a9 100644 --- a/arch/arm/mach-s3c/mach-rx1950.c +++ b/arch/arm/mach-s3c/mach-rx1950.c @@ -206,6 +206,15 @@ static const struct s3c_adc_bat_thresh bat_lut_acin[] = { { .volt = 3820, .cur = 0, .level = 0}, }; +static struct gpiod_lookup_table rx1950_bat_gpio_table = { + .dev_id = "s3c-adc-battery", + .table = { + /* Charge status S3C2410_GPF(3) */ + GPIO_LOOKUP("GPIOF", 3, "charge-status", GPIO_ACTIVE_HIGH), + { }, + }, +}; + static int rx1950_bat_init(void) { int ret; @@ -331,7 +340,6 @@ static struct s3c_adc_bat_pdata rx1950_bat_cfg = { .exit = rx1950_bat_exit, .enable_charger = rx1950_enable_charger, .disable_charger = rx1950_disable_charger, - .gpio_charge_finished = S3C2410_GPF(3), .lut_noac = bat_lut_noac, .lut_noac_cnt = ARRAY_SIZE(bat_lut_noac), .lut_acin = bat_lut_acin, @@ -840,6 +848,7 @@ static void __init rx1950_init_machine(void) pwm_add_table(rx1950_pwm_lookup, ARRAY_SIZE(rx1950_pwm_lookup)); gpiod_add_lookup_table(&rx1950_audio_gpio_table); + gpiod_add_lookup_table(&rx1950_bat_gpio_table); /* Configure the I2S pins (GPE0...GPE4) in correct mode */ s3c_gpio_cfgall_range(S3C2410_GPE(0), 5, S3C_GPIO_SFN(2), S3C_GPIO_PULL_NONE); diff --git a/arch/arm/mach-sa1100/collie.c b/arch/arm/mach-sa1100/collie.c index bd3a52fd09ce..d4e89a02c8c8 100644 --- a/arch/arm/mach-sa1100/collie.c +++ b/arch/arm/mach-sa1100/collie.c @@ -98,6 +98,26 @@ static struct mcp_plat_data collie_mcp_data = { .codec_pdata = &collie_ucb1x00_data, }; +/* Battery management GPIOs */ +static struct gpiod_lookup_table collie_battery_gpiod_table = { + /* the MCP codec mcp0 has the ucb1x00 as attached device */ + .dev_id = "ucb1x00", + .table = { + /* This is found on the main GPIO on the SA1100 */ + GPIO_LOOKUP("gpio", COLLIE_GPIO_CO, + "main battery full", GPIO_ACTIVE_HIGH), + GPIO_LOOKUP("gpio", COLLIE_GPIO_MAIN_BAT_LOW, + "main battery low", GPIO_ACTIVE_HIGH), + /* + * This is GPIO 0 on the Scoop expander, which is registered + * from common/scoop.c with this gpio chip label. + */ + GPIO_LOOKUP("sharp-scoop", 0, + "main charge on", GPIO_ACTIVE_HIGH), + { }, + }, +}; + static int collie_ir_startup(struct device *dev) { int rc = gpio_request(COLLIE_GPIO_IR_ON, "IrDA"); @@ -395,6 +415,7 @@ static void __init collie_init(void) platform_scoop_config = &collie_pcmcia_config; gpiod_add_lookup_table(&collie_power_gpiod_table); + gpiod_add_lookup_table(&collie_battery_gpiod_table); ret = platform_add_devices(devices, ARRAY_SIZE(devices)); if (ret) { diff --git a/arch/arm/mm/Kconfig b/arch/arm/mm/Kconfig index 65e4482e3849..02692fbe2db5 100644 --- a/arch/arm/mm/Kconfig +++ b/arch/arm/mm/Kconfig @@ -743,6 +743,7 @@ config SWP_EMULATE config CPU_BIG_ENDIAN bool "Build big-endian kernel" depends on ARCH_SUPPORTS_BIG_ENDIAN + depends on !LD_IS_LLD help Say Y if you plan on running a kernel in big-endian mode. Note that your board must be properly built and your board diff --git a/arch/arm/mm/Makefile b/arch/arm/mm/Makefile index c4ce477c5261..3510503bc5e6 100644 --- a/arch/arm/mm/Makefile +++ b/arch/arm/mm/Makefile @@ -7,6 +7,7 @@ obj-y := extable.o fault.o init.o iomap.o obj-y += dma-mapping$(MMUEXT).o obj-$(CONFIG_MMU) += fault-armv.o flush.o idmap.o ioremap.o \ mmap.o pgd.o mmu.o pageattr.o +KASAN_SANITIZE_mmu.o := n ifneq ($(CONFIG_MMU),y) obj-y += nommu.o @@ -16,6 +17,7 @@ endif obj-$(CONFIG_ARM_PTDUMP_CORE) += dump.o obj-$(CONFIG_ARM_PTDUMP_DEBUGFS) += ptdump_debugfs.o obj-$(CONFIG_MODULES) += proc-syms.o +KASAN_SANITIZE_physaddr.o := n obj-$(CONFIG_DEBUG_VIRTUAL) += physaddr.o obj-$(CONFIG_ALIGNMENT_TRAP) += alignment.o @@ -110,3 +112,6 @@ obj-$(CONFIG_CACHE_L2X0_PMU) += cache-l2x0-pmu.o obj-$(CONFIG_CACHE_XSC3L2) += cache-xsc3l2.o obj-$(CONFIG_CACHE_TAUROS2) += cache-tauros2.o obj-$(CONFIG_CACHE_UNIPHIER) += cache-uniphier.o + +KASAN_SANITIZE_kasan_init.o := n +obj-$(CONFIG_KASAN) += kasan_init.o diff --git a/arch/arm/mm/init.c b/arch/arm/mm/init.c index db623d7c30de..828a2561b229 100644 --- a/arch/arm/mm/init.c +++ b/arch/arm/mm/init.c @@ -223,7 +223,6 @@ void __init arm_memblock_init(const struct machine_desc *mdesc) if (mdesc->reserve) mdesc->reserve(); - early_init_fdt_reserve_self(); early_init_fdt_scan_reserved_mem(); /* reserve memory for DMA contiguous allocations */ diff --git a/arch/arm/mm/kasan_init.c b/arch/arm/mm/kasan_init.c new file mode 100644 index 000000000000..9c348042a724 --- /dev/null +++ b/arch/arm/mm/kasan_init.c @@ -0,0 +1,291 @@ +// SPDX-License-Identifier: GPL-2.0-only +/* + * This file contains kasan initialization code for ARM. + * + * Copyright (c) 2018 Samsung Electronics Co., Ltd. + * Author: Andrey Ryabinin <ryabinin.a.a@gmail.com> + * Author: Linus Walleij <linus.walleij@linaro.org> + */ + +#define pr_fmt(fmt) "kasan: " fmt +#include <linux/kasan.h> +#include <linux/kernel.h> +#include <linux/memblock.h> +#include <linux/sched/task.h> +#include <linux/start_kernel.h> +#include <linux/pgtable.h> +#include <asm/cputype.h> +#include <asm/highmem.h> +#include <asm/mach/map.h> +#include <asm/memory.h> +#include <asm/page.h> +#include <asm/pgalloc.h> +#include <asm/procinfo.h> +#include <asm/proc-fns.h> + +#include "mm.h" + +static pgd_t tmp_pgd_table[PTRS_PER_PGD] __initdata __aligned(PGD_SIZE); + +pmd_t tmp_pmd_table[PTRS_PER_PMD] __page_aligned_bss; + +static __init void *kasan_alloc_block(size_t size) +{ + return memblock_alloc_try_nid(size, size, __pa(MAX_DMA_ADDRESS), + MEMBLOCK_ALLOC_KASAN, NUMA_NO_NODE); +} + +static void __init kasan_pte_populate(pmd_t *pmdp, unsigned long addr, + unsigned long end, bool early) +{ + unsigned long next; + pte_t *ptep = pte_offset_kernel(pmdp, addr); + + do { + pte_t entry; + void *p; + + next = addr + PAGE_SIZE; + + if (!early) { + if (!pte_none(READ_ONCE(*ptep))) + continue; + + p = kasan_alloc_block(PAGE_SIZE); + if (!p) { + panic("%s failed to allocate shadow page for address 0x%lx\n", + __func__, addr); + return; + } + memset(p, KASAN_SHADOW_INIT, PAGE_SIZE); + entry = pfn_pte(virt_to_pfn(p), + __pgprot(pgprot_val(PAGE_KERNEL))); + } else if (pte_none(READ_ONCE(*ptep))) { + /* + * The early shadow memory is mapping all KASan + * operations to one and the same page in memory, + * "kasan_early_shadow_page" so that the instrumentation + * will work on a scratch area until we can set up the + * proper KASan shadow memory. + */ + entry = pfn_pte(virt_to_pfn(kasan_early_shadow_page), + __pgprot(_L_PTE_DEFAULT | L_PTE_DIRTY | L_PTE_XN)); + } else { + /* + * Early shadow mappings are PMD_SIZE aligned, so if the + * first entry is already set, they must all be set. + */ + return; + } + + set_pte_at(&init_mm, addr, ptep, entry); + } while (ptep++, addr = next, addr != end); +} + +/* + * The pmd (page middle directory) is only used on LPAE + */ +static void __init kasan_pmd_populate(pud_t *pudp, unsigned long addr, + unsigned long end, bool early) +{ + unsigned long next; + pmd_t *pmdp = pmd_offset(pudp, addr); + + do { + if (pmd_none(*pmdp)) { + /* + * We attempt to allocate a shadow block for the PMDs + * used by the PTEs for this address if it isn't already + * allocated. + */ + void *p = early ? kasan_early_shadow_pte : + kasan_alloc_block(PAGE_SIZE); + + if (!p) { + panic("%s failed to allocate shadow block for address 0x%lx\n", + __func__, addr); + return; + } + pmd_populate_kernel(&init_mm, pmdp, p); + flush_pmd_entry(pmdp); + } + + next = pmd_addr_end(addr, end); + kasan_pte_populate(pmdp, addr, next, early); + } while (pmdp++, addr = next, addr != end); +} + +static void __init kasan_pgd_populate(unsigned long addr, unsigned long end, + bool early) +{ + unsigned long next; + pgd_t *pgdp; + p4d_t *p4dp; + pud_t *pudp; + + pgdp = pgd_offset_k(addr); + + do { + /* + * Allocate and populate the shadow block of p4d folded into + * pud folded into pmd if it doesn't already exist + */ + if (!early && pgd_none(*pgdp)) { + void *p = kasan_alloc_block(PAGE_SIZE); + + if (!p) { + panic("%s failed to allocate shadow block for address 0x%lx\n", + __func__, addr); + return; + } + pgd_populate(&init_mm, pgdp, p); + } + + next = pgd_addr_end(addr, end); + /* + * We just immediately jump over the p4d and pud page + * directories since we believe ARM32 will never gain four + * nor five level page tables. + */ + p4dp = p4d_offset(pgdp, addr); + pudp = pud_offset(p4dp, addr); + + kasan_pmd_populate(pudp, addr, next, early); + } while (pgdp++, addr = next, addr != end); +} + +extern struct proc_info_list *lookup_processor_type(unsigned int); + +void __init kasan_early_init(void) +{ + struct proc_info_list *list; + + /* + * locate processor in the list of supported processor + * types. The linker builds this table for us from the + * entries in arch/arm/mm/proc-*.S + */ + list = lookup_processor_type(read_cpuid_id()); + if (list) { +#ifdef MULTI_CPU + processor = *list->proc; +#endif + } + + BUILD_BUG_ON((KASAN_SHADOW_END - (1UL << 29)) != KASAN_SHADOW_OFFSET); + /* + * We walk the page table and set all of the shadow memory to point + * to the scratch page. + */ + kasan_pgd_populate(KASAN_SHADOW_START, KASAN_SHADOW_END, true); +} + +static void __init clear_pgds(unsigned long start, + unsigned long end) +{ + for (; start && start < end; start += PMD_SIZE) + pmd_clear(pmd_off_k(start)); +} + +static int __init create_mapping(void *start, void *end) +{ + void *shadow_start, *shadow_end; + + shadow_start = kasan_mem_to_shadow(start); + shadow_end = kasan_mem_to_shadow(end); + + pr_info("Mapping kernel virtual memory block: %px-%px at shadow: %px-%px\n", + start, end, shadow_start, shadow_end); + + kasan_pgd_populate((unsigned long)shadow_start & PAGE_MASK, + PAGE_ALIGN((unsigned long)shadow_end), false); + return 0; +} + +void __init kasan_init(void) +{ + phys_addr_t pa_start, pa_end; + u64 i; + + /* + * We are going to perform proper setup of shadow memory. + * + * At first we should unmap early shadow (clear_pgds() call bellow). + * However, instrumented code can't execute without shadow memory. + * + * To keep the early shadow memory MMU tables around while setting up + * the proper shadow memory, we copy swapper_pg_dir (the initial page + * table) to tmp_pgd_table and use that to keep the early shadow memory + * mapped until the full shadow setup is finished. Then we swap back + * to the proper swapper_pg_dir. + */ + + memcpy(tmp_pgd_table, swapper_pg_dir, sizeof(tmp_pgd_table)); +#ifdef CONFIG_ARM_LPAE + /* We need to be in the same PGD or this won't work */ + BUILD_BUG_ON(pgd_index(KASAN_SHADOW_START) != + pgd_index(KASAN_SHADOW_END)); + memcpy(tmp_pmd_table, + pgd_page_vaddr(*pgd_offset_k(KASAN_SHADOW_START)), + sizeof(tmp_pmd_table)); + set_pgd(&tmp_pgd_table[pgd_index(KASAN_SHADOW_START)], + __pgd(__pa(tmp_pmd_table) | PMD_TYPE_TABLE | L_PGD_SWAPPER)); +#endif + cpu_switch_mm(tmp_pgd_table, &init_mm); + local_flush_tlb_all(); + + clear_pgds(KASAN_SHADOW_START, KASAN_SHADOW_END); + + kasan_populate_early_shadow(kasan_mem_to_shadow((void *)VMALLOC_START), + kasan_mem_to_shadow((void *)-1UL) + 1); + + for_each_mem_range(i, &pa_start, &pa_end) { + void *start = __va(pa_start); + void *end = __va(pa_end); + + /* Do not attempt to shadow highmem */ + if (pa_start >= arm_lowmem_limit) { + pr_info("Skip highmem block at %pa-%pa\n", &pa_start, &pa_end); + continue; + } + if (pa_end > arm_lowmem_limit) { + pr_info("Truncating shadow for memory block at %pa-%pa to lowmem region at %pa\n", + &pa_start, &pa_end, &arm_lowmem_limit); + end = __va(arm_lowmem_limit); + } + if (start >= end) { + pr_info("Skipping invalid memory block %pa-%pa (virtual %p-%p)\n", + &pa_start, &pa_end, start, end); + continue; + } + + create_mapping(start, end); + } + + /* + * 1. The module global variables are in MODULES_VADDR ~ MODULES_END, + * so we need to map this area. + * 2. PKMAP_BASE ~ PKMAP_BASE+PMD_SIZE's shadow and MODULES_VADDR + * ~ MODULES_END's shadow is in the same PMD_SIZE, so we can't + * use kasan_populate_zero_shadow. + */ + create_mapping((void *)MODULES_VADDR, (void *)(PKMAP_BASE + PMD_SIZE)); + + /* + * KAsan may reuse the contents of kasan_early_shadow_pte directly, so + * we should make sure that it maps the zero page read-only. + */ + for (i = 0; i < PTRS_PER_PTE; i++) + set_pte_at(&init_mm, KASAN_SHADOW_START + i*PAGE_SIZE, + &kasan_early_shadow_pte[i], + pfn_pte(virt_to_pfn(kasan_early_shadow_page), + __pgprot(pgprot_val(PAGE_KERNEL) + | L_PTE_RDONLY))); + + cpu_switch_mm(swapper_pg_dir, &init_mm); + local_flush_tlb_all(); + + memset(kasan_early_shadow_page, 0, PAGE_SIZE); + pr_info("Kernel address sanitizer initialized\n"); + init_task.kasan_depth = 0; +} diff --git a/arch/arm/mm/mmap.c b/arch/arm/mm/mmap.c index b8d912ac9e61..a0f8a0ca0788 100644 --- a/arch/arm/mm/mmap.c +++ b/arch/arm/mm/mmap.c @@ -165,25 +165,3 @@ int valid_mmap_phys_addr_range(unsigned long pfn, size_t size) { return (pfn + (size >> PAGE_SHIFT)) <= (1 + (PHYS_MASK >> PAGE_SHIFT)); } - -#ifdef CONFIG_STRICT_DEVMEM - -#include <linux/ioport.h> - -/* - * devmem_is_allowed() checks to see if /dev/mem access to a certain - * address is valid. The argument is a physical page number. - * We mimic x86 here by disallowing access to system RAM as well as - * device-exclusive MMIO regions. This effectively disable read()/write() - * on /dev/mem. - */ -int devmem_is_allowed(unsigned long pfn) -{ - if (iomem_is_exclusive(pfn << PAGE_SHIFT)) - return 0; - if (!page_is_ram(pfn)) - return 1; - return 0; -} - -#endif diff --git a/arch/arm/mm/mmu.c b/arch/arm/mm/mmu.c index ab69250a86bc..c06ebfbc48c4 100644 --- a/arch/arm/mm/mmu.c +++ b/arch/arm/mm/mmu.c @@ -29,6 +29,7 @@ #include <asm/procinfo.h> #include <asm/memory.h> #include <asm/pgalloc.h> +#include <asm/kasan_def.h> #include <asm/mach/arch.h> #include <asm/mach/map.h> @@ -39,6 +40,8 @@ #include "mm.h" #include "tcm.h" +extern unsigned long __atags_pointer; + /* * empty_zero_page is a special page that is used for * zero-initialized data and COW. @@ -946,7 +949,7 @@ static void __init create_mapping(struct map_desc *md) return; } - if ((md->type == MT_DEVICE || md->type == MT_ROM) && + if (md->type == MT_DEVICE && md->virtual >= PAGE_OFFSET && md->virtual < FIXADDR_START && (md->virtual < VMALLOC_START || md->virtual >= VMALLOC_END)) { pr_warn("BUG: mapping for 0x%08llx at 0x%08lx out of vmalloc space\n", @@ -1253,8 +1256,25 @@ static inline void prepare_page_table(void) /* * Clear out all the mappings below the kernel image. */ +#ifdef CONFIG_KASAN + /* + * KASan's shadow memory inserts itself between the TASK_SIZE + * and MODULES_VADDR. Do not clear the KASan shadow memory mappings. + */ + for (addr = 0; addr < KASAN_SHADOW_START; addr += PMD_SIZE) + pmd_clear(pmd_off_k(addr)); + /* + * Skip over the KASan shadow area. KASAN_SHADOW_END is sometimes + * equal to MODULES_VADDR and then we exit the pmd clearing. If we + * are using a thumb-compiled kernel, there there will be 8MB more + * to clear as KASan always offset to 16 MB below MODULES_VADDR. + */ + for (addr = KASAN_SHADOW_END; addr < MODULES_VADDR; addr += PMD_SIZE) + pmd_clear(pmd_off_k(addr)); +#else for (addr = 0; addr < MODULES_VADDR; addr += PMD_SIZE) pmd_clear(pmd_off_k(addr)); +#endif #ifdef CONFIG_XIP_KERNEL /* The XIP kernel is mapped in the module area -- skip over it */ @@ -1333,6 +1353,15 @@ static void __init devicemaps_init(const struct machine_desc *mdesc) for (addr = VMALLOC_START; addr < (FIXADDR_TOP & PMD_MASK); addr += PMD_SIZE) pmd_clear(pmd_off_k(addr)); + if (__atags_pointer) { + /* create a read-only mapping of the device tree */ + map.pfn = __phys_to_pfn(__atags_pointer & SECTION_MASK); + map.virtual = FDT_FIXED_BASE; + map.length = FDT_FIXED_SIZE; + map.type = MT_ROM; + create_mapping(&map); + } + /* * Map the kernel if it is XIP. * It is always first in the modulearea. @@ -1489,8 +1518,7 @@ static void __init map_lowmem(void) } #ifdef CONFIG_ARM_PV_FIXUP -extern unsigned long __atags_pointer; -typedef void pgtables_remap(long long offset, unsigned long pgd, void *bdata); +typedef void pgtables_remap(long long offset, unsigned long pgd); pgtables_remap lpae_pgtables_remap_asm; /* @@ -1503,7 +1531,6 @@ static void __init early_paging_init(const struct machine_desc *mdesc) unsigned long pa_pgd; unsigned int cr, ttbcr; long long offset; - void *boot_data; if (!mdesc->pv_fixup) return; @@ -1520,7 +1547,6 @@ static void __init early_paging_init(const struct machine_desc *mdesc) */ lpae_pgtables_remap = (pgtables_remap *)(unsigned long)__pa(lpae_pgtables_remap_asm); pa_pgd = __pa(swapper_pg_dir); - boot_data = __va(__atags_pointer); barrier(); pr_info("Switching physical address space to 0x%08llx\n", @@ -1556,7 +1582,7 @@ static void __init early_paging_init(const struct machine_desc *mdesc) * needs to be assembly. It's fairly simple, as we're using the * temporary tables setup by the initial assembly code. */ - lpae_pgtables_remap(offset, pa_pgd, boot_data); + lpae_pgtables_remap(offset, pa_pgd); /* Re-enable the caches and cacheable TLB walks */ asm volatile("mcr p15, 0, %0, c2, c0, 2" : : "r" (ttbcr)); diff --git a/arch/arm/mm/pgd.c b/arch/arm/mm/pgd.c index c5e1b27046a8..f8e9bc58a84f 100644 --- a/arch/arm/mm/pgd.c +++ b/arch/arm/mm/pgd.c @@ -66,7 +66,21 @@ pgd_t *pgd_alloc(struct mm_struct *mm) new_pmd = pmd_alloc(mm, new_pud, 0); if (!new_pmd) goto no_pmd; -#endif +#ifdef CONFIG_KASAN + /* + * Copy PMD table for KASAN shadow mappings. + */ + init_pgd = pgd_offset_k(TASK_SIZE); + init_p4d = p4d_offset(init_pgd, TASK_SIZE); + init_pud = pud_offset(init_p4d, TASK_SIZE); + init_pmd = pmd_offset(init_pud, TASK_SIZE); + new_pmd = pmd_offset(new_pud, TASK_SIZE); + memcpy(new_pmd, init_pmd, + (pmd_index(MODULES_VADDR) - pmd_index(TASK_SIZE)) + * sizeof(pmd_t)); + clean_dcache_area(new_pmd, PTRS_PER_PMD * sizeof(pmd_t)); +#endif /* CONFIG_KASAN */ +#endif /* CONFIG_LPAE */ if (!vectors_high()) { /* diff --git a/arch/arm/mm/pv-fixup-asm.S b/arch/arm/mm/pv-fixup-asm.S index 8eade0416739..5c5e1952000a 100644 --- a/arch/arm/mm/pv-fixup-asm.S +++ b/arch/arm/mm/pv-fixup-asm.S @@ -39,8 +39,8 @@ ENTRY(lpae_pgtables_remap_asm) /* Update level 2 entries for the boot data */ add r7, r2, #0x1000 - add r7, r7, r3, lsr #SECTION_SHIFT - L2_ORDER - bic r7, r7, #(1 << L2_ORDER) - 1 + movw r3, #FDT_FIXED_BASE >> (SECTION_SHIFT - L2_ORDER) + add r7, r7, r3 ldrd r4, r5, [r7] adds r4, r4, r0 adc r5, r5, r1 diff --git a/arch/arm/tools/syscall.tbl b/arch/arm/tools/syscall.tbl index d056a548358e..20e1170e2e0a 100644 --- a/arch/arm/tools/syscall.tbl +++ b/arch/arm/tools/syscall.tbl @@ -454,3 +454,4 @@ 438 common pidfd_getfd sys_pidfd_getfd 439 common faccessat2 sys_faccessat2 440 common process_madvise sys_process_madvise +441 common epoll_pwait2 sys_epoll_pwait2 diff --git a/arch/arm/vdso/Makefile b/arch/arm/vdso/Makefile index 150ce6e6a5d3..b558bee0e1f6 100644 --- a/arch/arm/vdso/Makefile +++ b/arch/arm/vdso/Makefile @@ -42,6 +42,8 @@ GCOV_PROFILE := n # Prevents link failures: __sanitizer_cov_trace_pc() is not linked in. KCOV_INSTRUMENT := n +KASAN_SANITIZE := n + # Force dependency $(obj)/vdso.o : $(obj)/vdso.so diff --git a/arch/arm/vfp/entry.S b/arch/arm/vfp/entry.S index 0186cf9da890..27b0a1f27fbd 100644 --- a/arch/arm/vfp/entry.S +++ b/arch/arm/vfp/entry.S @@ -37,20 +37,3 @@ ENDPROC(vfp_null_entry) .align 2 .LCvfp: .word vfp_vector - -@ This code is called if the VFP does not exist. It needs to flag the -@ failure to the VFP initialisation code. - - __INIT -ENTRY(vfp_testing_entry) - dec_preempt_count_ti r10, r4 - ldr r0, VFP_arch_address - str r0, [r0] @ set to non-zero value - ret r9 @ we have handled the fault -ENDPROC(vfp_testing_entry) - - .align 2 -VFP_arch_address: - .word VFP_arch - - __FINIT diff --git a/arch/arm/vfp/vfphw.S b/arch/arm/vfp/vfphw.S index 4fcff9f59947..d5837bf05a9a 100644 --- a/arch/arm/vfp/vfphw.S +++ b/arch/arm/vfp/vfphw.S @@ -79,11 +79,6 @@ ENTRY(vfp_support_entry) DBGSTR3 "instr %08x pc %08x state %p", r0, r2, r10 .fpu vfpv2 - ldr r3, [sp, #S_PSR] @ Neither lazy restore nor FP exceptions - and r3, r3, #MODE_MASK @ are supported in kernel mode - teq r3, #USR_MODE - bne vfp_kmode_exception @ Returns through lr - VFPFMRX r1, FPEXC @ Is the VFP enabled? DBGSTR1 "fpexc %08x", r1 tst r1, #FPEXC_EN diff --git a/arch/arm/vfp/vfpmodule.c b/arch/arm/vfp/vfpmodule.c index 8c9e7f9f0277..2cb355c1b5b7 100644 --- a/arch/arm/vfp/vfpmodule.c +++ b/arch/arm/vfp/vfpmodule.c @@ -23,6 +23,7 @@ #include <asm/cputype.h> #include <asm/system_info.h> #include <asm/thread_notify.h> +#include <asm/traps.h> #include <asm/vfp.h> #include "vfpinstr.h" @@ -31,7 +32,6 @@ /* * Our undef handlers (in entry.S) */ -asmlinkage void vfp_testing_entry(void); asmlinkage void vfp_support_entry(void); asmlinkage void vfp_null_entry(void); @@ -42,7 +42,7 @@ asmlinkage void (*vfp_vector)(void) = vfp_null_entry; * Used in startup: set to non-zero if VFP checks fail * After startup, holds VFP architecture */ -unsigned int VFP_arch; +static unsigned int __initdata VFP_arch; /* * The pointer to the vfpstate structure of the thread which currently @@ -436,7 +436,7 @@ static void vfp_enable(void *unused) * present on all CPUs within a SMP complex. Needs to be called prior to * vfp_init(). */ -void vfp_disable(void) +void __init vfp_disable(void) { if (VFP_arch) { pr_debug("%s: should be called prior to vfp_init\n", __func__); @@ -642,7 +642,9 @@ static int vfp_starting_cpu(unsigned int unused) return 0; } -void vfp_kmode_exception(void) +#ifdef CONFIG_KERNEL_MODE_NEON + +static int vfp_kmode_exception(struct pt_regs *regs, unsigned int instr) { /* * If we reach this point, a floating point exception has been raised @@ -660,9 +662,51 @@ void vfp_kmode_exception(void) pr_crit("BUG: unsupported FP instruction in kernel mode\n"); else pr_crit("BUG: FP instruction issued in kernel mode with FP unit disabled\n"); + pr_crit("FPEXC == 0x%08x\n", fmrx(FPEXC)); + return 1; } -#ifdef CONFIG_KERNEL_MODE_NEON +static struct undef_hook vfp_kmode_exception_hook[] = {{ + .instr_mask = 0xfe000000, + .instr_val = 0xf2000000, + .cpsr_mask = MODE_MASK | PSR_T_BIT, + .cpsr_val = SVC_MODE, + .fn = vfp_kmode_exception, +}, { + .instr_mask = 0xff100000, + .instr_val = 0xf4000000, + .cpsr_mask = MODE_MASK | PSR_T_BIT, + .cpsr_val = SVC_MODE, + .fn = vfp_kmode_exception, +}, { + .instr_mask = 0xef000000, + .instr_val = 0xef000000, + .cpsr_mask = MODE_MASK | PSR_T_BIT, + .cpsr_val = SVC_MODE | PSR_T_BIT, + .fn = vfp_kmode_exception, +}, { + .instr_mask = 0xff100000, + .instr_val = 0xf9000000, + .cpsr_mask = MODE_MASK | PSR_T_BIT, + .cpsr_val = SVC_MODE | PSR_T_BIT, + .fn = vfp_kmode_exception, +}, { + .instr_mask = 0x0c000e00, + .instr_val = 0x0c000a00, + .cpsr_mask = MODE_MASK, + .cpsr_val = SVC_MODE, + .fn = vfp_kmode_exception, +}}; + +static int __init vfp_kmode_exception_hook_init(void) +{ + int i; + + for (i = 0; i < ARRAY_SIZE(vfp_kmode_exception_hook); i++) + register_undef_hook(&vfp_kmode_exception_hook[i]); + return 0; +} +subsys_initcall(vfp_kmode_exception_hook_init); /* * Kernel-side NEON support functions @@ -708,6 +752,21 @@ EXPORT_SYMBOL(kernel_neon_end); #endif /* CONFIG_KERNEL_MODE_NEON */ +static int __init vfp_detect(struct pt_regs *regs, unsigned int instr) +{ + VFP_arch = UINT_MAX; /* mark as not present */ + regs->ARM_pc += 4; + return 0; +} + +static struct undef_hook vfp_detect_hook __initdata = { + .instr_mask = 0x0c000e00, + .instr_val = 0x0c000a00, + .cpsr_mask = MODE_MASK, + .cpsr_val = SVC_MODE, + .fn = vfp_detect, +}; + /* * VFP support code initialisation. */ @@ -728,10 +787,11 @@ static int __init vfp_init(void) * The handler is already setup to just log calls, so * we just need to read the VFPSID register. */ - vfp_vector = vfp_testing_entry; + register_undef_hook(&vfp_detect_hook); barrier(); vfpsid = fmrx(FPSID); barrier(); + unregister_undef_hook(&vfp_detect_hook); vfp_vector = vfp_null_entry; pr_info("VFP support v0.3: "); diff --git a/arch/arm64/Kconfig b/arch/arm64/Kconfig index 9f0139ba8a1d..d0d94f77d000 100644 --- a/arch/arm64/Kconfig +++ b/arch/arm64/Kconfig @@ -13,7 +13,6 @@ config ARM64 select ARCH_BINFMT_ELF_STATE select ARCH_HAS_DEBUG_VIRTUAL select ARCH_HAS_DEBUG_VM_PGTABLE - select ARCH_HAS_DEVMEM_IS_ALLOWED select ARCH_HAS_DMA_PREP_COHERENT select ARCH_HAS_ACPI_TABLE_UPGRADE if ACPI select ARCH_HAS_FAST_MULTIPLIER @@ -113,6 +112,7 @@ config ARM64 select GENERIC_IRQ_PROBE select GENERIC_IRQ_SHOW select GENERIC_IRQ_SHOW_LEVEL + select GENERIC_LIB_DEVMEM_IS_ALLOWED select GENERIC_PCI_IOMAP select GENERIC_PTDUMP select GENERIC_SCHED_CLOCK @@ -137,6 +137,7 @@ config ARM64 select HAVE_ARCH_JUMP_LABEL_RELATIVE select HAVE_ARCH_KASAN if !(ARM64_16K_PAGES && ARM64_VA_BITS_48) select HAVE_ARCH_KASAN_SW_TAGS if HAVE_ARCH_KASAN + select HAVE_ARCH_KASAN_HW_TAGS if (HAVE_ARCH_KASAN && ARM64_MTE) select HAVE_ARCH_KGDB select HAVE_ARCH_MMAP_RND_BITS select HAVE_ARCH_MMAP_RND_COMPAT_BITS if COMPAT @@ -334,7 +335,7 @@ config BROKEN_GAS_INST config KASAN_SHADOW_OFFSET hex - depends on KASAN + depends on KASAN_GENERIC || KASAN_SW_TAGS default 0xdfff800000000000 if (ARM64_VA_BITS_48 || ARM64_VA_BITS_52) && !KASAN_SW_TAGS default 0xdfffc00000000000 if ARM64_VA_BITS_47 && !KASAN_SW_TAGS default 0xdffffe0000000000 if ARM64_VA_BITS_42 && !KASAN_SW_TAGS @@ -1571,6 +1572,9 @@ endmenu menu "ARMv8.5 architectural features" +config AS_HAS_ARMV8_5 + def_bool $(cc-option,-Wa$(comma)-march=armv8.5-a) + config ARM64_BTI bool "Branch Target Identification support" default y @@ -1645,6 +1649,9 @@ config ARM64_MTE bool "Memory Tagging Extension support" default y depends on ARM64_AS_HAS_MTE && ARM64_TAGGED_ADDR_ABI + depends on AS_HAS_ARMV8_5 + # Required for tag checking in the uaccess routines + depends on ARM64_PAN select ARCH_USES_HIGH_VMA_FLAGS help Memory Tagging (part of the ARMv8.5 Extensions) provides diff --git a/arch/arm64/Makefile b/arch/arm64/Makefile index 6a87d592bd00..6be9b3750250 100644 --- a/arch/arm64/Makefile +++ b/arch/arm64/Makefile @@ -96,6 +96,11 @@ ifeq ($(CONFIG_AS_HAS_ARMV8_4), y) asm-arch := armv8.4-a endif +ifeq ($(CONFIG_AS_HAS_ARMV8_5), y) +# make sure to pass the newest target architecture to -march. +asm-arch := armv8.5-a +endif + ifdef asm-arch KBUILD_CFLAGS += -Wa,-march=$(asm-arch) \ -DARM64_ASM_ARCH='"$(asm-arch)"' @@ -132,7 +137,7 @@ head-y := arch/arm64/kernel/head.o ifeq ($(CONFIG_KASAN_SW_TAGS), y) KASAN_SHADOW_SCALE_SHIFT := 4 -else +else ifeq ($(CONFIG_KASAN_GENERIC), y) KASAN_SHADOW_SCALE_SHIFT := 3 endif diff --git a/arch/arm64/include/asm/assembler.h b/arch/arm64/include/asm/assembler.h index ddbe6bf00e33..bf125c591116 100644 --- a/arch/arm64/include/asm/assembler.h +++ b/arch/arm64/include/asm/assembler.h @@ -473,7 +473,7 @@ USER(\label, ic ivau, \tmp2) // invalidate I line PoU #define NOKPROBE(x) #endif -#ifdef CONFIG_KASAN +#if defined(CONFIG_KASAN_GENERIC) || defined(CONFIG_KASAN_SW_TAGS) #define EXPORT_SYMBOL_NOKASAN(name) #else #define EXPORT_SYMBOL_NOKASAN(name) EXPORT_SYMBOL(name) diff --git a/arch/arm64/include/asm/cache.h b/arch/arm64/include/asm/cache.h index 63d43b5f82f6..77cbbe3625f2 100644 --- a/arch/arm64/include/asm/cache.h +++ b/arch/arm64/include/asm/cache.h @@ -6,6 +6,7 @@ #define __ASM_CACHE_H #include <asm/cputype.h> +#include <asm/mte-kasan.h> #define CTR_L1IP_SHIFT 14 #define CTR_L1IP_MASK 3 @@ -51,6 +52,8 @@ #ifdef CONFIG_KASAN_SW_TAGS #define ARCH_SLAB_MINALIGN (1ULL << KASAN_SHADOW_SCALE_SHIFT) +#elif defined(CONFIG_KASAN_HW_TAGS) +#define ARCH_SLAB_MINALIGN MTE_GRANULE_SIZE #endif #ifndef __ASSEMBLY__ diff --git a/arch/arm64/include/asm/cpucaps.h b/arch/arm64/include/asm/cpucaps.h index a7242ef2a2cd..b77d997b173b 100644 --- a/arch/arm64/include/asm/cpucaps.h +++ b/arch/arm64/include/asm/cpucaps.h @@ -19,7 +19,7 @@ #define ARM64_HAS_VIRT_HOST_EXTN 11 #define ARM64_WORKAROUND_CAVIUM_27456 12 #define ARM64_HAS_32BIT_EL0 13 -#define ARM64_HARDEN_EL2_VECTORS 14 +#define ARM64_SPECTRE_V3A 14 #define ARM64_HAS_CNP 15 #define ARM64_HAS_NO_FPSIMD 16 #define ARM64_WORKAROUND_REPEAT_TLBI 17 @@ -65,7 +65,8 @@ #define ARM64_MTE 57 #define ARM64_WORKAROUND_1508412 58 #define ARM64_HAS_LDAPR 59 +#define ARM64_KVM_PROTECTED_MODE 60 -#define ARM64_NCAPS 60 +#define ARM64_NCAPS 61 #endif /* __ASM_CPUCAPS_H */ diff --git a/arch/arm64/include/asm/cpufeature.h b/arch/arm64/include/asm/cpufeature.h index 1c406e8ae27e..9a555809b89c 100644 --- a/arch/arm64/include/asm/cpufeature.h +++ b/arch/arm64/include/asm/cpufeature.h @@ -705,6 +705,11 @@ static inline bool system_supports_generic_auth(void) cpus_have_const_cap(ARM64_HAS_GENERIC_AUTH); } +static inline bool system_has_full_ptr_auth(void) +{ + return system_supports_address_auth() && system_supports_generic_auth(); +} + static __always_inline bool system_uses_irq_prio_masking(void) { return IS_ENABLED(CONFIG_ARM64_PSEUDO_NMI) && diff --git a/arch/arm64/include/asm/el2_setup.h b/arch/arm64/include/asm/el2_setup.h new file mode 100644 index 000000000000..a7f5a1bbc8ac --- /dev/null +++ b/arch/arm64/include/asm/el2_setup.h @@ -0,0 +1,181 @@ +/* SPDX-License-Identifier: GPL-2.0-only */ +/* + * Copyright (C) 2012,2013 - ARM Ltd + * Author: Marc Zyngier <marc.zyngier@arm.com> + */ + +#ifndef __ARM_KVM_INIT_H__ +#define __ARM_KVM_INIT_H__ + +#ifndef __ASSEMBLY__ +#error Assembly-only header +#endif + +#include <asm/kvm_arm.h> +#include <asm/ptrace.h> +#include <asm/sysreg.h> +#include <linux/irqchip/arm-gic-v3.h> + +.macro __init_el2_sctlr + mov_q x0, INIT_SCTLR_EL2_MMU_OFF + msr sctlr_el2, x0 + isb +.endm + +/* + * Allow Non-secure EL1 and EL0 to access physical timer and counter. + * This is not necessary for VHE, since the host kernel runs in EL2, + * and EL0 accesses are configured in the later stage of boot process. + * Note that when HCR_EL2.E2H == 1, CNTHCTL_EL2 has the same bit layout + * as CNTKCTL_EL1, and CNTKCTL_EL1 accessing instructions are redefined + * to access CNTHCTL_EL2. This allows the kernel designed to run at EL1 + * to transparently mess with the EL0 bits via CNTKCTL_EL1 access in + * EL2. + */ +.macro __init_el2_timers mode +.ifeqs "\mode", "nvhe" + mrs x0, cnthctl_el2 + orr x0, x0, #3 // Enable EL1 physical timers + msr cnthctl_el2, x0 +.endif + msr cntvoff_el2, xzr // Clear virtual offset +.endm + +.macro __init_el2_debug mode + mrs x1, id_aa64dfr0_el1 + sbfx x0, x1, #ID_AA64DFR0_PMUVER_SHIFT, #4 + cmp x0, #1 + b.lt 1f // Skip if no PMU present + mrs x0, pmcr_el0 // Disable debug access traps + ubfx x0, x0, #11, #5 // to EL2 and allow access to +1: + csel x2, xzr, x0, lt // all PMU counters from EL1 + + /* Statistical profiling */ + ubfx x0, x1, #ID_AA64DFR0_PMSVER_SHIFT, #4 + cbz x0, 3f // Skip if SPE not present + +.ifeqs "\mode", "nvhe" + mrs_s x0, SYS_PMBIDR_EL1 // If SPE available at EL2, + and x0, x0, #(1 << SYS_PMBIDR_EL1_P_SHIFT) + cbnz x0, 2f // then permit sampling of physical + mov x0, #(1 << SYS_PMSCR_EL2_PCT_SHIFT | \ + 1 << SYS_PMSCR_EL2_PA_SHIFT) + msr_s SYS_PMSCR_EL2, x0 // addresses and physical counter +2: + mov x0, #(MDCR_EL2_E2PB_MASK << MDCR_EL2_E2PB_SHIFT) + orr x2, x2, x0 // If we don't have VHE, then + // use EL1&0 translation. +.else + orr x2, x2, #MDCR_EL2_TPMS // For VHE, use EL2 translation + // and disable access from EL1 +.endif + +3: + msr mdcr_el2, x2 // Configure debug traps +.endm + +/* LORegions */ +.macro __init_el2_lor + mrs x1, id_aa64mmfr1_el1 + ubfx x0, x1, #ID_AA64MMFR1_LOR_SHIFT, 4 + cbz x0, 1f + msr_s SYS_LORC_EL1, xzr +1: +.endm + +/* Stage-2 translation */ +.macro __init_el2_stage2 + msr vttbr_el2, xzr +.endm + +/* GICv3 system register access */ +.macro __init_el2_gicv3 + mrs x0, id_aa64pfr0_el1 + ubfx x0, x0, #ID_AA64PFR0_GIC_SHIFT, #4 + cbz x0, 1f + + mrs_s x0, SYS_ICC_SRE_EL2 + orr x0, x0, #ICC_SRE_EL2_SRE // Set ICC_SRE_EL2.SRE==1 + orr x0, x0, #ICC_SRE_EL2_ENABLE // Set ICC_SRE_EL2.Enable==1 + msr_s SYS_ICC_SRE_EL2, x0 + isb // Make sure SRE is now set + mrs_s x0, SYS_ICC_SRE_EL2 // Read SRE back, + tbz x0, #0, 1f // and check that it sticks + msr_s SYS_ICH_HCR_EL2, xzr // Reset ICC_HCR_EL2 to defaults +1: +.endm + +.macro __init_el2_hstr + msr hstr_el2, xzr // Disable CP15 traps to EL2 +.endm + +/* Virtual CPU ID registers */ +.macro __init_el2_nvhe_idregs + mrs x0, midr_el1 + mrs x1, mpidr_el1 + msr vpidr_el2, x0 + msr vmpidr_el2, x1 +.endm + +/* Coprocessor traps */ +.macro __init_el2_nvhe_cptr + mov x0, #0x33ff + msr cptr_el2, x0 // Disable copro. traps to EL2 +.endm + +/* SVE register access */ +.macro __init_el2_nvhe_sve + mrs x1, id_aa64pfr0_el1 + ubfx x1, x1, #ID_AA64PFR0_SVE_SHIFT, #4 + cbz x1, 1f + + bic x0, x0, #CPTR_EL2_TZ // Also disable SVE traps + msr cptr_el2, x0 // Disable copro. traps to EL2 + isb + mov x1, #ZCR_ELx_LEN_MASK // SVE: Enable full vector + msr_s SYS_ZCR_EL2, x1 // length for EL1. +1: +.endm + +.macro __init_el2_nvhe_prepare_eret + mov x0, #INIT_PSTATE_EL1 + msr spsr_el2, x0 +.endm + +/** + * Initialize EL2 registers to sane values. This should be called early on all + * cores that were booted in EL2. + * + * Regs: x0, x1 and x2 are clobbered. + */ +.macro init_el2_state mode +.ifnes "\mode", "vhe" +.ifnes "\mode", "nvhe" +.error "Invalid 'mode' argument" +.endif +.endif + + __init_el2_sctlr + __init_el2_timers \mode + __init_el2_debug \mode + __init_el2_lor + __init_el2_stage2 + __init_el2_gicv3 + __init_el2_hstr + + /* + * When VHE is not in use, early init of EL2 needs to be done here. + * When VHE _is_ in use, EL1 will not be used in the host and + * requires no configuration, and all non-hyp-specific EL2 setup + * will be done via the _EL1 system register aliases in __cpu_setup. + */ +.ifeqs "\mode", "nvhe" + __init_el2_nvhe_idregs + __init_el2_nvhe_cptr + __init_el2_nvhe_sve + __init_el2_nvhe_prepare_eret +.endif +.endm + +#endif /* __ARM_KVM_INIT_H__ */ diff --git a/arch/arm64/include/asm/esr.h b/arch/arm64/include/asm/esr.h index 85a3e49f92f4..29f97eb3dad4 100644 --- a/arch/arm64/include/asm/esr.h +++ b/arch/arm64/include/asm/esr.h @@ -106,6 +106,7 @@ #define ESR_ELx_FSC_TYPE (0x3C) #define ESR_ELx_FSC_LEVEL (0x03) #define ESR_ELx_FSC_EXTABT (0x10) +#define ESR_ELx_FSC_MTE (0x11) #define ESR_ELx_FSC_SERROR (0x11) #define ESR_ELx_FSC_ACCESS (0x08) #define ESR_ELx_FSC_FAULT (0x04) diff --git a/arch/arm64/include/asm/exception.h b/arch/arm64/include/asm/exception.h index 78537393b650..6546158d2f2d 100644 --- a/arch/arm64/include/asm/exception.h +++ b/arch/arm64/include/asm/exception.h @@ -31,6 +31,10 @@ static inline u32 disr_to_esr(u64 disr) return esr; } +asmlinkage void el1_sync_handler(struct pt_regs *regs); +asmlinkage void el0_sync_handler(struct pt_regs *regs); +asmlinkage void el0_sync_compat_handler(struct pt_regs *regs); + asmlinkage void noinstr enter_el1_irq_or_nmi(struct pt_regs *regs); asmlinkage void noinstr exit_el1_irq_or_nmi(struct pt_regs *regs); asmlinkage void enter_from_user_mode(void); diff --git a/arch/arm64/include/asm/io.h b/arch/arm64/include/asm/io.h index fd172c41df90..5ea8656a2030 100644 --- a/arch/arm64/include/asm/io.h +++ b/arch/arm64/include/asm/io.h @@ -201,6 +201,4 @@ extern void __iomem *ioremap_cache(phys_addr_t phys_addr, size_t size); extern int valid_phys_addr_range(phys_addr_t addr, size_t size); extern int valid_mmap_phys_addr_range(unsigned long pfn, size_t size); -extern int devmem_is_allowed(unsigned long pfn); - #endif /* __ASM_IO_H */ diff --git a/arch/arm64/include/asm/kasan.h b/arch/arm64/include/asm/kasan.h index b0dc4abc3589..0aaf9044cd6a 100644 --- a/arch/arm64/include/asm/kasan.h +++ b/arch/arm64/include/asm/kasan.h @@ -12,7 +12,9 @@ #define arch_kasan_reset_tag(addr) __tag_reset(addr) #define arch_kasan_get_tag(addr) __tag_get(addr) -#ifdef CONFIG_KASAN +#if defined(CONFIG_KASAN_GENERIC) || defined(CONFIG_KASAN_SW_TAGS) + +void kasan_init(void); /* * KASAN_SHADOW_START: beginning of the kernel virtual addresses. @@ -33,7 +35,6 @@ #define _KASAN_SHADOW_START(va) (KASAN_SHADOW_END - (1UL << ((va) - KASAN_SHADOW_SCALE_SHIFT))) #define KASAN_SHADOW_START _KASAN_SHADOW_START(vabits_actual) -void kasan_init(void); void kasan_copy_shadow(pgd_t *pgdir); asmlinkage void kasan_early_init(void); diff --git a/arch/arm64/include/asm/kvm_arm.h b/arch/arm64/include/asm/kvm_arm.h index 64ce29378467..4e90c2debf70 100644 --- a/arch/arm64/include/asm/kvm_arm.h +++ b/arch/arm64/include/asm/kvm_arm.h @@ -80,6 +80,7 @@ HCR_FMO | HCR_IMO | HCR_PTW ) #define HCR_VIRT_EXCP_MASK (HCR_VSE | HCR_VI | HCR_VF) #define HCR_HOST_NVHE_FLAGS (HCR_RW | HCR_API | HCR_APK | HCR_ATA) +#define HCR_HOST_NVHE_PROTECTED_FLAGS (HCR_HOST_NVHE_FLAGS | HCR_TSC) #define HCR_HOST_VHE_FLAGS (HCR_RW | HCR_TGE | HCR_E2H) /* TCR_EL2 Registers bits */ diff --git a/arch/arm64/include/asm/kvm_asm.h b/arch/arm64/include/asm/kvm_asm.h index 54387ccd1ab2..8a33d83ea843 100644 --- a/arch/arm64/include/asm/kvm_asm.h +++ b/arch/arm64/include/asm/kvm_asm.h @@ -34,8 +34,6 @@ */ #define KVM_VECTOR_PREAMBLE (2 * AARCH64_INSN_SIZE) -#define __SMCCC_WORKAROUND_1_SMC_SZ 36 - #define KVM_HOST_SMCCC_ID(id) \ ARM_SMCCC_CALL_VAL(ARM_SMCCC_FAST_CALL, \ ARM_SMCCC_SMC_64, \ @@ -150,6 +148,14 @@ extern void *__vhe_undefined_symbol; #endif +struct kvm_nvhe_init_params { + unsigned long mair_el2; + unsigned long tcr_el2; + unsigned long tpidr_el2; + unsigned long stack_hyp_va; + phys_addr_t pgd_pa; +}; + /* Translate a kernel address @ptr into its equivalent linear mapping */ #define kvm_ksym_ref(ptr) \ ({ \ @@ -165,17 +171,14 @@ struct kvm_vcpu; struct kvm_s2_mmu; DECLARE_KVM_NVHE_SYM(__kvm_hyp_init); -DECLARE_KVM_NVHE_SYM(__kvm_hyp_host_vector); DECLARE_KVM_HYP_SYM(__kvm_hyp_vector); #define __kvm_hyp_init CHOOSE_NVHE_SYM(__kvm_hyp_init) -#define __kvm_hyp_host_vector CHOOSE_NVHE_SYM(__kvm_hyp_host_vector) #define __kvm_hyp_vector CHOOSE_HYP_SYM(__kvm_hyp_vector) extern unsigned long kvm_arm_hyp_percpu_base[NR_CPUS]; DECLARE_KVM_NVHE_SYM(__per_cpu_start); DECLARE_KVM_NVHE_SYM(__per_cpu_end); -extern atomic_t arm64_el2_vector_last_slot; DECLARE_KVM_HYP_SYM(__bp_harden_hyp_vecs); #define __bp_harden_hyp_vecs CHOOSE_HYP_SYM(__bp_harden_hyp_vecs) @@ -189,8 +192,6 @@ extern void __kvm_timer_set_cntvoff(u64 cntvoff); extern int __kvm_vcpu_run(struct kvm_vcpu *vcpu); -extern void __kvm_enable_ssbs(void); - extern u64 __vgic_v3_get_ich_vtr_el2(void); extern u64 __vgic_v3_read_vmcr(void); extern void __vgic_v3_write_vmcr(u32 vmcr); @@ -198,7 +199,11 @@ extern void __vgic_v3_init_lrs(void); extern u32 __kvm_get_mdcr_el2(void); -extern char __smccc_workaround_1_smc[__SMCCC_WORKAROUND_1_SMC_SZ]; +#if defined(GCC_VERSION) && GCC_VERSION < 50000 +#define SYM_CONSTRAINT "i" +#else +#define SYM_CONSTRAINT "S" +#endif /* * Obtain the PC-relative address of a kernel symbol @@ -216,7 +221,7 @@ extern char __smccc_workaround_1_smc[__SMCCC_WORKAROUND_1_SMC_SZ]; typeof(s) *addr; \ asm("adrp %0, %1\n" \ "add %0, %0, :lo12:%1\n" \ - : "=r" (addr) : "S" (&s)); \ + : "=r" (addr) : SYM_CONSTRAINT (&s)); \ addr; \ }) diff --git a/arch/arm64/include/asm/kvm_coproc.h b/arch/arm64/include/asm/kvm_coproc.h deleted file mode 100644 index d6bb40122fdb..000000000000 --- a/arch/arm64/include/asm/kvm_coproc.h +++ /dev/null @@ -1,38 +0,0 @@ -/* SPDX-License-Identifier: GPL-2.0-only */ -/* - * Copyright (C) 2012,2013 - ARM Ltd - * Author: Marc Zyngier <marc.zyngier@arm.com> - * - * Derived from arch/arm/include/asm/kvm_coproc.h - * Copyright (C) 2012 Rusty Russell IBM Corporation - */ - -#ifndef __ARM64_KVM_COPROC_H__ -#define __ARM64_KVM_COPROC_H__ - -#include <linux/kvm_host.h> - -void kvm_reset_sys_regs(struct kvm_vcpu *vcpu); - -struct kvm_sys_reg_table { - const struct sys_reg_desc *table; - size_t num; -}; - -int kvm_handle_cp14_load_store(struct kvm_vcpu *vcpu); -int kvm_handle_cp14_32(struct kvm_vcpu *vcpu); -int kvm_handle_cp14_64(struct kvm_vcpu *vcpu); -int kvm_handle_cp15_32(struct kvm_vcpu *vcpu); -int kvm_handle_cp15_64(struct kvm_vcpu *vcpu); -int kvm_handle_sys_reg(struct kvm_vcpu *vcpu); - -#define kvm_coproc_table_init kvm_sys_reg_table_init -void kvm_sys_reg_table_init(void); - -struct kvm_one_reg; -int kvm_arm_copy_sys_reg_indices(struct kvm_vcpu *vcpu, u64 __user *uindices); -int kvm_arm_sys_reg_get_reg(struct kvm_vcpu *vcpu, const struct kvm_one_reg *); -int kvm_arm_sys_reg_set_reg(struct kvm_vcpu *vcpu, const struct kvm_one_reg *); -unsigned long kvm_arm_num_sys_reg_descs(struct kvm_vcpu *vcpu); - -#endif /* __ARM64_KVM_COPROC_H__ */ diff --git a/arch/arm64/include/asm/kvm_emulate.h b/arch/arm64/include/asm/kvm_emulate.h index 00bc6f1234ba..f612c090f2e4 100644 --- a/arch/arm64/include/asm/kvm_emulate.h +++ b/arch/arm64/include/asm/kvm_emulate.h @@ -21,20 +21,25 @@ #include <asm/cputype.h> #include <asm/virt.h> -unsigned long *vcpu_reg32(const struct kvm_vcpu *vcpu, u8 reg_num); -unsigned long vcpu_read_spsr32(const struct kvm_vcpu *vcpu); -void vcpu_write_spsr32(struct kvm_vcpu *vcpu, unsigned long v); +#define CURRENT_EL_SP_EL0_VECTOR 0x0 +#define CURRENT_EL_SP_ELx_VECTOR 0x200 +#define LOWER_EL_AArch64_VECTOR 0x400 +#define LOWER_EL_AArch32_VECTOR 0x600 + +enum exception_type { + except_type_sync = 0, + except_type_irq = 0x80, + except_type_fiq = 0x100, + except_type_serror = 0x180, +}; bool kvm_condition_valid32(const struct kvm_vcpu *vcpu); -void kvm_skip_instr32(struct kvm_vcpu *vcpu, bool is_wide_instr); +void kvm_skip_instr32(struct kvm_vcpu *vcpu); void kvm_inject_undefined(struct kvm_vcpu *vcpu); void kvm_inject_vabt(struct kvm_vcpu *vcpu); void kvm_inject_dabt(struct kvm_vcpu *vcpu, unsigned long addr); void kvm_inject_pabt(struct kvm_vcpu *vcpu, unsigned long addr); -void kvm_inject_undef32(struct kvm_vcpu *vcpu); -void kvm_inject_dabt32(struct kvm_vcpu *vcpu, unsigned long addr); -void kvm_inject_pabt32(struct kvm_vcpu *vcpu, unsigned long addr); static __always_inline bool vcpu_el1_is_32bit(struct kvm_vcpu *vcpu) { @@ -168,30 +173,6 @@ static __always_inline void vcpu_set_reg(struct kvm_vcpu *vcpu, u8 reg_num, vcpu_gp_regs(vcpu)->regs[reg_num] = val; } -static inline unsigned long vcpu_read_spsr(const struct kvm_vcpu *vcpu) -{ - if (vcpu_mode_is_32bit(vcpu)) - return vcpu_read_spsr32(vcpu); - - if (vcpu->arch.sysregs_loaded_on_cpu) - return read_sysreg_el1(SYS_SPSR); - else - return __vcpu_sys_reg(vcpu, SPSR_EL1); -} - -static inline void vcpu_write_spsr(struct kvm_vcpu *vcpu, unsigned long v) -{ - if (vcpu_mode_is_32bit(vcpu)) { - vcpu_write_spsr32(vcpu, v); - return; - } - - if (vcpu->arch.sysregs_loaded_on_cpu) - write_sysreg_el1(v, SYS_SPSR); - else - __vcpu_sys_reg(vcpu, SPSR_EL1) = v; -} - /* * The layout of SPSR for an AArch32 state is different when observed from an * AArch64 SPSR_ELx or an AArch32 SPSR_*. This function generates the AArch32 @@ -477,32 +458,9 @@ static inline unsigned long vcpu_data_host_to_guest(struct kvm_vcpu *vcpu, return data; /* Leave LE untouched */ } -static __always_inline void kvm_skip_instr(struct kvm_vcpu *vcpu, bool is_wide_instr) -{ - if (vcpu_mode_is_32bit(vcpu)) { - kvm_skip_instr32(vcpu, is_wide_instr); - } else { - *vcpu_pc(vcpu) += 4; - *vcpu_cpsr(vcpu) &= ~PSR_BTYPE_MASK; - } - - /* advance the singlestep state machine */ - *vcpu_cpsr(vcpu) &= ~DBG_SPSR_SS; -} - -/* - * Skip an instruction which has been emulated at hyp while most guest sysregs - * are live. - */ -static __always_inline void __kvm_skip_instr(struct kvm_vcpu *vcpu) +static __always_inline void kvm_incr_pc(struct kvm_vcpu *vcpu) { - *vcpu_pc(vcpu) = read_sysreg_el2(SYS_ELR); - vcpu_gp_regs(vcpu)->pstate = read_sysreg_el2(SYS_SPSR); - - kvm_skip_instr(vcpu, kvm_vcpu_trap_il_is32bit(vcpu)); - - write_sysreg_el2(vcpu_gp_regs(vcpu)->pstate, SYS_SPSR); - write_sysreg_el2(*vcpu_pc(vcpu), SYS_ELR); + vcpu->arch.flags |= KVM_ARM64_INCREMENT_PC; } #endif /* __ARM64_KVM_EMULATE_H__ */ diff --git a/arch/arm64/include/asm/kvm_host.h b/arch/arm64/include/asm/kvm_host.h index 0cd9f0f75c13..11beda85ee7e 100644 --- a/arch/arm64/include/asm/kvm_host.h +++ b/arch/arm64/include/asm/kvm_host.h @@ -50,6 +50,16 @@ #define KVM_DIRTY_LOG_MANUAL_CAPS (KVM_DIRTY_LOG_MANUAL_PROTECT_ENABLE | \ KVM_DIRTY_LOG_INITIALLY_SET) +/* + * Mode of operation configurable with kvm-arm.mode early param. + * See Documentation/admin-guide/kernel-parameters.txt for more information. + */ +enum kvm_mode { + KVM_MODE_DEFAULT, + KVM_MODE_PROTECTED, +}; +enum kvm_mode kvm_get_mode(void); + DECLARE_STATIC_KEY_FALSE(userspace_irqchip_in_use); extern unsigned int kvm_sve_max_vl; @@ -58,8 +68,6 @@ int kvm_arm_init_sve(void); int __attribute_const__ kvm_target_cpu(void); int kvm_reset_vcpu(struct kvm_vcpu *vcpu); void kvm_arm_vcpu_destroy(struct kvm_vcpu *vcpu); -int kvm_arch_vm_ioctl_check_extension(struct kvm *kvm, long ext); -void __extended_idmap_trampoline(phys_addr_t boot_pgd, phys_addr_t idmap_start); struct kvm_vmid { /* The VMID generation used for the virt. memory system */ @@ -89,6 +97,9 @@ struct kvm_s2_mmu { struct kvm *kvm; }; +struct kvm_arch_memory_slot { +}; + struct kvm_arch { struct kvm_s2_mmu mmu; @@ -120,6 +131,7 @@ struct kvm_arch { unsigned int pmuver; u8 pfr0_csv2; + u8 pfr0_csv3; }; struct kvm_vcpu_fault_info { @@ -203,48 +215,6 @@ enum vcpu_sysreg { NR_SYS_REGS /* Nothing after this line! */ }; -/* 32bit mapping */ -#define c0_MPIDR (MPIDR_EL1 * 2) /* MultiProcessor ID Register */ -#define c0_CSSELR (CSSELR_EL1 * 2)/* Cache Size Selection Register */ -#define c1_SCTLR (SCTLR_EL1 * 2) /* System Control Register */ -#define c1_ACTLR (ACTLR_EL1 * 2) /* Auxiliary Control Register */ -#define c1_CPACR (CPACR_EL1 * 2) /* Coprocessor Access Control */ -#define c2_TTBR0 (TTBR0_EL1 * 2) /* Translation Table Base Register 0 */ -#define c2_TTBR0_high (c2_TTBR0 + 1) /* TTBR0 top 32 bits */ -#define c2_TTBR1 (TTBR1_EL1 * 2) /* Translation Table Base Register 1 */ -#define c2_TTBR1_high (c2_TTBR1 + 1) /* TTBR1 top 32 bits */ -#define c2_TTBCR (TCR_EL1 * 2) /* Translation Table Base Control R. */ -#define c3_DACR (DACR32_EL2 * 2)/* Domain Access Control Register */ -#define c5_DFSR (ESR_EL1 * 2) /* Data Fault Status Register */ -#define c5_IFSR (IFSR32_EL2 * 2)/* Instruction Fault Status Register */ -#define c5_ADFSR (AFSR0_EL1 * 2) /* Auxiliary Data Fault Status R */ -#define c5_AIFSR (AFSR1_EL1 * 2) /* Auxiliary Instr Fault Status R */ -#define c6_DFAR (FAR_EL1 * 2) /* Data Fault Address Register */ -#define c6_IFAR (c6_DFAR + 1) /* Instruction Fault Address Register */ -#define c7_PAR (PAR_EL1 * 2) /* Physical Address Register */ -#define c7_PAR_high (c7_PAR + 1) /* PAR top 32 bits */ -#define c10_PRRR (MAIR_EL1 * 2) /* Primary Region Remap Register */ -#define c10_NMRR (c10_PRRR + 1) /* Normal Memory Remap Register */ -#define c12_VBAR (VBAR_EL1 * 2) /* Vector Base Address Register */ -#define c13_CID (CONTEXTIDR_EL1 * 2) /* Context ID Register */ -#define c13_TID_URW (TPIDR_EL0 * 2) /* Thread ID, User R/W */ -#define c13_TID_URO (TPIDRRO_EL0 * 2)/* Thread ID, User R/O */ -#define c13_TID_PRIV (TPIDR_EL1 * 2) /* Thread ID, Privileged */ -#define c10_AMAIR0 (AMAIR_EL1 * 2) /* Aux Memory Attr Indirection Reg */ -#define c10_AMAIR1 (c10_AMAIR0 + 1)/* Aux Memory Attr Indirection Reg */ -#define c14_CNTKCTL (CNTKCTL_EL1 * 2) /* Timer Control Register (PL1) */ - -#define cp14_DBGDSCRext (MDSCR_EL1 * 2) -#define cp14_DBGBCR0 (DBGBCR0_EL1 * 2) -#define cp14_DBGBVR0 (DBGBVR0_EL1 * 2) -#define cp14_DBGBXVR0 (cp14_DBGBVR0 + 1) -#define cp14_DBGWCR0 (DBGWCR0_EL1 * 2) -#define cp14_DBGWVR0 (DBGWVR0_EL1 * 2) -#define cp14_DBGDCCINT (MDCCINT_EL1 * 2) -#define cp14_DBGVCR (DBGVCR32_EL2 * 2) - -#define NR_COPRO_REGS (NR_SYS_REGS * 2) - struct kvm_cpu_context { struct user_pt_regs regs; /* sp = sp_el0 */ @@ -255,10 +225,7 @@ struct kvm_cpu_context { struct user_fpsimd_state fp_regs; - union { - u64 sys_regs[NR_SYS_REGS]; - u32 copro[NR_COPRO_REGS]; - }; + u64 sys_regs[NR_SYS_REGS]; struct kvm_vcpu *__hyp_running_vcpu; }; @@ -409,8 +376,33 @@ struct kvm_vcpu_arch { #define KVM_ARM64_GUEST_HAS_SVE (1 << 5) /* SVE exposed to guest */ #define KVM_ARM64_VCPU_SVE_FINALIZED (1 << 6) /* SVE config completed */ #define KVM_ARM64_GUEST_HAS_PTRAUTH (1 << 7) /* PTRAUTH exposed to guest */ +#define KVM_ARM64_PENDING_EXCEPTION (1 << 8) /* Exception pending */ +#define KVM_ARM64_EXCEPT_MASK (7 << 9) /* Target EL/MODE */ -#define vcpu_has_sve(vcpu) (system_supports_sve() && \ +/* + * When KVM_ARM64_PENDING_EXCEPTION is set, KVM_ARM64_EXCEPT_MASK can + * take the following values: + * + * For AArch32 EL1: + */ +#define KVM_ARM64_EXCEPT_AA32_UND (0 << 9) +#define KVM_ARM64_EXCEPT_AA32_IABT (1 << 9) +#define KVM_ARM64_EXCEPT_AA32_DABT (2 << 9) +/* For AArch64: */ +#define KVM_ARM64_EXCEPT_AA64_ELx_SYNC (0 << 9) +#define KVM_ARM64_EXCEPT_AA64_ELx_IRQ (1 << 9) +#define KVM_ARM64_EXCEPT_AA64_ELx_FIQ (2 << 9) +#define KVM_ARM64_EXCEPT_AA64_ELx_SERR (3 << 9) +#define KVM_ARM64_EXCEPT_AA64_EL1 (0 << 11) +#define KVM_ARM64_EXCEPT_AA64_EL2 (1 << 11) + +/* + * Overlaps with KVM_ARM64_EXCEPT_MASK on purpose so that it can't be + * set together with an exception... + */ +#define KVM_ARM64_INCREMENT_PC (1 << 9) /* Increment PC */ + +#define vcpu_has_sve(vcpu) (system_supports_sve() && \ ((vcpu)->arch.flags & KVM_ARM64_GUEST_HAS_SVE)) #ifdef CONFIG_ARM64_PTR_AUTH @@ -440,14 +432,96 @@ struct kvm_vcpu_arch { u64 vcpu_read_sys_reg(const struct kvm_vcpu *vcpu, int reg); void vcpu_write_sys_reg(struct kvm_vcpu *vcpu, u64 val, int reg); -/* - * CP14 and CP15 live in the same array, as they are backed by the - * same system registers. - */ -#define CPx_BIAS IS_ENABLED(CONFIG_CPU_BIG_ENDIAN) +static inline bool __vcpu_read_sys_reg_from_cpu(int reg, u64 *val) +{ + /* + * *** VHE ONLY *** + * + * System registers listed in the switch are not saved on every + * exit from the guest but are only saved on vcpu_put. + * + * Note that MPIDR_EL1 for the guest is set by KVM via VMPIDR_EL2 but + * should never be listed below, because the guest cannot modify its + * own MPIDR_EL1 and MPIDR_EL1 is accessed for VCPU A from VCPU B's + * thread when emulating cross-VCPU communication. + */ + if (!has_vhe()) + return false; + + switch (reg) { + case CSSELR_EL1: *val = read_sysreg_s(SYS_CSSELR_EL1); break; + case SCTLR_EL1: *val = read_sysreg_s(SYS_SCTLR_EL12); break; + case CPACR_EL1: *val = read_sysreg_s(SYS_CPACR_EL12); break; + case TTBR0_EL1: *val = read_sysreg_s(SYS_TTBR0_EL12); break; + case TTBR1_EL1: *val = read_sysreg_s(SYS_TTBR1_EL12); break; + case TCR_EL1: *val = read_sysreg_s(SYS_TCR_EL12); break; + case ESR_EL1: *val = read_sysreg_s(SYS_ESR_EL12); break; + case AFSR0_EL1: *val = read_sysreg_s(SYS_AFSR0_EL12); break; + case AFSR1_EL1: *val = read_sysreg_s(SYS_AFSR1_EL12); break; + case FAR_EL1: *val = read_sysreg_s(SYS_FAR_EL12); break; + case MAIR_EL1: *val = read_sysreg_s(SYS_MAIR_EL12); break; + case VBAR_EL1: *val = read_sysreg_s(SYS_VBAR_EL12); break; + case CONTEXTIDR_EL1: *val = read_sysreg_s(SYS_CONTEXTIDR_EL12);break; + case TPIDR_EL0: *val = read_sysreg_s(SYS_TPIDR_EL0); break; + case TPIDRRO_EL0: *val = read_sysreg_s(SYS_TPIDRRO_EL0); break; + case TPIDR_EL1: *val = read_sysreg_s(SYS_TPIDR_EL1); break; + case AMAIR_EL1: *val = read_sysreg_s(SYS_AMAIR_EL12); break; + case CNTKCTL_EL1: *val = read_sysreg_s(SYS_CNTKCTL_EL12); break; + case ELR_EL1: *val = read_sysreg_s(SYS_ELR_EL12); break; + case PAR_EL1: *val = read_sysreg_par(); break; + case DACR32_EL2: *val = read_sysreg_s(SYS_DACR32_EL2); break; + case IFSR32_EL2: *val = read_sysreg_s(SYS_IFSR32_EL2); break; + case DBGVCR32_EL2: *val = read_sysreg_s(SYS_DBGVCR32_EL2); break; + default: return false; + } + + return true; +} -#define vcpu_cp14(v,r) ((v)->arch.ctxt.copro[(r) ^ CPx_BIAS]) -#define vcpu_cp15(v,r) ((v)->arch.ctxt.copro[(r) ^ CPx_BIAS]) +static inline bool __vcpu_write_sys_reg_to_cpu(u64 val, int reg) +{ + /* + * *** VHE ONLY *** + * + * System registers listed in the switch are not restored on every + * entry to the guest but are only restored on vcpu_load. + * + * Note that MPIDR_EL1 for the guest is set by KVM via VMPIDR_EL2 but + * should never be listed below, because the MPIDR should only be set + * once, before running the VCPU, and never changed later. + */ + if (!has_vhe()) + return false; + + switch (reg) { + case CSSELR_EL1: write_sysreg_s(val, SYS_CSSELR_EL1); break; + case SCTLR_EL1: write_sysreg_s(val, SYS_SCTLR_EL12); break; + case CPACR_EL1: write_sysreg_s(val, SYS_CPACR_EL12); break; + case TTBR0_EL1: write_sysreg_s(val, SYS_TTBR0_EL12); break; + case TTBR1_EL1: write_sysreg_s(val, SYS_TTBR1_EL12); break; + case TCR_EL1: write_sysreg_s(val, SYS_TCR_EL12); break; + case ESR_EL1: write_sysreg_s(val, SYS_ESR_EL12); break; + case AFSR0_EL1: write_sysreg_s(val, SYS_AFSR0_EL12); break; + case AFSR1_EL1: write_sysreg_s(val, SYS_AFSR1_EL12); break; + case FAR_EL1: write_sysreg_s(val, SYS_FAR_EL12); break; + case MAIR_EL1: write_sysreg_s(val, SYS_MAIR_EL12); break; + case VBAR_EL1: write_sysreg_s(val, SYS_VBAR_EL12); break; + case CONTEXTIDR_EL1: write_sysreg_s(val, SYS_CONTEXTIDR_EL12);break; + case TPIDR_EL0: write_sysreg_s(val, SYS_TPIDR_EL0); break; + case TPIDRRO_EL0: write_sysreg_s(val, SYS_TPIDRRO_EL0); break; + case TPIDR_EL1: write_sysreg_s(val, SYS_TPIDR_EL1); break; + case AMAIR_EL1: write_sysreg_s(val, SYS_AMAIR_EL12); break; + case CNTKCTL_EL1: write_sysreg_s(val, SYS_CNTKCTL_EL12); break; + case ELR_EL1: write_sysreg_s(val, SYS_ELR_EL12); break; + case PAR_EL1: write_sysreg_s(val, SYS_PAR_EL1); break; + case DACR32_EL2: write_sysreg_s(val, SYS_DACR32_EL2); break; + case IFSR32_EL2: write_sysreg_s(val, SYS_IFSR32_EL2); break; + case DBGVCR32_EL2: write_sysreg_s(val, SYS_DBGVCR32_EL2); break; + default: return false; + } + + return true; +} struct kvm_vm_stat { ulong remote_tlb_flush; @@ -473,6 +547,12 @@ unsigned long kvm_arm_num_regs(struct kvm_vcpu *vcpu); int kvm_arm_copy_reg_indices(struct kvm_vcpu *vcpu, u64 __user *indices); int kvm_arm_get_reg(struct kvm_vcpu *vcpu, const struct kvm_one_reg *reg); int kvm_arm_set_reg(struct kvm_vcpu *vcpu, const struct kvm_one_reg *reg); + +unsigned long kvm_arm_num_sys_reg_descs(struct kvm_vcpu *vcpu); +int kvm_arm_copy_sys_reg_indices(struct kvm_vcpu *vcpu, u64 __user *uindices); +int kvm_arm_sys_reg_get_reg(struct kvm_vcpu *vcpu, const struct kvm_one_reg *); +int kvm_arm_sys_reg_set_reg(struct kvm_vcpu *vcpu, const struct kvm_one_reg *); + int __kvm_arm_vcpu_get_events(struct kvm_vcpu *vcpu, struct kvm_vcpu_events *events); @@ -535,6 +615,17 @@ void kvm_mmu_wp_memory_region(struct kvm *kvm, int slot); int handle_exit(struct kvm_vcpu *vcpu, int exception_index); void handle_exit_early(struct kvm_vcpu *vcpu, int exception_index); +int kvm_handle_cp14_load_store(struct kvm_vcpu *vcpu); +int kvm_handle_cp14_32(struct kvm_vcpu *vcpu); +int kvm_handle_cp14_64(struct kvm_vcpu *vcpu); +int kvm_handle_cp15_32(struct kvm_vcpu *vcpu); +int kvm_handle_cp15_64(struct kvm_vcpu *vcpu); +int kvm_handle_sys_reg(struct kvm_vcpu *vcpu); + +void kvm_reset_sys_regs(struct kvm_vcpu *vcpu); + +void kvm_sys_reg_table_init(void); + /* MMIO helpers */ void kvm_mmio_write_buf(void *buf, unsigned int len, unsigned long data); unsigned long kvm_mmio_read_buf(const void *buf, unsigned int len); @@ -654,4 +745,7 @@ bool kvm_arm_vcpu_is_finalized(struct kvm_vcpu *vcpu); #define kvm_arm_vcpu_sve_finalized(vcpu) \ ((vcpu)->arch.flags & KVM_ARM64_VCPU_SVE_FINALIZED) +#define kvm_vcpu_has_pmu(vcpu) \ + (test_bit(KVM_ARM_VCPU_PMU_V3, (vcpu)->arch.features)) + #endif /* __ARM64_KVM_HOST_H__ */ diff --git a/arch/arm64/include/asm/kvm_hyp.h b/arch/arm64/include/asm/kvm_hyp.h index 6b664de5ec1f..c0450828378b 100644 --- a/arch/arm64/include/asm/kvm_hyp.h +++ b/arch/arm64/include/asm/kvm_hyp.h @@ -14,6 +14,7 @@ DECLARE_PER_CPU(struct kvm_cpu_context, kvm_hyp_ctxt); DECLARE_PER_CPU(unsigned long, kvm_hyp_vector); +DECLARE_PER_CPU(struct kvm_nvhe_init_params, kvm_init_params); #define read_sysreg_elx(r,nvh,vh) \ ({ \ @@ -92,10 +93,11 @@ void deactivate_traps_vhe_put(void); u64 __guest_enter(struct kvm_vcpu *vcpu); +bool kvm_host_psci_handler(struct kvm_cpu_context *host_ctxt); + void __noreturn hyp_panic(void); #ifdef __KVM_NVHE_HYPERVISOR__ void __noreturn __hyp_do_panic(bool restore_host, u64 spsr, u64 elr, u64 par); #endif #endif /* __ARM64_KVM_HYP_H__ */ - diff --git a/arch/arm64/include/asm/kvm_mmu.h b/arch/arm64/include/asm/kvm_mmu.h index 331394306cce..e52d82aeadca 100644 --- a/arch/arm64/include/asm/kvm_mmu.h +++ b/arch/arm64/include/asm/kvm_mmu.h @@ -72,6 +72,52 @@ alternative_cb kvm_update_va_mask alternative_cb_end .endm +/* + * Convert a kernel image address to a PA + * reg: kernel address to be converted in place + * tmp: temporary register + * + * The actual code generation takes place in kvm_get_kimage_voffset, and + * the instructions below are only there to reserve the space and + * perform the register allocation (kvm_get_kimage_voffset uses the + * specific registers encoded in the instructions). + */ +.macro kimg_pa reg, tmp +alternative_cb kvm_get_kimage_voffset + movz \tmp, #0 + movk \tmp, #0, lsl #16 + movk \tmp, #0, lsl #32 + movk \tmp, #0, lsl #48 +alternative_cb_end + + /* reg = __pa(reg) */ + sub \reg, \reg, \tmp +.endm + +/* + * Convert a kernel image address to a hyp VA + * reg: kernel address to be converted in place + * tmp: temporary register + * + * The actual code generation takes place in kvm_get_kimage_voffset, and + * the instructions below are only there to reserve the space and + * perform the register allocation (kvm_update_kimg_phys_offset uses the + * specific registers encoded in the instructions). + */ +.macro kimg_hyp_va reg, tmp +alternative_cb kvm_update_kimg_phys_offset + movz \tmp, #0 + movk \tmp, #0, lsl #16 + movk \tmp, #0, lsl #32 + movk \tmp, #0, lsl #48 +alternative_cb_end + + sub \reg, \reg, \tmp + mov_q \tmp, PAGE_OFFSET + orr \reg, \reg, \tmp + kern_hyp_va \reg +.endm + #else #include <linux/pgtable.h> @@ -98,6 +144,24 @@ static __always_inline unsigned long __kern_hyp_va(unsigned long v) #define kern_hyp_va(v) ((typeof(v))(__kern_hyp_va((unsigned long)(v)))) +static __always_inline unsigned long __kimg_hyp_va(unsigned long v) +{ + unsigned long offset; + + asm volatile(ALTERNATIVE_CB("movz %0, #0\n" + "movk %0, #0, lsl #16\n" + "movk %0, #0, lsl #32\n" + "movk %0, #0, lsl #48\n", + kvm_update_kimg_phys_offset) + : "=r" (offset)); + + return __kern_hyp_va((v - offset) | PAGE_OFFSET); +} + +#define kimg_fn_hyp_va(v) ((typeof(*v))(__kimg_hyp_va((unsigned long)(v)))) + +#define kimg_fn_ptr(x) (typeof(x) **)(x) + /* * We currently support using a VM-specified IPA size. For backward * compatibility, the default IPA size is fixed to 40bits. @@ -208,52 +272,6 @@ static inline int kvm_write_guest_lock(struct kvm *kvm, gpa_t gpa, return ret; } -/* - * EL2 vectors can be mapped and rerouted in a number of ways, - * depending on the kernel configuration and CPU present: - * - * - If the CPU is affected by Spectre-v2, the hardening sequence is - * placed in one of the vector slots, which is executed before jumping - * to the real vectors. - * - * - If the CPU also has the ARM64_HARDEN_EL2_VECTORS cap, the slot - * containing the hardening sequence is mapped next to the idmap page, - * and executed before jumping to the real vectors. - * - * - If the CPU only has the ARM64_HARDEN_EL2_VECTORS cap, then an - * empty slot is selected, mapped next to the idmap page, and - * executed before jumping to the real vectors. - * - * Note that ARM64_HARDEN_EL2_VECTORS is somewhat incompatible with - * VHE, as we don't have hypervisor-specific mappings. If the system - * is VHE and yet selects this capability, it will be ignored. - */ -extern void *__kvm_bp_vect_base; -extern int __kvm_harden_el2_vector_slot; - -static inline void *kvm_get_hyp_vector(void) -{ - struct bp_hardening_data *data = arm64_get_bp_hardening_data(); - void *vect = kern_hyp_va(kvm_ksym_ref(__kvm_hyp_vector)); - int slot = -1; - - if (cpus_have_const_cap(ARM64_SPECTRE_V2) && data->fn) { - vect = kern_hyp_va(kvm_ksym_ref(__bp_harden_hyp_vecs)); - slot = data->hyp_vectors_slot; - } - - if (this_cpu_has_cap(ARM64_HARDEN_EL2_VECTORS) && !has_vhe()) { - vect = __kvm_bp_vect_base; - if (slot == -1) - slot = __kvm_harden_el2_vector_slot; - } - - if (slot != -1) - vect += slot * SZ_2K; - - return vect; -} - #define kvm_phys_to_vttbr(addr) phys_to_ttbr(addr) static __always_inline u64 kvm_get_vttbr(struct kvm_s2_mmu *mmu) diff --git a/arch/arm64/include/asm/memory.h b/arch/arm64/include/asm/memory.h index 556cb2d62b5b..18fce223b67b 100644 --- a/arch/arm64/include/asm/memory.h +++ b/arch/arm64/include/asm/memory.h @@ -72,7 +72,7 @@ * address space for the shadow region respectively. They can bloat the stack * significantly, so double the (minimum) stack size when they are in use. */ -#ifdef CONFIG_KASAN +#if defined(CONFIG_KASAN_GENERIC) || defined(CONFIG_KASAN_SW_TAGS) #define KASAN_SHADOW_OFFSET _AC(CONFIG_KASAN_SHADOW_OFFSET, UL) #define KASAN_SHADOW_END ((UL(1) << (64 - KASAN_SHADOW_SCALE_SHIFT)) \ + KASAN_SHADOW_OFFSET) @@ -214,7 +214,7 @@ static inline unsigned long kaslr_offset(void) (__force __typeof__(addr))__addr; \ }) -#ifdef CONFIG_KASAN_SW_TAGS +#if defined(CONFIG_KASAN_SW_TAGS) || defined(CONFIG_KASAN_HW_TAGS) #define __tag_shifted(tag) ((u64)(tag) << 56) #define __tag_reset(addr) __untagged_addr(addr) #define __tag_get(addr) (__u8)((u64)(addr) >> 56) @@ -222,7 +222,7 @@ static inline unsigned long kaslr_offset(void) #define __tag_shifted(tag) 0UL #define __tag_reset(addr) (addr) #define __tag_get(addr) 0 -#endif /* CONFIG_KASAN_SW_TAGS */ +#endif /* CONFIG_KASAN_SW_TAGS || CONFIG_KASAN_HW_TAGS */ static inline const void *__tag_set(const void *addr, u8 tag) { @@ -230,6 +230,15 @@ static inline const void *__tag_set(const void *addr, u8 tag) return (const void *)(__addr | __tag_shifted(tag)); } +#ifdef CONFIG_KASAN_HW_TAGS +#define arch_enable_tagging() mte_enable_kernel() +#define arch_init_tags(max_tag) mte_init_tags(max_tag) +#define arch_get_random_tag() mte_get_random_tag() +#define arch_get_mem_tag(addr) mte_get_mem_tag(addr) +#define arch_set_mem_tag_range(addr, size, tag) \ + mte_set_mem_tag_range((addr), (size), (tag)) +#endif /* CONFIG_KASAN_HW_TAGS */ + /* * Physical vs virtual RAM address space conversion. These are * private definitions which should NOT be used outside memory.h diff --git a/arch/arm64/include/asm/mmu.h b/arch/arm64/include/asm/mmu.h index b2e91c187e2a..75beffe2ee8a 100644 --- a/arch/arm64/include/asm/mmu.h +++ b/arch/arm64/include/asm/mmu.h @@ -12,9 +12,6 @@ #define USER_ASID_FLAG (UL(1) << USER_ASID_BIT) #define TTBR_ASID_MASK (UL(0xffff) << 48) -#define BP_HARDEN_EL2_SLOTS 4 -#define __BP_HARDEN_HYP_VECS_SZ (BP_HARDEN_EL2_SLOTS * SZ_2K) - #ifndef __ASSEMBLY__ #include <linux/refcount.h> @@ -41,32 +38,6 @@ static inline bool arm64_kernel_unmapped_at_el0(void) return cpus_have_const_cap(ARM64_UNMAP_KERNEL_AT_EL0); } -typedef void (*bp_hardening_cb_t)(void); - -struct bp_hardening_data { - int hyp_vectors_slot; - bp_hardening_cb_t fn; -}; - -DECLARE_PER_CPU_READ_MOSTLY(struct bp_hardening_data, bp_hardening_data); - -static inline struct bp_hardening_data *arm64_get_bp_hardening_data(void) -{ - return this_cpu_ptr(&bp_hardening_data); -} - -static inline void arm64_apply_bp_hardening(void) -{ - struct bp_hardening_data *d; - - if (!cpus_have_const_cap(ARM64_SPECTRE_V2)) - return; - - d = arm64_get_bp_hardening_data(); - if (d->fn) - d->fn(); -} - extern void arm64_memblock_init(void); extern void paging_init(void); extern void bootmem_init(void); diff --git a/arch/arm64/include/asm/mte-def.h b/arch/arm64/include/asm/mte-def.h new file mode 100644 index 000000000000..2d73a1612f09 --- /dev/null +++ b/arch/arm64/include/asm/mte-def.h @@ -0,0 +1,14 @@ +/* SPDX-License-Identifier: GPL-2.0 */ +/* + * Copyright (C) 2020 ARM Ltd. + */ +#ifndef __ASM_MTE_DEF_H +#define __ASM_MTE_DEF_H + +#define MTE_GRANULE_SIZE UL(16) +#define MTE_GRANULE_MASK (~(MTE_GRANULE_SIZE - 1)) +#define MTE_TAG_SHIFT 56 +#define MTE_TAG_SIZE 4 +#define MTE_TAG_MASK GENMASK((MTE_TAG_SHIFT + (MTE_TAG_SIZE - 1)), MTE_TAG_SHIFT) + +#endif /* __ASM_MTE_DEF_H */ diff --git a/arch/arm64/include/asm/mte-kasan.h b/arch/arm64/include/asm/mte-kasan.h new file mode 100644 index 000000000000..26349a4b5e2e --- /dev/null +++ b/arch/arm64/include/asm/mte-kasan.h @@ -0,0 +1,67 @@ +/* SPDX-License-Identifier: GPL-2.0 */ +/* + * Copyright (C) 2020 ARM Ltd. + */ +#ifndef __ASM_MTE_KASAN_H +#define __ASM_MTE_KASAN_H + +#include <asm/mte-def.h> + +#ifndef __ASSEMBLY__ + +#include <linux/types.h> + +/* + * The functions below are meant to be used only for the + * KASAN_HW_TAGS interface defined in asm/memory.h. + */ +#ifdef CONFIG_ARM64_MTE + +static inline u8 mte_get_ptr_tag(void *ptr) +{ + /* Note: The format of KASAN tags is 0xF<x> */ + u8 tag = 0xF0 | (u8)(((u64)(ptr)) >> MTE_TAG_SHIFT); + + return tag; +} + +u8 mte_get_mem_tag(void *addr); +u8 mte_get_random_tag(void); +void *mte_set_mem_tag_range(void *addr, size_t size, u8 tag); + +void mte_enable_kernel(void); +void mte_init_tags(u64 max_tag); + +#else /* CONFIG_ARM64_MTE */ + +static inline u8 mte_get_ptr_tag(void *ptr) +{ + return 0xFF; +} + +static inline u8 mte_get_mem_tag(void *addr) +{ + return 0xFF; +} +static inline u8 mte_get_random_tag(void) +{ + return 0xFF; +} +static inline void *mte_set_mem_tag_range(void *addr, size_t size, u8 tag) +{ + return addr; +} + +static inline void mte_enable_kernel(void) +{ +} + +static inline void mte_init_tags(u64 max_tag) +{ +} + +#endif /* CONFIG_ARM64_MTE */ + +#endif /* __ASSEMBLY__ */ + +#endif /* __ASM_MTE_KASAN_H */ diff --git a/arch/arm64/include/asm/mte.h b/arch/arm64/include/asm/mte.h index 1c99fcadb58c..d02aff9f493d 100644 --- a/arch/arm64/include/asm/mte.h +++ b/arch/arm64/include/asm/mte.h @@ -5,17 +5,21 @@ #ifndef __ASM_MTE_H #define __ASM_MTE_H -#define MTE_GRANULE_SIZE UL(16) -#define MTE_GRANULE_MASK (~(MTE_GRANULE_SIZE - 1)) -#define MTE_TAG_SHIFT 56 -#define MTE_TAG_SIZE 4 +#include <asm/compiler.h> +#include <asm/mte-def.h> + +#define __MTE_PREAMBLE ARM64_ASM_PREAMBLE ".arch_extension memtag\n" #ifndef __ASSEMBLY__ +#include <linux/bitfield.h> #include <linux/page-flags.h> +#include <linux/types.h> #include <asm/pgtable-types.h> +extern u64 gcr_kernel_excl; + void mte_clear_page_tags(void *addr); unsigned long mte_copy_tags_from_user(void *to, const void __user *from, unsigned long n); @@ -45,7 +49,9 @@ long get_mte_ctrl(struct task_struct *task); int mte_ptrace_copy_tags(struct task_struct *child, long request, unsigned long addr, unsigned long data); -#else +void mte_assign_mem_tag_range(void *addr, size_t size); + +#else /* CONFIG_ARM64_MTE */ /* unused if !CONFIG_ARM64_MTE, silence the compiler */ #define PG_mte_tagged 0 @@ -80,7 +86,11 @@ static inline int mte_ptrace_copy_tags(struct task_struct *child, return -EIO; } -#endif +static inline void mte_assign_mem_tag_range(void *addr, size_t size) +{ +} + +#endif /* CONFIG_ARM64_MTE */ #endif /* __ASSEMBLY__ */ #endif /* __ASM_MTE_H */ diff --git a/arch/arm64/include/asm/percpu.h b/arch/arm64/include/asm/percpu.h index 1599e17379d8..8f1661603b78 100644 --- a/arch/arm64/include/asm/percpu.h +++ b/arch/arm64/include/asm/percpu.h @@ -239,6 +239,12 @@ PERCPU_RET_OP(add, add, ldadd) #define this_cpu_cmpxchg_8(pcp, o, n) \ _pcp_protect_return(cmpxchg_relaxed, pcp, o, n) +#ifdef __KVM_NVHE_HYPERVISOR__ +extern unsigned long __hyp_per_cpu_offset(unsigned int cpu); +#define __per_cpu_offset +#define per_cpu_offset(cpu) __hyp_per_cpu_offset((cpu)) +#endif + #include <asm-generic/percpu.h> /* Redefine macros for nVHE hyp under DEBUG_PREEMPT to avoid its dependencies. */ diff --git a/arch/arm64/include/asm/processor.h b/arch/arm64/include/asm/processor.h index 724249f37af5..ca2cd75d3286 100644 --- a/arch/arm64/include/asm/processor.h +++ b/arch/arm64/include/asm/processor.h @@ -152,7 +152,7 @@ struct thread_struct { #endif #ifdef CONFIG_ARM64_MTE u64 sctlr_tcf0; - u64 gcr_user_incl; + u64 gcr_user_excl; #endif }; diff --git a/arch/arm64/include/asm/sections.h b/arch/arm64/include/asm/sections.h index 3994169985ef..8ff579361731 100644 --- a/arch/arm64/include/asm/sections.h +++ b/arch/arm64/include/asm/sections.h @@ -11,6 +11,7 @@ extern char __alt_instructions[], __alt_instructions_end[]; extern char __hibernate_exit_text_start[], __hibernate_exit_text_end[]; extern char __hyp_idmap_text_start[], __hyp_idmap_text_end[]; extern char __hyp_text_start[], __hyp_text_end[]; +extern char __hyp_data_ro_after_init_start[], __hyp_data_ro_after_init_end[]; extern char __idmap_text_start[], __idmap_text_end[]; extern char __initdata_begin[], __initdata_end[]; extern char __inittext_begin[], __inittext_end[]; diff --git a/arch/arm64/include/asm/smp.h b/arch/arm64/include/asm/smp.h index 2e7f529ec5a6..bcb01ca15325 100644 --- a/arch/arm64/include/asm/smp.h +++ b/arch/arm64/include/asm/smp.h @@ -46,9 +46,9 @@ DECLARE_PER_CPU_READ_MOSTLY(int, cpu_number); * Logical CPU mapping. */ extern u64 __cpu_logical_map[NR_CPUS]; -extern u64 cpu_logical_map(int cpu); +extern u64 cpu_logical_map(unsigned int cpu); -static inline void set_cpu_logical_map(int cpu, u64 hwid) +static inline void set_cpu_logical_map(unsigned int cpu, u64 hwid) { __cpu_logical_map[cpu] = hwid; } diff --git a/arch/arm64/include/asm/spectre.h b/arch/arm64/include/asm/spectre.h index fcdfbce302bd..f62ca39da6c5 100644 --- a/arch/arm64/include/asm/spectre.h +++ b/arch/arm64/include/asm/spectre.h @@ -9,7 +9,15 @@ #ifndef __ASM_SPECTRE_H #define __ASM_SPECTRE_H +#define BP_HARDEN_EL2_SLOTS 4 +#define __BP_HARDEN_HYP_VECS_SZ ((BP_HARDEN_EL2_SLOTS - 1) * SZ_2K) + +#ifndef __ASSEMBLY__ + +#include <linux/percpu.h> + #include <asm/cpufeature.h> +#include <asm/virt.h> /* Watch out, ordering is important here. */ enum mitigation_state { @@ -20,13 +28,70 @@ enum mitigation_state { struct task_struct; +/* + * Note: the order of this enum corresponds to __bp_harden_hyp_vecs and + * we rely on having the direct vectors first. + */ +enum arm64_hyp_spectre_vector { + /* + * Take exceptions directly to __kvm_hyp_vector. This must be + * 0 so that it used by default when mitigations are not needed. + */ + HYP_VECTOR_DIRECT, + + /* + * Bounce via a slot in the hypervisor text mapping of + * __bp_harden_hyp_vecs, which contains an SMC call. + */ + HYP_VECTOR_SPECTRE_DIRECT, + + /* + * Bounce via a slot in a special mapping of __bp_harden_hyp_vecs + * next to the idmap page. + */ + HYP_VECTOR_INDIRECT, + + /* + * Bounce via a slot in a special mapping of __bp_harden_hyp_vecs + * next to the idmap page, which contains an SMC call. + */ + HYP_VECTOR_SPECTRE_INDIRECT, +}; + +typedef void (*bp_hardening_cb_t)(void); + +struct bp_hardening_data { + enum arm64_hyp_spectre_vector slot; + bp_hardening_cb_t fn; +}; + +DECLARE_PER_CPU_READ_MOSTLY(struct bp_hardening_data, bp_hardening_data); + +static inline void arm64_apply_bp_hardening(void) +{ + struct bp_hardening_data *d; + + if (!cpus_have_const_cap(ARM64_SPECTRE_V2)) + return; + + d = this_cpu_ptr(&bp_hardening_data); + if (d->fn) + d->fn(); +} + enum mitigation_state arm64_get_spectre_v2_state(void); bool has_spectre_v2(const struct arm64_cpu_capabilities *cap, int scope); void spectre_v2_enable_mitigation(const struct arm64_cpu_capabilities *__unused); +bool has_spectre_v3a(const struct arm64_cpu_capabilities *cap, int scope); +void spectre_v3a_enable_mitigation(const struct arm64_cpu_capabilities *__unused); + enum mitigation_state arm64_get_spectre_v4_state(void); bool has_spectre_v4(const struct arm64_cpu_capabilities *cap, int scope); void spectre_v4_enable_mitigation(const struct arm64_cpu_capabilities *__unused); void spectre_v4_enable_task_mitigation(struct task_struct *tsk); +enum mitigation_state arm64_get_meltdown_state(void); + +#endif /* __ASSEMBLY__ */ #endif /* __ASM_SPECTRE_H */ diff --git a/arch/arm64/include/asm/string.h b/arch/arm64/include/asm/string.h index b31e8e87a0db..3a3264ff47b9 100644 --- a/arch/arm64/include/asm/string.h +++ b/arch/arm64/include/asm/string.h @@ -5,7 +5,7 @@ #ifndef __ASM_STRING_H #define __ASM_STRING_H -#ifndef CONFIG_KASAN +#if !(defined(CONFIG_KASAN_GENERIC) || defined(CONFIG_KASAN_SW_TAGS)) #define __HAVE_ARCH_STRRCHR extern char *strrchr(const char *, int c); @@ -48,7 +48,8 @@ extern void *__memset(void *, int, __kernel_size_t); void memcpy_flushcache(void *dst, const void *src, size_t cnt); #endif -#if defined(CONFIG_KASAN) && !defined(__SANITIZE_ADDRESS__) +#if (defined(CONFIG_KASAN_GENERIC) || defined(CONFIG_KASAN_SW_TAGS)) && \ + !defined(__SANITIZE_ADDRESS__) /* * For files that are not instrumented (e.g. mm/slub.c) we diff --git a/arch/arm64/include/asm/sysreg.h b/arch/arm64/include/asm/sysreg.h index cf7922f23808..8b5e7e5c3cc8 100644 --- a/arch/arm64/include/asm/sysreg.h +++ b/arch/arm64/include/asm/sysreg.h @@ -469,6 +469,7 @@ #define SYS_PMCCFILTR_EL0 sys_reg(3, 3, 14, 15, 7) +#define SYS_SCTLR_EL2 sys_reg(3, 4, 1, 0, 0) #define SYS_ZCR_EL2 sys_reg(3, 4, 1, 2, 0) #define SYS_DACR32_EL2 sys_reg(3, 4, 3, 0, 0) #define SYS_SPSR_EL2 sys_reg(3, 4, 4, 0, 0) diff --git a/arch/arm64/include/asm/uaccess.h b/arch/arm64/include/asm/uaccess.h index abb31aa1f8ca..6f986e09a781 100644 --- a/arch/arm64/include/asm/uaccess.h +++ b/arch/arm64/include/asm/uaccess.h @@ -159,8 +159,28 @@ static inline void __uaccess_enable_hw_pan(void) CONFIG_ARM64_PAN)); } +/* + * The Tag Check Flag (TCF) mode for MTE is per EL, hence TCF0 + * affects EL0 and TCF affects EL1 irrespective of which TTBR is + * used. + * The kernel accesses TTBR0 usually with LDTR/STTR instructions + * when UAO is available, so these would act as EL0 accesses using + * TCF0. + * However futex.h code uses exclusives which would be executed as + * EL1, this can potentially cause a tag check fault even if the + * user disables TCF0. + * + * To address the problem we set the PSTATE.TCO bit in uaccess_enable() + * and reset it in uaccess_disable(). + * + * The Tag check override (TCO) bit disables temporarily the tag checking + * preventing the issue. + */ static inline void uaccess_disable_privileged(void) { + asm volatile(ALTERNATIVE("nop", SET_PSTATE_TCO(0), + ARM64_MTE, CONFIG_KASAN_HW_TAGS)); + if (uaccess_ttbr0_disable()) return; @@ -169,6 +189,9 @@ static inline void uaccess_disable_privileged(void) static inline void uaccess_enable_privileged(void) { + asm volatile(ALTERNATIVE("nop", SET_PSTATE_TCO(1), + ARM64_MTE, CONFIG_KASAN_HW_TAGS)); + if (uaccess_ttbr0_enable()) return; diff --git a/arch/arm64/include/asm/unistd.h b/arch/arm64/include/asm/unistd.h index b3b2019f8d16..86a9d7b3eabe 100644 --- a/arch/arm64/include/asm/unistd.h +++ b/arch/arm64/include/asm/unistd.h @@ -38,7 +38,7 @@ #define __ARM_NR_compat_set_tls (__ARM_NR_COMPAT_BASE + 5) #define __ARM_NR_COMPAT_END (__ARM_NR_COMPAT_BASE + 0x800) -#define __NR_compat_syscalls 441 +#define __NR_compat_syscalls 442 #endif #define __ARCH_WANT_SYS_CLONE diff --git a/arch/arm64/include/asm/unistd32.h b/arch/arm64/include/asm/unistd32.h index 107f08e03b9f..cccfbbefbf95 100644 --- a/arch/arm64/include/asm/unistd32.h +++ b/arch/arm64/include/asm/unistd32.h @@ -889,6 +889,8 @@ __SYSCALL(__NR_pidfd_getfd, sys_pidfd_getfd) __SYSCALL(__NR_faccessat2, sys_faccessat2) #define __NR_process_madvise 440 __SYSCALL(__NR_process_madvise, sys_process_madvise) +#define __NR_epoll_pwait2 441 +__SYSCALL(__NR_epoll_pwait2, compat_sys_epoll_pwait2) /* * Please add new compat syscalls above this comment and update diff --git a/arch/arm64/include/asm/virt.h b/arch/arm64/include/asm/virt.h index 6069be50baf9..ee6a48df89d9 100644 --- a/arch/arm64/include/asm/virt.h +++ b/arch/arm64/include/asm/virt.h @@ -65,9 +65,19 @@ extern u32 __boot_cpu_mode[2]; void __hyp_set_vectors(phys_addr_t phys_vector_base); void __hyp_reset_vectors(void); +DECLARE_STATIC_KEY_FALSE(kvm_protected_mode_initialized); + /* Reports the availability of HYP mode */ static inline bool is_hyp_mode_available(void) { + /* + * If KVM protected mode is initialized, all CPUs must have been booted + * in EL2. Avoid checking __boot_cpu_mode as CPUs now come up in EL1. + */ + if (IS_ENABLED(CONFIG_KVM) && + static_branch_likely(&kvm_protected_mode_initialized)) + return true; + return (__boot_cpu_mode[0] == BOOT_CPU_MODE_EL2 && __boot_cpu_mode[1] == BOOT_CPU_MODE_EL2); } @@ -75,6 +85,14 @@ static inline bool is_hyp_mode_available(void) /* Check if the bootloader has booted CPUs in different modes */ static inline bool is_hyp_mode_mismatched(void) { + /* + * If KVM protected mode is initialized, all CPUs must have been booted + * in EL2. Avoid checking __boot_cpu_mode as CPUs now come up in EL1. + */ + if (IS_ENABLED(CONFIG_KVM) && + static_branch_likely(&kvm_protected_mode_initialized)) + return false; + return __boot_cpu_mode[0] != __boot_cpu_mode[1]; } @@ -97,6 +115,14 @@ static __always_inline bool has_vhe(void) return cpus_have_final_cap(ARM64_HAS_VIRT_HOST_EXTN); } +static __always_inline bool is_protected_kvm_enabled(void) +{ + if (is_vhe_hyp_code()) + return false; + else + return cpus_have_final_cap(ARM64_KVM_PROTECTED_MODE); +} + #endif /* __ASSEMBLY__ */ #endif /* ! __ASM__VIRT_H */ diff --git a/arch/arm64/include/uapi/asm/kvm.h b/arch/arm64/include/uapi/asm/kvm.h index 1c17c3a24411..24223adae150 100644 --- a/arch/arm64/include/uapi/asm/kvm.h +++ b/arch/arm64/include/uapi/asm/kvm.h @@ -156,9 +156,6 @@ struct kvm_sync_regs { __u64 device_irq_level; }; -struct kvm_arch_memory_slot { -}; - /* * PMU filter structure. Describe a range of events with a particular * action. To be used with KVM_ARM_VCPU_PMU_V3_FILTER. diff --git a/arch/arm64/kernel/asm-offsets.c b/arch/arm64/kernel/asm-offsets.c index 679b19b8a7ff..f42fd9e33981 100644 --- a/arch/arm64/kernel/asm-offsets.c +++ b/arch/arm64/kernel/asm-offsets.c @@ -47,6 +47,9 @@ int main(void) DEFINE(THREAD_KEYS_USER, offsetof(struct task_struct, thread.keys_user)); DEFINE(THREAD_KEYS_KERNEL, offsetof(struct task_struct, thread.keys_kernel)); #endif +#ifdef CONFIG_ARM64_MTE + DEFINE(THREAD_GCR_EL1_USER, offsetof(struct task_struct, thread.gcr_user_excl)); +#endif BLANK(); DEFINE(S_X0, offsetof(struct pt_regs, regs[0])); DEFINE(S_X2, offsetof(struct pt_regs, regs[2])); @@ -109,6 +112,11 @@ int main(void) DEFINE(CPU_APGAKEYLO_EL1, offsetof(struct kvm_cpu_context, sys_regs[APGAKEYLO_EL1])); DEFINE(HOST_CONTEXT_VCPU, offsetof(struct kvm_cpu_context, __hyp_running_vcpu)); DEFINE(HOST_DATA_CONTEXT, offsetof(struct kvm_host_data, host_ctxt)); + DEFINE(NVHE_INIT_MAIR_EL2, offsetof(struct kvm_nvhe_init_params, mair_el2)); + DEFINE(NVHE_INIT_TCR_EL2, offsetof(struct kvm_nvhe_init_params, tcr_el2)); + DEFINE(NVHE_INIT_TPIDR_EL2, offsetof(struct kvm_nvhe_init_params, tpidr_el2)); + DEFINE(NVHE_INIT_STACK_HYP_VA, offsetof(struct kvm_nvhe_init_params, stack_hyp_va)); + DEFINE(NVHE_INIT_PGD_PA, offsetof(struct kvm_nvhe_init_params, pgd_pa)); #endif #ifdef CONFIG_CPU_PM DEFINE(CPU_CTX_SP, offsetof(struct cpu_suspend_ctx, sp)); diff --git a/arch/arm64/kernel/cpu_errata.c b/arch/arm64/kernel/cpu_errata.c index cafaf0da05b7..a63428301f42 100644 --- a/arch/arm64/kernel/cpu_errata.c +++ b/arch/arm64/kernel/cpu_errata.c @@ -196,16 +196,6 @@ has_neoverse_n1_erratum_1542419(const struct arm64_cpu_capabilities *entry, return is_midr_in_range(midr, &range) && has_dic; } -#ifdef CONFIG_RANDOMIZE_BASE - -static const struct midr_range ca57_a72[] = { - MIDR_ALL_VERSIONS(MIDR_CORTEX_A57), - MIDR_ALL_VERSIONS(MIDR_CORTEX_A72), - {}, -}; - -#endif - #ifdef CONFIG_ARM64_WORKAROUND_REPEAT_TLBI static const struct arm64_cpu_capabilities arm64_repeat_tlbi_list[] = { #ifdef CONFIG_QCOM_FALKOR_ERRATUM_1009 @@ -461,9 +451,12 @@ const struct arm64_cpu_capabilities arm64_errata[] = { }, #ifdef CONFIG_RANDOMIZE_BASE { - .desc = "EL2 vector hardening", - .capability = ARM64_HARDEN_EL2_VECTORS, - ERRATA_MIDR_RANGE_LIST(ca57_a72), + /* Must come after the Spectre-v2 entry */ + .desc = "Spectre-v3a", + .capability = ARM64_SPECTRE_V3A, + .type = ARM64_CPUCAP_LOCAL_CPU_ERRATUM, + .matches = has_spectre_v3a, + .cpu_enable = spectre_v3a_enable_mitigation, }, #endif { diff --git a/arch/arm64/kernel/cpufeature.c b/arch/arm64/kernel/cpufeature.c index 39138f6d3ba2..7ffb5f1d8b68 100644 --- a/arch/arm64/kernel/cpufeature.c +++ b/arch/arm64/kernel/cpufeature.c @@ -70,10 +70,12 @@ #include <linux/types.h> #include <linux/mm.h> #include <linux/cpu.h> +#include <linux/kasan.h> #include <asm/cpu.h> #include <asm/cpufeature.h> #include <asm/cpu_ops.h> #include <asm/fpsimd.h> +#include <asm/kvm_host.h> #include <asm/mmu_context.h> #include <asm/mte.h> #include <asm/processor.h> @@ -1709,9 +1711,26 @@ static void cpu_enable_mte(struct arm64_cpu_capabilities const *cap) cleared_zero_page = true; mte_clear_page_tags(lm_alias(empty_zero_page)); } + + kasan_init_hw_tags_cpu(); } #endif /* CONFIG_ARM64_MTE */ +#ifdef CONFIG_KVM +static bool is_kvm_protected_mode(const struct arm64_cpu_capabilities *entry, int __unused) +{ + if (kvm_get_mode() != KVM_MODE_PROTECTED) + return false; + + if (is_kernel_in_hyp_mode()) { + pr_warn("Protected KVM not available with VHE\n"); + return false; + } + + return true; +} +#endif /* CONFIG_KVM */ + /* Internal helper functions to match cpu capability type */ static bool cpucap_late_cpu_optional(const struct arm64_cpu_capabilities *cap) @@ -1803,6 +1822,12 @@ static const struct arm64_cpu_capabilities arm64_features[] = { .field_pos = ID_AA64PFR0_EL1_SHIFT, .min_field_value = ID_AA64PFR0_EL1_32BIT_64BIT, }, + { + .desc = "Protected KVM", + .capability = ARM64_KVM_PROTECTED_MODE, + .type = ARM64_CPUCAP_SYSTEM_FEATURE, + .matches = is_kvm_protected_mode, + }, #endif { .desc = "Kernel page table isolation (KPTI)", @@ -2831,14 +2856,28 @@ static int __init enable_mrs_emulation(void) core_initcall(enable_mrs_emulation); +enum mitigation_state arm64_get_meltdown_state(void) +{ + if (__meltdown_safe) + return SPECTRE_UNAFFECTED; + + if (arm64_kernel_unmapped_at_el0()) + return SPECTRE_MITIGATED; + + return SPECTRE_VULNERABLE; +} + ssize_t cpu_show_meltdown(struct device *dev, struct device_attribute *attr, char *buf) { - if (__meltdown_safe) + switch (arm64_get_meltdown_state()) { + case SPECTRE_UNAFFECTED: return sprintf(buf, "Not affected\n"); - if (arm64_kernel_unmapped_at_el0()) + case SPECTRE_MITIGATED: return sprintf(buf, "Mitigation: PTI\n"); - return sprintf(buf, "Vulnerable\n"); + default: + return sprintf(buf, "Vulnerable\n"); + } } diff --git a/arch/arm64/kernel/entry.S b/arch/arm64/kernel/entry.S index 51c762156099..2a93fa5f4e49 100644 --- a/arch/arm64/kernel/entry.S +++ b/arch/arm64/kernel/entry.S @@ -173,6 +173,43 @@ alternative_else_nop_endif #endif .endm + .macro mte_set_gcr, tmp, tmp2 +#ifdef CONFIG_ARM64_MTE + /* + * Calculate and set the exclude mask preserving + * the RRND (bit[16]) setting. + */ + mrs_s \tmp2, SYS_GCR_EL1 + bfi \tmp2, \tmp, #0, #16 + msr_s SYS_GCR_EL1, \tmp2 + isb +#endif + .endm + + .macro mte_set_kernel_gcr, tmp, tmp2 +#ifdef CONFIG_KASAN_HW_TAGS +alternative_if_not ARM64_MTE + b 1f +alternative_else_nop_endif + ldr_l \tmp, gcr_kernel_excl + + mte_set_gcr \tmp, \tmp2 +1: +#endif + .endm + + .macro mte_set_user_gcr, tsk, tmp, tmp2 +#ifdef CONFIG_ARM64_MTE +alternative_if_not ARM64_MTE + b 1f +alternative_else_nop_endif + ldr \tmp, [\tsk, #THREAD_GCR_EL1_USER] + + mte_set_gcr \tmp, \tmp2 +1: +#endif + .endm + .macro kernel_entry, el, regsize = 64 .if \regsize == 32 mov w0, w0 // zero upper 32 bits of x0 @@ -212,6 +249,8 @@ alternative_else_nop_endif ptrauth_keys_install_kernel tsk, x20, x22, x23 + mte_set_kernel_gcr x22, x23 + scs_load tsk, x20 .else add x21, sp, #S_FRAME_SIZE @@ -315,6 +354,8 @@ alternative_else_nop_endif /* No kernel C function calls after this as user keys are set. */ ptrauth_keys_install_user tsk, x0, x1, x2 + mte_set_user_gcr tsk, x0, x1 + apply_ssbd 0, x0, x1 .endif diff --git a/arch/arm64/kernel/head.S b/arch/arm64/kernel/head.S index f2eb206920a2..a0dc987724ed 100644 --- a/arch/arm64/kernel/head.S +++ b/arch/arm64/kernel/head.S @@ -11,7 +11,6 @@ #include <linux/linkage.h> #include <linux/init.h> -#include <linux/irqchip/arm-gic-v3.h> #include <linux/pgtable.h> #include <asm/asm_pointer_auth.h> @@ -21,6 +20,7 @@ #include <asm/asm-offsets.h> #include <asm/cache.h> #include <asm/cputype.h> +#include <asm/el2_setup.h> #include <asm/elf.h> #include <asm/image.h> #include <asm/kernel-pgtable.h> @@ -433,7 +433,7 @@ SYM_FUNC_START_LOCAL(__primary_switched) bl __pi_memset dsb ishst // Make zero page visible to PTW -#ifdef CONFIG_KASAN +#if defined(CONFIG_KASAN_GENERIC) || defined(CONFIG_KASAN_SW_TAGS) bl kasan_early_init #endif #ifdef CONFIG_RANDOMIZE_BASE @@ -493,155 +493,56 @@ SYM_INNER_LABEL(init_el1, SYM_L_LOCAL) eret SYM_INNER_LABEL(init_el2, SYM_L_LOCAL) - mov_q x0, INIT_SCTLR_EL2_MMU_OFF - msr sctlr_el2, x0 - #ifdef CONFIG_ARM64_VHE /* - * Check for VHE being present. For the rest of the EL2 setup, - * x2 being non-zero indicates that we do have VHE, and that the - * kernel is intended to run at EL2. + * Check for VHE being present. x2 being non-zero indicates that we + * do have VHE, and that the kernel is intended to run at EL2. */ mrs x2, id_aa64mmfr1_el1 ubfx x2, x2, #ID_AA64MMFR1_VHE_SHIFT, #4 #else mov x2, xzr #endif + cbz x2, init_el2_nvhe - /* Hyp configuration. */ - mov_q x0, HCR_HOST_NVHE_FLAGS - cbz x2, set_hcr + /* + * When VHE _is_ in use, EL1 will not be used in the host and + * requires no configuration, and all non-hyp-specific EL2 setup + * will be done via the _EL1 system register aliases in __cpu_setup. + */ mov_q x0, HCR_HOST_VHE_FLAGS -set_hcr: msr hcr_el2, x0 isb - /* - * Allow Non-secure EL1 and EL0 to access physical timer and counter. - * This is not necessary for VHE, since the host kernel runs in EL2, - * and EL0 accesses are configured in the later stage of boot process. - * Note that when HCR_EL2.E2H == 1, CNTHCTL_EL2 has the same bit layout - * as CNTKCTL_EL1, and CNTKCTL_EL1 accessing instructions are redefined - * to access CNTHCTL_EL2. This allows the kernel designed to run at EL1 - * to transparently mess with the EL0 bits via CNTKCTL_EL1 access in - * EL2. - */ - cbnz x2, 1f - mrs x0, cnthctl_el2 - orr x0, x0, #3 // Enable EL1 physical timers - msr cnthctl_el2, x0 -1: - msr cntvoff_el2, xzr // Clear virtual offset - -#ifdef CONFIG_ARM_GIC_V3 - /* GICv3 system register access */ - mrs x0, id_aa64pfr0_el1 - ubfx x0, x0, #ID_AA64PFR0_GIC_SHIFT, #4 - cbz x0, 3f - - mrs_s x0, SYS_ICC_SRE_EL2 - orr x0, x0, #ICC_SRE_EL2_SRE // Set ICC_SRE_EL2.SRE==1 - orr x0, x0, #ICC_SRE_EL2_ENABLE // Set ICC_SRE_EL2.Enable==1 - msr_s SYS_ICC_SRE_EL2, x0 - isb // Make sure SRE is now set - mrs_s x0, SYS_ICC_SRE_EL2 // Read SRE back, - tbz x0, #0, 3f // and check that it sticks - msr_s SYS_ICH_HCR_EL2, xzr // Reset ICC_HCR_EL2 to defaults - -3: -#endif - - /* Populate ID registers. */ - mrs x0, midr_el1 - mrs x1, mpidr_el1 - msr vpidr_el2, x0 - msr vmpidr_el2, x1 - -#ifdef CONFIG_COMPAT - msr hstr_el2, xzr // Disable CP15 traps to EL2 -#endif - - /* EL2 debug */ - mrs x1, id_aa64dfr0_el1 - sbfx x0, x1, #ID_AA64DFR0_PMUVER_SHIFT, #4 - cmp x0, #1 - b.lt 4f // Skip if no PMU present - mrs x0, pmcr_el0 // Disable debug access traps - ubfx x0, x0, #11, #5 // to EL2 and allow access to -4: - csel x3, xzr, x0, lt // all PMU counters from EL1 - - /* Statistical profiling */ - ubfx x0, x1, #ID_AA64DFR0_PMSVER_SHIFT, #4 - cbz x0, 7f // Skip if SPE not present - cbnz x2, 6f // VHE? - mrs_s x4, SYS_PMBIDR_EL1 // If SPE available at EL2, - and x4, x4, #(1 << SYS_PMBIDR_EL1_P_SHIFT) - cbnz x4, 5f // then permit sampling of physical - mov x4, #(1 << SYS_PMSCR_EL2_PCT_SHIFT | \ - 1 << SYS_PMSCR_EL2_PA_SHIFT) - msr_s SYS_PMSCR_EL2, x4 // addresses and physical counter -5: - mov x1, #(MDCR_EL2_E2PB_MASK << MDCR_EL2_E2PB_SHIFT) - orr x3, x3, x1 // If we don't have VHE, then - b 7f // use EL1&0 translation. -6: // For VHE, use EL2 translation - orr x3, x3, #MDCR_EL2_TPMS // and disable access from EL1 -7: - msr mdcr_el2, x3 // Configure debug traps - - /* LORegions */ - mrs x1, id_aa64mmfr1_el1 - ubfx x0, x1, #ID_AA64MMFR1_LOR_SHIFT, 4 - cbz x0, 1f - msr_s SYS_LORC_EL1, xzr -1: - - /* Stage-2 translation */ - msr vttbr_el2, xzr - - cbz x2, install_el2_stub + init_el2_state vhe isb + mov_q x0, INIT_PSTATE_EL2 msr spsr_el2, x0 msr elr_el2, lr mov w0, #BOOT_CPU_MODE_EL2 eret -SYM_INNER_LABEL(install_el2_stub, SYM_L_LOCAL) +SYM_INNER_LABEL(init_el2_nvhe, SYM_L_LOCAL) /* * When VHE is not in use, early init of EL2 and EL1 needs to be * done here. - * When VHE _is_ in use, EL1 will not be used in the host and - * requires no configuration, and all non-hyp-specific EL2 setup - * will be done via the _EL1 system register aliases in __cpu_setup. */ mov_q x0, INIT_SCTLR_EL1_MMU_OFF msr sctlr_el1, x0 - /* Coprocessor traps. */ - mov x0, #0x33ff - msr cptr_el2, x0 // Disable copro. traps to EL2 - - /* SVE register access */ - mrs x1, id_aa64pfr0_el1 - ubfx x1, x1, #ID_AA64PFR0_SVE_SHIFT, #4 - cbz x1, 7f - - bic x0, x0, #CPTR_EL2_TZ // Also disable SVE traps - msr cptr_el2, x0 // Disable copro. traps to EL2 + mov_q x0, HCR_HOST_NVHE_FLAGS + msr hcr_el2, x0 isb - mov x1, #ZCR_ELx_LEN_MASK // SVE: Enable full vector - msr_s SYS_ZCR_EL2, x1 // length for EL1. + + init_el2_state nvhe /* Hypervisor stub */ -7: adr_l x0, __hyp_stub_vectors + adr_l x0, __hyp_stub_vectors msr vbar_el2, x0 - isb - mov x0, #INIT_PSTATE_EL1 - msr spsr_el2, x0 + msr elr_el2, lr mov w0, #BOOT_CPU_MODE_EL2 eret diff --git a/arch/arm64/kernel/hibernate.c b/arch/arm64/kernel/hibernate.c index 42003774d261..9c9f47e9f7f4 100644 --- a/arch/arm64/kernel/hibernate.c +++ b/arch/arm64/kernel/hibernate.c @@ -371,6 +371,11 @@ static void swsusp_mte_restore_tags(void) unsigned long pfn = xa_state.xa_index; struct page *page = pfn_to_online_page(pfn); + /* + * It is not required to invoke page_kasan_tag_reset(page) + * at this point since the tags stored in page->flags are + * already restored. + */ mte_restore_page_tags(page_address(page), tags); mte_free_tag_storage(tags); diff --git a/arch/arm64/kernel/image-vars.h b/arch/arm64/kernel/image-vars.h index c615b285ff5b..f676243abac6 100644 --- a/arch/arm64/kernel/image-vars.h +++ b/arch/arm64/kernel/image-vars.h @@ -37,7 +37,7 @@ __efistub_strncmp = __pi_strncmp; __efistub_strrchr = __pi_strrchr; __efistub___clean_dcache_area_poc = __pi___clean_dcache_area_poc; -#ifdef CONFIG_KASAN +#if defined(CONFIG_KASAN_GENERIC) || defined(CONFIG_KASAN_SW_TAGS) __efistub___memcpy = __pi_memcpy; __efistub___memmove = __pi_memmove; __efistub___memset = __pi_memset; @@ -64,13 +64,12 @@ __efistub__ctype = _ctype; /* Alternative callbacks for init-time patching of nVHE hyp code. */ KVM_NVHE_ALIAS(kvm_patch_vector_branch); KVM_NVHE_ALIAS(kvm_update_va_mask); +KVM_NVHE_ALIAS(kvm_update_kimg_phys_offset); +KVM_NVHE_ALIAS(kvm_get_kimage_voffset); /* Global kernel state accessed by nVHE hyp code. */ KVM_NVHE_ALIAS(kvm_vgic_global_state); -/* Kernel constant needed to compute idmap addresses. */ -KVM_NVHE_ALIAS(kimage_voffset); - /* Kernel symbols used to call panic() from nVHE hyp code (via ERET). */ KVM_NVHE_ALIAS(__hyp_panic_string); KVM_NVHE_ALIAS(panic); @@ -78,9 +77,6 @@ KVM_NVHE_ALIAS(panic); /* Vectors installed by hyp-init on reset HVC. */ KVM_NVHE_ALIAS(__hyp_stub_vectors); -/* IDMAP TCR_EL1.T0SZ as computed by the EL1 init code */ -KVM_NVHE_ALIAS(idmap_t0sz); - /* Kernel symbol used by icache_is_vpipt(). */ KVM_NVHE_ALIAS(__icache_flags); @@ -103,6 +99,9 @@ KVM_NVHE_ALIAS(gic_nonsecure_priorities); KVM_NVHE_ALIAS(__start___kvm_ex_table); KVM_NVHE_ALIAS(__stop___kvm_ex_table); +/* Array containing bases of nVHE per-CPU memory regions. */ +KVM_NVHE_ALIAS(kvm_arm_hyp_percpu_base); + #endif /* CONFIG_KVM */ #endif /* __ARM64_KERNEL_IMAGE_VARS_H */ diff --git a/arch/arm64/kernel/kaslr.c b/arch/arm64/kernel/kaslr.c index 0921aa1520b0..1c74c45b9494 100644 --- a/arch/arm64/kernel/kaslr.c +++ b/arch/arm64/kernel/kaslr.c @@ -161,7 +161,8 @@ u64 __init kaslr_early_init(u64 dt_phys) /* use the top 16 bits to randomize the linear region */ memstart_offset_seed = seed >> 48; - if (IS_ENABLED(CONFIG_KASAN)) + if (IS_ENABLED(CONFIG_KASAN_GENERIC) || + IS_ENABLED(CONFIG_KASAN_SW_TAGS)) /* * KASAN does not expect the module region to intersect the * vmalloc region, since shadow memory is allocated for each diff --git a/arch/arm64/kernel/module.c b/arch/arm64/kernel/module.c index 2a1ad95d9b2c..fe21e0f06492 100644 --- a/arch/arm64/kernel/module.c +++ b/arch/arm64/kernel/module.c @@ -30,7 +30,8 @@ void *module_alloc(unsigned long size) if (IS_ENABLED(CONFIG_ARM64_MODULE_PLTS)) gfp_mask |= __GFP_NOWARN; - if (IS_ENABLED(CONFIG_KASAN)) + if (IS_ENABLED(CONFIG_KASAN_GENERIC) || + IS_ENABLED(CONFIG_KASAN_SW_TAGS)) /* don't exceed the static module region - see below */ module_alloc_end = MODULES_END; @@ -39,7 +40,8 @@ void *module_alloc(unsigned long size) NUMA_NO_NODE, __builtin_return_address(0)); if (!p && IS_ENABLED(CONFIG_ARM64_MODULE_PLTS) && - !IS_ENABLED(CONFIG_KASAN)) + !IS_ENABLED(CONFIG_KASAN_GENERIC) && + !IS_ENABLED(CONFIG_KASAN_SW_TAGS)) /* * KASAN can only deal with module allocations being served * from the reserved module region, since the remainder of diff --git a/arch/arm64/kernel/mte.c b/arch/arm64/kernel/mte.c index ef15c8a2a49d..dc9ada64feed 100644 --- a/arch/arm64/kernel/mte.c +++ b/arch/arm64/kernel/mte.c @@ -13,13 +13,18 @@ #include <linux/swap.h> #include <linux/swapops.h> #include <linux/thread_info.h> +#include <linux/types.h> #include <linux/uio.h> +#include <asm/barrier.h> #include <asm/cpufeature.h> #include <asm/mte.h> +#include <asm/mte-kasan.h> #include <asm/ptrace.h> #include <asm/sysreg.h> +u64 gcr_kernel_excl __ro_after_init; + static void mte_sync_page_tags(struct page *page, pte_t *ptep, bool check_swap) { pte_t old_pte = READ_ONCE(*ptep); @@ -31,6 +36,15 @@ static void mte_sync_page_tags(struct page *page, pte_t *ptep, bool check_swap) return; } + page_kasan_tag_reset(page); + /* + * We need smp_wmb() in between setting the flags and clearing the + * tags because if another thread reads page->flags and builds a + * tagged address out of it, there is an actual dependency to the + * memory access, but on the current thread we do not guarantee that + * the new page->flags are visible before the tags were updated. + */ + smp_wmb(); mte_clear_page_tags(page_address(page)); } @@ -72,6 +86,78 @@ int memcmp_pages(struct page *page1, struct page *page2) return ret; } +u8 mte_get_mem_tag(void *addr) +{ + if (!system_supports_mte()) + return 0xFF; + + asm(__MTE_PREAMBLE "ldg %0, [%0]" + : "+r" (addr)); + + return mte_get_ptr_tag(addr); +} + +u8 mte_get_random_tag(void) +{ + void *addr; + + if (!system_supports_mte()) + return 0xFF; + + asm(__MTE_PREAMBLE "irg %0, %0" + : "+r" (addr)); + + return mte_get_ptr_tag(addr); +} + +void *mte_set_mem_tag_range(void *addr, size_t size, u8 tag) +{ + void *ptr = addr; + + if ((!system_supports_mte()) || (size == 0)) + return addr; + + /* Make sure that size is MTE granule aligned. */ + WARN_ON(size & (MTE_GRANULE_SIZE - 1)); + + /* Make sure that the address is MTE granule aligned. */ + WARN_ON((u64)addr & (MTE_GRANULE_SIZE - 1)); + + tag = 0xF0 | tag; + ptr = (void *)__tag_set(ptr, tag); + + mte_assign_mem_tag_range(ptr, size); + + return ptr; +} + +void mte_init_tags(u64 max_tag) +{ + static bool gcr_kernel_excl_initialized; + + if (!gcr_kernel_excl_initialized) { + /* + * The format of the tags in KASAN is 0xFF and in MTE is 0xF. + * This conversion extracts an MTE tag from a KASAN tag. + */ + u64 incl = GENMASK(FIELD_GET(MTE_TAG_MASK >> MTE_TAG_SHIFT, + max_tag), 0); + + gcr_kernel_excl = ~incl & SYS_GCR_EL1_EXCL_MASK; + gcr_kernel_excl_initialized = true; + } + + /* Enable the kernel exclude mask for random tags generation. */ + write_sysreg_s(SYS_GCR_EL1_RRND | gcr_kernel_excl, SYS_GCR_EL1); +} + +void mte_enable_kernel(void) +{ + /* Enable MTE Sync Mode for EL1. */ + sysreg_clear_set(sctlr_el1, SCTLR_ELx_TCF_MASK, SCTLR_ELx_TCF_SYNC); + isb(); +} + static void update_sctlr_el1_tcf0(u64 tcf0) { /* ISB required for the kernel uaccess routines */ @@ -92,23 +178,26 @@ static void set_sctlr_el1_tcf0(u64 tcf0) preempt_enable(); } -static void update_gcr_el1_excl(u64 incl) +static void update_gcr_el1_excl(u64 excl) { - u64 excl = ~incl & SYS_GCR_EL1_EXCL_MASK; /* - * Note that 'incl' is an include mask (controlled by the user via - * prctl()) while GCR_EL1 accepts an exclude mask. + * Note that the mask controlled by the user via prctl() is an + * include while GCR_EL1 accepts an exclude mask. * No need for ISB since this only affects EL0 currently, implicit * with ERET. */ sysreg_clear_set_s(SYS_GCR_EL1, SYS_GCR_EL1_EXCL_MASK, excl); } -static void set_gcr_el1_excl(u64 incl) +static void set_gcr_el1_excl(u64 excl) { - current->thread.gcr_user_incl = incl; - update_gcr_el1_excl(incl); + current->thread.gcr_user_excl = excl; + + /* + * SYS_GCR_EL1 will be set to current->thread.gcr_user_excl value + * by mte_set_user_gcr() in kernel_exit, + */ } void flush_mte_state(void) @@ -123,7 +212,7 @@ void flush_mte_state(void) /* disable tag checking */ set_sctlr_el1_tcf0(SCTLR_EL1_TCF0_NONE); /* reset tag generation mask */ - set_gcr_el1_excl(0); + set_gcr_el1_excl(SYS_GCR_EL1_EXCL_MASK); } void mte_thread_switch(struct task_struct *next) @@ -134,7 +223,6 @@ void mte_thread_switch(struct task_struct *next) /* avoid expensive SCTLR_EL1 accesses if no change */ if (current->thread.sctlr_tcf0 != next->thread.sctlr_tcf0) update_sctlr_el1_tcf0(next->thread.sctlr_tcf0); - update_gcr_el1_excl(next->thread.gcr_user_incl); } void mte_suspend_exit(void) @@ -142,13 +230,14 @@ void mte_suspend_exit(void) if (!system_supports_mte()) return; - update_gcr_el1_excl(current->thread.gcr_user_incl); + update_gcr_el1_excl(gcr_kernel_excl); } long set_mte_ctrl(struct task_struct *task, unsigned long arg) { u64 tcf0; - u64 gcr_incl = (arg & PR_MTE_TAG_MASK) >> PR_MTE_TAG_SHIFT; + u64 gcr_excl = ~((arg & PR_MTE_TAG_MASK) >> PR_MTE_TAG_SHIFT) & + SYS_GCR_EL1_EXCL_MASK; if (!system_supports_mte()) return 0; @@ -169,10 +258,10 @@ long set_mte_ctrl(struct task_struct *task, unsigned long arg) if (task != current) { task->thread.sctlr_tcf0 = tcf0; - task->thread.gcr_user_incl = gcr_incl; + task->thread.gcr_user_excl = gcr_excl; } else { set_sctlr_el1_tcf0(tcf0); - set_gcr_el1_excl(gcr_incl); + set_gcr_el1_excl(gcr_excl); } return 0; @@ -181,11 +270,12 @@ long set_mte_ctrl(struct task_struct *task, unsigned long arg) long get_mte_ctrl(struct task_struct *task) { unsigned long ret; + u64 incl = ~task->thread.gcr_user_excl & SYS_GCR_EL1_EXCL_MASK; if (!system_supports_mte()) return 0; - ret = task->thread.gcr_user_incl << PR_MTE_TAG_SHIFT; + ret = incl << PR_MTE_TAG_SHIFT; switch (task->thread.sctlr_tcf0) { case SCTLR_EL1_TCF0_NONE: diff --git a/arch/arm64/kernel/proton-pack.c b/arch/arm64/kernel/proton-pack.c index 4c25c008504f..902e4084c477 100644 --- a/arch/arm64/kernel/proton-pack.c +++ b/arch/arm64/kernel/proton-pack.c @@ -1,6 +1,6 @@ // SPDX-License-Identifier: GPL-2.0-only /* - * Handle detection, reporting and mitigation of Spectre v1, v2 and v4, as + * Handle detection, reporting and mitigation of Spectre v1, v2, v3a and v4, as * detailed at: * * https://developer.arm.com/support/arm-security-updates/speculative-processor-vulnerability @@ -27,6 +27,7 @@ #include <asm/insn.h> #include <asm/spectre.h> #include <asm/traps.h> +#include <asm/virt.h> /* * We try to ensure that the mitigation state can never change as the result of @@ -171,72 +172,26 @@ bool has_spectre_v2(const struct arm64_cpu_capabilities *entry, int scope) return true; } -DEFINE_PER_CPU_READ_MOSTLY(struct bp_hardening_data, bp_hardening_data); - enum mitigation_state arm64_get_spectre_v2_state(void) { return spectre_v2_state; } -#ifdef CONFIG_KVM -#include <asm/cacheflush.h> -#include <asm/kvm_asm.h> - -atomic_t arm64_el2_vector_last_slot = ATOMIC_INIT(-1); - -static void __copy_hyp_vect_bpi(int slot, const char *hyp_vecs_start, - const char *hyp_vecs_end) -{ - void *dst = lm_alias(__bp_harden_hyp_vecs + slot * SZ_2K); - int i; - - for (i = 0; i < SZ_2K; i += 0x80) - memcpy(dst + i, hyp_vecs_start, hyp_vecs_end - hyp_vecs_start); - - __flush_icache_range((uintptr_t)dst, (uintptr_t)dst + SZ_2K); -} +DEFINE_PER_CPU_READ_MOSTLY(struct bp_hardening_data, bp_hardening_data); static void install_bp_hardening_cb(bp_hardening_cb_t fn) { - static DEFINE_RAW_SPINLOCK(bp_lock); - int cpu, slot = -1; - const char *hyp_vecs_start = __smccc_workaround_1_smc; - const char *hyp_vecs_end = __smccc_workaround_1_smc + - __SMCCC_WORKAROUND_1_SMC_SZ; + __this_cpu_write(bp_hardening_data.fn, fn); /* * Vinz Clortho takes the hyp_vecs start/end "keys" at * the door when we're a guest. Skip the hyp-vectors work. */ - if (!is_hyp_mode_available()) { - __this_cpu_write(bp_hardening_data.fn, fn); + if (!is_hyp_mode_available()) return; - } - - raw_spin_lock(&bp_lock); - for_each_possible_cpu(cpu) { - if (per_cpu(bp_hardening_data.fn, cpu) == fn) { - slot = per_cpu(bp_hardening_data.hyp_vectors_slot, cpu); - break; - } - } - - if (slot == -1) { - slot = atomic_inc_return(&arm64_el2_vector_last_slot); - BUG_ON(slot >= BP_HARDEN_EL2_SLOTS); - __copy_hyp_vect_bpi(slot, hyp_vecs_start, hyp_vecs_end); - } - __this_cpu_write(bp_hardening_data.hyp_vectors_slot, slot); - __this_cpu_write(bp_hardening_data.fn, fn); - raw_spin_unlock(&bp_lock); -} -#else -static void install_bp_hardening_cb(bp_hardening_cb_t fn) -{ - __this_cpu_write(bp_hardening_data.fn, fn); + __this_cpu_write(bp_hardening_data.slot, HYP_VECTOR_SPECTRE_DIRECT); } -#endif /* CONFIG_KVM */ static void call_smc_arch_workaround_1(void) { @@ -318,6 +273,33 @@ void spectre_v2_enable_mitigation(const struct arm64_cpu_capabilities *__unused) } /* + * Spectre-v3a. + * + * Phew, there's not an awful lot to do here! We just instruct EL2 to use + * an indirect trampoline for the hyp vectors so that guests can't read + * VBAR_EL2 to defeat randomisation of the hypervisor VA layout. + */ +bool has_spectre_v3a(const struct arm64_cpu_capabilities *entry, int scope) +{ + static const struct midr_range spectre_v3a_unsafe_list[] = { + MIDR_ALL_VERSIONS(MIDR_CORTEX_A57), + MIDR_ALL_VERSIONS(MIDR_CORTEX_A72), + {}, + }; + + WARN_ON(scope != SCOPE_LOCAL_CPU || preemptible()); + return is_midr_in_range_list(read_cpuid_id(), spectre_v3a_unsafe_list); +} + +void spectre_v3a_enable_mitigation(const struct arm64_cpu_capabilities *__unused) +{ + struct bp_hardening_data *data = this_cpu_ptr(&bp_hardening_data); + + if (this_cpu_has_cap(ARM64_SPECTRE_V3A)) + data->slot += HYP_VECTOR_INDIRECT; +} + +/* * Spectre v4. * * If you thought Spectre v2 was nasty, wait until you see this mess. A CPU is diff --git a/arch/arm64/kernel/setup.c b/arch/arm64/kernel/setup.c index 1a57a76e1cc2..c18aacde8bb0 100644 --- a/arch/arm64/kernel/setup.c +++ b/arch/arm64/kernel/setup.c @@ -276,7 +276,7 @@ arch_initcall(reserve_memblock_reserved_regions); u64 __cpu_logical_map[NR_CPUS] = { [0 ... NR_CPUS-1] = INVALID_HWID }; -u64 cpu_logical_map(int cpu) +u64 cpu_logical_map(unsigned int cpu) { return __cpu_logical_map[cpu]; } @@ -358,7 +358,7 @@ void __init __no_sanitize_address setup_arch(char **cmdline_p) smp_build_mpidr_hash(); /* Init percpu seeds for random tags after cpus are set up. */ - kasan_init_tags(); + kasan_init_sw_tags(); #ifdef CONFIG_ARM64_SW_TTBR0_PAN /* diff --git a/arch/arm64/kernel/sleep.S b/arch/arm64/kernel/sleep.S index 4be7f7eed875..6bdef7362c0e 100644 --- a/arch/arm64/kernel/sleep.S +++ b/arch/arm64/kernel/sleep.S @@ -133,7 +133,7 @@ SYM_FUNC_START(_cpu_resume) */ bl cpu_do_resume -#ifdef CONFIG_KASAN +#if defined(CONFIG_KASAN) && CONFIG_KASAN_STACK mov x0, sp bl kasan_unpoison_task_stack_below #endif diff --git a/arch/arm64/kernel/smp.c b/arch/arm64/kernel/smp.c index 2499b895efea..19b1705ae5cb 100644 --- a/arch/arm64/kernel/smp.c +++ b/arch/arm64/kernel/smp.c @@ -462,6 +462,8 @@ void __init smp_prepare_boot_cpu(void) /* Conditionally switch to GIC PMR for interrupt masking */ if (system_uses_irq_prio_masking()) init_gic_priority_masking(); + + kasan_init_hw_tags(); } static u64 __init of_get_cpu_mpidr(struct device_node *dn) diff --git a/arch/arm64/kernel/topology.c b/arch/arm64/kernel/topology.c index c8308befdb1e..f6faa697e83e 100644 --- a/arch/arm64/kernel/topology.c +++ b/arch/arm64/kernel/topology.c @@ -314,7 +314,7 @@ void topology_scale_freq_tick(void) if (unlikely(core_cnt <= prev_core_cnt || const_cnt <= prev_const_cnt)) - goto store_and_exit; + return; /* * /\core arch_max_freq_scale @@ -331,10 +331,6 @@ void topology_scale_freq_tick(void) scale = min_t(unsigned long, scale, SCHED_CAPACITY_SCALE); this_cpu_write(freq_scale, (unsigned long)scale); - -store_and_exit: - this_cpu_write(arch_core_cycles_prev, core_cnt); - this_cpu_write(arch_const_cycles_prev, const_cnt); } #ifdef CONFIG_ACPI_CPPC_LIB diff --git a/arch/arm64/kernel/vmlinux.lds.S b/arch/arm64/kernel/vmlinux.lds.S index 5d5857c5b025..4c0b0c89ad59 100644 --- a/arch/arm64/kernel/vmlinux.lds.S +++ b/arch/arm64/kernel/vmlinux.lds.S @@ -30,6 +30,13 @@ jiffies = jiffies_64; *(__kvm_ex_table) \ __stop___kvm_ex_table = .; +#define HYPERVISOR_DATA_SECTIONS \ + HYP_SECTION_NAME(.data..ro_after_init) : { \ + __hyp_data_ro_after_init_start = .; \ + *(HYP_SECTION_NAME(.data..ro_after_init)) \ + __hyp_data_ro_after_init_end = .; \ + } + #define HYPERVISOR_PERCPU_SECTION \ . = ALIGN(PAGE_SIZE); \ HYP_SECTION_NAME(.data..percpu) : { \ @@ -37,6 +44,7 @@ jiffies = jiffies_64; } #else /* CONFIG_KVM */ #define HYPERVISOR_EXTABLE +#define HYPERVISOR_DATA_SECTIONS #define HYPERVISOR_PERCPU_SECTION #endif @@ -232,6 +240,8 @@ SECTIONS _sdata = .; RW_DATA(L1_CACHE_BYTES, PAGE_SIZE, THREAD_ALIGN) + HYPERVISOR_DATA_SECTIONS + /* * Data written with the MMU off but read with the MMU on requires * cache lines to be invalidated, discarding up to a Cache Writeback diff --git a/arch/arm64/kvm/Makefile b/arch/arm64/kvm/Makefile index 1504c81fbf5d..60fd181df624 100644 --- a/arch/arm64/kvm/Makefile +++ b/arch/arm64/kvm/Makefile @@ -13,10 +13,10 @@ obj-$(CONFIG_KVM) += hyp/ kvm-y := $(KVM)/kvm_main.o $(KVM)/coalesced_mmio.o $(KVM)/eventfd.o \ $(KVM)/vfio.o $(KVM)/irqchip.o \ arm.o mmu.o mmio.o psci.o perf.o hypercalls.o pvtime.o \ - inject_fault.o regmap.o va_layout.o handle_exit.o \ + inject_fault.o va_layout.o handle_exit.o \ guest.o debug.o reset.o sys_regs.o \ vgic-sys-reg-v3.o fpsimd.o pmu.o \ - aarch32.o arch_timer.o \ + arch_timer.o \ vgic/vgic.o vgic/vgic-init.o \ vgic/vgic-irqfd.o vgic/vgic-v2.o \ vgic/vgic-v3.o vgic/vgic-v4.o \ diff --git a/arch/arm64/kvm/aarch32.c b/arch/arm64/kvm/aarch32.c deleted file mode 100644 index 40a62a99fbf8..000000000000 --- a/arch/arm64/kvm/aarch32.c +++ /dev/null @@ -1,232 +0,0 @@ -// SPDX-License-Identifier: GPL-2.0-only -/* - * (not much of an) Emulation layer for 32bit guests. - * - * Copyright (C) 2012,2013 - ARM Ltd - * Author: Marc Zyngier <marc.zyngier@arm.com> - * - * based on arch/arm/kvm/emulate.c - * Copyright (C) 2012 - Virtual Open Systems and Columbia University - * Author: Christoffer Dall <c.dall@virtualopensystems.com> - */ - -#include <linux/bits.h> -#include <linux/kvm_host.h> -#include <asm/kvm_emulate.h> -#include <asm/kvm_hyp.h> - -#define DFSR_FSC_EXTABT_LPAE 0x10 -#define DFSR_FSC_EXTABT_nLPAE 0x08 -#define DFSR_LPAE BIT(9) - -/* - * Table taken from ARMv8 ARM DDI0487B-B, table G1-10. - */ -static const u8 return_offsets[8][2] = { - [0] = { 0, 0 }, /* Reset, unused */ - [1] = { 4, 2 }, /* Undefined */ - [2] = { 0, 0 }, /* SVC, unused */ - [3] = { 4, 4 }, /* Prefetch abort */ - [4] = { 8, 8 }, /* Data abort */ - [5] = { 0, 0 }, /* HVC, unused */ - [6] = { 4, 4 }, /* IRQ, unused */ - [7] = { 4, 4 }, /* FIQ, unused */ -}; - -static bool pre_fault_synchronize(struct kvm_vcpu *vcpu) -{ - preempt_disable(); - if (vcpu->arch.sysregs_loaded_on_cpu) { - kvm_arch_vcpu_put(vcpu); - return true; - } - - preempt_enable(); - return false; -} - -static void post_fault_synchronize(struct kvm_vcpu *vcpu, bool loaded) -{ - if (loaded) { - kvm_arch_vcpu_load(vcpu, smp_processor_id()); - preempt_enable(); - } -} - -/* - * When an exception is taken, most CPSR fields are left unchanged in the - * handler. However, some are explicitly overridden (e.g. M[4:0]). - * - * The SPSR/SPSR_ELx layouts differ, and the below is intended to work with - * either format. Note: SPSR.J bit doesn't exist in SPSR_ELx, but this bit was - * obsoleted by the ARMv7 virtualization extensions and is RES0. - * - * For the SPSR layout seen from AArch32, see: - * - ARM DDI 0406C.d, page B1-1148 - * - ARM DDI 0487E.a, page G8-6264 - * - * For the SPSR_ELx layout for AArch32 seen from AArch64, see: - * - ARM DDI 0487E.a, page C5-426 - * - * Here we manipulate the fields in order of the AArch32 SPSR_ELx layout, from - * MSB to LSB. - */ -static unsigned long get_except32_cpsr(struct kvm_vcpu *vcpu, u32 mode) -{ - u32 sctlr = vcpu_cp15(vcpu, c1_SCTLR); - unsigned long old, new; - - old = *vcpu_cpsr(vcpu); - new = 0; - - new |= (old & PSR_AA32_N_BIT); - new |= (old & PSR_AA32_Z_BIT); - new |= (old & PSR_AA32_C_BIT); - new |= (old & PSR_AA32_V_BIT); - new |= (old & PSR_AA32_Q_BIT); - - // CPSR.IT[7:0] are set to zero upon any exception - // See ARM DDI 0487E.a, section G1.12.3 - // See ARM DDI 0406C.d, section B1.8.3 - - new |= (old & PSR_AA32_DIT_BIT); - - // CPSR.SSBS is set to SCTLR.DSSBS upon any exception - // See ARM DDI 0487E.a, page G8-6244 - if (sctlr & BIT(31)) - new |= PSR_AA32_SSBS_BIT; - - // CPSR.PAN is unchanged unless SCTLR.SPAN == 0b0 - // SCTLR.SPAN is RES1 when ARMv8.1-PAN is not implemented - // See ARM DDI 0487E.a, page G8-6246 - new |= (old & PSR_AA32_PAN_BIT); - if (!(sctlr & BIT(23))) - new |= PSR_AA32_PAN_BIT; - - // SS does not exist in AArch32, so ignore - - // CPSR.IL is set to zero upon any exception - // See ARM DDI 0487E.a, page G1-5527 - - new |= (old & PSR_AA32_GE_MASK); - - // CPSR.IT[7:0] are set to zero upon any exception - // See prior comment above - - // CPSR.E is set to SCTLR.EE upon any exception - // See ARM DDI 0487E.a, page G8-6245 - // See ARM DDI 0406C.d, page B4-1701 - if (sctlr & BIT(25)) - new |= PSR_AA32_E_BIT; - - // CPSR.A is unchanged upon an exception to Undefined, Supervisor - // CPSR.A is set upon an exception to other modes - // See ARM DDI 0487E.a, pages G1-5515 to G1-5516 - // See ARM DDI 0406C.d, page B1-1182 - new |= (old & PSR_AA32_A_BIT); - if (mode != PSR_AA32_MODE_UND && mode != PSR_AA32_MODE_SVC) - new |= PSR_AA32_A_BIT; - - // CPSR.I is set upon any exception - // See ARM DDI 0487E.a, pages G1-5515 to G1-5516 - // See ARM DDI 0406C.d, page B1-1182 - new |= PSR_AA32_I_BIT; - - // CPSR.F is set upon an exception to FIQ - // CPSR.F is unchanged upon an exception to other modes - // See ARM DDI 0487E.a, pages G1-5515 to G1-5516 - // See ARM DDI 0406C.d, page B1-1182 - new |= (old & PSR_AA32_F_BIT); - if (mode == PSR_AA32_MODE_FIQ) - new |= PSR_AA32_F_BIT; - - // CPSR.T is set to SCTLR.TE upon any exception - // See ARM DDI 0487E.a, page G8-5514 - // See ARM DDI 0406C.d, page B1-1181 - if (sctlr & BIT(30)) - new |= PSR_AA32_T_BIT; - - new |= mode; - - return new; -} - -static void prepare_fault32(struct kvm_vcpu *vcpu, u32 mode, u32 vect_offset) -{ - unsigned long spsr = *vcpu_cpsr(vcpu); - bool is_thumb = (spsr & PSR_AA32_T_BIT); - u32 return_offset = return_offsets[vect_offset >> 2][is_thumb]; - u32 sctlr = vcpu_cp15(vcpu, c1_SCTLR); - - *vcpu_cpsr(vcpu) = get_except32_cpsr(vcpu, mode); - - /* Note: These now point to the banked copies */ - vcpu_write_spsr(vcpu, host_spsr_to_spsr32(spsr)); - *vcpu_reg32(vcpu, 14) = *vcpu_pc(vcpu) + return_offset; - - /* Branch to exception vector */ - if (sctlr & (1 << 13)) - vect_offset += 0xffff0000; - else /* always have security exceptions */ - vect_offset += vcpu_cp15(vcpu, c12_VBAR); - - *vcpu_pc(vcpu) = vect_offset; -} - -void kvm_inject_undef32(struct kvm_vcpu *vcpu) -{ - bool loaded = pre_fault_synchronize(vcpu); - - prepare_fault32(vcpu, PSR_AA32_MODE_UND, 4); - post_fault_synchronize(vcpu, loaded); -} - -/* - * Modelled after TakeDataAbortException() and TakePrefetchAbortException - * pseudocode. - */ -static void inject_abt32(struct kvm_vcpu *vcpu, bool is_pabt, - unsigned long addr) -{ - u32 vect_offset; - u32 *far, *fsr; - bool is_lpae; - bool loaded; - - loaded = pre_fault_synchronize(vcpu); - - if (is_pabt) { - vect_offset = 12; - far = &vcpu_cp15(vcpu, c6_IFAR); - fsr = &vcpu_cp15(vcpu, c5_IFSR); - } else { /* !iabt */ - vect_offset = 16; - far = &vcpu_cp15(vcpu, c6_DFAR); - fsr = &vcpu_cp15(vcpu, c5_DFSR); - } - - prepare_fault32(vcpu, PSR_AA32_MODE_ABT, vect_offset); - - *far = addr; - - /* Give the guest an IMPLEMENTATION DEFINED exception */ - is_lpae = (vcpu_cp15(vcpu, c2_TTBCR) >> 31); - if (is_lpae) { - *fsr = DFSR_LPAE | DFSR_FSC_EXTABT_LPAE; - } else { - /* no need to shuffle FS[4] into DFSR[10] as its 0 */ - *fsr = DFSR_FSC_EXTABT_nLPAE; - } - - post_fault_synchronize(vcpu, loaded); -} - -void kvm_inject_dabt32(struct kvm_vcpu *vcpu, unsigned long addr) -{ - inject_abt32(vcpu, false, addr); -} - -void kvm_inject_pabt32(struct kvm_vcpu *vcpu, unsigned long addr) -{ - inject_abt32(vcpu, true, addr); -} diff --git a/arch/arm64/kvm/arm.c b/arch/arm64/kvm/arm.c index c0ffb019ca8b..6e637d2b4cfb 100644 --- a/arch/arm64/kvm/arm.c +++ b/arch/arm64/kvm/arm.c @@ -19,6 +19,7 @@ #include <linux/kvm_irqfd.h> #include <linux/irqbypass.h> #include <linux/sched/stat.h> +#include <linux/psci.h> #include <trace/events/kvm.h> #define CREATE_TRACE_POINTS @@ -35,7 +36,6 @@ #include <asm/kvm_asm.h> #include <asm/kvm_mmu.h> #include <asm/kvm_emulate.h> -#include <asm/kvm_coproc.h> #include <asm/sections.h> #include <kvm/arm_hypercalls.h> @@ -46,10 +46,14 @@ __asm__(".arch_extension virt"); #endif +static enum kvm_mode kvm_mode = KVM_MODE_DEFAULT; +DEFINE_STATIC_KEY_FALSE(kvm_protected_mode_initialized); + DECLARE_KVM_HYP_PER_CPU(unsigned long, kvm_hyp_vector); static DEFINE_PER_CPU(unsigned long, kvm_arm_hyp_stack_page); unsigned long kvm_arm_hyp_percpu_base[NR_CPUS]; +DECLARE_KVM_NVHE_PER_CPU(struct kvm_nvhe_init_params, kvm_init_params); /* The VMID used in the VTTBR */ static atomic64_t kvm_vmid_gen = ATOMIC64_INIT(1); @@ -61,6 +65,10 @@ static bool vgic_present; static DEFINE_PER_CPU(unsigned char, kvm_arm_hardware_enabled); DEFINE_STATIC_KEY_FALSE(userspace_irqchip_in_use); +extern u64 kvm_nvhe_sym(__cpu_logical_map)[NR_CPUS]; +extern u32 kvm_nvhe_sym(kvm_host_psci_version); +extern struct psci_0_1_function_ids kvm_nvhe_sym(kvm_host_psci_0_1_function_ids); + int kvm_arch_vcpu_should_kick(struct kvm_vcpu *vcpu) { return kvm_vcpu_exiting_guest_mode(vcpu) == IN_GUEST_MODE; @@ -102,7 +110,7 @@ static int kvm_arm_default_max_vcpus(void) return vgic_present ? kvm_vgic_get_max_vcpus() : KVM_MAX_VCPUS; } -static void set_default_csv2(struct kvm *kvm) +static void set_default_spectre(struct kvm *kvm) { /* * The default is to expose CSV2 == 1 if the HW isn't affected. @@ -114,6 +122,8 @@ static void set_default_csv2(struct kvm *kvm) */ if (arm64_get_spectre_v2_state() == SPECTRE_UNAFFECTED) kvm->arch.pfr0_csv2 = 1; + if (arm64_get_meltdown_state() == SPECTRE_UNAFFECTED) + kvm->arch.pfr0_csv3 = 1; } /** @@ -141,7 +151,7 @@ int kvm_arch_init_vm(struct kvm *kvm, unsigned long type) /* The maximum number of VCPUs is limited by the host's GIC model */ kvm->arch.max_vcpus = kvm_arm_default_max_vcpus(); - set_default_csv2(kvm); + set_default_spectre(kvm); return ret; out_free_stage2_pgd: @@ -198,6 +208,8 @@ int kvm_vm_ioctl_check_extension(struct kvm *kvm, long ext) case KVM_CAP_ARM_IRQ_LINE_LAYOUT_2: case KVM_CAP_ARM_NISV_TO_USER: case KVM_CAP_ARM_INJECT_EXT_DABT: + case KVM_CAP_SET_GUEST_DEBUG: + case KVM_CAP_VCPU_ATTRIBUTES: r = 1; break; case KVM_CAP_ARM_SET_DEVICE_ADDR: @@ -229,10 +241,35 @@ int kvm_vm_ioctl_check_extension(struct kvm *kvm, long ext) case KVM_CAP_STEAL_TIME: r = kvm_arm_pvtime_supported(); break; - default: - r = kvm_arch_vm_ioctl_check_extension(kvm, ext); + case KVM_CAP_ARM_EL1_32BIT: + r = cpus_have_const_cap(ARM64_HAS_32BIT_EL1); + break; + case KVM_CAP_GUEST_DEBUG_HW_BPS: + r = get_num_brps(); + break; + case KVM_CAP_GUEST_DEBUG_HW_WPS: + r = get_num_wrps(); + break; + case KVM_CAP_ARM_PMU_V3: + r = kvm_arm_support_pmu_v3(); + break; + case KVM_CAP_ARM_INJECT_SERROR_ESR: + r = cpus_have_const_cap(ARM64_HAS_RAS_EXTN); break; + case KVM_CAP_ARM_VM_IPA_SIZE: + r = get_kvm_ipa_limit(); + break; + case KVM_CAP_ARM_SVE: + r = system_supports_sve(); + break; + case KVM_CAP_ARM_PTRAUTH_ADDRESS: + case KVM_CAP_ARM_PTRAUTH_GENERIC: + r = system_has_full_ptr_auth(); + break; + default: + r = 0; } + return r; } @@ -1311,47 +1348,52 @@ static unsigned long nvhe_percpu_order(void) return size ? get_order(size) : 0; } -static int kvm_map_vectors(void) +/* A lookup table holding the hypervisor VA for each vector slot */ +static void *hyp_spectre_vector_selector[BP_HARDEN_EL2_SLOTS]; + +static int __kvm_vector_slot2idx(enum arm64_hyp_spectre_vector slot) { - /* - * SV2 = ARM64_SPECTRE_V2 - * HEL2 = ARM64_HARDEN_EL2_VECTORS - * - * !SV2 + !HEL2 -> use direct vectors - * SV2 + !HEL2 -> use hardened vectors in place - * !SV2 + HEL2 -> allocate one vector slot and use exec mapping - * SV2 + HEL2 -> use hardened vectors and use exec mapping - */ - if (cpus_have_const_cap(ARM64_SPECTRE_V2)) { - __kvm_bp_vect_base = kvm_ksym_ref(__bp_harden_hyp_vecs); - __kvm_bp_vect_base = kern_hyp_va(__kvm_bp_vect_base); - } + return slot - (slot != HYP_VECTOR_DIRECT); +} - if (cpus_have_const_cap(ARM64_HARDEN_EL2_VECTORS)) { - phys_addr_t vect_pa = __pa_symbol(__bp_harden_hyp_vecs); - unsigned long size = __BP_HARDEN_HYP_VECS_SZ; +static void kvm_init_vector_slot(void *base, enum arm64_hyp_spectre_vector slot) +{ + int idx = __kvm_vector_slot2idx(slot); - /* - * Always allocate a spare vector slot, as we don't - * know yet which CPUs have a BP hardening slot that - * we can reuse. - */ - __kvm_harden_el2_vector_slot = atomic_inc_return(&arm64_el2_vector_last_slot); - BUG_ON(__kvm_harden_el2_vector_slot >= BP_HARDEN_EL2_SLOTS); - return create_hyp_exec_mappings(vect_pa, size, - &__kvm_bp_vect_base); + hyp_spectre_vector_selector[slot] = base + (idx * SZ_2K); +} + +static int kvm_init_vector_slots(void) +{ + int err; + void *base; + + base = kern_hyp_va(kvm_ksym_ref(__kvm_hyp_vector)); + kvm_init_vector_slot(base, HYP_VECTOR_DIRECT); + + base = kern_hyp_va(kvm_ksym_ref(__bp_harden_hyp_vecs)); + kvm_init_vector_slot(base, HYP_VECTOR_SPECTRE_DIRECT); + + if (!cpus_have_const_cap(ARM64_SPECTRE_V3A)) + return 0; + + if (!has_vhe()) { + err = create_hyp_exec_mappings(__pa_symbol(__bp_harden_hyp_vecs), + __BP_HARDEN_HYP_VECS_SZ, &base); + if (err) + return err; } + kvm_init_vector_slot(base, HYP_VECTOR_INDIRECT); + kvm_init_vector_slot(base, HYP_VECTOR_SPECTRE_INDIRECT); return 0; } static void cpu_init_hyp_mode(void) { - phys_addr_t pgd_ptr; - unsigned long hyp_stack_ptr; - unsigned long vector_ptr; - unsigned long tpidr_el2; + struct kvm_nvhe_init_params *params = this_cpu_ptr_nvhe_sym(kvm_init_params); struct arm_smccc_res res; + unsigned long tcr; /* Switch from the HYP stub to our own HYP init vector */ __hyp_set_vectors(kvm_get_idmap_vector()); @@ -1361,13 +1403,38 @@ static void cpu_init_hyp_mode(void) * kernel's mapping to the linear mapping, and store it in tpidr_el2 * so that we can use adr_l to access per-cpu variables in EL2. */ - tpidr_el2 = (unsigned long)this_cpu_ptr_nvhe_sym(__per_cpu_start) - - (unsigned long)kvm_ksym_ref(CHOOSE_NVHE_SYM(__per_cpu_start)); + params->tpidr_el2 = (unsigned long)this_cpu_ptr_nvhe_sym(__per_cpu_start) - + (unsigned long)kvm_ksym_ref(CHOOSE_NVHE_SYM(__per_cpu_start)); + + params->mair_el2 = read_sysreg(mair_el1); + + /* + * The ID map may be configured to use an extended virtual address + * range. This is only the case if system RAM is out of range for the + * currently configured page size and VA_BITS, in which case we will + * also need the extended virtual range for the HYP ID map, or we won't + * be able to enable the EL2 MMU. + * + * However, at EL2, there is only one TTBR register, and we can't switch + * between translation tables *and* update TCR_EL2.T0SZ at the same + * time. Bottom line: we need to use the extended range with *both* our + * translation tables. + * + * So use the same T0SZ value we use for the ID map. + */ + tcr = (read_sysreg(tcr_el1) & TCR_EL2_MASK) | TCR_EL2_RES1; + tcr &= ~TCR_T0SZ_MASK; + tcr |= (idmap_t0sz & GENMASK(TCR_TxSZ_WIDTH - 1, 0)) << TCR_T0SZ_OFFSET; + params->tcr_el2 = tcr; + + params->stack_hyp_va = kern_hyp_va(__this_cpu_read(kvm_arm_hyp_stack_page) + PAGE_SIZE); + params->pgd_pa = kvm_mmu_get_httbr(); - pgd_ptr = kvm_mmu_get_httbr(); - hyp_stack_ptr = __this_cpu_read(kvm_arm_hyp_stack_page) + PAGE_SIZE; - hyp_stack_ptr = kern_hyp_va(hyp_stack_ptr); - vector_ptr = (unsigned long)kern_hyp_va(kvm_ksym_ref(__kvm_hyp_host_vector)); + /* + * Flush the init params from the data cache because the struct will + * be read while the MMU is off. + */ + kvm_flush_dcache_to_poc(params, sizeof(*params)); /* * Call initialization code, and switch to the full blown HYP code. @@ -1376,8 +1443,7 @@ static void cpu_init_hyp_mode(void) * cpus_have_const_cap() wrapper. */ BUG_ON(!system_capabilities_finalized()); - arm_smccc_1_1_hvc(KVM_HOST_SMCCC_FUNC(__kvm_hyp_init), - pgd_ptr, tpidr_el2, hyp_stack_ptr, vector_ptr, &res); + arm_smccc_1_1_hvc(KVM_HOST_SMCCC_FUNC(__kvm_hyp_init), virt_to_phys(params), &res); WARN_ON(res.a0 != SMCCC_RET_SUCCESS); /* @@ -1396,13 +1462,40 @@ static void cpu_hyp_reset(void) __hyp_reset_vectors(); } +/* + * EL2 vectors can be mapped and rerouted in a number of ways, + * depending on the kernel configuration and CPU present: + * + * - If the CPU is affected by Spectre-v2, the hardening sequence is + * placed in one of the vector slots, which is executed before jumping + * to the real vectors. + * + * - If the CPU also has the ARM64_SPECTRE_V3A cap, the slot + * containing the hardening sequence is mapped next to the idmap page, + * and executed before jumping to the real vectors. + * + * - If the CPU only has the ARM64_SPECTRE_V3A cap, then an + * empty slot is selected, mapped next to the idmap page, and + * executed before jumping to the real vectors. + * + * Note that ARM64_SPECTRE_V3A is somewhat incompatible with + * VHE, as we don't have hypervisor-specific mappings. If the system + * is VHE and yet selects this capability, it will be ignored. + */ +static void cpu_set_hyp_vector(void) +{ + struct bp_hardening_data *data = this_cpu_ptr(&bp_hardening_data); + void *vector = hyp_spectre_vector_selector[data->slot]; + + *this_cpu_ptr_hyp_sym(kvm_hyp_vector) = (unsigned long)vector; +} + static void cpu_hyp_reinit(void) { kvm_init_host_cpu_context(&this_cpu_ptr_hyp_sym(kvm_host_data)->host_ctxt); cpu_hyp_reset(); - - *this_cpu_ptr_hyp_sym(kvm_hyp_vector) = (unsigned long)kvm_get_hyp_vector(); + cpu_set_hyp_vector(); if (is_kernel_in_hyp_mode()) kvm_timer_init_vhe(); @@ -1439,7 +1532,8 @@ static void _kvm_arch_hardware_disable(void *discard) void kvm_arch_hardware_disable(void) { - _kvm_arch_hardware_disable(NULL); + if (!is_protected_kvm_enabled()) + _kvm_arch_hardware_disable(NULL); } #ifdef CONFIG_CPU_PM @@ -1482,11 +1576,13 @@ static struct notifier_block hyp_init_cpu_pm_nb = { static void __init hyp_cpu_pm_init(void) { - cpu_pm_register_notifier(&hyp_init_cpu_pm_nb); + if (!is_protected_kvm_enabled()) + cpu_pm_register_notifier(&hyp_init_cpu_pm_nb); } static void __init hyp_cpu_pm_exit(void) { - cpu_pm_unregister_notifier(&hyp_init_cpu_pm_nb); + if (!is_protected_kvm_enabled()) + cpu_pm_unregister_notifier(&hyp_init_cpu_pm_nb); } #else static inline void hyp_cpu_pm_init(void) @@ -1497,6 +1593,36 @@ static inline void hyp_cpu_pm_exit(void) } #endif +static void init_cpu_logical_map(void) +{ + unsigned int cpu; + + /* + * Copy the MPIDR <-> logical CPU ID mapping to hyp. + * Only copy the set of online CPUs whose features have been chacked + * against the finalized system capabilities. The hypervisor will not + * allow any other CPUs from the `possible` set to boot. + */ + for_each_online_cpu(cpu) + kvm_nvhe_sym(__cpu_logical_map)[cpu] = cpu_logical_map(cpu); +} + +static bool init_psci_relay(void) +{ + /* + * If PSCI has not been initialized, protected KVM cannot install + * itself on newly booted CPUs. + */ + if (!psci_ops.get_version) { + kvm_err("Cannot initialize protected mode without PSCI\n"); + return false; + } + + kvm_nvhe_sym(kvm_host_psci_version) = psci_ops.get_version(); + kvm_nvhe_sym(kvm_host_psci_0_1_function_ids) = get_psci_0_1_function_ids(); + return true; +} + static int init_common_resources(void) { return kvm_set_ipa_limit(); @@ -1541,10 +1667,11 @@ static int init_subsystems(void) goto out; kvm_perf_init(); - kvm_coproc_table_init(); + kvm_sys_reg_table_init(); out: - on_each_cpu(_kvm_arch_hardware_disable, NULL, 1); + if (err || !is_protected_kvm_enabled()) + on_each_cpu(_kvm_arch_hardware_disable, NULL, 1); return err; } @@ -1618,6 +1745,14 @@ static int init_hyp_mode(void) goto out_err; } + err = create_hyp_mappings(kvm_ksym_ref(__hyp_data_ro_after_init_start), + kvm_ksym_ref(__hyp_data_ro_after_init_end), + PAGE_HYP_RO); + if (err) { + kvm_err("Cannot map .hyp.data..ro_after_init section\n"); + goto out_err; + } + err = create_hyp_mappings(kvm_ksym_ref(__start_rodata), kvm_ksym_ref(__end_rodata), PAGE_HYP_RO); if (err) { @@ -1632,12 +1767,6 @@ static int init_hyp_mode(void) goto out_err; } - err = kvm_map_vectors(); - if (err) { - kvm_err("Cannot map vectors\n"); - goto out_err; - } - /* * Map the Hyp stack pages */ @@ -1667,6 +1796,13 @@ static int init_hyp_mode(void) } } + if (is_protected_kvm_enabled()) { + init_cpu_logical_map(); + + if (!init_psci_relay()) + goto out_err; + } + return 0; out_err: @@ -1781,14 +1917,24 @@ int kvm_arch_init(void *opaque) goto out_err; } + err = kvm_init_vector_slots(); + if (err) { + kvm_err("Cannot initialise vector slots\n"); + goto out_err; + } + err = init_subsystems(); if (err) goto out_hyp; - if (in_hyp_mode) + if (is_protected_kvm_enabled()) { + static_branch_enable(&kvm_protected_mode_initialized); + kvm_info("Protected nVHE mode initialized successfully\n"); + } else if (in_hyp_mode) { kvm_info("VHE mode initialized successfully\n"); - else + } else { kvm_info("Hyp mode initialized successfully\n"); + } return 0; @@ -1806,6 +1952,25 @@ void kvm_arch_exit(void) kvm_perf_teardown(); } +static int __init early_kvm_mode_cfg(char *arg) +{ + if (!arg) + return -EINVAL; + + if (strcmp(arg, "protected") == 0) { + kvm_mode = KVM_MODE_PROTECTED; + return 0; + } + + return -EINVAL; +} +early_param("kvm-arm.mode", early_kvm_mode_cfg); + +enum kvm_mode kvm_get_mode(void) +{ + return kvm_mode; +} + static int arm_init(void) { int rc = kvm_init(NULL, sizeof(struct kvm_vcpu), 0, THIS_MODULE); diff --git a/arch/arm64/kvm/guest.c b/arch/arm64/kvm/guest.c index dfb5218137ca..9bbd30e62799 100644 --- a/arch/arm64/kvm/guest.c +++ b/arch/arm64/kvm/guest.c @@ -24,7 +24,6 @@ #include <asm/fpsimd.h> #include <asm/kvm.h> #include <asm/kvm_emulate.h> -#include <asm/kvm_coproc.h> #include <asm/sigcontext.h> #include "trace.h" @@ -252,10 +251,32 @@ static int set_core_reg(struct kvm_vcpu *vcpu, const struct kvm_one_reg *reg) memcpy(addr, valp, KVM_REG_SIZE(reg->id)); if (*vcpu_cpsr(vcpu) & PSR_MODE32_BIT) { - int i; + int i, nr_reg; + + switch (*vcpu_cpsr(vcpu)) { + /* + * Either we are dealing with user mode, and only the + * first 15 registers (+ PC) must be narrowed to 32bit. + * AArch32 r0-r14 conveniently map to AArch64 x0-x14. + */ + case PSR_AA32_MODE_USR: + case PSR_AA32_MODE_SYS: + nr_reg = 15; + break; + + /* + * Otherwide, this is a priviledged mode, and *all* the + * registers must be narrowed to 32bit. + */ + default: + nr_reg = 31; + break; + } + + for (i = 0; i < nr_reg; i++) + vcpu_set_reg(vcpu, i, (u32)vcpu_get_reg(vcpu, i)); - for (i = 0; i < 16; i++) - *vcpu_reg32(vcpu, i) = (u32)*vcpu_reg32(vcpu, i); + *vcpu_pc(vcpu) = (u32)*vcpu_pc(vcpu); } out: return err; diff --git a/arch/arm64/kvm/handle_exit.c b/arch/arm64/kvm/handle_exit.c index 5d690d60ccad..cebe39f3b1b6 100644 --- a/arch/arm64/kvm/handle_exit.c +++ b/arch/arm64/kvm/handle_exit.c @@ -14,7 +14,6 @@ #include <asm/esr.h> #include <asm/exception.h> #include <asm/kvm_asm.h> -#include <asm/kvm_coproc.h> #include <asm/kvm_emulate.h> #include <asm/kvm_mmu.h> #include <asm/debug-monitors.h> @@ -61,7 +60,7 @@ static int handle_smc(struct kvm_vcpu *vcpu) * otherwise return to the same address... */ vcpu_set_reg(vcpu, 0, ~0UL); - kvm_skip_instr(vcpu, kvm_vcpu_trap_il_is32bit(vcpu)); + kvm_incr_pc(vcpu); return 1; } @@ -100,7 +99,7 @@ static int kvm_handle_wfx(struct kvm_vcpu *vcpu) kvm_clear_request(KVM_REQ_UNHALT, vcpu); } - kvm_skip_instr(vcpu, kvm_vcpu_trap_il_is32bit(vcpu)); + kvm_incr_pc(vcpu); return 1; } @@ -221,7 +220,7 @@ static int handle_trap_exceptions(struct kvm_vcpu *vcpu) * that fail their condition code check" */ if (!kvm_condition_valid(vcpu)) { - kvm_skip_instr(vcpu, kvm_vcpu_trap_il_is32bit(vcpu)); + kvm_incr_pc(vcpu); handled = 1; } else { exit_handle_fn exit_handler; @@ -241,23 +240,6 @@ int handle_exit(struct kvm_vcpu *vcpu, int exception_index) { struct kvm_run *run = vcpu->run; - if (ARM_SERROR_PENDING(exception_index)) { - u8 esr_ec = ESR_ELx_EC(kvm_vcpu_get_esr(vcpu)); - - /* - * HVC/SMC already have an adjusted PC, which we need - * to correct in order to return to after having - * injected the SError. - */ - if (esr_ec == ESR_ELx_EC_HVC32 || esr_ec == ESR_ELx_EC_HVC64 || - esr_ec == ESR_ELx_EC_SMC32 || esr_ec == ESR_ELx_EC_SMC64) { - u32 adj = kvm_vcpu_trap_il_is32bit(vcpu) ? 4 : 2; - *vcpu_pc(vcpu) -= adj; - } - - return 1; - } - exception_index = ARM_EXCEPTION_CODE(exception_index); switch (exception_index) { diff --git a/arch/arm64/kvm/hyp/Makefile b/arch/arm64/kvm/hyp/Makefile index 4a81eddabcd8..687598e41b21 100644 --- a/arch/arm64/kvm/hyp/Makefile +++ b/arch/arm64/kvm/hyp/Makefile @@ -10,4 +10,4 @@ subdir-ccflags-y := -I$(incdir) \ -DDISABLE_BRANCH_PROFILING \ $(DISABLE_STACKLEAK_PLUGIN) -obj-$(CONFIG_KVM) += vhe/ nvhe/ pgtable.o smccc_wa.o +obj-$(CONFIG_KVM) += vhe/ nvhe/ pgtable.o diff --git a/arch/arm64/kvm/hyp/aarch32.c b/arch/arm64/kvm/hyp/aarch32.c index ae56d8a4b382..f98cbe2626a1 100644 --- a/arch/arm64/kvm/hyp/aarch32.c +++ b/arch/arm64/kvm/hyp/aarch32.c @@ -123,13 +123,13 @@ static void kvm_adjust_itstate(struct kvm_vcpu *vcpu) * kvm_skip_instr - skip a trapped instruction and proceed to the next * @vcpu: The vcpu pointer */ -void kvm_skip_instr32(struct kvm_vcpu *vcpu, bool is_wide_instr) +void kvm_skip_instr32(struct kvm_vcpu *vcpu) { u32 pc = *vcpu_pc(vcpu); bool is_thumb; is_thumb = !!(*vcpu_cpsr(vcpu) & PSR_AA32_T_BIT); - if (is_thumb && !is_wide_instr) + if (is_thumb && !kvm_vcpu_trap_il_is32bit(vcpu)) pc += 2; else pc += 4; diff --git a/arch/arm64/kvm/hyp/exception.c b/arch/arm64/kvm/hyp/exception.c new file mode 100644 index 000000000000..73629094f903 --- /dev/null +++ b/arch/arm64/kvm/hyp/exception.c @@ -0,0 +1,331 @@ +// SPDX-License-Identifier: GPL-2.0-only +/* + * Fault injection for both 32 and 64bit guests. + * + * Copyright (C) 2012,2013 - ARM Ltd + * Author: Marc Zyngier <marc.zyngier@arm.com> + * + * Based on arch/arm/kvm/emulate.c + * Copyright (C) 2012 - Virtual Open Systems and Columbia University + * Author: Christoffer Dall <c.dall@virtualopensystems.com> + */ + +#include <hyp/adjust_pc.h> +#include <linux/kvm_host.h> +#include <asm/kvm_emulate.h> + +#if !defined (__KVM_NVHE_HYPERVISOR__) && !defined (__KVM_VHE_HYPERVISOR__) +#error Hypervisor code only! +#endif + +static inline u64 __vcpu_read_sys_reg(const struct kvm_vcpu *vcpu, int reg) +{ + u64 val; + + if (__vcpu_read_sys_reg_from_cpu(reg, &val)) + return val; + + return __vcpu_sys_reg(vcpu, reg); +} + +static inline void __vcpu_write_sys_reg(struct kvm_vcpu *vcpu, u64 val, int reg) +{ + if (__vcpu_write_sys_reg_to_cpu(val, reg)) + return; + + __vcpu_sys_reg(vcpu, reg) = val; +} + +static void __vcpu_write_spsr(struct kvm_vcpu *vcpu, u64 val) +{ + write_sysreg_el1(val, SYS_SPSR); +} + +static void __vcpu_write_spsr_abt(struct kvm_vcpu *vcpu, u64 val) +{ + if (has_vhe()) + write_sysreg(val, spsr_abt); + else + vcpu->arch.ctxt.spsr_abt = val; +} + +static void __vcpu_write_spsr_und(struct kvm_vcpu *vcpu, u64 val) +{ + if (has_vhe()) + write_sysreg(val, spsr_und); + else + vcpu->arch.ctxt.spsr_und = val; +} + +/* + * This performs the exception entry at a given EL (@target_mode), stashing PC + * and PSTATE into ELR and SPSR respectively, and compute the new PC/PSTATE. + * The EL passed to this function *must* be a non-secure, privileged mode with + * bit 0 being set (PSTATE.SP == 1). + * + * When an exception is taken, most PSTATE fields are left unchanged in the + * handler. However, some are explicitly overridden (e.g. M[4:0]). Luckily all + * of the inherited bits have the same position in the AArch64/AArch32 SPSR_ELx + * layouts, so we don't need to shuffle these for exceptions from AArch32 EL0. + * + * For the SPSR_ELx layout for AArch64, see ARM DDI 0487E.a page C5-429. + * For the SPSR_ELx layout for AArch32, see ARM DDI 0487E.a page C5-426. + * + * Here we manipulate the fields in order of the AArch64 SPSR_ELx layout, from + * MSB to LSB. + */ +static void enter_exception64(struct kvm_vcpu *vcpu, unsigned long target_mode, + enum exception_type type) +{ + unsigned long sctlr, vbar, old, new, mode; + u64 exc_offset; + + mode = *vcpu_cpsr(vcpu) & (PSR_MODE_MASK | PSR_MODE32_BIT); + + if (mode == target_mode) + exc_offset = CURRENT_EL_SP_ELx_VECTOR; + else if ((mode | PSR_MODE_THREAD_BIT) == target_mode) + exc_offset = CURRENT_EL_SP_EL0_VECTOR; + else if (!(mode & PSR_MODE32_BIT)) + exc_offset = LOWER_EL_AArch64_VECTOR; + else + exc_offset = LOWER_EL_AArch32_VECTOR; + + switch (target_mode) { + case PSR_MODE_EL1h: + vbar = __vcpu_read_sys_reg(vcpu, VBAR_EL1); + sctlr = __vcpu_read_sys_reg(vcpu, SCTLR_EL1); + __vcpu_write_sys_reg(vcpu, *vcpu_pc(vcpu), ELR_EL1); + break; + default: + /* Don't do that */ + BUG(); + } + + *vcpu_pc(vcpu) = vbar + exc_offset + type; + + old = *vcpu_cpsr(vcpu); + new = 0; + + new |= (old & PSR_N_BIT); + new |= (old & PSR_Z_BIT); + new |= (old & PSR_C_BIT); + new |= (old & PSR_V_BIT); + + // TODO: TCO (if/when ARMv8.5-MemTag is exposed to guests) + + new |= (old & PSR_DIT_BIT); + + // PSTATE.UAO is set to zero upon any exception to AArch64 + // See ARM DDI 0487E.a, page D5-2579. + + // PSTATE.PAN is unchanged unless SCTLR_ELx.SPAN == 0b0 + // SCTLR_ELx.SPAN is RES1 when ARMv8.1-PAN is not implemented + // See ARM DDI 0487E.a, page D5-2578. + new |= (old & PSR_PAN_BIT); + if (!(sctlr & SCTLR_EL1_SPAN)) + new |= PSR_PAN_BIT; + + // PSTATE.SS is set to zero upon any exception to AArch64 + // See ARM DDI 0487E.a, page D2-2452. + + // PSTATE.IL is set to zero upon any exception to AArch64 + // See ARM DDI 0487E.a, page D1-2306. + + // PSTATE.SSBS is set to SCTLR_ELx.DSSBS upon any exception to AArch64 + // See ARM DDI 0487E.a, page D13-3258 + if (sctlr & SCTLR_ELx_DSSBS) + new |= PSR_SSBS_BIT; + + // PSTATE.BTYPE is set to zero upon any exception to AArch64 + // See ARM DDI 0487E.a, pages D1-2293 to D1-2294. + + new |= PSR_D_BIT; + new |= PSR_A_BIT; + new |= PSR_I_BIT; + new |= PSR_F_BIT; + + new |= target_mode; + + *vcpu_cpsr(vcpu) = new; + __vcpu_write_spsr(vcpu, old); +} + +/* + * When an exception is taken, most CPSR fields are left unchanged in the + * handler. However, some are explicitly overridden (e.g. M[4:0]). + * + * The SPSR/SPSR_ELx layouts differ, and the below is intended to work with + * either format. Note: SPSR.J bit doesn't exist in SPSR_ELx, but this bit was + * obsoleted by the ARMv7 virtualization extensions and is RES0. + * + * For the SPSR layout seen from AArch32, see: + * - ARM DDI 0406C.d, page B1-1148 + * - ARM DDI 0487E.a, page G8-6264 + * + * For the SPSR_ELx layout for AArch32 seen from AArch64, see: + * - ARM DDI 0487E.a, page C5-426 + * + * Here we manipulate the fields in order of the AArch32 SPSR_ELx layout, from + * MSB to LSB. + */ +static unsigned long get_except32_cpsr(struct kvm_vcpu *vcpu, u32 mode) +{ + u32 sctlr = __vcpu_read_sys_reg(vcpu, SCTLR_EL1); + unsigned long old, new; + + old = *vcpu_cpsr(vcpu); + new = 0; + + new |= (old & PSR_AA32_N_BIT); + new |= (old & PSR_AA32_Z_BIT); + new |= (old & PSR_AA32_C_BIT); + new |= (old & PSR_AA32_V_BIT); + new |= (old & PSR_AA32_Q_BIT); + + // CPSR.IT[7:0] are set to zero upon any exception + // See ARM DDI 0487E.a, section G1.12.3 + // See ARM DDI 0406C.d, section B1.8.3 + + new |= (old & PSR_AA32_DIT_BIT); + + // CPSR.SSBS is set to SCTLR.DSSBS upon any exception + // See ARM DDI 0487E.a, page G8-6244 + if (sctlr & BIT(31)) + new |= PSR_AA32_SSBS_BIT; + + // CPSR.PAN is unchanged unless SCTLR.SPAN == 0b0 + // SCTLR.SPAN is RES1 when ARMv8.1-PAN is not implemented + // See ARM DDI 0487E.a, page G8-6246 + new |= (old & PSR_AA32_PAN_BIT); + if (!(sctlr & BIT(23))) + new |= PSR_AA32_PAN_BIT; + + // SS does not exist in AArch32, so ignore + + // CPSR.IL is set to zero upon any exception + // See ARM DDI 0487E.a, page G1-5527 + + new |= (old & PSR_AA32_GE_MASK); + + // CPSR.IT[7:0] are set to zero upon any exception + // See prior comment above + + // CPSR.E is set to SCTLR.EE upon any exception + // See ARM DDI 0487E.a, page G8-6245 + // See ARM DDI 0406C.d, page B4-1701 + if (sctlr & BIT(25)) + new |= PSR_AA32_E_BIT; + + // CPSR.A is unchanged upon an exception to Undefined, Supervisor + // CPSR.A is set upon an exception to other modes + // See ARM DDI 0487E.a, pages G1-5515 to G1-5516 + // See ARM DDI 0406C.d, page B1-1182 + new |= (old & PSR_AA32_A_BIT); + if (mode != PSR_AA32_MODE_UND && mode != PSR_AA32_MODE_SVC) + new |= PSR_AA32_A_BIT; + + // CPSR.I is set upon any exception + // See ARM DDI 0487E.a, pages G1-5515 to G1-5516 + // See ARM DDI 0406C.d, page B1-1182 + new |= PSR_AA32_I_BIT; + + // CPSR.F is set upon an exception to FIQ + // CPSR.F is unchanged upon an exception to other modes + // See ARM DDI 0487E.a, pages G1-5515 to G1-5516 + // See ARM DDI 0406C.d, page B1-1182 + new |= (old & PSR_AA32_F_BIT); + if (mode == PSR_AA32_MODE_FIQ) + new |= PSR_AA32_F_BIT; + + // CPSR.T is set to SCTLR.TE upon any exception + // See ARM DDI 0487E.a, page G8-5514 + // See ARM DDI 0406C.d, page B1-1181 + if (sctlr & BIT(30)) + new |= PSR_AA32_T_BIT; + + new |= mode; + + return new; +} + +/* + * Table taken from ARMv8 ARM DDI0487B-B, table G1-10. + */ +static const u8 return_offsets[8][2] = { + [0] = { 0, 0 }, /* Reset, unused */ + [1] = { 4, 2 }, /* Undefined */ + [2] = { 0, 0 }, /* SVC, unused */ + [3] = { 4, 4 }, /* Prefetch abort */ + [4] = { 8, 8 }, /* Data abort */ + [5] = { 0, 0 }, /* HVC, unused */ + [6] = { 4, 4 }, /* IRQ, unused */ + [7] = { 4, 4 }, /* FIQ, unused */ +}; + +static void enter_exception32(struct kvm_vcpu *vcpu, u32 mode, u32 vect_offset) +{ + unsigned long spsr = *vcpu_cpsr(vcpu); + bool is_thumb = (spsr & PSR_AA32_T_BIT); + u32 sctlr = __vcpu_read_sys_reg(vcpu, SCTLR_EL1); + u32 return_address; + + *vcpu_cpsr(vcpu) = get_except32_cpsr(vcpu, mode); + return_address = *vcpu_pc(vcpu); + return_address += return_offsets[vect_offset >> 2][is_thumb]; + + /* KVM only enters the ABT and UND modes, so only deal with those */ + switch(mode) { + case PSR_AA32_MODE_ABT: + __vcpu_write_spsr_abt(vcpu, host_spsr_to_spsr32(spsr)); + vcpu_gp_regs(vcpu)->compat_lr_abt = return_address; + break; + + case PSR_AA32_MODE_UND: + __vcpu_write_spsr_und(vcpu, host_spsr_to_spsr32(spsr)); + vcpu_gp_regs(vcpu)->compat_lr_und = return_address; + break; + } + + /* Branch to exception vector */ + if (sctlr & (1 << 13)) + vect_offset += 0xffff0000; + else /* always have security exceptions */ + vect_offset += __vcpu_read_sys_reg(vcpu, VBAR_EL1); + + *vcpu_pc(vcpu) = vect_offset; +} + +void kvm_inject_exception(struct kvm_vcpu *vcpu) +{ + if (vcpu_el1_is_32bit(vcpu)) { + switch (vcpu->arch.flags & KVM_ARM64_EXCEPT_MASK) { + case KVM_ARM64_EXCEPT_AA32_UND: + enter_exception32(vcpu, PSR_AA32_MODE_UND, 4); + break; + case KVM_ARM64_EXCEPT_AA32_IABT: + enter_exception32(vcpu, PSR_AA32_MODE_ABT, 12); + break; + case KVM_ARM64_EXCEPT_AA32_DABT: + enter_exception32(vcpu, PSR_AA32_MODE_ABT, 16); + break; + default: + /* Err... */ + break; + } + } else { + switch (vcpu->arch.flags & KVM_ARM64_EXCEPT_MASK) { + case (KVM_ARM64_EXCEPT_AA64_ELx_SYNC | + KVM_ARM64_EXCEPT_AA64_EL1): + enter_exception64(vcpu, PSR_MODE_EL1h, except_type_sync); + break; + default: + /* + * Only EL1_SYNC makes sense so far, EL2_{SYNC,IRQ} + * will be implemented at some point. Everything + * else gets silently ignored. + */ + break; + } + } +} diff --git a/arch/arm64/kvm/hyp/hyp-entry.S b/arch/arm64/kvm/hyp/hyp-entry.S index 0a5b36eb54b3..d179056e1af8 100644 --- a/arch/arm64/kvm/hyp/hyp-entry.S +++ b/arch/arm64/kvm/hyp/hyp-entry.S @@ -13,6 +13,7 @@ #include <asm/kvm_arm.h> #include <asm/kvm_asm.h> #include <asm/mmu.h> +#include <asm/spectre.h> .macro save_caller_saved_regs_vect /* x0 and x1 were saved in the vector entry */ @@ -187,52 +188,60 @@ SYM_CODE_START(__kvm_hyp_vector) valid_vect el1_error // Error 32-bit EL1 SYM_CODE_END(__kvm_hyp_vector) -.macro hyp_ventry - .align 7 +.macro spectrev2_smccc_wa1_smc + sub sp, sp, #(8 * 4) + stp x2, x3, [sp, #(8 * 0)] + stp x0, x1, [sp, #(8 * 2)] + mov w0, #ARM_SMCCC_ARCH_WORKAROUND_1 + smc #0 + ldp x2, x3, [sp, #(8 * 0)] + add sp, sp, #(8 * 2) +.endm + +.macro hyp_ventry indirect, spectrev2 + .align 7 1: esb - .rept 26 - nop - .endr -/* - * The default sequence is to directly branch to the KVM vectors, - * using the computed offset. This applies for VHE as well as - * !ARM64_HARDEN_EL2_VECTORS. The first vector must always run the preamble. - * - * For ARM64_HARDEN_EL2_VECTORS configurations, this gets replaced - * with: - * - * stp x0, x1, [sp, #-16]! - * movz x0, #(addr & 0xffff) - * movk x0, #((addr >> 16) & 0xffff), lsl #16 - * movk x0, #((addr >> 32) & 0xffff), lsl #32 - * br x0 - * - * Where: - * addr = kern_hyp_va(__kvm_hyp_vector) + vector-offset + KVM_VECTOR_PREAMBLE. - * See kvm_patch_vector_branch for details. - */ -alternative_cb kvm_patch_vector_branch + .if \spectrev2 != 0 + spectrev2_smccc_wa1_smc + .else stp x0, x1, [sp, #-16]! - b __kvm_hyp_vector + (1b - 0b + KVM_VECTOR_PREAMBLE) + .endif + .if \indirect != 0 + alternative_cb kvm_patch_vector_branch + /* + * For ARM64_SPECTRE_V3A configurations, these NOPs get replaced with: + * + * movz x0, #(addr & 0xffff) + * movk x0, #((addr >> 16) & 0xffff), lsl #16 + * movk x0, #((addr >> 32) & 0xffff), lsl #32 + * br x0 + * + * Where: + * addr = kern_hyp_va(__kvm_hyp_vector) + vector-offset + KVM_VECTOR_PREAMBLE. + * See kvm_patch_vector_branch for details. + */ nop nop nop -alternative_cb_end + nop + alternative_cb_end + .endif + b __kvm_hyp_vector + (1b - 0b + KVM_VECTOR_PREAMBLE) .endm -.macro generate_vectors +.macro generate_vectors indirect, spectrev2 0: .rept 16 - hyp_ventry + hyp_ventry \indirect, \spectrev2 .endr .org 0b + SZ_2K // Safety measure .endm .align 11 SYM_CODE_START(__bp_harden_hyp_vecs) - .rept BP_HARDEN_EL2_SLOTS - generate_vectors - .endr + generate_vectors indirect = 0, spectrev2 = 1 // HYP_VECTOR_SPECTRE_DIRECT + generate_vectors indirect = 1, spectrev2 = 0 // HYP_VECTOR_INDIRECT + generate_vectors indirect = 1, spectrev2 = 1 // HYP_VECTOR_SPECTRE_INDIRECT 1: .org __bp_harden_hyp_vecs + __BP_HARDEN_HYP_VECS_SZ .org 1b SYM_CODE_END(__bp_harden_hyp_vecs) diff --git a/arch/arm64/kvm/hyp/include/hyp/adjust_pc.h b/arch/arm64/kvm/hyp/include/hyp/adjust_pc.h new file mode 100644 index 000000000000..b1f60923a8fe --- /dev/null +++ b/arch/arm64/kvm/hyp/include/hyp/adjust_pc.h @@ -0,0 +1,62 @@ +// SPDX-License-Identifier: GPL-2.0-only +/* + * Guest PC manipulation helpers + * + * Copyright (C) 2012,2013 - ARM Ltd + * Copyright (C) 2020 - Google LLC + * Author: Marc Zyngier <maz@kernel.org> + */ + +#ifndef __ARM64_KVM_HYP_ADJUST_PC_H__ +#define __ARM64_KVM_HYP_ADJUST_PC_H__ + +#include <asm/kvm_emulate.h> +#include <asm/kvm_host.h> + +void kvm_inject_exception(struct kvm_vcpu *vcpu); + +static inline void kvm_skip_instr(struct kvm_vcpu *vcpu) +{ + if (vcpu_mode_is_32bit(vcpu)) { + kvm_skip_instr32(vcpu); + } else { + *vcpu_pc(vcpu) += 4; + *vcpu_cpsr(vcpu) &= ~PSR_BTYPE_MASK; + } + + /* advance the singlestep state machine */ + *vcpu_cpsr(vcpu) &= ~DBG_SPSR_SS; +} + +/* + * Skip an instruction which has been emulated at hyp while most guest sysregs + * are live. + */ +static inline void __kvm_skip_instr(struct kvm_vcpu *vcpu) +{ + *vcpu_pc(vcpu) = read_sysreg_el2(SYS_ELR); + vcpu_gp_regs(vcpu)->pstate = read_sysreg_el2(SYS_SPSR); + + kvm_skip_instr(vcpu); + + write_sysreg_el2(vcpu_gp_regs(vcpu)->pstate, SYS_SPSR); + write_sysreg_el2(*vcpu_pc(vcpu), SYS_ELR); +} + +/* + * Adjust the guest PC on entry, depending on flags provided by EL1 + * for the purpose of emulation (MMIO, sysreg) or exception injection. + */ +static inline void __adjust_pc(struct kvm_vcpu *vcpu) +{ + if (vcpu->arch.flags & KVM_ARM64_PENDING_EXCEPTION) { + kvm_inject_exception(vcpu); + vcpu->arch.flags &= ~(KVM_ARM64_PENDING_EXCEPTION | + KVM_ARM64_EXCEPT_MASK); + } else if (vcpu->arch.flags & KVM_ARM64_INCREMENT_PC) { + kvm_skip_instr(vcpu); + vcpu->arch.flags &= ~KVM_ARM64_INCREMENT_PC; + } +} + +#endif diff --git a/arch/arm64/kvm/hyp/include/hyp/switch.h b/arch/arm64/kvm/hyp/include/hyp/switch.h index 1f875a8f20c4..84473574c2e7 100644 --- a/arch/arm64/kvm/hyp/include/hyp/switch.h +++ b/arch/arm64/kvm/hyp/include/hyp/switch.h @@ -7,6 +7,8 @@ #ifndef __ARM64_KVM_HYP_SWITCH_H__ #define __ARM64_KVM_HYP_SWITCH_H__ +#include <hyp/adjust_pc.h> + #include <linux/arm-smccc.h> #include <linux/kvm_host.h> #include <linux/types.h> @@ -409,6 +411,21 @@ static inline bool fixup_guest_exit(struct kvm_vcpu *vcpu, u64 *exit_code) if (ARM_EXCEPTION_CODE(*exit_code) != ARM_EXCEPTION_IRQ) vcpu->arch.fault.esr_el2 = read_sysreg_el2(SYS_ESR); + if (ARM_SERROR_PENDING(*exit_code)) { + u8 esr_ec = kvm_vcpu_trap_get_class(vcpu); + + /* + * HVC already have an adjusted PC, which we need to + * correct in order to return to after having injected + * the SError. + * + * SMC, on the other hand, is *trapped*, meaning its + * preferred return address is the SMC itself. + */ + if (esr_ec == ESR_ELx_EC_HVC32 || esr_ec == ESR_ELx_EC_HVC64) + write_sysreg_el2(read_sysreg_el2(SYS_ELR) - 4, SYS_ELR); + } + /* * We're using the raw exception code in order to only process * the trap if no SError is pending. We will come back to the diff --git a/arch/arm64/kvm/hyp/include/nvhe/trap_handler.h b/arch/arm64/kvm/hyp/include/nvhe/trap_handler.h new file mode 100644 index 000000000000..1e6d995968a1 --- /dev/null +++ b/arch/arm64/kvm/hyp/include/nvhe/trap_handler.h @@ -0,0 +1,18 @@ +/* SPDX-License-Identifier: GPL-2.0-only */ +/* + * Trap handler helpers. + * + * Copyright (C) 2020 - Google LLC + * Author: Marc Zyngier <maz@kernel.org> + */ + +#ifndef __ARM64_KVM_NVHE_TRAP_HANDLER_H__ +#define __ARM64_KVM_NVHE_TRAP_HANDLER_H__ + +#include <asm/kvm_host.h> + +#define cpu_reg(ctxt, r) (ctxt)->regs.regs[r] +#define DECLARE_REG(type, name, ctxt, reg) \ + type name = (type)cpu_reg(ctxt, (reg)) + +#endif /* __ARM64_KVM_NVHE_TRAP_HANDLER_H__ */ diff --git a/arch/arm64/kvm/hyp/nvhe/Makefile b/arch/arm64/kvm/hyp/nvhe/Makefile index ddde15fe85f2..1f1e351c5fe2 100644 --- a/arch/arm64/kvm/hyp/nvhe/Makefile +++ b/arch/arm64/kvm/hyp/nvhe/Makefile @@ -6,9 +6,10 @@ asflags-y := -D__KVM_NVHE_HYPERVISOR__ ccflags-y := -D__KVM_NVHE_HYPERVISOR__ -obj-y := timer-sr.o sysreg-sr.o debug-sr.o switch.o tlb.o hyp-init.o host.o hyp-main.o +obj-y := timer-sr.o sysreg-sr.o debug-sr.o switch.o tlb.o hyp-init.o host.o \ + hyp-main.o hyp-smp.o psci-relay.o obj-y += ../vgic-v3-sr.o ../aarch32.o ../vgic-v2-cpuif-proxy.o ../entry.o \ - ../fpsimd.o ../hyp-entry.o + ../fpsimd.o ../hyp-entry.o ../exception.o ## ## Build rules for compiling nVHE hyp code diff --git a/arch/arm64/kvm/hyp/nvhe/host.S b/arch/arm64/kvm/hyp/nvhe/host.S index ed27f06a31ba..a820dfdc9c25 100644 --- a/arch/arm64/kvm/hyp/nvhe/host.S +++ b/arch/arm64/kvm/hyp/nvhe/host.S @@ -13,8 +13,6 @@ .text SYM_FUNC_START(__host_exit) - stp x0, x1, [sp, #-16]! - get_host_ctxt x0, x1 /* Store the host regs x2 and x3 */ @@ -41,6 +39,7 @@ SYM_FUNC_START(__host_exit) bl handle_trap /* Restore host regs x0-x17 */ +__host_enter_restore_full: ldp x0, x1, [x29, #CPU_XREG_OFFSET(0)] ldp x2, x3, [x29, #CPU_XREG_OFFSET(2)] ldp x4, x5, [x29, #CPU_XREG_OFFSET(4)] @@ -64,6 +63,14 @@ __host_enter_without_restoring: SYM_FUNC_END(__host_exit) /* + * void __noreturn __host_enter(struct kvm_cpu_context *host_ctxt); + */ +SYM_FUNC_START(__host_enter) + mov x29, x0 + b __host_enter_restore_full +SYM_FUNC_END(__host_enter) + +/* * void __noreturn __hyp_do_panic(bool restore_host, u64 spsr, u64 elr, u64 par); */ SYM_FUNC_START(__hyp_do_panic) @@ -99,13 +106,15 @@ SYM_FUNC_END(__hyp_do_panic) mrs x0, esr_el2 lsr x0, x0, #ESR_ELx_EC_SHIFT cmp x0, #ESR_ELx_EC_HVC64 - ldp x0, x1, [sp], #16 b.ne __host_exit + ldp x0, x1, [sp] // Don't fixup the stack yet + /* Check for a stub HVC call */ cmp x0, #HVC_STUB_HCALL_NR b.hs __host_exit + add sp, sp, #16 /* * Compute the idmap address of __kvm_handle_stub_hvc and * jump there. Since we use kimage_voffset, do not use the @@ -115,10 +124,7 @@ SYM_FUNC_END(__hyp_do_panic) * Preserve x0-x4, which may contain stub parameters. */ ldr x5, =__kvm_handle_stub_hvc - ldr_l x6, kimage_voffset - - /* x5 = __pa(x5) */ - sub x5, x5, x6 + kimg_pa x5, x6 br x5 .L__vect_end\@: .if ((.L__vect_end\@ - .L__vect_start\@) > 0x80) @@ -183,3 +189,41 @@ SYM_CODE_START(__kvm_hyp_host_vector) invalid_host_el1_vect // FIQ 32-bit EL1 invalid_host_el1_vect // Error 32-bit EL1 SYM_CODE_END(__kvm_hyp_host_vector) + +/* + * Forward SMC with arguments in struct kvm_cpu_context, and + * store the result into the same struct. Assumes SMCCC 1.2 or older. + * + * x0: struct kvm_cpu_context* + */ +SYM_CODE_START(__kvm_hyp_host_forward_smc) + /* + * Use x18 to keep the pointer to the host context because + * x18 is callee-saved in SMCCC but not in AAPCS64. + */ + mov x18, x0 + + ldp x0, x1, [x18, #CPU_XREG_OFFSET(0)] + ldp x2, x3, [x18, #CPU_XREG_OFFSET(2)] + ldp x4, x5, [x18, #CPU_XREG_OFFSET(4)] + ldp x6, x7, [x18, #CPU_XREG_OFFSET(6)] + ldp x8, x9, [x18, #CPU_XREG_OFFSET(8)] + ldp x10, x11, [x18, #CPU_XREG_OFFSET(10)] + ldp x12, x13, [x18, #CPU_XREG_OFFSET(12)] + ldp x14, x15, [x18, #CPU_XREG_OFFSET(14)] + ldp x16, x17, [x18, #CPU_XREG_OFFSET(16)] + + smc #0 + + stp x0, x1, [x18, #CPU_XREG_OFFSET(0)] + stp x2, x3, [x18, #CPU_XREG_OFFSET(2)] + stp x4, x5, [x18, #CPU_XREG_OFFSET(4)] + stp x6, x7, [x18, #CPU_XREG_OFFSET(6)] + stp x8, x9, [x18, #CPU_XREG_OFFSET(8)] + stp x10, x11, [x18, #CPU_XREG_OFFSET(10)] + stp x12, x13, [x18, #CPU_XREG_OFFSET(12)] + stp x14, x15, [x18, #CPU_XREG_OFFSET(14)] + stp x16, x17, [x18, #CPU_XREG_OFFSET(16)] + + ret +SYM_CODE_END(__kvm_hyp_host_forward_smc) diff --git a/arch/arm64/kvm/hyp/nvhe/hyp-init.S b/arch/arm64/kvm/hyp/nvhe/hyp-init.S index b11a9d7db677..31b060a44045 100644 --- a/arch/arm64/kvm/hyp/nvhe/hyp-init.S +++ b/arch/arm64/kvm/hyp/nvhe/hyp-init.S @@ -9,6 +9,7 @@ #include <asm/alternative.h> #include <asm/assembler.h> +#include <asm/el2_setup.h> #include <asm/kvm_arm.h> #include <asm/kvm_asm.h> #include <asm/kvm_mmu.h> @@ -47,10 +48,7 @@ __invalid: /* * x0: SMCCC function ID - * x1: HYP pgd - * x2: per-CPU offset - * x3: HYP stack - * x4: HYP vectors + * x1: struct kvm_nvhe_init_params PA */ __do_hyp_init: /* Check for a stub HVC call */ @@ -71,48 +69,53 @@ __do_hyp_init: mov x0, #SMCCC_RET_NOT_SUPPORTED eret -1: - /* Set tpidr_el2 for use by HYP to free a register */ - msr tpidr_el2, x2 +1: mov x0, x1 + mov x4, lr + bl ___kvm_hyp_init + mov lr, x4 - phys_to_ttbr x0, x1 -alternative_if ARM64_HAS_CNP - orr x0, x0, #TTBR_CNP_BIT + /* Hello, World! */ + mov x0, #SMCCC_RET_SUCCESS + eret +SYM_CODE_END(__kvm_hyp_init) + +/* + * Initialize the hypervisor in EL2. + * + * Only uses x0..x3 so as to not clobber callee-saved SMCCC registers + * and leave x4 for the caller. + * + * x0: struct kvm_nvhe_init_params PA + */ +SYM_CODE_START_LOCAL(___kvm_hyp_init) +alternative_if ARM64_KVM_PROTECTED_MODE + mov_q x1, HCR_HOST_NVHE_PROTECTED_FLAGS + msr hcr_el2, x1 alternative_else_nop_endif - msr ttbr0_el2, x0 - mrs x0, tcr_el1 - mov_q x1, TCR_EL2_MASK - and x0, x0, x1 - mov x1, #TCR_EL2_RES1 - orr x0, x0, x1 + ldr x1, [x0, #NVHE_INIT_TPIDR_EL2] + msr tpidr_el2, x1 - /* - * The ID map may be configured to use an extended virtual address - * range. This is only the case if system RAM is out of range for the - * currently configured page size and VA_BITS, in which case we will - * also need the extended virtual range for the HYP ID map, or we won't - * be able to enable the EL2 MMU. - * - * However, at EL2, there is only one TTBR register, and we can't switch - * between translation tables *and* update TCR_EL2.T0SZ at the same - * time. Bottom line: we need to use the extended range with *both* our - * translation tables. - * - * So use the same T0SZ value we use for the ID map. - */ - ldr_l x1, idmap_t0sz - bfi x0, x1, TCR_T0SZ_OFFSET, TCR_TxSZ_WIDTH + ldr x1, [x0, #NVHE_INIT_STACK_HYP_VA] + mov sp, x1 + + ldr x1, [x0, #NVHE_INIT_MAIR_EL2] + msr mair_el2, x1 + + ldr x1, [x0, #NVHE_INIT_PGD_PA] + phys_to_ttbr x2, x1 +alternative_if ARM64_HAS_CNP + orr x2, x2, #TTBR_CNP_BIT +alternative_else_nop_endif + msr ttbr0_el2, x2 /* * Set the PS bits in TCR_EL2. */ - tcr_compute_pa_size x0, #TCR_EL2_PS_SHIFT, x1, x2 + ldr x1, [x0, #NVHE_INIT_TCR_EL2] + tcr_compute_pa_size x1, #TCR_EL2_PS_SHIFT, x2, x3 + msr tcr_el2, x1 - msr tcr_el2, x0 - - mrs x0, mair_el1 - msr mair_el2, x0 isb /* Invalidate the stale TLBs from Bootloader */ @@ -134,14 +137,70 @@ alternative_else_nop_endif msr sctlr_el2, x0 isb - /* Set the stack and new vectors */ - mov sp, x3 - msr vbar_el2, x4 + /* Set the host vector */ + ldr x0, =__kvm_hyp_host_vector + kimg_hyp_va x0, x1 + msr vbar_el2, x0 - /* Hello, World! */ - mov x0, #SMCCC_RET_SUCCESS - eret -SYM_CODE_END(__kvm_hyp_init) + ret +SYM_CODE_END(___kvm_hyp_init) + +/* + * PSCI CPU_ON entry point + * + * x0: struct kvm_nvhe_init_params PA + */ +SYM_CODE_START(kvm_hyp_cpu_entry) + mov x1, #1 // is_cpu_on = true + b __kvm_hyp_init_cpu +SYM_CODE_END(kvm_hyp_cpu_entry) + +/* + * PSCI CPU_SUSPEND / SYSTEM_SUSPEND entry point + * + * x0: struct kvm_nvhe_init_params PA + */ +SYM_CODE_START(kvm_hyp_cpu_resume) + mov x1, #0 // is_cpu_on = false + b __kvm_hyp_init_cpu +SYM_CODE_END(kvm_hyp_cpu_resume) + +/* + * Common code for CPU entry points. Initializes EL2 state and + * installs the hypervisor before handing over to a C handler. + * + * x0: struct kvm_nvhe_init_params PA + * x1: bool is_cpu_on + */ +SYM_CODE_START_LOCAL(__kvm_hyp_init_cpu) + mov x28, x0 // Stash arguments + mov x29, x1 + + /* Check that the core was booted in EL2. */ + mrs x0, CurrentEL + cmp x0, #CurrentEL_EL2 + b.eq 2f + + /* The core booted in EL1. KVM cannot be initialized on it. */ +1: wfe + wfi + b 1b + +2: msr SPsel, #1 // We want to use SP_EL{1,2} + + /* Initialize EL2 CPU state to sane values. */ + init_el2_state nvhe // Clobbers x0..x2 + + /* Enable MMU, set vectors and stack. */ + mov x0, x28 + bl ___kvm_hyp_init // Clobbers x0..x3 + + /* Leave idmap. */ + mov x0, x29 + ldr x1, =kvm_host_psci_cpu_entry + kimg_hyp_va x1, x2 + br x1 +SYM_CODE_END(__kvm_hyp_init_cpu) SYM_CODE_START(__kvm_handle_stub_hvc) cmp x0, #HVC_SOFT_RESTART @@ -176,6 +235,11 @@ reset: msr sctlr_el2, x5 isb +alternative_if ARM64_KVM_PROTECTED_MODE + mov_q x5, HCR_HOST_NVHE_FLAGS + msr hcr_el2, x5 +alternative_else_nop_endif + /* Install stub vectors */ adr_l x5, __hyp_stub_vectors msr vbar_el2, x5 diff --git a/arch/arm64/kvm/hyp/nvhe/hyp-main.c b/arch/arm64/kvm/hyp/nvhe/hyp-main.c index e2eafe2c93af..bde658d51404 100644 --- a/arch/arm64/kvm/hyp/nvhe/hyp-main.c +++ b/arch/arm64/kvm/hyp/nvhe/hyp-main.c @@ -12,106 +12,183 @@ #include <asm/kvm_hyp.h> #include <asm/kvm_mmu.h> -#include <kvm/arm_hypercalls.h> +#include <nvhe/trap_handler.h> -static void handle_host_hcall(unsigned long func_id, - struct kvm_cpu_context *host_ctxt) +DEFINE_PER_CPU(struct kvm_nvhe_init_params, kvm_init_params); + +void __kvm_hyp_host_forward_smc(struct kvm_cpu_context *host_ctxt); + +static void handle___kvm_vcpu_run(struct kvm_cpu_context *host_ctxt) { - unsigned long ret = 0; + DECLARE_REG(struct kvm_vcpu *, vcpu, host_ctxt, 1); - switch (func_id) { - case KVM_HOST_SMCCC_FUNC(__kvm_vcpu_run): { - unsigned long r1 = host_ctxt->regs.regs[1]; - struct kvm_vcpu *vcpu = (struct kvm_vcpu *)r1; + cpu_reg(host_ctxt, 1) = __kvm_vcpu_run(kern_hyp_va(vcpu)); +} - ret = __kvm_vcpu_run(kern_hyp_va(vcpu)); - break; - } - case KVM_HOST_SMCCC_FUNC(__kvm_flush_vm_context): - __kvm_flush_vm_context(); - break; - case KVM_HOST_SMCCC_FUNC(__kvm_tlb_flush_vmid_ipa): { - unsigned long r1 = host_ctxt->regs.regs[1]; - struct kvm_s2_mmu *mmu = (struct kvm_s2_mmu *)r1; - phys_addr_t ipa = host_ctxt->regs.regs[2]; - int level = host_ctxt->regs.regs[3]; +static void handle___kvm_flush_vm_context(struct kvm_cpu_context *host_ctxt) +{ + __kvm_flush_vm_context(); +} - __kvm_tlb_flush_vmid_ipa(kern_hyp_va(mmu), ipa, level); - break; - } - case KVM_HOST_SMCCC_FUNC(__kvm_tlb_flush_vmid): { - unsigned long r1 = host_ctxt->regs.regs[1]; - struct kvm_s2_mmu *mmu = (struct kvm_s2_mmu *)r1; +static void handle___kvm_tlb_flush_vmid_ipa(struct kvm_cpu_context *host_ctxt) +{ + DECLARE_REG(struct kvm_s2_mmu *, mmu, host_ctxt, 1); + DECLARE_REG(phys_addr_t, ipa, host_ctxt, 2); + DECLARE_REG(int, level, host_ctxt, 3); - __kvm_tlb_flush_vmid(kern_hyp_va(mmu)); - break; - } - case KVM_HOST_SMCCC_FUNC(__kvm_tlb_flush_local_vmid): { - unsigned long r1 = host_ctxt->regs.regs[1]; - struct kvm_s2_mmu *mmu = (struct kvm_s2_mmu *)r1; + __kvm_tlb_flush_vmid_ipa(kern_hyp_va(mmu), ipa, level); +} - __kvm_tlb_flush_local_vmid(kern_hyp_va(mmu)); - break; - } - case KVM_HOST_SMCCC_FUNC(__kvm_timer_set_cntvoff): { - u64 cntvoff = host_ctxt->regs.regs[1]; +static void handle___kvm_tlb_flush_vmid(struct kvm_cpu_context *host_ctxt) +{ + DECLARE_REG(struct kvm_s2_mmu *, mmu, host_ctxt, 1); - __kvm_timer_set_cntvoff(cntvoff); - break; - } - case KVM_HOST_SMCCC_FUNC(__kvm_enable_ssbs): - __kvm_enable_ssbs(); - break; - case KVM_HOST_SMCCC_FUNC(__vgic_v3_get_ich_vtr_el2): - ret = __vgic_v3_get_ich_vtr_el2(); - break; - case KVM_HOST_SMCCC_FUNC(__vgic_v3_read_vmcr): - ret = __vgic_v3_read_vmcr(); - break; - case KVM_HOST_SMCCC_FUNC(__vgic_v3_write_vmcr): { - u32 vmcr = host_ctxt->regs.regs[1]; + __kvm_tlb_flush_vmid(kern_hyp_va(mmu)); +} - __vgic_v3_write_vmcr(vmcr); - break; - } - case KVM_HOST_SMCCC_FUNC(__vgic_v3_init_lrs): - __vgic_v3_init_lrs(); - break; - case KVM_HOST_SMCCC_FUNC(__kvm_get_mdcr_el2): - ret = __kvm_get_mdcr_el2(); - break; - case KVM_HOST_SMCCC_FUNC(__vgic_v3_save_aprs): { - unsigned long r1 = host_ctxt->regs.regs[1]; - struct vgic_v3_cpu_if *cpu_if = (struct vgic_v3_cpu_if *)r1; +static void handle___kvm_tlb_flush_local_vmid(struct kvm_cpu_context *host_ctxt) +{ + DECLARE_REG(struct kvm_s2_mmu *, mmu, host_ctxt, 1); - __vgic_v3_save_aprs(kern_hyp_va(cpu_if)); - break; - } - case KVM_HOST_SMCCC_FUNC(__vgic_v3_restore_aprs): { - unsigned long r1 = host_ctxt->regs.regs[1]; - struct vgic_v3_cpu_if *cpu_if = (struct vgic_v3_cpu_if *)r1; + __kvm_tlb_flush_local_vmid(kern_hyp_va(mmu)); +} - __vgic_v3_restore_aprs(kern_hyp_va(cpu_if)); - break; - } - default: - /* Invalid host HVC. */ - host_ctxt->regs.regs[0] = SMCCC_RET_NOT_SUPPORTED; - return; - } +static void handle___kvm_timer_set_cntvoff(struct kvm_cpu_context *host_ctxt) +{ + __kvm_timer_set_cntvoff(cpu_reg(host_ctxt, 1)); +} + +static void handle___kvm_enable_ssbs(struct kvm_cpu_context *host_ctxt) +{ + u64 tmp; - host_ctxt->regs.regs[0] = SMCCC_RET_SUCCESS; - host_ctxt->regs.regs[1] = ret; + tmp = read_sysreg_el2(SYS_SCTLR); + tmp |= SCTLR_ELx_DSSBS; + write_sysreg_el2(tmp, SYS_SCTLR); +} + +static void handle___vgic_v3_get_ich_vtr_el2(struct kvm_cpu_context *host_ctxt) +{ + cpu_reg(host_ctxt, 1) = __vgic_v3_get_ich_vtr_el2(); +} + +static void handle___vgic_v3_read_vmcr(struct kvm_cpu_context *host_ctxt) +{ + cpu_reg(host_ctxt, 1) = __vgic_v3_read_vmcr(); +} + +static void handle___vgic_v3_write_vmcr(struct kvm_cpu_context *host_ctxt) +{ + __vgic_v3_write_vmcr(cpu_reg(host_ctxt, 1)); +} + +static void handle___vgic_v3_init_lrs(struct kvm_cpu_context *host_ctxt) +{ + __vgic_v3_init_lrs(); +} + +static void handle___kvm_get_mdcr_el2(struct kvm_cpu_context *host_ctxt) +{ + cpu_reg(host_ctxt, 1) = __kvm_get_mdcr_el2(); +} + +static void handle___vgic_v3_save_aprs(struct kvm_cpu_context *host_ctxt) +{ + DECLARE_REG(struct vgic_v3_cpu_if *, cpu_if, host_ctxt, 1); + + __vgic_v3_save_aprs(kern_hyp_va(cpu_if)); +} + +static void handle___vgic_v3_restore_aprs(struct kvm_cpu_context *host_ctxt) +{ + DECLARE_REG(struct vgic_v3_cpu_if *, cpu_if, host_ctxt, 1); + + __vgic_v3_restore_aprs(kern_hyp_va(cpu_if)); +} + +typedef void (*hcall_t)(struct kvm_cpu_context *); + +#define HANDLE_FUNC(x) [__KVM_HOST_SMCCC_FUNC_##x] = kimg_fn_ptr(handle_##x) + +static const hcall_t *host_hcall[] = { + HANDLE_FUNC(__kvm_vcpu_run), + HANDLE_FUNC(__kvm_flush_vm_context), + HANDLE_FUNC(__kvm_tlb_flush_vmid_ipa), + HANDLE_FUNC(__kvm_tlb_flush_vmid), + HANDLE_FUNC(__kvm_tlb_flush_local_vmid), + HANDLE_FUNC(__kvm_timer_set_cntvoff), + HANDLE_FUNC(__kvm_enable_ssbs), + HANDLE_FUNC(__vgic_v3_get_ich_vtr_el2), + HANDLE_FUNC(__vgic_v3_read_vmcr), + HANDLE_FUNC(__vgic_v3_write_vmcr), + HANDLE_FUNC(__vgic_v3_init_lrs), + HANDLE_FUNC(__kvm_get_mdcr_el2), + HANDLE_FUNC(__vgic_v3_save_aprs), + HANDLE_FUNC(__vgic_v3_restore_aprs), +}; + +static void handle_host_hcall(struct kvm_cpu_context *host_ctxt) +{ + DECLARE_REG(unsigned long, id, host_ctxt, 0); + const hcall_t *kfn; + hcall_t hfn; + + id -= KVM_HOST_SMCCC_ID(0); + + if (unlikely(id >= ARRAY_SIZE(host_hcall))) + goto inval; + + kfn = host_hcall[id]; + if (unlikely(!kfn)) + goto inval; + + cpu_reg(host_ctxt, 0) = SMCCC_RET_SUCCESS; + + hfn = kimg_fn_hyp_va(kfn); + hfn(host_ctxt); + + return; +inval: + cpu_reg(host_ctxt, 0) = SMCCC_RET_NOT_SUPPORTED; +} + +static void default_host_smc_handler(struct kvm_cpu_context *host_ctxt) +{ + __kvm_hyp_host_forward_smc(host_ctxt); +} + +static void skip_host_instruction(void) +{ + write_sysreg_el2(read_sysreg_el2(SYS_ELR) + 4, SYS_ELR); +} + +static void handle_host_smc(struct kvm_cpu_context *host_ctxt) +{ + bool handled; + + handled = kvm_host_psci_handler(host_ctxt); + if (!handled) + default_host_smc_handler(host_ctxt); + + /* + * Unlike HVC, the return address of an SMC is the instruction's PC. + * Move the return address past the instruction. + */ + skip_host_instruction(); } void handle_trap(struct kvm_cpu_context *host_ctxt) { u64 esr = read_sysreg_el2(SYS_ESR); - unsigned long func_id; - if (ESR_ELx_EC(esr) != ESR_ELx_EC_HVC64) + switch (ESR_ELx_EC(esr)) { + case ESR_ELx_EC_HVC64: + handle_host_hcall(host_ctxt); + break; + case ESR_ELx_EC_SMC64: + handle_host_smc(host_ctxt); + break; + default: hyp_panic(); - - func_id = host_ctxt->regs.regs[0]; - handle_host_hcall(func_id, host_ctxt); + } } diff --git a/arch/arm64/kvm/hyp/nvhe/hyp-smp.c b/arch/arm64/kvm/hyp/nvhe/hyp-smp.c new file mode 100644 index 000000000000..cbab0c6246e2 --- /dev/null +++ b/arch/arm64/kvm/hyp/nvhe/hyp-smp.c @@ -0,0 +1,40 @@ +// SPDX-License-Identifier: GPL-2.0-only +/* + * Copyright (C) 2020 - Google LLC + * Author: David Brazdil <dbrazdil@google.com> + */ + +#include <asm/kvm_asm.h> +#include <asm/kvm_hyp.h> +#include <asm/kvm_mmu.h> + +/* + * nVHE copy of data structures tracking available CPU cores. + * Only entries for CPUs that were online at KVM init are populated. + * Other CPUs should not be allowed to boot because their features were + * not checked against the finalized system capabilities. + */ +u64 __ro_after_init __cpu_logical_map[NR_CPUS] = { [0 ... NR_CPUS-1] = INVALID_HWID }; + +u64 cpu_logical_map(unsigned int cpu) +{ + if (cpu >= ARRAY_SIZE(__cpu_logical_map)) + hyp_panic(); + + return __cpu_logical_map[cpu]; +} + +unsigned long __hyp_per_cpu_offset(unsigned int cpu) +{ + unsigned long *cpu_base_array; + unsigned long this_cpu_base; + unsigned long elf_base; + + if (cpu >= ARRAY_SIZE(kvm_arm_hyp_percpu_base)) + hyp_panic(); + + cpu_base_array = (unsigned long *)hyp_symbol_addr(kvm_arm_hyp_percpu_base); + this_cpu_base = kern_hyp_va(cpu_base_array[cpu]); + elf_base = (unsigned long)hyp_symbol_addr(__per_cpu_start); + return this_cpu_base - elf_base; +} diff --git a/arch/arm64/kvm/hyp/nvhe/hyp.lds.S b/arch/arm64/kvm/hyp/nvhe/hyp.lds.S index a797abace13f..1206d0d754d5 100644 --- a/arch/arm64/kvm/hyp/nvhe/hyp.lds.S +++ b/arch/arm64/kvm/hyp/nvhe/hyp.lds.S @@ -21,4 +21,5 @@ SECTIONS { HYP_SECTION_NAME(.data..percpu) : { PERCPU_INPUT(L1_CACHE_BYTES) } + HYP_SECTION(.data..ro_after_init) } diff --git a/arch/arm64/kvm/hyp/nvhe/psci-relay.c b/arch/arm64/kvm/hyp/nvhe/psci-relay.c new file mode 100644 index 000000000000..08dc9de69314 --- /dev/null +++ b/arch/arm64/kvm/hyp/nvhe/psci-relay.c @@ -0,0 +1,324 @@ +// SPDX-License-Identifier: GPL-2.0-only +/* + * Copyright (C) 2020 - Google LLC + * Author: David Brazdil <dbrazdil@google.com> + */ + +#include <asm/kvm_asm.h> +#include <asm/kvm_hyp.h> +#include <asm/kvm_mmu.h> +#include <kvm/arm_hypercalls.h> +#include <linux/arm-smccc.h> +#include <linux/kvm_host.h> +#include <linux/psci.h> +#include <kvm/arm_psci.h> +#include <uapi/linux/psci.h> + +#include <nvhe/trap_handler.h> + +void kvm_hyp_cpu_entry(unsigned long r0); +void kvm_hyp_cpu_resume(unsigned long r0); + +void __noreturn __host_enter(struct kvm_cpu_context *host_ctxt); + +/* Config options set by the host. */ +__ro_after_init u32 kvm_host_psci_version; +__ro_after_init struct psci_0_1_function_ids kvm_host_psci_0_1_function_ids; +__ro_after_init s64 hyp_physvirt_offset; + +#define __hyp_pa(x) ((phys_addr_t)((x)) + hyp_physvirt_offset) + +#define INVALID_CPU_ID UINT_MAX + +struct psci_boot_args { + atomic_t lock; + unsigned long pc; + unsigned long r0; +}; + +#define PSCI_BOOT_ARGS_UNLOCKED 0 +#define PSCI_BOOT_ARGS_LOCKED 1 + +#define PSCI_BOOT_ARGS_INIT \ + ((struct psci_boot_args){ \ + .lock = ATOMIC_INIT(PSCI_BOOT_ARGS_UNLOCKED), \ + }) + +static DEFINE_PER_CPU(struct psci_boot_args, cpu_on_args) = PSCI_BOOT_ARGS_INIT; +static DEFINE_PER_CPU(struct psci_boot_args, suspend_args) = PSCI_BOOT_ARGS_INIT; + +static u64 get_psci_func_id(struct kvm_cpu_context *host_ctxt) +{ + DECLARE_REG(u64, func_id, host_ctxt, 0); + + return func_id; +} + +static bool is_psci_0_1_call(u64 func_id) +{ + return (func_id == kvm_host_psci_0_1_function_ids.cpu_suspend) || + (func_id == kvm_host_psci_0_1_function_ids.cpu_on) || + (func_id == kvm_host_psci_0_1_function_ids.cpu_off) || + (func_id == kvm_host_psci_0_1_function_ids.migrate); +} + +static bool is_psci_0_2_call(u64 func_id) +{ + /* SMCCC reserves IDs 0x00-1F with the given 32/64-bit base for PSCI. */ + return (PSCI_0_2_FN(0) <= func_id && func_id <= PSCI_0_2_FN(31)) || + (PSCI_0_2_FN64(0) <= func_id && func_id <= PSCI_0_2_FN64(31)); +} + +static bool is_psci_call(u64 func_id) +{ + switch (kvm_host_psci_version) { + case PSCI_VERSION(0, 1): + return is_psci_0_1_call(func_id); + default: + return is_psci_0_2_call(func_id); + } +} + +static unsigned long psci_call(unsigned long fn, unsigned long arg0, + unsigned long arg1, unsigned long arg2) +{ + struct arm_smccc_res res; + + arm_smccc_1_1_smc(fn, arg0, arg1, arg2, &res); + return res.a0; +} + +static unsigned long psci_forward(struct kvm_cpu_context *host_ctxt) +{ + return psci_call(cpu_reg(host_ctxt, 0), cpu_reg(host_ctxt, 1), + cpu_reg(host_ctxt, 2), cpu_reg(host_ctxt, 3)); +} + +static __noreturn unsigned long psci_forward_noreturn(struct kvm_cpu_context *host_ctxt) +{ + psci_forward(host_ctxt); + hyp_panic(); /* unreachable */ +} + +static unsigned int find_cpu_id(u64 mpidr) +{ + unsigned int i; + + /* Reject invalid MPIDRs */ + if (mpidr & ~MPIDR_HWID_BITMASK) + return INVALID_CPU_ID; + + for (i = 0; i < NR_CPUS; i++) { + if (cpu_logical_map(i) == mpidr) + return i; + } + + return INVALID_CPU_ID; +} + +static __always_inline bool try_acquire_boot_args(struct psci_boot_args *args) +{ + return atomic_cmpxchg_acquire(&args->lock, + PSCI_BOOT_ARGS_UNLOCKED, + PSCI_BOOT_ARGS_LOCKED) == + PSCI_BOOT_ARGS_UNLOCKED; +} + +static __always_inline void release_boot_args(struct psci_boot_args *args) +{ + atomic_set_release(&args->lock, PSCI_BOOT_ARGS_UNLOCKED); +} + +static int psci_cpu_on(u64 func_id, struct kvm_cpu_context *host_ctxt) +{ + DECLARE_REG(u64, mpidr, host_ctxt, 1); + DECLARE_REG(unsigned long, pc, host_ctxt, 2); + DECLARE_REG(unsigned long, r0, host_ctxt, 3); + + unsigned int cpu_id; + struct psci_boot_args *boot_args; + struct kvm_nvhe_init_params *init_params; + int ret; + + /* + * Find the logical CPU ID for the given MPIDR. The search set is + * the set of CPUs that were online at the point of KVM initialization. + * Booting other CPUs is rejected because their cpufeatures were not + * checked against the finalized capabilities. This could be relaxed + * by doing the feature checks in hyp. + */ + cpu_id = find_cpu_id(mpidr); + if (cpu_id == INVALID_CPU_ID) + return PSCI_RET_INVALID_PARAMS; + + boot_args = per_cpu_ptr(hyp_symbol_addr(cpu_on_args), cpu_id); + init_params = per_cpu_ptr(hyp_symbol_addr(kvm_init_params), cpu_id); + + /* Check if the target CPU is already being booted. */ + if (!try_acquire_boot_args(boot_args)) + return PSCI_RET_ALREADY_ON; + + boot_args->pc = pc; + boot_args->r0 = r0; + wmb(); + + ret = psci_call(func_id, mpidr, + __hyp_pa(hyp_symbol_addr(kvm_hyp_cpu_entry)), + __hyp_pa(init_params)); + + /* If successful, the lock will be released by the target CPU. */ + if (ret != PSCI_RET_SUCCESS) + release_boot_args(boot_args); + + return ret; +} + +static int psci_cpu_suspend(u64 func_id, struct kvm_cpu_context *host_ctxt) +{ + DECLARE_REG(u64, power_state, host_ctxt, 1); + DECLARE_REG(unsigned long, pc, host_ctxt, 2); + DECLARE_REG(unsigned long, r0, host_ctxt, 3); + + struct psci_boot_args *boot_args; + struct kvm_nvhe_init_params *init_params; + + boot_args = this_cpu_ptr(hyp_symbol_addr(suspend_args)); + init_params = this_cpu_ptr(hyp_symbol_addr(kvm_init_params)); + + /* + * No need to acquire a lock before writing to boot_args because a core + * can only suspend itself. Racy CPU_ON calls use a separate struct. + */ + boot_args->pc = pc; + boot_args->r0 = r0; + + /* + * Will either return if shallow sleep state, or wake up into the entry + * point if it is a deep sleep state. + */ + return psci_call(func_id, power_state, + __hyp_pa(hyp_symbol_addr(kvm_hyp_cpu_resume)), + __hyp_pa(init_params)); +} + +static int psci_system_suspend(u64 func_id, struct kvm_cpu_context *host_ctxt) +{ + DECLARE_REG(unsigned long, pc, host_ctxt, 1); + DECLARE_REG(unsigned long, r0, host_ctxt, 2); + + struct psci_boot_args *boot_args; + struct kvm_nvhe_init_params *init_params; + + boot_args = this_cpu_ptr(hyp_symbol_addr(suspend_args)); + init_params = this_cpu_ptr(hyp_symbol_addr(kvm_init_params)); + + /* + * No need to acquire a lock before writing to boot_args because a core + * can only suspend itself. Racy CPU_ON calls use a separate struct. + */ + boot_args->pc = pc; + boot_args->r0 = r0; + + /* Will only return on error. */ + return psci_call(func_id, + __hyp_pa(hyp_symbol_addr(kvm_hyp_cpu_resume)), + __hyp_pa(init_params), 0); +} + +asmlinkage void __noreturn kvm_host_psci_cpu_entry(bool is_cpu_on) +{ + struct psci_boot_args *boot_args; + struct kvm_cpu_context *host_ctxt; + + host_ctxt = &this_cpu_ptr(hyp_symbol_addr(kvm_host_data))->host_ctxt; + + if (is_cpu_on) + boot_args = this_cpu_ptr(hyp_symbol_addr(cpu_on_args)); + else + boot_args = this_cpu_ptr(hyp_symbol_addr(suspend_args)); + + cpu_reg(host_ctxt, 0) = boot_args->r0; + write_sysreg_el2(boot_args->pc, SYS_ELR); + + if (is_cpu_on) + release_boot_args(boot_args); + + __host_enter(host_ctxt); +} + +static unsigned long psci_0_1_handler(u64 func_id, struct kvm_cpu_context *host_ctxt) +{ + if ((func_id == kvm_host_psci_0_1_function_ids.cpu_off) || + (func_id == kvm_host_psci_0_1_function_ids.migrate)) + return psci_forward(host_ctxt); + else if (func_id == kvm_host_psci_0_1_function_ids.cpu_on) + return psci_cpu_on(func_id, host_ctxt); + else if (func_id == kvm_host_psci_0_1_function_ids.cpu_suspend) + return psci_cpu_suspend(func_id, host_ctxt); + else + return PSCI_RET_NOT_SUPPORTED; +} + +static unsigned long psci_0_2_handler(u64 func_id, struct kvm_cpu_context *host_ctxt) +{ + switch (func_id) { + case PSCI_0_2_FN_PSCI_VERSION: + case PSCI_0_2_FN_CPU_OFF: + case PSCI_0_2_FN64_AFFINITY_INFO: + case PSCI_0_2_FN64_MIGRATE: + case PSCI_0_2_FN_MIGRATE_INFO_TYPE: + case PSCI_0_2_FN64_MIGRATE_INFO_UP_CPU: + return psci_forward(host_ctxt); + case PSCI_0_2_FN_SYSTEM_OFF: + case PSCI_0_2_FN_SYSTEM_RESET: + psci_forward_noreturn(host_ctxt); + unreachable(); + case PSCI_0_2_FN64_CPU_SUSPEND: + return psci_cpu_suspend(func_id, host_ctxt); + case PSCI_0_2_FN64_CPU_ON: + return psci_cpu_on(func_id, host_ctxt); + default: + return PSCI_RET_NOT_SUPPORTED; + } +} + +static unsigned long psci_1_0_handler(u64 func_id, struct kvm_cpu_context *host_ctxt) +{ + switch (func_id) { + case PSCI_1_0_FN_PSCI_FEATURES: + case PSCI_1_0_FN_SET_SUSPEND_MODE: + case PSCI_1_1_FN64_SYSTEM_RESET2: + return psci_forward(host_ctxt); + case PSCI_1_0_FN64_SYSTEM_SUSPEND: + return psci_system_suspend(func_id, host_ctxt); + default: + return psci_0_2_handler(func_id, host_ctxt); + } +} + +bool kvm_host_psci_handler(struct kvm_cpu_context *host_ctxt) +{ + u64 func_id = get_psci_func_id(host_ctxt); + unsigned long ret; + + if (!is_psci_call(func_id)) + return false; + + switch (kvm_host_psci_version) { + case PSCI_VERSION(0, 1): + ret = psci_0_1_handler(func_id, host_ctxt); + break; + case PSCI_VERSION(0, 2): + ret = psci_0_2_handler(func_id, host_ctxt); + break; + default: + ret = psci_1_0_handler(func_id, host_ctxt); + break; + } + + cpu_reg(host_ctxt, 0) = ret; + cpu_reg(host_ctxt, 1) = 0; + cpu_reg(host_ctxt, 2) = 0; + cpu_reg(host_ctxt, 3) = 0; + return true; +} diff --git a/arch/arm64/kvm/hyp/nvhe/switch.c b/arch/arm64/kvm/hyp/nvhe/switch.c index 8ae8160bc93a..f3d0e9eca56c 100644 --- a/arch/arm64/kvm/hyp/nvhe/switch.c +++ b/arch/arm64/kvm/hyp/nvhe/switch.c @@ -4,6 +4,7 @@ * Author: Marc Zyngier <marc.zyngier@arm.com> */ +#include <hyp/adjust_pc.h> #include <hyp/switch.h> #include <hyp/sysreg-sr.h> @@ -96,7 +97,10 @@ static void __deactivate_traps(struct kvm_vcpu *vcpu) mdcr_el2 |= MDCR_EL2_E2PB_MASK << MDCR_EL2_E2PB_SHIFT; write_sysreg(mdcr_el2, mdcr_el2); - write_sysreg(HCR_HOST_NVHE_FLAGS, hcr_el2); + if (is_protected_kvm_enabled()) + write_sysreg(HCR_HOST_NVHE_PROTECTED_FLAGS, hcr_el2); + else + write_sysreg(HCR_HOST_NVHE_FLAGS, hcr_el2); write_sysreg(CPTR_EL2_DEFAULT, cptr_el2); write_sysreg(__kvm_hyp_host_vector, vbar_el2); } @@ -189,6 +193,8 @@ int __kvm_vcpu_run(struct kvm_vcpu *vcpu) __sysreg_save_state_nvhe(host_ctxt); + __adjust_pc(vcpu); + /* * We must restore the 32-bit state before the sysregs, thanks * to erratum #852523 (Cortex-A57) or #853709 (Cortex-A72). diff --git a/arch/arm64/kvm/hyp/nvhe/sysreg-sr.c b/arch/arm64/kvm/hyp/nvhe/sysreg-sr.c index 88a25fc8fcd3..29305022bc04 100644 --- a/arch/arm64/kvm/hyp/nvhe/sysreg-sr.c +++ b/arch/arm64/kvm/hyp/nvhe/sysreg-sr.c @@ -33,14 +33,3 @@ void __sysreg_restore_state_nvhe(struct kvm_cpu_context *ctxt) __sysreg_restore_user_state(ctxt); __sysreg_restore_el2_return_state(ctxt); } - -void __kvm_enable_ssbs(void) -{ - u64 tmp; - - asm volatile( - "mrs %0, sctlr_el2\n" - "orr %0, %0, %1\n" - "msr sctlr_el2, %0" - : "=&r" (tmp) : "L" (SCTLR_ELx_DSSBS)); -} diff --git a/arch/arm64/kvm/hyp/smccc_wa.S b/arch/arm64/kvm/hyp/smccc_wa.S deleted file mode 100644 index b0441dbdf68b..000000000000 --- a/arch/arm64/kvm/hyp/smccc_wa.S +++ /dev/null @@ -1,32 +0,0 @@ -/* SPDX-License-Identifier: GPL-2.0-only */ -/* - * Copyright (C) 2015-2018 - ARM Ltd - * Author: Marc Zyngier <marc.zyngier@arm.com> - */ - -#include <linux/arm-smccc.h> -#include <linux/linkage.h> - -#include <asm/kvm_asm.h> -#include <asm/kvm_mmu.h> - - /* - * This is not executed directly and is instead copied into the vectors - * by install_bp_hardening_cb(). - */ - .data - .pushsection .rodata - .global __smccc_workaround_1_smc -SYM_DATA_START(__smccc_workaround_1_smc) - esb - sub sp, sp, #(8 * 4) - stp x2, x3, [sp, #(8 * 0)] - stp x0, x1, [sp, #(8 * 2)] - mov w0, #ARM_SMCCC_ARCH_WORKAROUND_1 - smc #0 - ldp x2, x3, [sp, #(8 * 0)] - ldp x0, x1, [sp, #(8 * 2)] - add sp, sp, #(8 * 4) -1: .org __smccc_workaround_1_smc + __SMCCC_WORKAROUND_1_SMC_SZ - .org 1b -SYM_DATA_END(__smccc_workaround_1_smc) diff --git a/arch/arm64/kvm/hyp/vgic-v2-cpuif-proxy.c b/arch/arm64/kvm/hyp/vgic-v2-cpuif-proxy.c index bd1bab551d48..8f0585640241 100644 --- a/arch/arm64/kvm/hyp/vgic-v2-cpuif-proxy.c +++ b/arch/arm64/kvm/hyp/vgic-v2-cpuif-proxy.c @@ -4,6 +4,8 @@ * Author: Marc Zyngier <marc.zyngier@arm.com> */ +#include <hyp/adjust_pc.h> + #include <linux/compiler.h> #include <linux/irqchip/arm-gic.h> #include <linux/kvm_host.h> diff --git a/arch/arm64/kvm/hyp/vgic-v3-sr.c b/arch/arm64/kvm/hyp/vgic-v3-sr.c index 452f4cacd674..80406f463c28 100644 --- a/arch/arm64/kvm/hyp/vgic-v3-sr.c +++ b/arch/arm64/kvm/hyp/vgic-v3-sr.c @@ -4,6 +4,8 @@ * Author: Marc Zyngier <marc.zyngier@arm.com> */ +#include <hyp/adjust_pc.h> + #include <linux/compiler.h> #include <linux/irqchip/arm-gic-v3.h> #include <linux/kvm_host.h> diff --git a/arch/arm64/kvm/hyp/vhe/Makefile b/arch/arm64/kvm/hyp/vhe/Makefile index 461e97c375cc..96bec0ecf9dd 100644 --- a/arch/arm64/kvm/hyp/vhe/Makefile +++ b/arch/arm64/kvm/hyp/vhe/Makefile @@ -8,4 +8,4 @@ ccflags-y := -D__KVM_VHE_HYPERVISOR__ obj-y := timer-sr.o sysreg-sr.o debug-sr.o switch.o tlb.o obj-y += ../vgic-v3-sr.o ../aarch32.o ../vgic-v2-cpuif-proxy.o ../entry.o \ - ../fpsimd.o ../hyp-entry.o + ../fpsimd.o ../hyp-entry.o ../exception.o diff --git a/arch/arm64/kvm/hyp/vhe/switch.c b/arch/arm64/kvm/hyp/vhe/switch.c index 62546e20b251..af8e940d0f03 100644 --- a/arch/arm64/kvm/hyp/vhe/switch.c +++ b/arch/arm64/kvm/hyp/vhe/switch.c @@ -4,6 +4,7 @@ * Author: Marc Zyngier <marc.zyngier@arm.com> */ +#include <hyp/adjust_pc.h> #include <hyp/switch.h> #include <linux/arm-smccc.h> @@ -133,6 +134,8 @@ static int __kvm_vcpu_run_vhe(struct kvm_vcpu *vcpu) __load_guest_stage2(vcpu->arch.hw_mmu); __activate_traps(vcpu); + __adjust_pc(vcpu); + sysreg_restore_guest_state_vhe(guest_ctxt); __debug_switch_to_guest(vcpu); diff --git a/arch/arm64/kvm/inject_fault.c b/arch/arm64/kvm/inject_fault.c index 34a96ab244fa..b47df73e98d7 100644 --- a/arch/arm64/kvm/inject_fault.c +++ b/arch/arm64/kvm/inject_fault.c @@ -14,119 +14,15 @@ #include <asm/kvm_emulate.h> #include <asm/esr.h> -#define CURRENT_EL_SP_EL0_VECTOR 0x0 -#define CURRENT_EL_SP_ELx_VECTOR 0x200 -#define LOWER_EL_AArch64_VECTOR 0x400 -#define LOWER_EL_AArch32_VECTOR 0x600 - -enum exception_type { - except_type_sync = 0, - except_type_irq = 0x80, - except_type_fiq = 0x100, - except_type_serror = 0x180, -}; - -/* - * This performs the exception entry at a given EL (@target_mode), stashing PC - * and PSTATE into ELR and SPSR respectively, and compute the new PC/PSTATE. - * The EL passed to this function *must* be a non-secure, privileged mode with - * bit 0 being set (PSTATE.SP == 1). - * - * When an exception is taken, most PSTATE fields are left unchanged in the - * handler. However, some are explicitly overridden (e.g. M[4:0]). Luckily all - * of the inherited bits have the same position in the AArch64/AArch32 SPSR_ELx - * layouts, so we don't need to shuffle these for exceptions from AArch32 EL0. - * - * For the SPSR_ELx layout for AArch64, see ARM DDI 0487E.a page C5-429. - * For the SPSR_ELx layout for AArch32, see ARM DDI 0487E.a page C5-426. - * - * Here we manipulate the fields in order of the AArch64 SPSR_ELx layout, from - * MSB to LSB. - */ -static void enter_exception64(struct kvm_vcpu *vcpu, unsigned long target_mode, - enum exception_type type) -{ - unsigned long sctlr, vbar, old, new, mode; - u64 exc_offset; - - mode = *vcpu_cpsr(vcpu) & (PSR_MODE_MASK | PSR_MODE32_BIT); - - if (mode == target_mode) - exc_offset = CURRENT_EL_SP_ELx_VECTOR; - else if ((mode | PSR_MODE_THREAD_BIT) == target_mode) - exc_offset = CURRENT_EL_SP_EL0_VECTOR; - else if (!(mode & PSR_MODE32_BIT)) - exc_offset = LOWER_EL_AArch64_VECTOR; - else - exc_offset = LOWER_EL_AArch32_VECTOR; - - switch (target_mode) { - case PSR_MODE_EL1h: - vbar = vcpu_read_sys_reg(vcpu, VBAR_EL1); - sctlr = vcpu_read_sys_reg(vcpu, SCTLR_EL1); - vcpu_write_sys_reg(vcpu, *vcpu_pc(vcpu), ELR_EL1); - break; - default: - /* Don't do that */ - BUG(); - } - - *vcpu_pc(vcpu) = vbar + exc_offset + type; - - old = *vcpu_cpsr(vcpu); - new = 0; - - new |= (old & PSR_N_BIT); - new |= (old & PSR_Z_BIT); - new |= (old & PSR_C_BIT); - new |= (old & PSR_V_BIT); - - // TODO: TCO (if/when ARMv8.5-MemTag is exposed to guests) - - new |= (old & PSR_DIT_BIT); - - // PSTATE.UAO is set to zero upon any exception to AArch64 - // See ARM DDI 0487E.a, page D5-2579. - - // PSTATE.PAN is unchanged unless SCTLR_ELx.SPAN == 0b0 - // SCTLR_ELx.SPAN is RES1 when ARMv8.1-PAN is not implemented - // See ARM DDI 0487E.a, page D5-2578. - new |= (old & PSR_PAN_BIT); - if (!(sctlr & SCTLR_EL1_SPAN)) - new |= PSR_PAN_BIT; - - // PSTATE.SS is set to zero upon any exception to AArch64 - // See ARM DDI 0487E.a, page D2-2452. - - // PSTATE.IL is set to zero upon any exception to AArch64 - // See ARM DDI 0487E.a, page D1-2306. - - // PSTATE.SSBS is set to SCTLR_ELx.DSSBS upon any exception to AArch64 - // See ARM DDI 0487E.a, page D13-3258 - if (sctlr & SCTLR_ELx_DSSBS) - new |= PSR_SSBS_BIT; - - // PSTATE.BTYPE is set to zero upon any exception to AArch64 - // See ARM DDI 0487E.a, pages D1-2293 to D1-2294. - - new |= PSR_D_BIT; - new |= PSR_A_BIT; - new |= PSR_I_BIT; - new |= PSR_F_BIT; - - new |= target_mode; - - *vcpu_cpsr(vcpu) = new; - vcpu_write_spsr(vcpu, old); -} - static void inject_abt64(struct kvm_vcpu *vcpu, bool is_iabt, unsigned long addr) { unsigned long cpsr = *vcpu_cpsr(vcpu); bool is_aarch32 = vcpu_mode_is_32bit(vcpu); u32 esr = 0; - enter_exception64(vcpu, PSR_MODE_EL1h, except_type_sync); + vcpu->arch.flags |= (KVM_ARM64_EXCEPT_AA64_EL1 | + KVM_ARM64_EXCEPT_AA64_ELx_SYNC | + KVM_ARM64_PENDING_EXCEPTION); vcpu_write_sys_reg(vcpu, addr, FAR_EL1); @@ -156,7 +52,9 @@ static void inject_undef64(struct kvm_vcpu *vcpu) { u32 esr = (ESR_ELx_EC_UNKNOWN << ESR_ELx_EC_SHIFT); - enter_exception64(vcpu, PSR_MODE_EL1h, except_type_sync); + vcpu->arch.flags |= (KVM_ARM64_EXCEPT_AA64_EL1 | + KVM_ARM64_EXCEPT_AA64_ELx_SYNC | + KVM_ARM64_PENDING_EXCEPTION); /* * Build an unknown exception, depending on the instruction @@ -168,6 +66,53 @@ static void inject_undef64(struct kvm_vcpu *vcpu) vcpu_write_sys_reg(vcpu, esr, ESR_EL1); } +#define DFSR_FSC_EXTABT_LPAE 0x10 +#define DFSR_FSC_EXTABT_nLPAE 0x08 +#define DFSR_LPAE BIT(9) +#define TTBCR_EAE BIT(31) + +static void inject_undef32(struct kvm_vcpu *vcpu) +{ + vcpu->arch.flags |= (KVM_ARM64_EXCEPT_AA32_UND | + KVM_ARM64_PENDING_EXCEPTION); +} + +/* + * Modelled after TakeDataAbortException() and TakePrefetchAbortException + * pseudocode. + */ +static void inject_abt32(struct kvm_vcpu *vcpu, bool is_pabt, u32 addr) +{ + u64 far; + u32 fsr; + + /* Give the guest an IMPLEMENTATION DEFINED exception */ + if (vcpu_read_sys_reg(vcpu, TCR_EL1) & TTBCR_EAE) { + fsr = DFSR_LPAE | DFSR_FSC_EXTABT_LPAE; + } else { + /* no need to shuffle FS[4] into DFSR[10] as its 0 */ + fsr = DFSR_FSC_EXTABT_nLPAE; + } + + far = vcpu_read_sys_reg(vcpu, FAR_EL1); + + if (is_pabt) { + vcpu->arch.flags |= (KVM_ARM64_EXCEPT_AA32_IABT | + KVM_ARM64_PENDING_EXCEPTION); + far &= GENMASK(31, 0); + far |= (u64)addr << 32; + vcpu_write_sys_reg(vcpu, fsr, IFSR32_EL2); + } else { /* !iabt */ + vcpu->arch.flags |= (KVM_ARM64_EXCEPT_AA32_DABT | + KVM_ARM64_PENDING_EXCEPTION); + far &= GENMASK(63, 32); + far |= addr; + vcpu_write_sys_reg(vcpu, fsr, ESR_EL1); + } + + vcpu_write_sys_reg(vcpu, far, FAR_EL1); +} + /** * kvm_inject_dabt - inject a data abort into the guest * @vcpu: The VCPU to receive the data abort @@ -179,7 +124,7 @@ static void inject_undef64(struct kvm_vcpu *vcpu) void kvm_inject_dabt(struct kvm_vcpu *vcpu, unsigned long addr) { if (vcpu_el1_is_32bit(vcpu)) - kvm_inject_dabt32(vcpu, addr); + inject_abt32(vcpu, false, addr); else inject_abt64(vcpu, false, addr); } @@ -195,7 +140,7 @@ void kvm_inject_dabt(struct kvm_vcpu *vcpu, unsigned long addr) void kvm_inject_pabt(struct kvm_vcpu *vcpu, unsigned long addr) { if (vcpu_el1_is_32bit(vcpu)) - kvm_inject_pabt32(vcpu, addr); + inject_abt32(vcpu, true, addr); else inject_abt64(vcpu, true, addr); } @@ -210,7 +155,7 @@ void kvm_inject_pabt(struct kvm_vcpu *vcpu, unsigned long addr) void kvm_inject_undefined(struct kvm_vcpu *vcpu) { if (vcpu_el1_is_32bit(vcpu)) - kvm_inject_undef32(vcpu); + inject_undef32(vcpu); else inject_undef64(vcpu); } diff --git a/arch/arm64/kvm/mmio.c b/arch/arm64/kvm/mmio.c index 6a2826f1bf5e..3e2d8ba11a02 100644 --- a/arch/arm64/kvm/mmio.c +++ b/arch/arm64/kvm/mmio.c @@ -115,7 +115,7 @@ int kvm_handle_mmio_return(struct kvm_vcpu *vcpu) * The MMIO instruction is emulated and should not be re-executed * in the guest. */ - kvm_skip_instr(vcpu, kvm_vcpu_trap_il_is32bit(vcpu)); + kvm_incr_pc(vcpu); return 0; } diff --git a/arch/arm64/kvm/mmu.c b/arch/arm64/kvm/mmu.c index 75814a02d189..7d2257cc5438 100644 --- a/arch/arm64/kvm/mmu.c +++ b/arch/arm64/kvm/mmu.c @@ -1023,7 +1023,7 @@ int kvm_handle_guest_abort(struct kvm_vcpu *vcpu) * cautious, and skip the instruction. */ if (kvm_is_error_hva(hva) && kvm_vcpu_dabt_is_cm(vcpu)) { - kvm_skip_instr(vcpu, kvm_vcpu_trap_il_is32bit(vcpu)); + kvm_incr_pc(vcpu); ret = 1; goto out_unlock; } diff --git a/arch/arm64/kvm/pmu-emul.c b/arch/arm64/kvm/pmu-emul.c index 2ed5ef8f274b..398f6df1bbe4 100644 --- a/arch/arm64/kvm/pmu-emul.c +++ b/arch/arm64/kvm/pmu-emul.c @@ -384,7 +384,7 @@ static void kvm_pmu_update_state(struct kvm_vcpu *vcpu) struct kvm_pmu *pmu = &vcpu->arch.pmu; bool overflow; - if (!kvm_arm_pmu_v3_ready(vcpu)) + if (!kvm_vcpu_has_pmu(vcpu)) return; overflow = !!kvm_pmu_overflow_status(vcpu); @@ -825,9 +825,12 @@ bool kvm_arm_support_pmu_v3(void) int kvm_arm_pmu_v3_enable(struct kvm_vcpu *vcpu) { - if (!vcpu->arch.pmu.created) + if (!kvm_vcpu_has_pmu(vcpu)) return 0; + if (!vcpu->arch.pmu.created) + return -EINVAL; + /* * A valid interrupt configuration for the PMU is either to have a * properly configured interrupt number and using an in-kernel @@ -835,9 +838,6 @@ int kvm_arm_pmu_v3_enable(struct kvm_vcpu *vcpu) */ if (irqchip_in_kernel(vcpu->kvm)) { int irq = vcpu->arch.pmu.irq_num; - if (!kvm_arm_pmu_irq_initialized(vcpu)) - return -EINVAL; - /* * If we are using an in-kernel vgic, at this point we know * the vgic will be initialized, so we can check the PMU irq @@ -851,7 +851,6 @@ int kvm_arm_pmu_v3_enable(struct kvm_vcpu *vcpu) } kvm_pmu_vcpu_reset(vcpu); - vcpu->arch.pmu.ready = true; return 0; } @@ -913,8 +912,7 @@ static bool pmu_irq_is_valid(struct kvm *kvm, int irq) int kvm_arm_pmu_v3_set_attr(struct kvm_vcpu *vcpu, struct kvm_device_attr *attr) { - if (!kvm_arm_support_pmu_v3() || - !test_bit(KVM_ARM_VCPU_PMU_V3, vcpu->arch.features)) + if (!kvm_vcpu_has_pmu(vcpu)) return -ENODEV; if (vcpu->arch.pmu.created) @@ -1015,7 +1013,7 @@ int kvm_arm_pmu_v3_get_attr(struct kvm_vcpu *vcpu, struct kvm_device_attr *attr) if (!irqchip_in_kernel(vcpu->kvm)) return -EINVAL; - if (!test_bit(KVM_ARM_VCPU_PMU_V3, vcpu->arch.features)) + if (!kvm_vcpu_has_pmu(vcpu)) return -ENODEV; if (!kvm_arm_pmu_irq_initialized(vcpu)) @@ -1035,8 +1033,7 @@ int kvm_arm_pmu_v3_has_attr(struct kvm_vcpu *vcpu, struct kvm_device_attr *attr) case KVM_ARM_VCPU_PMU_V3_IRQ: case KVM_ARM_VCPU_PMU_V3_INIT: case KVM_ARM_VCPU_PMU_V3_FILTER: - if (kvm_arm_support_pmu_v3() && - test_bit(KVM_ARM_VCPU_PMU_V3, vcpu->arch.features)) + if (kvm_vcpu_has_pmu(vcpu)) return 0; } diff --git a/arch/arm64/kvm/pvtime.c b/arch/arm64/kvm/pvtime.c index 920ac43077ad..78a09f7a6637 100644 --- a/arch/arm64/kvm/pvtime.c +++ b/arch/arm64/kvm/pvtime.c @@ -53,7 +53,6 @@ gpa_t kvm_init_stolen_time(struct kvm_vcpu *vcpu) struct pvclock_vcpu_stolen_time init_values = {}; struct kvm *kvm = vcpu->kvm; u64 base = vcpu->arch.steal.base; - int idx; if (base == GPA_INVALID) return base; @@ -63,10 +62,7 @@ gpa_t kvm_init_stolen_time(struct kvm_vcpu *vcpu) * the feature enabled. */ vcpu->arch.steal.last_steal = current->sched_info.run_delay; - - idx = srcu_read_lock(&kvm->srcu); - kvm_write_guest(kvm, base, &init_values, sizeof(init_values)); - srcu_read_unlock(&kvm->srcu, idx); + kvm_write_guest_lock(kvm, base, &init_values, sizeof(init_values)); return base; } diff --git a/arch/arm64/kvm/regmap.c b/arch/arm64/kvm/regmap.c deleted file mode 100644 index accc1d5fba61..000000000000 --- a/arch/arm64/kvm/regmap.c +++ /dev/null @@ -1,224 +0,0 @@ -// SPDX-License-Identifier: GPL-2.0-only -/* - * Copyright (C) 2012,2013 - ARM Ltd - * Author: Marc Zyngier <marc.zyngier@arm.com> - * - * Derived from arch/arm/kvm/emulate.c: - * Copyright (C) 2012 - Virtual Open Systems and Columbia University - * Author: Christoffer Dall <c.dall@virtualopensystems.com> - */ - -#include <linux/mm.h> -#include <linux/kvm_host.h> -#include <asm/kvm_emulate.h> -#include <asm/ptrace.h> - -#define VCPU_NR_MODES 6 -#define REG_OFFSET(_reg) \ - (offsetof(struct user_pt_regs, _reg) / sizeof(unsigned long)) - -#define USR_REG_OFFSET(R) REG_OFFSET(compat_usr(R)) - -static const unsigned long vcpu_reg_offsets[VCPU_NR_MODES][16] = { - /* USR Registers */ - { - USR_REG_OFFSET(0), USR_REG_OFFSET(1), USR_REG_OFFSET(2), - USR_REG_OFFSET(3), USR_REG_OFFSET(4), USR_REG_OFFSET(5), - USR_REG_OFFSET(6), USR_REG_OFFSET(7), USR_REG_OFFSET(8), - USR_REG_OFFSET(9), USR_REG_OFFSET(10), USR_REG_OFFSET(11), - USR_REG_OFFSET(12), USR_REG_OFFSET(13), USR_REG_OFFSET(14), - REG_OFFSET(pc) - }, - - /* FIQ Registers */ - { - USR_REG_OFFSET(0), USR_REG_OFFSET(1), USR_REG_OFFSET(2), - USR_REG_OFFSET(3), USR_REG_OFFSET(4), USR_REG_OFFSET(5), - USR_REG_OFFSET(6), USR_REG_OFFSET(7), - REG_OFFSET(compat_r8_fiq), /* r8 */ - REG_OFFSET(compat_r9_fiq), /* r9 */ - REG_OFFSET(compat_r10_fiq), /* r10 */ - REG_OFFSET(compat_r11_fiq), /* r11 */ - REG_OFFSET(compat_r12_fiq), /* r12 */ - REG_OFFSET(compat_sp_fiq), /* r13 */ - REG_OFFSET(compat_lr_fiq), /* r14 */ - REG_OFFSET(pc) - }, - - /* IRQ Registers */ - { - USR_REG_OFFSET(0), USR_REG_OFFSET(1), USR_REG_OFFSET(2), - USR_REG_OFFSET(3), USR_REG_OFFSET(4), USR_REG_OFFSET(5), - USR_REG_OFFSET(6), USR_REG_OFFSET(7), USR_REG_OFFSET(8), - USR_REG_OFFSET(9), USR_REG_OFFSET(10), USR_REG_OFFSET(11), - USR_REG_OFFSET(12), - REG_OFFSET(compat_sp_irq), /* r13 */ - REG_OFFSET(compat_lr_irq), /* r14 */ - REG_OFFSET(pc) - }, - - /* SVC Registers */ - { - USR_REG_OFFSET(0), USR_REG_OFFSET(1), USR_REG_OFFSET(2), - USR_REG_OFFSET(3), USR_REG_OFFSET(4), USR_REG_OFFSET(5), - USR_REG_OFFSET(6), USR_REG_OFFSET(7), USR_REG_OFFSET(8), - USR_REG_OFFSET(9), USR_REG_OFFSET(10), USR_REG_OFFSET(11), - USR_REG_OFFSET(12), - REG_OFFSET(compat_sp_svc), /* r13 */ - REG_OFFSET(compat_lr_svc), /* r14 */ - REG_OFFSET(pc) - }, - - /* ABT Registers */ - { - USR_REG_OFFSET(0), USR_REG_OFFSET(1), USR_REG_OFFSET(2), - USR_REG_OFFSET(3), USR_REG_OFFSET(4), USR_REG_OFFSET(5), - USR_REG_OFFSET(6), USR_REG_OFFSET(7), USR_REG_OFFSET(8), - USR_REG_OFFSET(9), USR_REG_OFFSET(10), USR_REG_OFFSET(11), - USR_REG_OFFSET(12), - REG_OFFSET(compat_sp_abt), /* r13 */ - REG_OFFSET(compat_lr_abt), /* r14 */ - REG_OFFSET(pc) - }, - - /* UND Registers */ - { - USR_REG_OFFSET(0), USR_REG_OFFSET(1), USR_REG_OFFSET(2), - USR_REG_OFFSET(3), USR_REG_OFFSET(4), USR_REG_OFFSET(5), - USR_REG_OFFSET(6), USR_REG_OFFSET(7), USR_REG_OFFSET(8), - USR_REG_OFFSET(9), USR_REG_OFFSET(10), USR_REG_OFFSET(11), - USR_REG_OFFSET(12), - REG_OFFSET(compat_sp_und), /* r13 */ - REG_OFFSET(compat_lr_und), /* r14 */ - REG_OFFSET(pc) - }, -}; - -/* - * Return a pointer to the register number valid in the current mode of - * the virtual CPU. - */ -unsigned long *vcpu_reg32(const struct kvm_vcpu *vcpu, u8 reg_num) -{ - unsigned long *reg_array = (unsigned long *)&vcpu->arch.ctxt.regs; - unsigned long mode = *vcpu_cpsr(vcpu) & PSR_AA32_MODE_MASK; - - switch (mode) { - case PSR_AA32_MODE_USR ... PSR_AA32_MODE_SVC: - mode &= ~PSR_MODE32_BIT; /* 0 ... 3 */ - break; - - case PSR_AA32_MODE_ABT: - mode = 4; - break; - - case PSR_AA32_MODE_UND: - mode = 5; - break; - - case PSR_AA32_MODE_SYS: - mode = 0; /* SYS maps to USR */ - break; - - default: - BUG(); - } - - return reg_array + vcpu_reg_offsets[mode][reg_num]; -} - -/* - * Return the SPSR for the current mode of the virtual CPU. - */ -static int vcpu_spsr32_mode(const struct kvm_vcpu *vcpu) -{ - unsigned long mode = *vcpu_cpsr(vcpu) & PSR_AA32_MODE_MASK; - switch (mode) { - case PSR_AA32_MODE_SVC: return KVM_SPSR_SVC; - case PSR_AA32_MODE_ABT: return KVM_SPSR_ABT; - case PSR_AA32_MODE_UND: return KVM_SPSR_UND; - case PSR_AA32_MODE_IRQ: return KVM_SPSR_IRQ; - case PSR_AA32_MODE_FIQ: return KVM_SPSR_FIQ; - default: BUG(); - } -} - -unsigned long vcpu_read_spsr32(const struct kvm_vcpu *vcpu) -{ - int spsr_idx = vcpu_spsr32_mode(vcpu); - - if (!vcpu->arch.sysregs_loaded_on_cpu) { - switch (spsr_idx) { - case KVM_SPSR_SVC: - return __vcpu_sys_reg(vcpu, SPSR_EL1); - case KVM_SPSR_ABT: - return vcpu->arch.ctxt.spsr_abt; - case KVM_SPSR_UND: - return vcpu->arch.ctxt.spsr_und; - case KVM_SPSR_IRQ: - return vcpu->arch.ctxt.spsr_irq; - case KVM_SPSR_FIQ: - return vcpu->arch.ctxt.spsr_fiq; - } - } - - switch (spsr_idx) { - case KVM_SPSR_SVC: - return read_sysreg_el1(SYS_SPSR); - case KVM_SPSR_ABT: - return read_sysreg(spsr_abt); - case KVM_SPSR_UND: - return read_sysreg(spsr_und); - case KVM_SPSR_IRQ: - return read_sysreg(spsr_irq); - case KVM_SPSR_FIQ: - return read_sysreg(spsr_fiq); - default: - BUG(); - } -} - -void vcpu_write_spsr32(struct kvm_vcpu *vcpu, unsigned long v) -{ - int spsr_idx = vcpu_spsr32_mode(vcpu); - - if (!vcpu->arch.sysregs_loaded_on_cpu) { - switch (spsr_idx) { - case KVM_SPSR_SVC: - __vcpu_sys_reg(vcpu, SPSR_EL1) = v; - break; - case KVM_SPSR_ABT: - vcpu->arch.ctxt.spsr_abt = v; - break; - case KVM_SPSR_UND: - vcpu->arch.ctxt.spsr_und = v; - break; - case KVM_SPSR_IRQ: - vcpu->arch.ctxt.spsr_irq = v; - break; - case KVM_SPSR_FIQ: - vcpu->arch.ctxt.spsr_fiq = v; - break; - } - - return; - } - - switch (spsr_idx) { - case KVM_SPSR_SVC: - write_sysreg_el1(v, SYS_SPSR); - break; - case KVM_SPSR_ABT: - write_sysreg(v, spsr_abt); - break; - case KVM_SPSR_UND: - write_sysreg(v, spsr_und); - break; - case KVM_SPSR_IRQ: - write_sysreg(v, spsr_irq); - break; - case KVM_SPSR_FIQ: - write_sysreg(v, spsr_fiq); - break; - } -} diff --git a/arch/arm64/kvm/reset.c b/arch/arm64/kvm/reset.c index f32490229a4c..47f3f035f3ea 100644 --- a/arch/arm64/kvm/reset.c +++ b/arch/arm64/kvm/reset.c @@ -25,7 +25,6 @@ #include <asm/ptrace.h> #include <asm/kvm_arm.h> #include <asm/kvm_asm.h> -#include <asm/kvm_coproc.h> #include <asm/kvm_emulate.h> #include <asm/kvm_mmu.h> #include <asm/virt.h> @@ -42,58 +41,6 @@ static u32 kvm_ipa_limit; #define VCPU_RESET_PSTATE_SVC (PSR_AA32_MODE_SVC | PSR_AA32_A_BIT | \ PSR_AA32_I_BIT | PSR_AA32_F_BIT) -static bool system_has_full_ptr_auth(void) -{ - return system_supports_address_auth() && system_supports_generic_auth(); -} - -/** - * kvm_arch_vm_ioctl_check_extension - * - * We currently assume that the number of HW registers is uniform - * across all CPUs (see cpuinfo_sanity_check). - */ -int kvm_arch_vm_ioctl_check_extension(struct kvm *kvm, long ext) -{ - int r; - - switch (ext) { - case KVM_CAP_ARM_EL1_32BIT: - r = cpus_have_const_cap(ARM64_HAS_32BIT_EL1); - break; - case KVM_CAP_GUEST_DEBUG_HW_BPS: - r = get_num_brps(); - break; - case KVM_CAP_GUEST_DEBUG_HW_WPS: - r = get_num_wrps(); - break; - case KVM_CAP_ARM_PMU_V3: - r = kvm_arm_support_pmu_v3(); - break; - case KVM_CAP_ARM_INJECT_SERROR_ESR: - r = cpus_have_const_cap(ARM64_HAS_RAS_EXTN); - break; - case KVM_CAP_SET_GUEST_DEBUG: - case KVM_CAP_VCPU_ATTRIBUTES: - r = 1; - break; - case KVM_CAP_ARM_VM_IPA_SIZE: - r = kvm_ipa_limit; - break; - case KVM_CAP_ARM_SVE: - r = system_supports_sve(); - break; - case KVM_CAP_ARM_PTRAUTH_ADDRESS: - case KVM_CAP_ARM_PTRAUTH_GENERIC: - r = system_has_full_ptr_auth(); - break; - default: - r = 0; - } - - return r; -} - unsigned int kvm_sve_max_vl; int kvm_arm_init_sve(void) @@ -286,6 +233,10 @@ int kvm_reset_vcpu(struct kvm_vcpu *vcpu) pstate = VCPU_RESET_PSTATE_EL1; } + if (kvm_vcpu_has_pmu(vcpu) && !kvm_arm_support_pmu_v3()) { + ret = -EINVAL; + goto out; + } break; } diff --git a/arch/arm64/kvm/sys_regs.c b/arch/arm64/kvm/sys_regs.c index c1fac9836af1..3313dedfa505 100644 --- a/arch/arm64/kvm/sys_regs.c +++ b/arch/arm64/kvm/sys_regs.c @@ -20,7 +20,6 @@ #include <asm/debug-monitors.h> #include <asm/esr.h> #include <asm/kvm_arm.h> -#include <asm/kvm_coproc.h> #include <asm/kvm_emulate.h> #include <asm/kvm_hyp.h> #include <asm/kvm_mmu.h> @@ -64,87 +63,6 @@ static bool write_to_read_only(struct kvm_vcpu *vcpu, return false; } -static bool __vcpu_read_sys_reg_from_cpu(int reg, u64 *val) -{ - /* - * System registers listed in the switch are not saved on every - * exit from the guest but are only saved on vcpu_put. - * - * Note that MPIDR_EL1 for the guest is set by KVM via VMPIDR_EL2 but - * should never be listed below, because the guest cannot modify its - * own MPIDR_EL1 and MPIDR_EL1 is accessed for VCPU A from VCPU B's - * thread when emulating cross-VCPU communication. - */ - switch (reg) { - case CSSELR_EL1: *val = read_sysreg_s(SYS_CSSELR_EL1); break; - case SCTLR_EL1: *val = read_sysreg_s(SYS_SCTLR_EL12); break; - case CPACR_EL1: *val = read_sysreg_s(SYS_CPACR_EL12); break; - case TTBR0_EL1: *val = read_sysreg_s(SYS_TTBR0_EL12); break; - case TTBR1_EL1: *val = read_sysreg_s(SYS_TTBR1_EL12); break; - case TCR_EL1: *val = read_sysreg_s(SYS_TCR_EL12); break; - case ESR_EL1: *val = read_sysreg_s(SYS_ESR_EL12); break; - case AFSR0_EL1: *val = read_sysreg_s(SYS_AFSR0_EL12); break; - case AFSR1_EL1: *val = read_sysreg_s(SYS_AFSR1_EL12); break; - case FAR_EL1: *val = read_sysreg_s(SYS_FAR_EL12); break; - case MAIR_EL1: *val = read_sysreg_s(SYS_MAIR_EL12); break; - case VBAR_EL1: *val = read_sysreg_s(SYS_VBAR_EL12); break; - case CONTEXTIDR_EL1: *val = read_sysreg_s(SYS_CONTEXTIDR_EL12);break; - case TPIDR_EL0: *val = read_sysreg_s(SYS_TPIDR_EL0); break; - case TPIDRRO_EL0: *val = read_sysreg_s(SYS_TPIDRRO_EL0); break; - case TPIDR_EL1: *val = read_sysreg_s(SYS_TPIDR_EL1); break; - case AMAIR_EL1: *val = read_sysreg_s(SYS_AMAIR_EL12); break; - case CNTKCTL_EL1: *val = read_sysreg_s(SYS_CNTKCTL_EL12); break; - case ELR_EL1: *val = read_sysreg_s(SYS_ELR_EL12); break; - case PAR_EL1: *val = read_sysreg_par(); break; - case DACR32_EL2: *val = read_sysreg_s(SYS_DACR32_EL2); break; - case IFSR32_EL2: *val = read_sysreg_s(SYS_IFSR32_EL2); break; - case DBGVCR32_EL2: *val = read_sysreg_s(SYS_DBGVCR32_EL2); break; - default: return false; - } - - return true; -} - -static bool __vcpu_write_sys_reg_to_cpu(u64 val, int reg) -{ - /* - * System registers listed in the switch are not restored on every - * entry to the guest but are only restored on vcpu_load. - * - * Note that MPIDR_EL1 for the guest is set by KVM via VMPIDR_EL2 but - * should never be listed below, because the MPIDR should only be set - * once, before running the VCPU, and never changed later. - */ - switch (reg) { - case CSSELR_EL1: write_sysreg_s(val, SYS_CSSELR_EL1); break; - case SCTLR_EL1: write_sysreg_s(val, SYS_SCTLR_EL12); break; - case CPACR_EL1: write_sysreg_s(val, SYS_CPACR_EL12); break; - case TTBR0_EL1: write_sysreg_s(val, SYS_TTBR0_EL12); break; - case TTBR1_EL1: write_sysreg_s(val, SYS_TTBR1_EL12); break; - case TCR_EL1: write_sysreg_s(val, SYS_TCR_EL12); break; - case ESR_EL1: write_sysreg_s(val, SYS_ESR_EL12); break; - case AFSR0_EL1: write_sysreg_s(val, SYS_AFSR0_EL12); break; - case AFSR1_EL1: write_sysreg_s(val, SYS_AFSR1_EL12); break; - case FAR_EL1: write_sysreg_s(val, SYS_FAR_EL12); break; - case MAIR_EL1: write_sysreg_s(val, SYS_MAIR_EL12); break; - case VBAR_EL1: write_sysreg_s(val, SYS_VBAR_EL12); break; - case CONTEXTIDR_EL1: write_sysreg_s(val, SYS_CONTEXTIDR_EL12);break; - case TPIDR_EL0: write_sysreg_s(val, SYS_TPIDR_EL0); break; - case TPIDRRO_EL0: write_sysreg_s(val, SYS_TPIDRRO_EL0); break; - case TPIDR_EL1: write_sysreg_s(val, SYS_TPIDR_EL1); break; - case AMAIR_EL1: write_sysreg_s(val, SYS_AMAIR_EL12); break; - case CNTKCTL_EL1: write_sysreg_s(val, SYS_CNTKCTL_EL12); break; - case ELR_EL1: write_sysreg_s(val, SYS_ELR_EL12); break; - case PAR_EL1: write_sysreg_s(val, SYS_PAR_EL1); break; - case DACR32_EL2: write_sysreg_s(val, SYS_DACR32_EL2); break; - case IFSR32_EL2: write_sysreg_s(val, SYS_IFSR32_EL2); break; - case DBGVCR32_EL2: write_sysreg_s(val, SYS_DBGVCR32_EL2); break; - default: return false; - } - - return true; -} - u64 vcpu_read_sys_reg(const struct kvm_vcpu *vcpu, int reg) { u64 val = 0x8badf00d8badf00d; @@ -169,7 +87,7 @@ void vcpu_write_sys_reg(struct kvm_vcpu *vcpu, u64 val, int reg) static u32 cache_levels; /* CSSELR values; used to index KVM_REG_ARM_DEMUX_ID_CCSIDR */ -#define CSSELR_MAX 12 +#define CSSELR_MAX 14 /* Which cache CCSIDR represents depends on CSSELR value. */ static u32 get_ccsidr(u32 csselr) @@ -209,6 +127,24 @@ static bool access_dcsw(struct kvm_vcpu *vcpu, return true; } +static void get_access_mask(const struct sys_reg_desc *r, u64 *mask, u64 *shift) +{ + switch (r->aarch32_map) { + case AA32_LO: + *mask = GENMASK_ULL(31, 0); + *shift = 0; + break; + case AA32_HI: + *mask = GENMASK_ULL(63, 32); + *shift = 32; + break; + default: + *mask = GENMASK_ULL(63, 0); + *shift = 0; + break; + } +} + /* * Generic accessor for VM registers. Only called as long as HCR_TVM * is set. If the guest enables the MMU, we stop trapping the VM @@ -219,26 +155,21 @@ static bool access_vm_reg(struct kvm_vcpu *vcpu, const struct sys_reg_desc *r) { bool was_enabled = vcpu_has_cache_enabled(vcpu); - u64 val; - int reg = r->reg; + u64 val, mask, shift; BUG_ON(!p->is_write); - /* See the 32bit mapping in kvm_host.h */ - if (p->is_aarch32) - reg = r->reg / 2; + get_access_mask(r, &mask, &shift); - if (!p->is_aarch32 || !p->is_32bit) { - val = p->regval; + if (~mask) { + val = vcpu_read_sys_reg(vcpu, r->reg); + val &= ~mask; } else { - val = vcpu_read_sys_reg(vcpu, reg); - if (r->reg % 2) - val = (p->regval << 32) | (u64)lower_32_bits(val); - else - val = ((u64)upper_32_bits(val) << 32) | - lower_32_bits(p->regval); + val = 0; } - vcpu_write_sys_reg(vcpu, val, reg); + + val |= (p->regval & (mask >> shift)) << shift; + vcpu_write_sys_reg(vcpu, val, r->reg); kvm_toggle_cache(vcpu, was_enabled); return true; @@ -248,17 +179,13 @@ static bool access_actlr(struct kvm_vcpu *vcpu, struct sys_reg_params *p, const struct sys_reg_desc *r) { + u64 mask, shift; + if (p->is_write) return ignore_write(vcpu, p); - p->regval = vcpu_read_sys_reg(vcpu, ACTLR_EL1); - - if (p->is_aarch32) { - if (r->Op2 & 2) - p->regval = upper_32_bits(p->regval); - else - p->regval = lower_32_bits(p->regval); - } + get_access_mask(r, &mask, &shift); + p->regval = (vcpu_read_sys_reg(vcpu, r->reg) & mask) >> shift; return true; } @@ -285,7 +212,7 @@ static bool access_gic_sgi(struct kvm_vcpu *vcpu, * equivalent to ICC_SGI0R_EL1, as there is no "alternative" secure * group. */ - if (p->is_aarch32) { + if (p->Op0 == 0) { /* AArch32 */ switch (p->Op1) { default: /* Keep GCC quiet */ case 0: /* ICC_SGI1R */ @@ -296,7 +223,7 @@ static bool access_gic_sgi(struct kvm_vcpu *vcpu, g1 = false; break; } - } else { + } else { /* AArch64 */ switch (p->Op2) { default: /* Keep GCC quiet */ case 5: /* ICC_SGI1R_EL1 */ @@ -438,26 +365,30 @@ static bool trap_debug_regs(struct kvm_vcpu *vcpu, */ static void reg_to_dbg(struct kvm_vcpu *vcpu, struct sys_reg_params *p, + const struct sys_reg_desc *rd, u64 *dbg_reg) { - u64 val = p->regval; + u64 mask, shift, val; - if (p->is_32bit) { - val &= 0xffffffffUL; - val |= ((*dbg_reg >> 32) << 32); - } + get_access_mask(rd, &mask, &shift); + val = *dbg_reg; + val &= ~mask; + val |= (p->regval & (mask >> shift)) << shift; *dbg_reg = val; + vcpu->arch.flags |= KVM_ARM64_DEBUG_DIRTY; } static void dbg_to_reg(struct kvm_vcpu *vcpu, struct sys_reg_params *p, + const struct sys_reg_desc *rd, u64 *dbg_reg) { - p->regval = *dbg_reg; - if (p->is_32bit) - p->regval &= 0xffffffffUL; + u64 mask, shift; + + get_access_mask(rd, &mask, &shift); + p->regval = (*dbg_reg & mask) >> shift; } static bool trap_bvr(struct kvm_vcpu *vcpu, @@ -467,9 +398,9 @@ static bool trap_bvr(struct kvm_vcpu *vcpu, u64 *dbg_reg = &vcpu->arch.vcpu_debug_state.dbg_bvr[rd->reg]; if (p->is_write) - reg_to_dbg(vcpu, p, dbg_reg); + reg_to_dbg(vcpu, p, rd, dbg_reg); else - dbg_to_reg(vcpu, p, dbg_reg); + dbg_to_reg(vcpu, p, rd, dbg_reg); trace_trap_reg(__func__, rd->reg, p->is_write, *dbg_reg); @@ -509,9 +440,9 @@ static bool trap_bcr(struct kvm_vcpu *vcpu, u64 *dbg_reg = &vcpu->arch.vcpu_debug_state.dbg_bcr[rd->reg]; if (p->is_write) - reg_to_dbg(vcpu, p, dbg_reg); + reg_to_dbg(vcpu, p, rd, dbg_reg); else - dbg_to_reg(vcpu, p, dbg_reg); + dbg_to_reg(vcpu, p, rd, dbg_reg); trace_trap_reg(__func__, rd->reg, p->is_write, *dbg_reg); @@ -552,9 +483,9 @@ static bool trap_wvr(struct kvm_vcpu *vcpu, u64 *dbg_reg = &vcpu->arch.vcpu_debug_state.dbg_wvr[rd->reg]; if (p->is_write) - reg_to_dbg(vcpu, p, dbg_reg); + reg_to_dbg(vcpu, p, rd, dbg_reg); else - dbg_to_reg(vcpu, p, dbg_reg); + dbg_to_reg(vcpu, p, rd, dbg_reg); trace_trap_reg(__func__, rd->reg, p->is_write, vcpu->arch.vcpu_debug_state.dbg_wvr[rd->reg]); @@ -595,9 +526,9 @@ static bool trap_wcr(struct kvm_vcpu *vcpu, u64 *dbg_reg = &vcpu->arch.vcpu_debug_state.dbg_wcr[rd->reg]; if (p->is_write) - reg_to_dbg(vcpu, p, dbg_reg); + reg_to_dbg(vcpu, p, rd, dbg_reg); else - dbg_to_reg(vcpu, p, dbg_reg); + dbg_to_reg(vcpu, p, rd, dbg_reg); trace_trap_reg(__func__, rd->reg, p->is_write, *dbg_reg); @@ -678,8 +609,9 @@ static void reset_pmcr(struct kvm_vcpu *vcpu, const struct sys_reg_desc *r) static bool check_pmu_access_disabled(struct kvm_vcpu *vcpu, u64 flags) { u64 reg = __vcpu_sys_reg(vcpu, PMUSERENR_EL0); - bool enabled = (reg & flags) || vcpu_mode_priv(vcpu); + bool enabled = kvm_vcpu_has_pmu(vcpu); + enabled &= (reg & flags) || vcpu_mode_priv(vcpu); if (!enabled) kvm_inject_undefined(vcpu); @@ -711,9 +643,6 @@ static bool access_pmcr(struct kvm_vcpu *vcpu, struct sys_reg_params *p, { u64 val; - if (!kvm_arm_pmu_v3_ready(vcpu)) - return trap_raz_wi(vcpu, p, r); - if (pmu_access_el0_disabled(vcpu)) return false; @@ -740,9 +669,6 @@ static bool access_pmcr(struct kvm_vcpu *vcpu, struct sys_reg_params *p, static bool access_pmselr(struct kvm_vcpu *vcpu, struct sys_reg_params *p, const struct sys_reg_desc *r) { - if (!kvm_arm_pmu_v3_ready(vcpu)) - return trap_raz_wi(vcpu, p, r); - if (pmu_access_event_counter_el0_disabled(vcpu)) return false; @@ -761,9 +687,6 @@ static bool access_pmceid(struct kvm_vcpu *vcpu, struct sys_reg_params *p, { u64 pmceid; - if (!kvm_arm_pmu_v3_ready(vcpu)) - return trap_raz_wi(vcpu, p, r); - BUG_ON(p->is_write); if (pmu_access_el0_disabled(vcpu)) @@ -794,10 +717,7 @@ static bool access_pmu_evcntr(struct kvm_vcpu *vcpu, struct sys_reg_params *p, const struct sys_reg_desc *r) { - u64 idx; - - if (!kvm_arm_pmu_v3_ready(vcpu)) - return trap_raz_wi(vcpu, p, r); + u64 idx = ~0UL; if (r->CRn == 9 && r->CRm == 13) { if (r->Op2 == 2) { @@ -813,8 +733,6 @@ static bool access_pmu_evcntr(struct kvm_vcpu *vcpu, return false; idx = ARMV8_PMU_CYCLE_IDX; - } else { - return false; } } else if (r->CRn == 0 && r->CRm == 9) { /* PMCCNTR */ @@ -828,10 +746,11 @@ static bool access_pmu_evcntr(struct kvm_vcpu *vcpu, return false; idx = ((r->CRm & 3) << 3) | (r->Op2 & 7); - } else { - return false; } + /* Catch any decoding mistake */ + WARN_ON(idx == ~0UL); + if (!pmu_counter_idx_valid(vcpu, idx)) return false; @@ -852,9 +771,6 @@ static bool access_pmu_evtyper(struct kvm_vcpu *vcpu, struct sys_reg_params *p, { u64 idx, reg; - if (!kvm_arm_pmu_v3_ready(vcpu)) - return trap_raz_wi(vcpu, p, r); - if (pmu_access_el0_disabled(vcpu)) return false; @@ -892,9 +808,6 @@ static bool access_pmcnten(struct kvm_vcpu *vcpu, struct sys_reg_params *p, { u64 val, mask; - if (!kvm_arm_pmu_v3_ready(vcpu)) - return trap_raz_wi(vcpu, p, r); - if (pmu_access_el0_disabled(vcpu)) return false; @@ -923,13 +836,8 @@ static bool access_pminten(struct kvm_vcpu *vcpu, struct sys_reg_params *p, { u64 mask = kvm_pmu_valid_counter_mask(vcpu); - if (!kvm_arm_pmu_v3_ready(vcpu)) - return trap_raz_wi(vcpu, p, r); - - if (!vcpu_mode_priv(vcpu)) { - kvm_inject_undefined(vcpu); + if (check_pmu_access_disabled(vcpu, 0)) return false; - } if (p->is_write) { u64 val = p->regval & mask; @@ -952,9 +860,6 @@ static bool access_pmovs(struct kvm_vcpu *vcpu, struct sys_reg_params *p, { u64 mask = kvm_pmu_valid_counter_mask(vcpu); - if (!kvm_arm_pmu_v3_ready(vcpu)) - return trap_raz_wi(vcpu, p, r); - if (pmu_access_el0_disabled(vcpu)) return false; @@ -977,9 +882,6 @@ static bool access_pmswinc(struct kvm_vcpu *vcpu, struct sys_reg_params *p, { u64 mask; - if (!kvm_arm_pmu_v3_ready(vcpu)) - return trap_raz_wi(vcpu, p, r); - if (!p->is_write) return read_from_write_only(vcpu, p, r); @@ -994,8 +896,10 @@ static bool access_pmswinc(struct kvm_vcpu *vcpu, struct sys_reg_params *p, static bool access_pmuserenr(struct kvm_vcpu *vcpu, struct sys_reg_params *p, const struct sys_reg_desc *r) { - if (!kvm_arm_pmu_v3_ready(vcpu)) - return trap_raz_wi(vcpu, p, r); + if (!kvm_vcpu_has_pmu(vcpu)) { + kvm_inject_undefined(vcpu); + return false; + } if (p->is_write) { if (!vcpu_mode_priv(vcpu)) { @@ -1122,6 +1026,8 @@ static u64 read_id_reg(const struct kvm_vcpu *vcpu, val &= ~(0xfUL << ID_AA64PFR0_AMU_SHIFT); val &= ~(0xfUL << ID_AA64PFR0_CSV2_SHIFT); val |= ((u64)vcpu->kvm->arch.pfr0_csv2 << ID_AA64PFR0_CSV2_SHIFT); + val &= ~(0xfUL << ID_AA64PFR0_CSV3_SHIFT); + val |= ((u64)vcpu->kvm->arch.pfr0_csv3 << ID_AA64PFR0_CSV3_SHIFT); } else if (id == SYS_ID_AA64PFR1_EL1) { val &= ~(0xfUL << ID_AA64PFR1_MTE_SHIFT); } else if (id == SYS_ID_AA64ISAR1_EL1 && !vcpu_has_ptrauth(vcpu)) { @@ -1130,10 +1036,15 @@ static u64 read_id_reg(const struct kvm_vcpu *vcpu, (0xfUL << ID_AA64ISAR1_GPA_SHIFT) | (0xfUL << ID_AA64ISAR1_GPI_SHIFT)); } else if (id == SYS_ID_AA64DFR0_EL1) { + u64 cap = 0; + /* Limit guests to PMUv3 for ARMv8.1 */ + if (kvm_vcpu_has_pmu(vcpu)) + cap = ID_AA64DFR0_PMUVER_8_1; + val = cpuid_feature_cap_perfmon_field(val, ID_AA64DFR0_PMUVER_SHIFT, - ID_AA64DFR0_PMUVER_8_1); + cap); } else if (id == SYS_ID_DFR0_EL1) { /* Limit guests to PMUv3 for ARMv8.1 */ val = cpuid_feature_cap_perfmon_field(val, @@ -1209,9 +1120,9 @@ static int set_id_aa64pfr0_el1(struct kvm_vcpu *vcpu, const struct kvm_one_reg *reg, void __user *uaddr) { const u64 id = sys_reg_to_index(rd); + u8 csv2, csv3; int err; u64 val; - u8 csv2; err = reg_from_user(&val, uaddr, id); if (err) @@ -1227,13 +1138,21 @@ static int set_id_aa64pfr0_el1(struct kvm_vcpu *vcpu, (csv2 && arm64_get_spectre_v2_state() != SPECTRE_UNAFFECTED)) return -EINVAL; - /* We can only differ with CSV2, and anything else is an error */ + /* Same thing for CSV3 */ + csv3 = cpuid_feature_extract_unsigned_field(val, ID_AA64PFR0_CSV3_SHIFT); + if (csv3 > 1 || + (csv3 && arm64_get_meltdown_state() != SPECTRE_UNAFFECTED)) + return -EINVAL; + + /* We can only differ with CSV[23], and anything else is an error */ val ^= read_id_reg(vcpu, rd, false); - val &= ~(0xFUL << ID_AA64PFR0_CSV2_SHIFT); + val &= ~((0xFUL << ID_AA64PFR0_CSV2_SHIFT) | + (0xFUL << ID_AA64PFR0_CSV3_SHIFT)); if (val) return -EINVAL; vcpu->kvm->arch.pfr0_csv2 = csv2; + vcpu->kvm->arch.pfr0_csv3 = csv3 ; return 0; } @@ -1327,10 +1246,6 @@ static bool access_csselr(struct kvm_vcpu *vcpu, struct sys_reg_params *p, { int reg = r->reg; - /* See the 32bit mapping in kvm_host.h */ - if (p->is_aarch32) - reg = r->reg / 2; - if (p->is_write) vcpu_write_sys_reg(vcpu, p->regval, reg); else @@ -1801,66 +1716,27 @@ static bool trap_dbgidr(struct kvm_vcpu *vcpu, } } -static bool trap_debug32(struct kvm_vcpu *vcpu, - struct sys_reg_params *p, - const struct sys_reg_desc *r) -{ - if (p->is_write) { - vcpu_cp14(vcpu, r->reg) = p->regval; - vcpu->arch.flags |= KVM_ARM64_DEBUG_DIRTY; - } else { - p->regval = vcpu_cp14(vcpu, r->reg); - } - - return true; -} - -/* AArch32 debug register mappings +/* + * AArch32 debug register mappings * * AArch32 DBGBVRn is mapped to DBGBVRn_EL1[31:0] * AArch32 DBGBXVRn is mapped to DBGBVRn_EL1[63:32] * - * All control registers and watchpoint value registers are mapped to - * the lower 32 bits of their AArch64 equivalents. We share the trap - * handlers with the above AArch64 code which checks what mode the - * system is in. + * None of the other registers share their location, so treat them as + * if they were 64bit. */ - -static bool trap_xvr(struct kvm_vcpu *vcpu, - struct sys_reg_params *p, - const struct sys_reg_desc *rd) -{ - u64 *dbg_reg = &vcpu->arch.vcpu_debug_state.dbg_bvr[rd->reg]; - - if (p->is_write) { - u64 val = *dbg_reg; - - val &= 0xffffffffUL; - val |= p->regval << 32; - *dbg_reg = val; - - vcpu->arch.flags |= KVM_ARM64_DEBUG_DIRTY; - } else { - p->regval = *dbg_reg >> 32; - } - - trace_trap_reg(__func__, rd->reg, p->is_write, *dbg_reg); - - return true; -} - -#define DBG_BCR_BVR_WCR_WVR(n) \ - /* DBGBVRn */ \ - { Op1( 0), CRn( 0), CRm((n)), Op2( 4), trap_bvr, NULL, n }, \ - /* DBGBCRn */ \ - { Op1( 0), CRn( 0), CRm((n)), Op2( 5), trap_bcr, NULL, n }, \ - /* DBGWVRn */ \ - { Op1( 0), CRn( 0), CRm((n)), Op2( 6), trap_wvr, NULL, n }, \ - /* DBGWCRn */ \ +#define DBG_BCR_BVR_WCR_WVR(n) \ + /* DBGBVRn */ \ + { AA32(LO), Op1( 0), CRn( 0), CRm((n)), Op2( 4), trap_bvr, NULL, n }, \ + /* DBGBCRn */ \ + { Op1( 0), CRn( 0), CRm((n)), Op2( 5), trap_bcr, NULL, n }, \ + /* DBGWVRn */ \ + { Op1( 0), CRn( 0), CRm((n)), Op2( 6), trap_wvr, NULL, n }, \ + /* DBGWCRn */ \ { Op1( 0), CRn( 0), CRm((n)), Op2( 7), trap_wcr, NULL, n } -#define DBGBXVR(n) \ - { Op1( 0), CRn( 1), CRm((n)), Op2( 1), trap_xvr, NULL, n } +#define DBGBXVR(n) \ + { AA32(HI), Op1( 0), CRn( 1), CRm((n)), Op2( 1), trap_bvr, NULL, n } /* * Trapped cp14 registers. We generally ignore most of the external @@ -1878,9 +1754,9 @@ static const struct sys_reg_desc cp14_regs[] = { { Op1( 0), CRn( 0), CRm( 1), Op2( 0), trap_raz_wi }, DBG_BCR_BVR_WCR_WVR(1), /* DBGDCCINT */ - { Op1( 0), CRn( 0), CRm( 2), Op2( 0), trap_debug32, NULL, cp14_DBGDCCINT }, + { Op1( 0), CRn( 0), CRm( 2), Op2( 0), trap_debug_regs, NULL, MDCCINT_EL1 }, /* DBGDSCRext */ - { Op1( 0), CRn( 0), CRm( 2), Op2( 2), trap_debug32, NULL, cp14_DBGDSCRext }, + { Op1( 0), CRn( 0), CRm( 2), Op2( 2), trap_debug_regs, NULL, MDSCR_EL1 }, DBG_BCR_BVR_WCR_WVR(2), /* DBGDTR[RT]Xint */ { Op1( 0), CRn( 0), CRm( 3), Op2( 0), trap_raz_wi }, @@ -1895,7 +1771,7 @@ static const struct sys_reg_desc cp14_regs[] = { { Op1( 0), CRn( 0), CRm( 6), Op2( 2), trap_raz_wi }, DBG_BCR_BVR_WCR_WVR(6), /* DBGVCR */ - { Op1( 0), CRn( 0), CRm( 7), Op2( 0), trap_debug32, NULL, cp14_DBGVCR }, + { Op1( 0), CRn( 0), CRm( 7), Op2( 0), trap_debug_regs, NULL, DBGVCR32_EL2 }, DBG_BCR_BVR_WCR_WVR(7), DBG_BCR_BVR_WCR_WVR(8), DBG_BCR_BVR_WCR_WVR(9), @@ -1981,19 +1857,29 @@ static const struct sys_reg_desc cp14_64_regs[] = { */ static const struct sys_reg_desc cp15_regs[] = { { Op1( 0), CRn( 0), CRm( 0), Op2( 1), access_ctr }, - { Op1( 0), CRn( 1), CRm( 0), Op2( 0), access_vm_reg, NULL, c1_SCTLR }, - { Op1( 0), CRn( 1), CRm( 0), Op2( 1), access_actlr }, - { Op1( 0), CRn( 1), CRm( 0), Op2( 3), access_actlr }, - { Op1( 0), CRn( 2), CRm( 0), Op2( 0), access_vm_reg, NULL, c2_TTBR0 }, - { Op1( 0), CRn( 2), CRm( 0), Op2( 1), access_vm_reg, NULL, c2_TTBR1 }, - { Op1( 0), CRn( 2), CRm( 0), Op2( 2), access_vm_reg, NULL, c2_TTBCR }, - { Op1( 0), CRn( 3), CRm( 0), Op2( 0), access_vm_reg, NULL, c3_DACR }, - { Op1( 0), CRn( 5), CRm( 0), Op2( 0), access_vm_reg, NULL, c5_DFSR }, - { Op1( 0), CRn( 5), CRm( 0), Op2( 1), access_vm_reg, NULL, c5_IFSR }, - { Op1( 0), CRn( 5), CRm( 1), Op2( 0), access_vm_reg, NULL, c5_ADFSR }, - { Op1( 0), CRn( 5), CRm( 1), Op2( 1), access_vm_reg, NULL, c5_AIFSR }, - { Op1( 0), CRn( 6), CRm( 0), Op2( 0), access_vm_reg, NULL, c6_DFAR }, - { Op1( 0), CRn( 6), CRm( 0), Op2( 2), access_vm_reg, NULL, c6_IFAR }, + { Op1( 0), CRn( 1), CRm( 0), Op2( 0), access_vm_reg, NULL, SCTLR_EL1 }, + /* ACTLR */ + { AA32(LO), Op1( 0), CRn( 1), CRm( 0), Op2( 1), access_actlr, NULL, ACTLR_EL1 }, + /* ACTLR2 */ + { AA32(HI), Op1( 0), CRn( 1), CRm( 0), Op2( 3), access_actlr, NULL, ACTLR_EL1 }, + { Op1( 0), CRn( 2), CRm( 0), Op2( 0), access_vm_reg, NULL, TTBR0_EL1 }, + { Op1( 0), CRn( 2), CRm( 0), Op2( 1), access_vm_reg, NULL, TTBR1_EL1 }, + /* TTBCR */ + { AA32(LO), Op1( 0), CRn( 2), CRm( 0), Op2( 2), access_vm_reg, NULL, TCR_EL1 }, + /* TTBCR2 */ + { AA32(HI), Op1( 0), CRn( 2), CRm( 0), Op2( 3), access_vm_reg, NULL, TCR_EL1 }, + { Op1( 0), CRn( 3), CRm( 0), Op2( 0), access_vm_reg, NULL, DACR32_EL2 }, + /* DFSR */ + { Op1( 0), CRn( 5), CRm( 0), Op2( 0), access_vm_reg, NULL, ESR_EL1 }, + { Op1( 0), CRn( 5), CRm( 0), Op2( 1), access_vm_reg, NULL, IFSR32_EL2 }, + /* ADFSR */ + { Op1( 0), CRn( 5), CRm( 1), Op2( 0), access_vm_reg, NULL, AFSR0_EL1 }, + /* AIFSR */ + { Op1( 0), CRn( 5), CRm( 1), Op2( 1), access_vm_reg, NULL, AFSR1_EL1 }, + /* DFAR */ + { AA32(LO), Op1( 0), CRn( 6), CRm( 0), Op2( 0), access_vm_reg, NULL, FAR_EL1 }, + /* IFAR */ + { AA32(HI), Op1( 0), CRn( 6), CRm( 0), Op2( 2), access_vm_reg, NULL, FAR_EL1 }, /* * DC{C,I,CI}SW operations: @@ -2019,15 +1905,19 @@ static const struct sys_reg_desc cp15_regs[] = { { Op1( 0), CRn( 9), CRm(14), Op2( 2), access_pminten }, { Op1( 0), CRn( 9), CRm(14), Op2( 3), access_pmovs }, - { Op1( 0), CRn(10), CRm( 2), Op2( 0), access_vm_reg, NULL, c10_PRRR }, - { Op1( 0), CRn(10), CRm( 2), Op2( 1), access_vm_reg, NULL, c10_NMRR }, - { Op1( 0), CRn(10), CRm( 3), Op2( 0), access_vm_reg, NULL, c10_AMAIR0 }, - { Op1( 0), CRn(10), CRm( 3), Op2( 1), access_vm_reg, NULL, c10_AMAIR1 }, + /* PRRR/MAIR0 */ + { AA32(LO), Op1( 0), CRn(10), CRm( 2), Op2( 0), access_vm_reg, NULL, MAIR_EL1 }, + /* NMRR/MAIR1 */ + { AA32(HI), Op1( 0), CRn(10), CRm( 2), Op2( 1), access_vm_reg, NULL, MAIR_EL1 }, + /* AMAIR0 */ + { AA32(LO), Op1( 0), CRn(10), CRm( 3), Op2( 0), access_vm_reg, NULL, AMAIR_EL1 }, + /* AMAIR1 */ + { AA32(HI), Op1( 0), CRn(10), CRm( 3), Op2( 1), access_vm_reg, NULL, AMAIR_EL1 }, /* ICC_SRE */ { Op1( 0), CRn(12), CRm(12), Op2( 5), access_gic_sre }, - { Op1( 0), CRn(13), CRm( 0), Op2( 1), access_vm_reg, NULL, c13_CID }, + { Op1( 0), CRn(13), CRm( 0), Op2( 1), access_vm_reg, NULL, CONTEXTIDR_EL1 }, /* Arch Tmers */ { SYS_DESC(SYS_AARCH32_CNTP_TVAL), access_arch_timer }, @@ -2102,14 +1992,14 @@ static const struct sys_reg_desc cp15_regs[] = { { Op1(1), CRn( 0), CRm( 0), Op2(0), access_ccsidr }, { Op1(1), CRn( 0), CRm( 0), Op2(1), access_clidr }, - { Op1(2), CRn( 0), CRm( 0), Op2(0), access_csselr, NULL, c0_CSSELR }, + { Op1(2), CRn( 0), CRm( 0), Op2(0), access_csselr, NULL, CSSELR_EL1 }, }; static const struct sys_reg_desc cp15_64_regs[] = { - { Op1( 0), CRn( 0), CRm( 2), Op2( 0), access_vm_reg, NULL, c2_TTBR0 }, + { Op1( 0), CRn( 0), CRm( 2), Op2( 0), access_vm_reg, NULL, TTBR0_EL1 }, { Op1( 0), CRn( 0), CRm( 9), Op2( 0), access_pmu_evcntr }, { Op1( 0), CRn( 0), CRm(12), Op2( 0), access_gic_sgi }, /* ICC_SGI1R */ - { Op1( 1), CRn( 0), CRm( 2), Op2( 0), access_vm_reg, NULL, c2_TTBR1 }, + { Op1( 1), CRn( 0), CRm( 2), Op2( 0), access_vm_reg, NULL, TTBR1_EL1 }, { Op1( 1), CRn( 0), CRm(12), Op2( 0), access_gic_sgi }, /* ICC_ASGI1R */ { Op1( 2), CRn( 0), CRm(12), Op2( 0), access_gic_sgi }, /* ICC_SGI0R */ { SYS_DESC(SYS_AARCH32_CNTP_CVAL), access_arch_timer }, @@ -2180,7 +2070,7 @@ static void perform_access(struct kvm_vcpu *vcpu, /* Skip instruction if instructed so */ if (likely(r->access(vcpu, params, r))) - kvm_skip_instr(vcpu, kvm_vcpu_trap_il_is32bit(vcpu)); + kvm_incr_pc(vcpu); } /* @@ -2253,8 +2143,6 @@ static int kvm_handle_cp_64(struct kvm_vcpu *vcpu, int Rt = kvm_vcpu_sys_get_rt(vcpu); int Rt2 = (esr >> 10) & 0x1f; - params.is_aarch32 = true; - params.is_32bit = false; params.CRm = (esr >> 1) & 0xf; params.is_write = ((esr & 1) == 0); @@ -2304,8 +2192,6 @@ static int kvm_handle_cp_32(struct kvm_vcpu *vcpu, u32 esr = kvm_vcpu_get_esr(vcpu); int Rt = kvm_vcpu_sys_get_rt(vcpu); - params.is_aarch32 = true; - params.is_32bit = true; params.CRm = (esr >> 1) & 0xf; params.regval = vcpu_get_reg(vcpu, Rt); params.is_write = ((esr & 1) == 0); @@ -2399,8 +2285,6 @@ int kvm_handle_sys_reg(struct kvm_vcpu *vcpu) trace_kvm_handle_sys_reg(esr); - params.is_aarch32 = false; - params.is_32bit = false; params.Op0 = (esr >> 20) & 3; params.Op1 = (esr >> 14) & 0x7; params.CRn = (esr >> 10) & 0xf; diff --git a/arch/arm64/kvm/sys_regs.h b/arch/arm64/kvm/sys_regs.h index 0f95964339b1..9d0621417c2a 100644 --- a/arch/arm64/kvm/sys_regs.h +++ b/arch/arm64/kvm/sys_regs.h @@ -19,14 +19,18 @@ struct sys_reg_params { u8 Op2; u64 regval; bool is_write; - bool is_aarch32; - bool is_32bit; /* Only valid if is_aarch32 is true */ }; struct sys_reg_desc { /* Sysreg string for debug */ const char *name; + enum { + AA32_ZEROHIGH, + AA32_LO, + AA32_HI, + } aarch32_map; + /* MRS/MSR instruction which accesses it. */ u8 Op0; u8 Op1; @@ -153,6 +157,7 @@ const struct sys_reg_desc *find_reg_by_id(u64 id, const struct sys_reg_desc table[], unsigned int num); +#define AA32(_x) .aarch32_map = AA32_##_x #define Op0(_x) .Op0 = _x #define Op1(_x) .Op1 = _x #define CRn(_x) .CRn = _x diff --git a/arch/arm64/kvm/va_layout.c b/arch/arm64/kvm/va_layout.c index e0404bcab019..d8cc51bd60bf 100644 --- a/arch/arm64/kvm/va_layout.c +++ b/arch/arm64/kvm/va_layout.c @@ -11,6 +11,7 @@ #include <asm/debug-monitors.h> #include <asm/insn.h> #include <asm/kvm_mmu.h> +#include <asm/memory.h> /* * The LSB of the HYP VA tag @@ -23,6 +24,30 @@ static u64 tag_val; static u64 va_mask; /* + * Compute HYP VA by using the same computation as kern_hyp_va(). + */ +static u64 __early_kern_hyp_va(u64 addr) +{ + addr &= va_mask; + addr |= tag_val << tag_lsb; + return addr; +} + +/* + * Store a hyp VA <-> PA offset into a hyp-owned variable. + */ +static void init_hyp_physvirt_offset(void) +{ + extern s64 kvm_nvhe_sym(hyp_physvirt_offset); + u64 kern_va, hyp_va; + + /* Compute the offset from the hyp VA and PA of a random symbol. */ + kern_va = (u64)kvm_ksym_ref(__hyp_text_start); + hyp_va = __early_kern_hyp_va(kern_va); + CHOOSE_NVHE_SYM(hyp_physvirt_offset) = (s64)__pa(kern_va) - (s64)hyp_va; +} + +/* * We want to generate a hyp VA with the following format (with V == * vabits_actual): * @@ -53,6 +78,8 @@ __init void kvm_compute_layout(void) tag_val |= get_random_long() & GENMASK_ULL(vabits_actual - 2, tag_lsb); } tag_val >>= tag_lsb; + + init_hyp_physvirt_offset(); } static u32 compute_instruction(int n, u32 rd, u32 rn) @@ -131,28 +158,21 @@ void __init kvm_update_va_mask(struct alt_instr *alt, } } -void *__kvm_bp_vect_base; -int __kvm_harden_el2_vector_slot; - void kvm_patch_vector_branch(struct alt_instr *alt, __le32 *origptr, __le32 *updptr, int nr_inst) { u64 addr; u32 insn; - BUG_ON(nr_inst != 5); + BUG_ON(nr_inst != 4); - if (has_vhe() || !cpus_have_const_cap(ARM64_HARDEN_EL2_VECTORS)) { - WARN_ON_ONCE(cpus_have_const_cap(ARM64_HARDEN_EL2_VECTORS)); + if (!cpus_have_const_cap(ARM64_SPECTRE_V3A) || WARN_ON_ONCE(has_vhe())) return; - } /* * Compute HYP VA by using the same computation as kern_hyp_va() */ - addr = (uintptr_t)kvm_ksym_ref(__kvm_hyp_vector); - addr &= va_mask; - addr |= tag_val << tag_lsb; + addr = __early_kern_hyp_va((u64)kvm_ksym_ref(__kvm_hyp_vector)); /* Use PC[10:7] to branch to the same vector in KVM */ addr |= ((u64)origptr & GENMASK_ULL(10, 7)); @@ -163,15 +183,6 @@ void kvm_patch_vector_branch(struct alt_instr *alt, */ addr += KVM_VECTOR_PREAMBLE; - /* stp x0, x1, [sp, #-16]! */ - insn = aarch64_insn_gen_load_store_pair(AARCH64_INSN_REG_0, - AARCH64_INSN_REG_1, - AARCH64_INSN_REG_SP, - -16, - AARCH64_INSN_VARIANT_64BIT, - AARCH64_INSN_LDST_STORE_PAIR_PRE_INDEX); - *updptr++ = cpu_to_le32(insn); - /* movz x0, #(addr & 0xffff) */ insn = aarch64_insn_gen_movewide(AARCH64_INSN_REG_0, (u16)addr, @@ -201,3 +212,58 @@ void kvm_patch_vector_branch(struct alt_instr *alt, AARCH64_INSN_BRANCH_NOLINK); *updptr++ = cpu_to_le32(insn); } + +static void generate_mov_q(u64 val, __le32 *origptr, __le32 *updptr, int nr_inst) +{ + u32 insn, oinsn, rd; + + BUG_ON(nr_inst != 4); + + /* Compute target register */ + oinsn = le32_to_cpu(*origptr); + rd = aarch64_insn_decode_register(AARCH64_INSN_REGTYPE_RD, oinsn); + + /* movz rd, #(val & 0xffff) */ + insn = aarch64_insn_gen_movewide(rd, + (u16)val, + 0, + AARCH64_INSN_VARIANT_64BIT, + AARCH64_INSN_MOVEWIDE_ZERO); + *updptr++ = cpu_to_le32(insn); + + /* movk rd, #((val >> 16) & 0xffff), lsl #16 */ + insn = aarch64_insn_gen_movewide(rd, + (u16)(val >> 16), + 16, + AARCH64_INSN_VARIANT_64BIT, + AARCH64_INSN_MOVEWIDE_KEEP); + *updptr++ = cpu_to_le32(insn); + + /* movk rd, #((val >> 32) & 0xffff), lsl #32 */ + insn = aarch64_insn_gen_movewide(rd, + (u16)(val >> 32), + 32, + AARCH64_INSN_VARIANT_64BIT, + AARCH64_INSN_MOVEWIDE_KEEP); + *updptr++ = cpu_to_le32(insn); + + /* movk rd, #((val >> 48) & 0xffff), lsl #48 */ + insn = aarch64_insn_gen_movewide(rd, + (u16)(val >> 48), + 48, + AARCH64_INSN_VARIANT_64BIT, + AARCH64_INSN_MOVEWIDE_KEEP); + *updptr++ = cpu_to_le32(insn); +} + +void kvm_update_kimg_phys_offset(struct alt_instr *alt, + __le32 *origptr, __le32 *updptr, int nr_inst) +{ + generate_mov_q(kimage_voffset + PHYS_OFFSET, origptr, updptr, nr_inst); +} + +void kvm_get_kimage_voffset(struct alt_instr *alt, + __le32 *origptr, __le32 *updptr, int nr_inst) +{ + generate_mov_q(kimage_voffset, origptr, updptr, nr_inst); +} diff --git a/arch/arm64/kvm/vgic-sys-reg-v3.c b/arch/arm64/kvm/vgic-sys-reg-v3.c index 2f92bdcb1188..07d5271e9f05 100644 --- a/arch/arm64/kvm/vgic-sys-reg-v3.c +++ b/arch/arm64/kvm/vgic-sys-reg-v3.c @@ -268,8 +268,6 @@ int vgic_v3_has_cpu_sysregs_attr(struct kvm_vcpu *vcpu, bool is_write, u64 id, params.regval = *reg; params.is_write = is_write; - params.is_aarch32 = false; - params.is_32bit = false; if (find_reg_by_id(sysreg, ¶ms, gic_v3_icc_reg_descs, ARRAY_SIZE(gic_v3_icc_reg_descs))) @@ -288,8 +286,6 @@ int vgic_v3_cpu_sysregs_uaccess(struct kvm_vcpu *vcpu, bool is_write, u64 id, if (is_write) params.regval = *reg; params.is_write = is_write; - params.is_aarch32 = false; - params.is_32bit = false; r = find_reg_by_id(sysreg, ¶ms, gic_v3_icc_reg_descs, ARRAY_SIZE(gic_v3_icc_reg_descs)); diff --git a/arch/arm64/kvm/vgic/vgic-v4.c b/arch/arm64/kvm/vgic/vgic-v4.c index b5fa73c9fd35..66508b03094f 100644 --- a/arch/arm64/kvm/vgic/vgic-v4.c +++ b/arch/arm64/kvm/vgic/vgic-v4.c @@ -353,6 +353,18 @@ int vgic_v4_load(struct kvm_vcpu *vcpu) return err; } +void vgic_v4_commit(struct kvm_vcpu *vcpu) +{ + struct its_vpe *vpe = &vcpu->arch.vgic_cpu.vgic_v3.its_vpe; + + /* + * No need to wait for the vPE to be ready across a shallow guest + * exit, as only a vcpu_put will invalidate it. + */ + if (!vpe->ready) + its_commit_vpe(vpe); +} + static struct vgic_its *vgic_get_its(struct kvm *kvm, struct kvm_kernel_irq_routing_entry *irq_entry) { diff --git a/arch/arm64/kvm/vgic/vgic.c b/arch/arm64/kvm/vgic/vgic.c index c3643b7f101b..1c597c9885fa 100644 --- a/arch/arm64/kvm/vgic/vgic.c +++ b/arch/arm64/kvm/vgic/vgic.c @@ -915,6 +915,9 @@ void kvm_vgic_flush_hwstate(struct kvm_vcpu *vcpu) if (can_access_vgic_from_kernel()) vgic_restore_state(vcpu); + + if (vgic_supports_direct_msis(vcpu->kvm)) + vgic_v4_commit(vcpu); } void kvm_vgic_load(struct kvm_vcpu *vcpu) diff --git a/arch/arm64/lib/mte.S b/arch/arm64/lib/mte.S index 351537c12f36..9e1a12e10053 100644 --- a/arch/arm64/lib/mte.S +++ b/arch/arm64/lib/mte.S @@ -149,3 +149,19 @@ SYM_FUNC_START(mte_restore_page_tags) ret SYM_FUNC_END(mte_restore_page_tags) + +/* + * Assign allocation tags for a region of memory based on the pointer tag + * x0 - source pointer + * x1 - size + * + * Note: The address must be non-NULL and MTE_GRANULE_SIZE aligned and + * size must be non-zero and MTE_GRANULE_SIZE aligned. + */ +SYM_FUNC_START(mte_assign_mem_tag_range) +1: stg x0, [x0] + add x0, x0, #MTE_GRANULE_SIZE + subs x1, x1, #MTE_GRANULE_SIZE + b.gt 1b + ret +SYM_FUNC_END(mte_assign_mem_tag_range) diff --git a/arch/arm64/mm/copypage.c b/arch/arm64/mm/copypage.c index 70a71f38b6a9..b5447e53cd73 100644 --- a/arch/arm64/mm/copypage.c +++ b/arch/arm64/mm/copypage.c @@ -23,6 +23,15 @@ void copy_highpage(struct page *to, struct page *from) if (system_supports_mte() && test_bit(PG_mte_tagged, &from->flags)) { set_bit(PG_mte_tagged, &to->flags); + page_kasan_tag_reset(to); + /* + * We need smp_wmb() in between setting the flags and clearing the + * tags because if another thread reads page->flags and builds a + * tagged address out of it, there is an actual dependency to the + * memory access, but on the current thread we do not guarantee that + * the new page->flags are visible before the tags were updated. + */ + smp_wmb(); mte_copy_page_tags(kto, kfrom); } } diff --git a/arch/arm64/mm/fault.c b/arch/arm64/mm/fault.c index 2848952b178d..3c40da479899 100644 --- a/arch/arm64/mm/fault.c +++ b/arch/arm64/mm/fault.c @@ -14,6 +14,7 @@ #include <linux/mm.h> #include <linux/hardirq.h> #include <linux/init.h> +#include <linux/kasan.h> #include <linux/kprobes.h> #include <linux/uaccess.h> #include <linux/page-flags.h> @@ -33,6 +34,7 @@ #include <asm/debug-monitors.h> #include <asm/esr.h> #include <asm/kprobes.h> +#include <asm/mte.h> #include <asm/processor.h> #include <asm/sysreg.h> #include <asm/system_misc.h> @@ -296,6 +298,57 @@ static void die_kernel_fault(const char *msg, unsigned long addr, do_exit(SIGKILL); } +#ifdef CONFIG_KASAN_HW_TAGS +static void report_tag_fault(unsigned long addr, unsigned int esr, + struct pt_regs *regs) +{ + bool is_write = ((esr & ESR_ELx_WNR) >> ESR_ELx_WNR_SHIFT) != 0; + + /* + * SAS bits aren't set for all faults reported in EL1, so we can't + * find out access size. + */ + kasan_report(addr, 0, is_write, regs->pc); +} +#else +/* Tag faults aren't enabled without CONFIG_KASAN_HW_TAGS. */ +static inline void report_tag_fault(unsigned long addr, unsigned int esr, + struct pt_regs *regs) { } +#endif + +static void do_tag_recovery(unsigned long addr, unsigned int esr, + struct pt_regs *regs) +{ + static bool reported; + + if (!READ_ONCE(reported)) { + report_tag_fault(addr, esr, regs); + WRITE_ONCE(reported, true); + } + + /* + * Disable MTE Tag Checking on the local CPU for the current EL. + * It will be done lazily on the other CPUs when they will hit a + * tag fault. + */ + sysreg_clear_set(sctlr_el1, SCTLR_ELx_TCF_MASK, SCTLR_ELx_TCF_NONE); + isb(); +} + +static bool is_el1_mte_sync_tag_check_fault(unsigned int esr) +{ + unsigned int ec = ESR_ELx_EC(esr); + unsigned int fsc = esr & ESR_ELx_FSC; + + if (ec != ESR_ELx_EC_DABT_CUR) + return false; + + if (fsc == ESR_ELx_FSC_MTE) + return true; + + return false; +} + static void __do_kernel_fault(unsigned long addr, unsigned int esr, struct pt_regs *regs) { @@ -312,6 +365,12 @@ static void __do_kernel_fault(unsigned long addr, unsigned int esr, "Ignoring spurious kernel translation fault at virtual address %016lx\n", addr)) return; + if (is_el1_mte_sync_tag_check_fault(esr)) { + do_tag_recovery(addr, esr, regs); + + return; + } + if (is_el1_permission_fault(addr, esr, regs)) { if (esr & ESR_ELx_WNR) msg = "write to read-only memory"; diff --git a/arch/arm64/mm/init.c b/arch/arm64/mm/init.c index 69d4251ee079..75addb36354a 100644 --- a/arch/arm64/mm/init.c +++ b/arch/arm64/mm/init.c @@ -295,6 +295,9 @@ void __init arm64_memblock_init(void) memstart_addr = round_down(memblock_start_of_DRAM(), ARM64_MEMSTART_ALIGN); + if ((memblock_end_of_DRAM() - memstart_addr) > linear_region_size) + pr_warn("Memory doesn't fit in the linear mapping, VA_BITS too small\n"); + /* * Remove the memory that we will not be able to cover with the * linear mapping. Take care not to clip the kernel which may be diff --git a/arch/arm64/mm/kasan_init.c b/arch/arm64/mm/kasan_init.c index b24e43d20667..d8e66c78440e 100644 --- a/arch/arm64/mm/kasan_init.c +++ b/arch/arm64/mm/kasan_init.c @@ -21,6 +21,8 @@ #include <asm/sections.h> #include <asm/tlbflush.h> +#if defined(CONFIG_KASAN_GENERIC) || defined(CONFIG_KASAN_SW_TAGS) + static pgd_t tmp_pg_dir[PTRS_PER_PGD] __initdata __aligned(PGD_SIZE); /* @@ -208,7 +210,7 @@ static void __init clear_pgds(unsigned long start, set_pgd(pgd_offset_k(start), __pgd(0)); } -void __init kasan_init(void) +static void __init kasan_init_shadow(void) { u64 kimg_shadow_start, kimg_shadow_end; u64 mod_shadow_start, mod_shadow_end; @@ -269,8 +271,21 @@ void __init kasan_init(void) memset(kasan_early_shadow_page, KASAN_SHADOW_INIT, PAGE_SIZE); cpu_replace_ttbr1(lm_alias(swapper_pg_dir)); +} - /* At this point kasan is fully initialized. Enable error messages */ +static void __init kasan_init_depth(void) +{ init_task.kasan_depth = 0; +} + +void __init kasan_init(void) +{ + kasan_init_shadow(); + kasan_init_depth(); +#if defined(CONFIG_KASAN_GENERIC) + /* CONFIG_KASAN_SW_TAGS also requires kasan_init_sw_tags(). */ pr_info("KernelAddressSanitizer initialized\n"); +#endif } + +#endif /* CONFIG_KASAN_GENERIC || CONFIG_KASAN_SW_TAGS */ diff --git a/arch/arm64/mm/mmap.c b/arch/arm64/mm/mmap.c index 3028bacbc4e9..07937b49cb88 100644 --- a/arch/arm64/mm/mmap.c +++ b/arch/arm64/mm/mmap.c @@ -47,24 +47,3 @@ int valid_mmap_phys_addr_range(unsigned long pfn, size_t size) { return !(((pfn << PAGE_SHIFT) + size) & ~PHYS_MASK); } - -#ifdef CONFIG_STRICT_DEVMEM - -#include <linux/ioport.h> - -/* - * devmem_is_allowed() checks to see if /dev/mem access to a certain address - * is valid. The argument is a physical page number. We mimic x86 here by - * disallowing access to system RAM as well as device-exclusive MMIO regions. - * This effectively disable read()/write() on /dev/mem. - */ -int devmem_is_allowed(unsigned long pfn) -{ - if (iomem_is_exclusive(pfn << PAGE_SHIFT)) - return 0; - if (!page_is_ram(pfn)) - return 1; - return 0; -} - -#endif diff --git a/arch/arm64/mm/mteswap.c b/arch/arm64/mm/mteswap.c index c52c1847079c..7c4ef56265ee 100644 --- a/arch/arm64/mm/mteswap.c +++ b/arch/arm64/mm/mteswap.c @@ -53,6 +53,15 @@ bool mte_restore_tags(swp_entry_t entry, struct page *page) if (!tags) return false; + page_kasan_tag_reset(page); + /* + * We need smp_wmb() in between setting the flags and clearing the + * tags because if another thread reads page->flags and builds a + * tagged address out of it, there is an actual dependency to the + * memory access, but on the current thread we do not guarantee that + * the new page->flags are visible before the tags were updated. + */ + smp_wmb(); mte_restore_page_tags(page_address(page), tags); return true; diff --git a/arch/arm64/mm/proc.S b/arch/arm64/mm/proc.S index a0831bf8a018..37a54b57178a 100644 --- a/arch/arm64/mm/proc.S +++ b/arch/arm64/mm/proc.S @@ -40,9 +40,15 @@ #define TCR_CACHE_FLAGS TCR_IRGN_WBWA | TCR_ORGN_WBWA #ifdef CONFIG_KASAN_SW_TAGS -#define TCR_KASAN_FLAGS TCR_TBI1 | TCR_TBID1 +#define TCR_KASAN_SW_FLAGS TCR_TBI1 | TCR_TBID1 #else -#define TCR_KASAN_FLAGS 0 +#define TCR_KASAN_SW_FLAGS 0 +#endif + +#ifdef CONFIG_KASAN_HW_TAGS +#define TCR_KASAN_HW_FLAGS SYS_TCR_EL1_TCMA1 | TCR_TBI1 +#else +#define TCR_KASAN_HW_FLAGS 0 #endif /* @@ -427,6 +433,10 @@ SYM_FUNC_START(__cpu_setup) */ mov_q x5, MAIR_EL1_SET #ifdef CONFIG_ARM64_MTE + mte_tcr .req x20 + + mov mte_tcr, #0 + /* * Update MAIR_EL1, GCR_EL1 and TFSR*_EL1 if MTE is supported * (ID_AA64PFR1_EL1[11:8] > 1). @@ -447,6 +457,9 @@ SYM_FUNC_START(__cpu_setup) /* clear any pending tag check faults in TFSR*_EL1 */ msr_s SYS_TFSR_EL1, xzr msr_s SYS_TFSRE0_EL1, xzr + + /* set the TCR_EL1 bits */ + mov_q mte_tcr, TCR_KASAN_HW_FLAGS 1: #endif msr mair_el1, x5 @@ -456,7 +469,11 @@ SYM_FUNC_START(__cpu_setup) */ mov_q x10, TCR_TxSZ(VA_BITS) | TCR_CACHE_FLAGS | TCR_SMP_FLAGS | \ TCR_TG_FLAGS | TCR_KASLR_FLAGS | TCR_ASID16 | \ - TCR_TBI0 | TCR_A1 | TCR_KASAN_FLAGS + TCR_TBI0 | TCR_A1 | TCR_KASAN_SW_FLAGS +#ifdef CONFIG_ARM64_MTE + orr x10, x10, mte_tcr + .unreq mte_tcr +#endif tcr_clear_errata_bits x10, x9, x5 #ifdef CONFIG_ARM64_VA_BITS_52 diff --git a/arch/arm64/mm/ptdump.c b/arch/arm64/mm/ptdump.c index 807dc634bbd2..04137a8f3d2d 100644 --- a/arch/arm64/mm/ptdump.c +++ b/arch/arm64/mm/ptdump.c @@ -29,7 +29,7 @@ enum address_markers_idx { PAGE_OFFSET_NR = 0, PAGE_END_NR, -#ifdef CONFIG_KASAN +#if defined(CONFIG_KASAN_GENERIC) || defined(CONFIG_KASAN_SW_TAGS) KASAN_START_NR, #endif }; @@ -37,7 +37,7 @@ enum address_markers_idx { static struct addr_marker address_markers[] = { { PAGE_OFFSET, "Linear Mapping start" }, { 0 /* PAGE_END */, "Linear Mapping end" }, -#ifdef CONFIG_KASAN +#if defined(CONFIG_KASAN_GENERIC) || defined(CONFIG_KASAN_SW_TAGS) { 0 /* KASAN_SHADOW_START */, "Kasan shadow start" }, { KASAN_SHADOW_END, "Kasan shadow end" }, #endif @@ -383,7 +383,7 @@ void ptdump_check_wx(void) static int ptdump_init(void) { address_markers[PAGE_END_NR].start_address = PAGE_END; -#ifdef CONFIG_KASAN +#if defined(CONFIG_KASAN_GENERIC) || defined(CONFIG_KASAN_SW_TAGS) address_markers[KASAN_START_NR].start_address = KASAN_SHADOW_START; #endif ptdump_initialize(); diff --git a/arch/ia64/kernel/syscalls/syscall.tbl b/arch/ia64/kernel/syscalls/syscall.tbl index b96ed8b8a508..bfc00f2bd437 100644 --- a/arch/ia64/kernel/syscalls/syscall.tbl +++ b/arch/ia64/kernel/syscalls/syscall.tbl @@ -361,3 +361,4 @@ 438 common pidfd_getfd sys_pidfd_getfd 439 common faccessat2 sys_faccessat2 440 common process_madvise sys_process_madvise +441 common epoll_pwait2 sys_epoll_pwait2 diff --git a/arch/ia64/scripts/unwcheck.py b/arch/ia64/scripts/unwcheck.py index c55276e31b6b..bfd1b671e35f 100644 --- a/arch/ia64/scripts/unwcheck.py +++ b/arch/ia64/scripts/unwcheck.py @@ -1,4 +1,4 @@ -#!/usr/bin/python +#!/usr/bin/env python # SPDX-License-Identifier: GPL-2.0 # # Usage: unwcheck.py FILE diff --git a/arch/m68k/68000/Makefile b/arch/m68k/68000/Makefile index 4f7d4b45a46f..674541fdf5b8 100644 --- a/arch/m68k/68000/Makefile +++ b/arch/m68k/68000/Makefile @@ -10,10 +10,11 @@ # 68328, 68EZ328, 68VZ328 -obj-y += entry.o ints.o timers.o -obj-$(CONFIG_M68328) += m68328.o -obj-$(CONFIG_M68EZ328) += m68EZ328.o -obj-$(CONFIG_M68VZ328) += m68VZ328.o +obj-y += entry.o ints.o timers.o m68328.o obj-$(CONFIG_ROM) += romvec.o +obj-$(CONFIG_DRAGEN2) += dragen2.o +obj-$(CONFIG_UCSIMM) += ucsimm.o +obj-$(CONFIG_UCDIMM) += ucsimm.o + extra-y := head.o diff --git a/arch/m68k/68000/dragen2.c b/arch/m68k/68000/dragen2.c new file mode 100644 index 000000000000..584893c57c37 --- /dev/null +++ b/arch/m68k/68000/dragen2.c @@ -0,0 +1,100 @@ +// SPDX-License-Identifier: GPL-2.0 +/* + * Copyright (C) 1993 Hamish Macdonald + * Copyright (C) 1999 D. Jeff Dionne + * Copyright (C) 2001 Georges Menie, Ken Desmet + * + * This file is subject to the terms and conditions of the GNU General Public + * License. See the file COPYING in the main directory of this archive + * for more details. + */ +#include <linux/init.h> +#include <asm/machdep.h> +#include <asm/MC68VZ328.h> + +/***************************************************************************/ +/* Init Drangon Engine hardware */ +/***************************************************************************/ + +static void dragen2_reset(void) +{ + local_irq_disable(); + +#ifdef CONFIG_INIT_LCD + PBDATA |= 0x20; /* disable CCFL light */ + PKDATA |= 0x4; /* disable LCD controller */ + LCKCON = 0; +#endif + + __asm__ __volatile__( + "reset\n\t" + "moveal #0x04000000, %a0\n\t" + "moveal 0(%a0), %sp\n\t" + "moveal 4(%a0), %a0\n\t" + "jmp (%a0)" + ); +} + +void __init init_dragen2(char *command, int size) +{ + mach_reset = dragen2_reset; + +#ifdef CONFIG_DIRECT_IO_ACCESS + SCR = 0x10; /* allow user access to internal registers */ +#endif + + /* CSGB Init */ + CSGBB = 0x4000; + CSB = 0x1a1; + + /* CS8900 init */ + /* PK3: hardware sleep function pin, active low */ + PKSEL |= PK(3); /* select pin as I/O */ + PKDIR |= PK(3); /* select pin as output */ + PKDATA |= PK(3); /* set pin high */ + + /* PF5: hardware reset function pin, active high */ + PFSEL |= PF(5); /* select pin as I/O */ + PFDIR |= PF(5); /* select pin as output */ + PFDATA &= ~PF(5); /* set pin low */ + + /* cs8900 hardware reset */ + PFDATA |= PF(5); + { int i; for (i = 0; i < 32000; ++i); } + PFDATA &= ~PF(5); + + /* INT1 enable (cs8900 IRQ) */ + PDPOL &= ~PD(1); /* active high signal */ + PDIQEG &= ~PD(1); + PDIRQEN |= PD(1); /* IRQ enabled */ + +#ifdef CONFIG_INIT_LCD + /* initialize LCD controller */ + LSSA = (long) screen_bits; + LVPW = 0x14; + LXMAX = 0x140; + LYMAX = 0xef; + LRRA = 0; + LPXCD = 3; + LPICF = 0x08; + LPOLCF = 0; + LCKCON = 0x80; + PCPDEN = 0xff; + PCSEL = 0; + + /* Enable LCD controller */ + PKDIR |= 0x4; + PKSEL |= 0x4; + PKDATA &= ~0x4; + + /* Enable CCFL backlighting circuit */ + PBDIR |= 0x20; + PBSEL |= 0x20; + PBDATA &= ~0x20; + + /* contrast control register */ + PFDIR |= 0x1; + PFSEL &= ~0x1; + PWMR = 0x037F; +#endif +} diff --git a/arch/m68k/68000/m68328.c b/arch/m68k/68000/m68328.c index 419751b15ec8..eab08da058c6 100644 --- a/arch/m68k/68000/m68328.c +++ b/arch/m68k/68000/m68328.c @@ -1,10 +1,11 @@ /***************************************************************************/ /* - * m68328.c - 68328 specific config + * m68328.c - 68328/68EZ328/68VZ328 specific config * * Copyright (C) 1993 Hamish Macdonald * Copyright (C) 1999 D. Jeff Dionne + * Copyright (C) 2001 Georges Menie, Ken Desmet * * This file is subject to the terms and conditions of the GNU General Public * License. See the file COPYING in the main directory of this archive @@ -20,18 +21,18 @@ #include <linux/kernel.h> #include <linux/rtc.h> #include <asm/machdep.h> -#include <asm/MC68328.h> -#if defined(CONFIG_PILOT) || defined(CONFIG_INIT_LCD) + +#if defined(CONFIG_INIT_LCD) && defined(CONFIG_M68VZ328) +#include "bootlogo-vz.h" +#elif defined(CONFIG_PILOT) || defined(CONFIG_INIT_LCD) #include "bootlogo.h" #endif -/***************************************************************************/ - -int m68328_hwclk(int set, struct rtc_time *t); +#include "m68328.h" /***************************************************************************/ -void m68328_reset (void) +static void m68328_reset(void) { local_irq_disable(); asm volatile ("moveal #0x10c00000, %a0;\n\t" @@ -45,12 +46,19 @@ void m68328_reset (void) void __init config_BSP(char *command, int len) { - pr_info("68328 support D. Jeff Dionne <jeff@uclinux.org>\n"); - pr_info("68328 support Kenneth Albanowski <kjahds@kjshds.com>\n"); - pr_info("68328/Pilot support Bernhard Kuhn <kuhn@lpr.e-technik.tu-muenchen.de>\n"); + mach_sched_init = hw_timer_init; + mach_hwclk = m68328_hwclk; + mach_reset = m68328_reset; - mach_hwclk = m68328_hwclk; - mach_reset = m68328_reset; +#if defined(CONFIG_PILOT) && defined(CONFIG_M68328) + mach_sched_init = NULL; +#elif defined(CONFIG_UCSIMM) + init_ucsimm(command, len); +#elif defined(CONFIG_UCDIMM) + init_ucsimm(command, len); +#elif defined(CONFIG_DRAGEN2) + init_dragen2(command, len); +#endif } /***************************************************************************/ diff --git a/arch/m68k/68000/m68328.h b/arch/m68k/68000/m68328.h new file mode 100644 index 000000000000..f6047c3168d4 --- /dev/null +++ b/arch/m68k/68000/m68328.h @@ -0,0 +1,5 @@ +// SPDX-License-Identifier: GPL-2.0 +void init_dragen2(char *command, int size); +void init_ucsimm(char *command, int size); +struct rtc_time; +int m68328_hwclk(int set, struct rtc_time *t); diff --git a/arch/m68k/68000/m68EZ328.c b/arch/m68k/68000/m68EZ328.c deleted file mode 100644 index 05f137dc257e..000000000000 --- a/arch/m68k/68000/m68EZ328.c +++ /dev/null @@ -1,77 +0,0 @@ -/***************************************************************************/ - -/* - * m68EZ328.c - 68EZ328 specific config - * - * Copyright (C) 1993 Hamish Macdonald - * Copyright (C) 1999 D. Jeff Dionne - * - * This file is subject to the terms and conditions of the GNU General Public - * License. See the file COPYING in the main directory of this archive - * for more details. - */ - -/***************************************************************************/ - -#include <linux/init.h> -#include <linux/types.h> -#include <linux/kernel.h> -#include <linux/rtc.h> -#include <linux/pgtable.h> -#include <asm/machdep.h> -#include <asm/MC68EZ328.h> -#ifdef CONFIG_UCSIMM -#include <asm/bootstd.h> -#endif - -/***************************************************************************/ - -int m68328_hwclk(int set, struct rtc_time *t); - -/***************************************************************************/ - -void m68ez328_reset(void) -{ - local_irq_disable(); - asm volatile ( - "moveal #0x10c00000, %a0;\n" - "moveb #0, 0xFFFFF300;\n" - "moveal 0(%a0), %sp;\n" - "moveal 4(%a0), %a0;\n" - "jmp (%a0);\n" - ); -} - -/***************************************************************************/ - -unsigned char *cs8900a_hwaddr; -static int errno; - -#ifdef CONFIG_UCSIMM -_bsc0(char *, getserialnum) -_bsc1(unsigned char *, gethwaddr, int, a) -_bsc1(char *, getbenv, char *, a) -#endif - -void __init config_BSP(char *command, int len) -{ - unsigned char *p; - - pr_info("68EZ328 DragonBallEZ support (C) 1999 Rt-Control, Inc\n"); - -#ifdef CONFIG_UCSIMM - pr_info("uCsimm serial string [%s]\n", getserialnum()); - p = cs8900a_hwaddr = gethwaddr(0); - pr_info("uCsimm hwaddr %pM\n", p); - - p = getbenv("APPEND"); - if (p) strcpy(p,command); - else command[0] = 0; -#endif - - mach_sched_init = hw_timer_init; - mach_hwclk = m68328_hwclk; - mach_reset = m68ez328_reset; -} - -/***************************************************************************/ diff --git a/arch/m68k/68000/m68VZ328.c b/arch/m68k/68000/m68VZ328.c deleted file mode 100644 index ada87b23afdc..000000000000 --- a/arch/m68k/68000/m68VZ328.c +++ /dev/null @@ -1,189 +0,0 @@ -/***************************************************************************/ - -/* - * m68VZ328.c - 68VZ328 specific config - * - * Copyright (C) 1993 Hamish Macdonald - * Copyright (C) 1999 D. Jeff Dionne - * Copyright (C) 2001 Georges Menie, Ken Desmet - * - * This file is subject to the terms and conditions of the GNU General Public - * License. See the file COPYING in the main directory of this archive - * for more details. - */ - -/***************************************************************************/ - -#include <linux/init.h> -#include <linux/types.h> -#include <linux/kernel.h> -#include <linux/kd.h> -#include <linux/netdevice.h> -#include <linux/interrupt.h> -#include <linux/irq.h> -#include <linux/rtc.h> -#include <linux/pgtable.h> - -#include <asm/machdep.h> -#include <asm/MC68VZ328.h> -#include <asm/bootstd.h> - -#ifdef CONFIG_INIT_LCD -#include "bootlogo-vz.h" -#endif - -/***************************************************************************/ - -int m68328_hwclk(int set, struct rtc_time *t); - -/***************************************************************************/ -/* Init Drangon Engine hardware */ -/***************************************************************************/ -#if defined(CONFIG_DRAGEN2) - -static void m68vz328_reset(void) -{ - local_irq_disable(); - -#ifdef CONFIG_INIT_LCD - PBDATA |= 0x20; /* disable CCFL light */ - PKDATA |= 0x4; /* disable LCD controller */ - LCKCON = 0; -#endif - - __asm__ __volatile__( - "reset\n\t" - "moveal #0x04000000, %a0\n\t" - "moveal 0(%a0), %sp\n\t" - "moveal 4(%a0), %a0\n\t" - "jmp (%a0)" - ); -} - -static void __init init_hardware(char *command, int size) -{ -#ifdef CONFIG_DIRECT_IO_ACCESS - SCR = 0x10; /* allow user access to internal registers */ -#endif - - /* CSGB Init */ - CSGBB = 0x4000; - CSB = 0x1a1; - - /* CS8900 init */ - /* PK3: hardware sleep function pin, active low */ - PKSEL |= PK(3); /* select pin as I/O */ - PKDIR |= PK(3); /* select pin as output */ - PKDATA |= PK(3); /* set pin high */ - - /* PF5: hardware reset function pin, active high */ - PFSEL |= PF(5); /* select pin as I/O */ - PFDIR |= PF(5); /* select pin as output */ - PFDATA &= ~PF(5); /* set pin low */ - - /* cs8900 hardware reset */ - PFDATA |= PF(5); - { int i; for (i = 0; i < 32000; ++i); } - PFDATA &= ~PF(5); - - /* INT1 enable (cs8900 IRQ) */ - PDPOL &= ~PD(1); /* active high signal */ - PDIQEG &= ~PD(1); - PDIRQEN |= PD(1); /* IRQ enabled */ - -#ifdef CONFIG_INIT_LCD - /* initialize LCD controller */ - LSSA = (long) screen_bits; - LVPW = 0x14; - LXMAX = 0x140; - LYMAX = 0xef; - LRRA = 0; - LPXCD = 3; - LPICF = 0x08; - LPOLCF = 0; - LCKCON = 0x80; - PCPDEN = 0xff; - PCSEL = 0; - - /* Enable LCD controller */ - PKDIR |= 0x4; - PKSEL |= 0x4; - PKDATA &= ~0x4; - - /* Enable CCFL backlighting circuit */ - PBDIR |= 0x20; - PBSEL |= 0x20; - PBDATA &= ~0x20; - - /* contrast control register */ - PFDIR |= 0x1; - PFSEL &= ~0x1; - PWMR = 0x037F; -#endif -} - -/***************************************************************************/ -/* Init RT-Control uCdimm hardware */ -/***************************************************************************/ -#elif defined(CONFIG_UCDIMM) - -static void m68vz328_reset(void) -{ - local_irq_disable(); - asm volatile ( - "moveal #0x10c00000, %a0;\n\t" - "moveb #0, 0xFFFFF300;\n\t" - "moveal 0(%a0), %sp;\n\t" - "moveal 4(%a0), %a0;\n\t" - "jmp (%a0);\n" - ); -} - -unsigned char *cs8900a_hwaddr; -static int errno; - -_bsc0(char *, getserialnum) -_bsc1(unsigned char *, gethwaddr, int, a) -_bsc1(char *, getbenv, char *, a) - -static void __init init_hardware(char *command, int size) -{ - char *p; - - pr_info("uCdimm serial string [%s]\n", getserialnum()); - p = cs8900a_hwaddr = gethwaddr(0); - pr_info("uCdimm hwaddr %pM\n", p); - p = getbenv("APPEND"); - if (p) - strcpy(p, command); - else - command[0] = 0; -} - -/***************************************************************************/ -#else - -static void m68vz328_reset(void) -{ -} - -static void __init init_hardware(char *command, int size) -{ -} - -/***************************************************************************/ -#endif -/***************************************************************************/ - -void __init config_BSP(char *command, int size) -{ - pr_info("68VZ328 DragonBallVZ support (c) 2001 Lineo, Inc.\n"); - - init_hardware(command, size); - - mach_sched_init = hw_timer_init; - mach_hwclk = m68328_hwclk; - mach_reset = m68vz328_reset; -} - -/***************************************************************************/ diff --git a/arch/m68k/68000/ucsimm.c b/arch/m68k/68000/ucsimm.c new file mode 100644 index 000000000000..7c6cbf643712 --- /dev/null +++ b/arch/m68k/68000/ucsimm.c @@ -0,0 +1,38 @@ +// SPDX-License-Identifier: GPL-2.0 +/* + * Copyright (C) 1993 Hamish Macdonald + * Copyright (C) 1999 D. Jeff Dionne + * Copyright (C) 2001 Georges Menie, Ken Desmet + * + * This file is subject to the terms and conditions of the GNU General Public + * License. See the file COPYING in the main directory of this archive + * for more details. + */ +#include <linux/init.h> +#include <asm/bootstd.h> +#include <asm/machdep.h> +#include <asm/MC68VZ328.h> + + +#include "m68328.h" + +unsigned char *cs8900a_hwaddr; +static int errno; + +_bsc0(char *, getserialnum) +_bsc1(unsigned char *, gethwaddr, int, a) +_bsc1(char *, getbenv, char *, a) + +void __init init_ucsimm(char *command, int size) +{ + char *p; + + pr_info("uCsimm/uCdimm serial string [%s]\n", getserialnum()); + p = cs8900a_hwaddr = gethwaddr(0); + pr_info("uCsimm/uCdimm hwaddr %pM\n", p); + p = getbenv("APPEND"); + if (p) + strcpy(p, command); + else + command[0] = 0; +} diff --git a/arch/m68k/Kconfig.cpu b/arch/m68k/Kconfig.cpu index 7246aa50298e..f4d23977d2a5 100644 --- a/arch/m68k/Kconfig.cpu +++ b/arch/m68k/Kconfig.cpu @@ -36,7 +36,7 @@ endchoice if M68KCLASSIC config M68000 - bool "MC68000" + bool depends on !MMU select CPU_HAS_NO_BITFIELDS select CPU_HAS_NO_MULDIV64 @@ -103,7 +103,7 @@ config M68060 processor, say Y. Otherwise, say N. config M68328 - bool "MC68328" + bool depends on !MMU select LEGACY_TIMER_TICK select M68000 @@ -111,7 +111,7 @@ config M68328 Motorola 68328 processor support. config M68EZ328 - bool "MC68EZ328" + bool depends on !MMU select LEGACY_TIMER_TICK select M68000 @@ -119,7 +119,7 @@ config M68EZ328 Motorola 68EX328 processor support. config M68VZ328 - bool "MC68VZ328" + bool depends on !MMU select LEGACY_TIMER_TICK select M68000 diff --git a/arch/m68k/Kconfig.machine b/arch/m68k/Kconfig.machine index cf6961d4e657..4d59ec2f5b8d 100644 --- a/arch/m68k/Kconfig.machine +++ b/arch/m68k/Kconfig.machine @@ -145,14 +145,13 @@ config SUN3 If you don't want to compile a kernel exclusively for a Sun 3, say N. -endif # M68KCLASSIC - config PILOT bool config PILOT3 bool "Pilot 1000/5000, PalmPilot Personal/Pro, or PalmIII support" - depends on M68328 + depends on !MMU + select M68328 select PILOT help Support for the Palm Pilot 1000/5000, Personal/Pro and PalmIII. @@ -165,19 +164,22 @@ config XCOPILOT_BUGS config UCSIMM bool "uCsimm module support" - depends on M68EZ328 + depends on !MMU + select M68EZ328 help Support for the Arcturus Networks uCsimm module. config UCDIMM bool "uDsimm module support" - depends on M68VZ328 + depends on !MMU + select M68VZ328 help Support for the Arcturus Networks uDsimm module. config DRAGEN2 bool "DragenEngine II board support" - depends on M68VZ328 + depends on !MMU + select M68VZ328 help Support for the DragenEngine II board. @@ -200,6 +202,8 @@ config MEMORY_RESERVE help Reserve certain memory regions on 68x328 based boards. +endif # M68KCLASSIC + config ARN5206 bool "Arnewsh 5206 board support" depends on M5206 diff --git a/arch/m68k/kernel/setup_no.c b/arch/m68k/kernel/setup_no.c index e377b4219528..d1b7988efc91 100644 --- a/arch/m68k/kernel/setup_no.c +++ b/arch/m68k/kernel/setup_no.c @@ -106,8 +106,16 @@ void __init setup_arch(char **cmdline_p) #ifdef CONFIG_UCDIMM pr_info("uCdimm by Lineo, Inc. <www.lineo.com>\n"); #endif +#ifdef CONFIG_M68328 + pr_info("68328 support D. Jeff Dionne <jeff@uclinux.org>\n"); + pr_info("68328 support Kenneth Albanowski <kjahds@kjshds.com>\n"); +#endif +#ifdef CONFIG_M68EZ328 + pr_info("68EZ328 DragonBallEZ support (C) 1999 Rt-Control, Inc\n"); +#endif #ifdef CONFIG_M68VZ328 pr_info("M68VZ328 support by Evan Stawnyczy <e@lineo.ca>\n"); + pr_info("68VZ328 DragonBallVZ support (c) 2001 Lineo, Inc.\n"); #endif #ifdef CONFIG_COLDFIRE pr_info("COLDFIRE port done by Greg Ungerer, gerg@snapgear.com\n"); @@ -121,6 +129,7 @@ void __init setup_arch(char **cmdline_p) pr_info("Flat model support (C) 1998,1999 Kenneth Albanowski, D. Jeff Dionne\n"); #if defined( CONFIG_PILOT ) && defined( CONFIG_M68328 ) + pr_info("68328/Pilot support Bernhard Kuhn <kuhn@lpr.e-technik.tu-muenchen.de>\n"); pr_info("TRG SuperPilot FLASH card support <info@trgnet.com>\n"); #endif #if defined( CONFIG_PILOT ) && defined( CONFIG_M68EZ328 ) diff --git a/arch/m68k/kernel/syscalls/syscall.tbl b/arch/m68k/kernel/syscalls/syscall.tbl index 625fb6d32842..7fe4e45c864c 100644 --- a/arch/m68k/kernel/syscalls/syscall.tbl +++ b/arch/m68k/kernel/syscalls/syscall.tbl @@ -440,3 +440,4 @@ 438 common pidfd_getfd sys_pidfd_getfd 439 common faccessat2 sys_faccessat2 440 common process_madvise sys_process_madvise +441 common epoll_pwait2 sys_epoll_pwait2 diff --git a/arch/m68k/kernel/vmlinux-nommu.lds b/arch/m68k/kernel/vmlinux-nommu.lds index 396e126a4258..387f334e87d3 100644 --- a/arch/m68k/kernel/vmlinux-nommu.lds +++ b/arch/m68k/kernel/vmlinux-nommu.lds @@ -81,7 +81,7 @@ SECTIONS { __init_end = .; } - BSS_SECTION(0, 0, 0) + BSS_SECTION(4, 0, 4) _end = .; diff --git a/arch/microblaze/kernel/syscalls/syscall.tbl b/arch/microblaze/kernel/syscalls/syscall.tbl index aae729c95cf9..a522adf194ab 100644 --- a/arch/microblaze/kernel/syscalls/syscall.tbl +++ b/arch/microblaze/kernel/syscalls/syscall.tbl @@ -446,3 +446,4 @@ 438 common pidfd_getfd sys_pidfd_getfd 439 common faccessat2 sys_faccessat2 440 common process_madvise sys_process_madvise +441 common epoll_pwait2 sys_epoll_pwait2 diff --git a/arch/mips/kernel/syscalls/syscall_n32.tbl b/arch/mips/kernel/syscalls/syscall_n32.tbl index 32817c954435..0f03ad223f33 100644 --- a/arch/mips/kernel/syscalls/syscall_n32.tbl +++ b/arch/mips/kernel/syscalls/syscall_n32.tbl @@ -379,3 +379,4 @@ 438 n32 pidfd_getfd sys_pidfd_getfd 439 n32 faccessat2 sys_faccessat2 440 n32 process_madvise sys_process_madvise +441 n32 epoll_pwait2 compat_sys_epoll_pwait2 diff --git a/arch/mips/kernel/syscalls/syscall_n64.tbl b/arch/mips/kernel/syscalls/syscall_n64.tbl index 9e4ea3c31b1c..91649690b52f 100644 --- a/arch/mips/kernel/syscalls/syscall_n64.tbl +++ b/arch/mips/kernel/syscalls/syscall_n64.tbl @@ -355,3 +355,4 @@ 438 n64 pidfd_getfd sys_pidfd_getfd 439 n64 faccessat2 sys_faccessat2 440 n64 process_madvise sys_process_madvise +441 n64 epoll_pwait2 sys_epoll_pwait2 diff --git a/arch/mips/kernel/syscalls/syscall_o32.tbl b/arch/mips/kernel/syscalls/syscall_o32.tbl index 29f5f28cf5ce..4bad0c40aed6 100644 --- a/arch/mips/kernel/syscalls/syscall_o32.tbl +++ b/arch/mips/kernel/syscalls/syscall_o32.tbl @@ -428,3 +428,4 @@ 438 o32 pidfd_getfd sys_pidfd_getfd 439 o32 faccessat2 sys_faccessat2 440 o32 process_madvise sys_process_madvise +441 o32 epoll_pwait2 sys_epoll_pwait2 compat_sys_epoll_pwait2 diff --git a/arch/parisc/kernel/syscalls/syscall.tbl b/arch/parisc/kernel/syscalls/syscall.tbl index f375ea528e59..6bcc31966b44 100644 --- a/arch/parisc/kernel/syscalls/syscall.tbl +++ b/arch/parisc/kernel/syscalls/syscall.tbl @@ -438,3 +438,4 @@ 438 common pidfd_getfd sys_pidfd_getfd 439 common faccessat2 sys_faccessat2 440 common process_madvise sys_process_madvise +441 common epoll_pwait2 sys_epoll_pwait2 compat_sys_epoll_pwait2 diff --git a/arch/powerpc/Kconfig b/arch/powerpc/Kconfig index ae7391627054..107bb4319e0e 100644 --- a/arch/powerpc/Kconfig +++ b/arch/powerpc/Kconfig @@ -161,6 +161,7 @@ config PPC select DCACHE_WORD_ACCESS if PPC64 && CPU_LITTLE_ENDIAN select DMA_OPS if PPC64 select DMA_OPS_BYPASS if PPC64 + select ARCH_HAS_DMA_MAP_DIRECT if PPC64 && PPC_PSERIES select DYNAMIC_FTRACE if FUNCTION_TRACER select EDAC_ATOMIC_SCRUB select EDAC_SUPPORT diff --git a/arch/powerpc/kernel/dma-iommu.c b/arch/powerpc/kernel/dma-iommu.c index a1c744194018..111249fd619d 100644 --- a/arch/powerpc/kernel/dma-iommu.c +++ b/arch/powerpc/kernel/dma-iommu.c @@ -10,6 +10,63 @@ #include <linux/pci.h> #include <asm/iommu.h> +#ifdef CONFIG_ARCH_HAS_DMA_MAP_DIRECT +#define can_map_direct(dev, addr) \ + ((dev)->bus_dma_limit >= phys_to_dma((dev), (addr))) + +bool arch_dma_map_page_direct(struct device *dev, phys_addr_t addr) +{ + if (likely(!dev->bus_dma_limit)) + return false; + + return can_map_direct(dev, addr); +} + +#define is_direct_handle(dev, h) ((h) >= (dev)->archdata.dma_offset) + +bool arch_dma_unmap_page_direct(struct device *dev, dma_addr_t dma_handle) +{ + if (likely(!dev->bus_dma_limit)) + return false; + + return is_direct_handle(dev, dma_handle); +} + +bool arch_dma_map_sg_direct(struct device *dev, struct scatterlist *sg, + int nents) +{ + struct scatterlist *s; + int i; + + if (likely(!dev->bus_dma_limit)) + return false; + + for_each_sg(sg, s, nents, i) { + if (!can_map_direct(dev, sg_phys(s) + s->offset + s->length)) + return false; + } + + return true; +} + +bool arch_dma_unmap_sg_direct(struct device *dev, struct scatterlist *sg, + int nents) +{ + struct scatterlist *s; + int i; + + if (likely(!dev->bus_dma_limit)) + return false; + + for_each_sg(sg, s, nents, i) { + if (!is_direct_handle(dev, s->dma_address + s->length)) + return false; + } + + return true; +} +#endif /* CONFIG_ARCH_HAS_DMA_MAP_DIRECT */ + /* * Generic iommu implementation */ @@ -90,8 +147,18 @@ int dma_iommu_dma_supported(struct device *dev, u64 mask) struct iommu_table *tbl = get_iommu_table_base(dev); if (dev_is_pci(dev) && dma_iommu_bypass_supported(dev, mask)) { - dev->dma_ops_bypass = true; - dev_dbg(dev, "iommu: 64-bit OK, using fixed ops\n"); + /* + * dma_iommu_bypass_supported() sets dma_max when there is + * 1:1 mapping but it is somehow limited. + * ibm,pmemory is one example. + */ + dev->dma_ops_bypass = dev->bus_dma_limit == 0; + if (!dev->dma_ops_bypass) + dev_warn(dev, + "iommu: 64-bit OK but direct DMA is limited by %llx\n", + dev->bus_dma_limit); + else + dev_dbg(dev, "iommu: 64-bit OK, using fixed ops\n"); return 1; } diff --git a/arch/powerpc/kernel/syscalls/syscall.tbl b/arch/powerpc/kernel/syscalls/syscall.tbl index 1275daec7fec..f744eb5cba88 100644 --- a/arch/powerpc/kernel/syscalls/syscall.tbl +++ b/arch/powerpc/kernel/syscalls/syscall.tbl @@ -530,3 +530,4 @@ 438 common pidfd_getfd sys_pidfd_getfd 439 common faccessat2 sys_faccessat2 440 common process_madvise sys_process_madvise +441 common epoll_pwait2 sys_epoll_pwait2 compat_sys_epoll_pwait2 diff --git a/arch/powerpc/platforms/pseries/iommu.c b/arch/powerpc/platforms/pseries/iommu.c index e4198700ed1a..9fc5217f0c8e 100644 --- a/arch/powerpc/platforms/pseries/iommu.c +++ b/arch/powerpc/platforms/pseries/iommu.c @@ -839,7 +839,7 @@ static void remove_ddw(struct device_node *np, bool remove_prop) np, ret); } -static u64 find_existing_ddw(struct device_node *pdn) +static u64 find_existing_ddw(struct device_node *pdn, int *window_shift) { struct direct_window *window; const struct dynamic_dma_window_prop *direct64; @@ -851,6 +851,7 @@ static u64 find_existing_ddw(struct device_node *pdn) if (window->device == pdn) { direct64 = window->prop; dma_addr = be64_to_cpu(direct64->dma_base); + *window_shift = be32_to_cpu(direct64->window_shift); break; } } @@ -1111,11 +1112,12 @@ static void reset_dma_window(struct pci_dev *dev, struct device_node *par_dn) */ static u64 enable_ddw(struct pci_dev *dev, struct device_node *pdn) { - int len, ret; + int len = 0, ret; + int max_ram_len = order_base_2(ddw_memory_hotplug_max()); struct ddw_query_response query; struct ddw_create_response create; int page_shift; - u64 dma_addr, max_addr; + u64 dma_addr; struct device_node *dn; u32 ddw_avail[DDW_APPLICABLE_SIZE]; struct direct_window *window; @@ -1123,10 +1125,15 @@ static u64 enable_ddw(struct pci_dev *dev, struct device_node *pdn) struct dynamic_dma_window_prop *ddwprop; struct failed_ddw_pdn *fpdn; bool default_win_removed = false; + bool pmem_present; + + dn = of_find_node_by_type(NULL, "ibm,pmemory"); + pmem_present = dn != NULL; + of_node_put(dn); mutex_lock(&direct_window_init_mutex); - dma_addr = find_existing_ddw(pdn); + dma_addr = find_existing_ddw(pdn, &len); if (dma_addr != 0) goto out_unlock; @@ -1212,14 +1219,29 @@ static u64 enable_ddw(struct pci_dev *dev, struct device_node *pdn) } /* verify the window * number of ptes will map the partition */ /* check largest block * page size > max memory hotplug addr */ - max_addr = ddw_memory_hotplug_max(); - if (query.largest_available_block < (max_addr >> page_shift)) { - dev_dbg(&dev->dev, "can't map partition max 0x%llx with %llu " - "%llu-sized pages\n", max_addr, query.largest_available_block, - 1ULL << page_shift); + /* + * The "ibm,pmemory" can appear anywhere in the address space. + * Assuming it is still backed by page structs, try MAX_PHYSMEM_BITS + * for the upper limit and fallback to max RAM otherwise but this + * disables device::dma_ops_bypass. + */ + len = max_ram_len; + if (pmem_present) { + if (query.largest_available_block >= + (1ULL << (MAX_PHYSMEM_BITS - page_shift))) + len = MAX_PHYSMEM_BITS - page_shift; + else + dev_info(&dev->dev, "Skipping ibm,pmemory"); + } + + if (query.largest_available_block < (1ULL << (len - page_shift))) { + dev_dbg(&dev->dev, + "can't map partition max 0x%llx with %llu %llu-sized pages\n", + 1ULL << len, + query.largest_available_block, + 1ULL << page_shift); goto out_failed; } - len = order_base_2(max_addr); win64 = kzalloc(sizeof(struct property), GFP_KERNEL); if (!win64) { dev_info(&dev->dev, @@ -1299,6 +1321,15 @@ out_failed: out_unlock: mutex_unlock(&direct_window_init_mutex); + + /* + * If we have persistent memory and the window size is only as big + * as RAM, then we failed to create a window to cover persistent + * memory and need to set the DMA limit. + */ + if (pmem_present && dma_addr && (len == max_ram_len)) + dev->dev.bus_dma_limit = dma_addr + (1ULL << len); + return dma_addr; } diff --git a/arch/riscv/Kconfig b/arch/riscv/Kconfig index 880c2b3b65d0..81b76d44725d 100644 --- a/arch/riscv/Kconfig +++ b/arch/riscv/Kconfig @@ -15,6 +15,7 @@ config RISCV select ARCH_CLOCKSOURCE_INIT select ARCH_SUPPORTS_ATOMIC_RMW select ARCH_SUPPORTS_DEBUG_PAGEALLOC if MMU + select ARCH_STACKWALK select ARCH_HAS_BINFMT_FLAT select ARCH_HAS_DEBUG_VM_PGTABLE select ARCH_HAS_DEBUG_VIRTUAL if MMU @@ -43,6 +44,7 @@ config RISCV select GENERIC_IOREMAP select GENERIC_IRQ_MULTI_HANDLER select GENERIC_IRQ_SHOW + select GENERIC_LIB_DEVMEM_IS_ALLOWED select GENERIC_PCI_IOMAP select GENERIC_PTDUMP if MMU select GENERIC_SCHED_CLOCK @@ -68,6 +70,7 @@ config RISCV select HAVE_FUTEX_CMPXCHG if FUTEX select HAVE_GCC_PLUGINS select HAVE_GENERIC_VDSO if MMU && 64BIT + select HAVE_IRQ_TIME_ACCOUNTING select HAVE_PCI select HAVE_PERF_EVENTS select HAVE_PERF_REGS diff --git a/arch/riscv/Kconfig.socs b/arch/riscv/Kconfig.socs index 8a55f6156661..3284d5c291be 100644 --- a/arch/riscv/Kconfig.socs +++ b/arch/riscv/Kconfig.socs @@ -5,7 +5,7 @@ config SOC_SIFIVE select SERIAL_SIFIVE if TTY select SERIAL_SIFIVE_CONSOLE if TTY select CLK_SIFIVE - select CLK_SIFIVE_FU540_PRCI + select CLK_SIFIVE_PRCI select SIFIVE_PLIC help This enables support for SiFive SoC platform hardware. diff --git a/arch/riscv/Makefile b/arch/riscv/Makefile index 0289a97325d1..8c29e553ef7f 100644 --- a/arch/riscv/Makefile +++ b/arch/riscv/Makefile @@ -96,5 +96,11 @@ $(BOOT_TARGETS): vmlinux $(Q)$(MAKE) $(build)=$(boot) $(boot)/$@ @$(kecho) ' Kernel: $(boot)/$@ is ready' +Image.%: Image + $(Q)$(MAKE) $(build)=$(boot) $(boot)/$@ + zinstall install: $(Q)$(MAKE) $(build)=$(boot) $@ + +archclean: + $(Q)$(MAKE) $(clean)=$(boot) diff --git a/arch/riscv/boot/.gitignore b/arch/riscv/boot/.gitignore index 574c10f8ff68..90e66adb7de5 100644 --- a/arch/riscv/boot/.gitignore +++ b/arch/riscv/boot/.gitignore @@ -1,5 +1,6 @@ # SPDX-License-Identifier: GPL-2.0-only Image -Image.gz +Image.* loader loader.lds +loader.bin diff --git a/arch/riscv/boot/Makefile b/arch/riscv/boot/Makefile index c59fca695f9d..03404c84f971 100644 --- a/arch/riscv/boot/Makefile +++ b/arch/riscv/boot/Makefile @@ -18,7 +18,7 @@ KCOV_INSTRUMENT := n OBJCOPYFLAGS_Image :=-O binary -R .note -R .note.gnu.build-id -R .comment -S -targets := Image loader +targets := Image Image.* loader loader.o loader.lds loader.bin $(obj)/Image: vmlinux FORCE $(call if_changed,objcopy) diff --git a/arch/riscv/include/asm/sections.h b/arch/riscv/include/asm/sections.h index 3a9971b1210f..1595c5b60cfd 100644 --- a/arch/riscv/include/asm/sections.h +++ b/arch/riscv/include/asm/sections.h @@ -9,5 +9,7 @@ extern char _start[]; extern char _start_kernel[]; +extern char __init_data_begin[], __init_data_end[]; +extern char __init_text_begin[], __init_text_end[]; #endif /* __ASM_SECTIONS_H */ diff --git a/arch/riscv/include/asm/set_memory.h b/arch/riscv/include/asm/set_memory.h index d690b08dff2a..211eb8244a45 100644 --- a/arch/riscv/include/asm/set_memory.h +++ b/arch/riscv/include/asm/set_memory.h @@ -15,11 +15,15 @@ int set_memory_ro(unsigned long addr, int numpages); int set_memory_rw(unsigned long addr, int numpages); int set_memory_x(unsigned long addr, int numpages); int set_memory_nx(unsigned long addr, int numpages); +int set_memory_rw_nx(unsigned long addr, int numpages); +void protect_kernel_text_data(void); #else static inline int set_memory_ro(unsigned long addr, int numpages) { return 0; } static inline int set_memory_rw(unsigned long addr, int numpages) { return 0; } static inline int set_memory_x(unsigned long addr, int numpages) { return 0; } static inline int set_memory_nx(unsigned long addr, int numpages) { return 0; } +static inline void protect_kernel_text_data(void) {}; +static inline int set_memory_rw_nx(unsigned long addr, int numpages) { return 0; } #endif int set_direct_map_invalid_noflush(struct page *page); diff --git a/arch/riscv/include/asm/stacktrace.h b/arch/riscv/include/asm/stacktrace.h new file mode 100644 index 000000000000..470a65c4ccdc --- /dev/null +++ b/arch/riscv/include/asm/stacktrace.h @@ -0,0 +1,17 @@ +/* SPDX-License-Identifier: GPL-2.0 */ + +#ifndef _ASM_RISCV_STACKTRACE_H +#define _ASM_RISCV_STACKTRACE_H + +#include <linux/sched.h> +#include <asm/ptrace.h> + +struct stackframe { + unsigned long fp; + unsigned long ra; +}; + +extern void notrace walk_stackframe(struct task_struct *task, struct pt_regs *regs, + bool (*fn)(void *, unsigned long), void *arg); + +#endif /* _ASM_RISCV_STACKTRACE_H */ diff --git a/arch/riscv/include/asm/string.h b/arch/riscv/include/asm/string.h index 924af13f8555..5477e7ecb6e1 100644 --- a/arch/riscv/include/asm/string.h +++ b/arch/riscv/include/asm/string.h @@ -12,16 +12,16 @@ #define __HAVE_ARCH_MEMSET extern asmlinkage void *memset(void *, int, size_t); extern asmlinkage void *__memset(void *, int, size_t); - #define __HAVE_ARCH_MEMCPY extern asmlinkage void *memcpy(void *, const void *, size_t); extern asmlinkage void *__memcpy(void *, const void *, size_t); - +#define __HAVE_ARCH_MEMMOVE +extern asmlinkage void *memmove(void *, const void *, size_t); +extern asmlinkage void *__memmove(void *, const void *, size_t); /* For those files which don't want to check by kasan. */ #if defined(CONFIG_KASAN) && !defined(__SANITIZE_ADDRESS__) - #define memcpy(dst, src, len) __memcpy(dst, src, len) #define memset(s, c, n) __memset(s, c, n) - +#define memmove(dst, src, len) __memmove(dst, src, len) #endif #endif /* _ASM_RISCV_STRING_H */ diff --git a/arch/riscv/kernel/Makefile b/arch/riscv/kernel/Makefile index fa896c5f7ccb..f6caf4d9ca15 100644 --- a/arch/riscv/kernel/Makefile +++ b/arch/riscv/kernel/Makefile @@ -56,5 +56,3 @@ obj-$(CONFIG_KGDB) += kgdb.o obj-$(CONFIG_JUMP_LABEL) += jump_label.o obj-$(CONFIG_EFI) += efi.o - -clean: diff --git a/arch/riscv/kernel/asm-offsets.c b/arch/riscv/kernel/asm-offsets.c index db203442c08f..b79ffa3561fd 100644 --- a/arch/riscv/kernel/asm-offsets.c +++ b/arch/riscv/kernel/asm-offsets.c @@ -11,6 +11,8 @@ #include <asm/thread_info.h> #include <asm/ptrace.h> +void asm_offsets(void); + void asm_offsets(void) { OFFSET(TASK_THREAD_RA, task_struct, thread.ra); diff --git a/arch/riscv/kernel/head.S b/arch/riscv/kernel/head.S index 7e849797c9c3..16e9941900c4 100644 --- a/arch/riscv/kernel/head.S +++ b/arch/riscv/kernel/head.S @@ -182,7 +182,6 @@ setup_trap_vector: END(_start) - __INIT ENTRY(_start_kernel) /* Mask all interrupts */ csrw CSR_IE, zero diff --git a/arch/riscv/kernel/perf_callchain.c b/arch/riscv/kernel/perf_callchain.c index cf190197a22f..0bb1854dce83 100644 --- a/arch/riscv/kernel/perf_callchain.c +++ b/arch/riscv/kernel/perf_callchain.c @@ -4,11 +4,7 @@ #include <linux/perf_event.h> #include <linux/uaccess.h> -/* Kernel callchain */ -struct stackframe { - unsigned long fp; - unsigned long ra; -}; +#include <asm/stacktrace.h> /* * Get the return address for a single stackframe and return a pointer to the @@ -74,13 +70,11 @@ void perf_callchain_user(struct perf_callchain_entry_ctx *entry, fp = user_backtrace(entry, fp, 0); } -bool fill_callchain(unsigned long pc, void *entry) +static bool fill_callchain(void *entry, unsigned long pc) { return perf_callchain_store(entry, pc); } -void notrace walk_stackframe(struct task_struct *task, - struct pt_regs *regs, bool (*fn)(unsigned long, void *), void *arg); void perf_callchain_kernel(struct perf_callchain_entry_ctx *entry, struct pt_regs *regs) { diff --git a/arch/riscv/kernel/riscv_ksyms.c b/arch/riscv/kernel/riscv_ksyms.c index 450492e1cb4e..5ab1c7e1a6ed 100644 --- a/arch/riscv/kernel/riscv_ksyms.c +++ b/arch/riscv/kernel/riscv_ksyms.c @@ -11,5 +11,7 @@ */ EXPORT_SYMBOL(memset); EXPORT_SYMBOL(memcpy); +EXPORT_SYMBOL(memmove); EXPORT_SYMBOL(__memset); EXPORT_SYMBOL(__memcpy); +EXPORT_SYMBOL(__memmove); diff --git a/arch/riscv/kernel/setup.c b/arch/riscv/kernel/setup.c index 117f3212a8e4..1d85e9bf783c 100644 --- a/arch/riscv/kernel/setup.c +++ b/arch/riscv/kernel/setup.c @@ -4,6 +4,8 @@ * Chen Liqin <liqin.chen@sunplusct.com> * Lennox Wu <lennox.wu@sunplusct.com> * Copyright (C) 2012 Regents of the University of California + * Copyright (C) 2020 FORTH-ICS/CARV + * Nick Kossifidis <mick@ics.forth.gr> */ #include <linux/init.h> @@ -22,6 +24,7 @@ #include <asm/cpu_ops.h> #include <asm/early_ioremap.h> #include <asm/setup.h> +#include <asm/set_memory.h> #include <asm/sections.h> #include <asm/sbi.h> #include <asm/tlbflush.h> @@ -51,6 +54,163 @@ atomic_t hart_lottery __section(".sdata"); unsigned long boot_cpu_hartid; static DEFINE_PER_CPU(struct cpu, cpu_devices); +/* + * Place kernel memory regions on the resource tree so that + * kexec-tools can retrieve them from /proc/iomem. While there + * also add "System RAM" regions for compatibility with other + * archs, and the rest of the known regions for completeness. + */ +static struct resource code_res = { .name = "Kernel code", }; +static struct resource data_res = { .name = "Kernel data", }; +static struct resource rodata_res = { .name = "Kernel rodata", }; +static struct resource bss_res = { .name = "Kernel bss", }; + +static int __init add_resource(struct resource *parent, + struct resource *res) +{ + int ret = 0; + + ret = insert_resource(parent, res); + if (ret < 0) { + pr_err("Failed to add a %s resource at %llx\n", + res->name, (unsigned long long) res->start); + return ret; + } + + return 1; +} + +static int __init add_kernel_resources(struct resource *res) +{ + int ret = 0; + + /* + * The memory region of the kernel image is continuous and + * was reserved on setup_bootmem, find it here and register + * it as a resource, then register the various segments of + * the image as child nodes + */ + if (!(res->start <= code_res.start && res->end >= data_res.end)) + return 0; + + res->name = "Kernel image"; + res->flags = IORESOURCE_SYSTEM_RAM | IORESOURCE_BUSY; + + /* + * We removed a part of this region on setup_bootmem so + * we need to expand the resource for the bss to fit in. + */ + res->end = bss_res.end; + + ret = add_resource(&iomem_resource, res); + if (ret < 0) + return ret; + + ret = add_resource(res, &code_res); + if (ret < 0) + return ret; + + ret = add_resource(res, &rodata_res); + if (ret < 0) + return ret; + + ret = add_resource(res, &data_res); + if (ret < 0) + return ret; + + ret = add_resource(res, &bss_res); + + return ret; +} + +static void __init init_resources(void) +{ + struct memblock_region *region = NULL; + struct resource *res = NULL; + int ret = 0; + + code_res.start = __pa_symbol(_text); + code_res.end = __pa_symbol(_etext) - 1; + code_res.flags = IORESOURCE_SYSTEM_RAM | IORESOURCE_BUSY; + + rodata_res.start = __pa_symbol(__start_rodata); + rodata_res.end = __pa_symbol(__end_rodata) - 1; + rodata_res.flags = IORESOURCE_SYSTEM_RAM | IORESOURCE_BUSY; + + data_res.start = __pa_symbol(_data); + data_res.end = __pa_symbol(_edata) - 1; + data_res.flags = IORESOURCE_SYSTEM_RAM | IORESOURCE_BUSY; + + bss_res.start = __pa_symbol(__bss_start); + bss_res.end = __pa_symbol(__bss_stop) - 1; + bss_res.flags = IORESOURCE_SYSTEM_RAM | IORESOURCE_BUSY; + + /* + * Start by adding the reserved regions, if they overlap + * with /memory regions, insert_resource later on will take + * care of it. + */ + for_each_reserved_mem_region(region) { + res = memblock_alloc(sizeof(struct resource), SMP_CACHE_BYTES); + if (!res) + panic("%s: Failed to allocate %zu bytes\n", __func__, + sizeof(struct resource)); + + res->name = "Reserved"; + res->flags = IORESOURCE_MEM | IORESOURCE_BUSY; + res->start = __pfn_to_phys(memblock_region_reserved_base_pfn(region)); + res->end = __pfn_to_phys(memblock_region_reserved_end_pfn(region)) - 1; + + ret = add_kernel_resources(res); + if (ret < 0) + goto error; + else if (ret) + continue; + + /* + * Ignore any other reserved regions within + * system memory. + */ + if (memblock_is_memory(res->start)) + continue; + + ret = add_resource(&iomem_resource, res); + if (ret < 0) + goto error; + } + + /* Add /memory regions to the resource tree */ + for_each_mem_region(region) { + res = memblock_alloc(sizeof(struct resource), SMP_CACHE_BYTES); + if (!res) + panic("%s: Failed to allocate %zu bytes\n", __func__, + sizeof(struct resource)); + + if (unlikely(memblock_is_nomap(region))) { + res->name = "Reserved"; + res->flags = IORESOURCE_MEM | IORESOURCE_BUSY; + } else { + res->name = "System RAM"; + res->flags = IORESOURCE_SYSTEM_RAM | IORESOURCE_BUSY; + } + + res->start = __pfn_to_phys(memblock_region_memory_base_pfn(region)); + res->end = __pfn_to_phys(memblock_region_memory_end_pfn(region)) - 1; + + ret = add_resource(&iomem_resource, res); + if (ret < 0) + goto error; + } + + return; + + error: + memblock_free((phys_addr_t) res, sizeof(struct resource)); + /* Better an empty resource tree than an inconsistent one */ + release_child_resources(&iomem_resource); +} + + static void __init parse_dtb(void) { /* Early scan of device tree from init memory */ @@ -81,6 +241,7 @@ void __init setup_arch(char **cmdline_p) efi_init(); setup_bootmem(); paging_init(); + init_resources(); #if IS_ENABLED(CONFIG_BUILTIN_DTB) unflatten_and_copy_device_tree(); #else @@ -90,6 +251,11 @@ void __init setup_arch(char **cmdline_p) pr_err("No DTB found in kernel mappings\n"); #endif + if (IS_ENABLED(CONFIG_RISCV_SBI)) + sbi_init(); + + if (IS_ENABLED(CONFIG_STRICT_KERNEL_RWX)) + protect_kernel_text_data(); #ifdef CONFIG_SWIOTLB swiotlb_init(1); #endif @@ -98,10 +264,6 @@ void __init setup_arch(char **cmdline_p) kasan_init(); #endif -#if IS_ENABLED(CONFIG_RISCV_SBI) - sbi_init(); -#endif - #ifdef CONFIG_SMP setup_smp(); #endif @@ -123,3 +285,12 @@ static int __init topology_init(void) return 0; } subsys_initcall(topology_init); + +void free_initmem(void) +{ + unsigned long init_begin = (unsigned long)__init_begin; + unsigned long init_end = (unsigned long)__init_end; + + set_memory_rw_nx(init_begin, (init_end - init_begin) >> PAGE_SHIFT); + free_initmem_default(POISON_FREE_INITMEM); +} diff --git a/arch/riscv/kernel/stacktrace.c b/arch/riscv/kernel/stacktrace.c index 595342910c3f..48b870a685b3 100644 --- a/arch/riscv/kernel/stacktrace.c +++ b/arch/riscv/kernel/stacktrace.c @@ -12,17 +12,14 @@ #include <linux/stacktrace.h> #include <linux/ftrace.h> +#include <asm/stacktrace.h> + register unsigned long sp_in_global __asm__("sp"); #ifdef CONFIG_FRAME_POINTER -struct stackframe { - unsigned long fp; - unsigned long ra; -}; - void notrace walk_stackframe(struct task_struct *task, struct pt_regs *regs, - bool (*fn)(unsigned long, void *), void *arg) + bool (*fn)(void *, unsigned long), void *arg) { unsigned long fp, sp, pc; @@ -46,7 +43,7 @@ void notrace walk_stackframe(struct task_struct *task, struct pt_regs *regs, unsigned long low, high; struct stackframe *frame; - if (unlikely(!__kernel_text_address(pc) || fn(pc, arg))) + if (unlikely(!__kernel_text_address(pc) || !fn(arg, pc))) break; /* Validate frame pointer */ @@ -66,7 +63,7 @@ void notrace walk_stackframe(struct task_struct *task, struct pt_regs *regs, #else /* !CONFIG_FRAME_POINTER */ void notrace walk_stackframe(struct task_struct *task, - struct pt_regs *regs, bool (*fn)(unsigned long, void *), void *arg) + struct pt_regs *regs, bool (*fn)(void *, unsigned long), void *arg) { unsigned long sp, pc; unsigned long *ksp; @@ -88,7 +85,7 @@ void notrace walk_stackframe(struct task_struct *task, ksp = (unsigned long *)sp; while (!kstack_end(ksp)) { - if (__kernel_text_address(pc) && unlikely(fn(pc, arg))) + if (__kernel_text_address(pc) && unlikely(!fn(arg, pc))) break; pc = (*ksp++) - 0x4; } @@ -96,13 +93,12 @@ void notrace walk_stackframe(struct task_struct *task, #endif /* CONFIG_FRAME_POINTER */ - -static bool print_trace_address(unsigned long pc, void *arg) +static bool print_trace_address(void *arg, unsigned long pc) { const char *loglvl = arg; print_ip_sym(loglvl, pc); - return false; + return true; } void show_stack(struct task_struct *task, unsigned long *sp, const char *loglvl) @@ -111,14 +107,14 @@ void show_stack(struct task_struct *task, unsigned long *sp, const char *loglvl) walk_stackframe(task, NULL, print_trace_address, (void *)loglvl); } -static bool save_wchan(unsigned long pc, void *arg) +static bool save_wchan(void *arg, unsigned long pc) { if (!in_sched_functions(pc)) { unsigned long *p = arg; *p = pc; - return true; + return false; } - return false; + return true; } unsigned long get_wchan(struct task_struct *task) @@ -130,42 +126,12 @@ unsigned long get_wchan(struct task_struct *task) return pc; } - #ifdef CONFIG_STACKTRACE -static bool __save_trace(unsigned long pc, void *arg, bool nosched) -{ - struct stack_trace *trace = arg; - - if (unlikely(nosched && in_sched_functions(pc))) - return false; - if (unlikely(trace->skip > 0)) { - trace->skip--; - return false; - } - - trace->entries[trace->nr_entries++] = pc; - return (trace->nr_entries >= trace->max_entries); -} - -static bool save_trace(unsigned long pc, void *arg) -{ - return __save_trace(pc, arg, false); -} - -/* - * Save stack-backtrace addresses into a stack_trace buffer. - */ -void save_stack_trace_tsk(struct task_struct *tsk, struct stack_trace *trace) -{ - walk_stackframe(tsk, NULL, save_trace, trace); -} -EXPORT_SYMBOL_GPL(save_stack_trace_tsk); - -void save_stack_trace(struct stack_trace *trace) +void arch_stack_walk(stack_trace_consume_fn consume_entry, void *cookie, + struct task_struct *task, struct pt_regs *regs) { - save_stack_trace_tsk(NULL, trace); + walk_stackframe(task, regs, consume_entry, cookie); } -EXPORT_SYMBOL_GPL(save_stack_trace); #endif /* CONFIG_STACKTRACE */ diff --git a/arch/riscv/kernel/vmlinux.lds.S b/arch/riscv/kernel/vmlinux.lds.S index 3ffbd6cbdb86..de03cb22d0e9 100644 --- a/arch/riscv/kernel/vmlinux.lds.S +++ b/arch/riscv/kernel/vmlinux.lds.S @@ -29,8 +29,30 @@ SECTIONS HEAD_TEXT_SECTION . = ALIGN(PAGE_SIZE); + .text : { + _text = .; + _stext = .; + TEXT_TEXT + SCHED_TEXT + CPUIDLE_TEXT + LOCK_TEXT + KPROBES_TEXT + ENTRY_TEXT + IRQENTRY_TEXT + SOFTIRQENTRY_TEXT + *(.fixup) + _etext = .; + } + + . = ALIGN(SECTION_ALIGN); __init_begin = .; - INIT_TEXT_SECTION(PAGE_SIZE) + __init_text_begin = .; + .init.text : AT(ADDR(.init.text) - LOAD_OFFSET) ALIGN(SECTION_ALIGN) { \ + _sinittext = .; \ + INIT_TEXT \ + _einittext = .; \ + } + . = ALIGN(8); __soc_early_init_table : { __soc_early_init_table_start = .; @@ -47,35 +69,28 @@ SECTIONS { EXIT_TEXT } + + __init_text_end = .; + . = ALIGN(SECTION_ALIGN); +#ifdef CONFIG_EFI + . = ALIGN(PECOFF_SECTION_ALIGNMENT); + __pecoff_text_end = .; +#endif + /* Start of init data section */ + __init_data_begin = .; + INIT_DATA_SECTION(16) .exit.data : { EXIT_DATA } PERCPU_SECTION(L1_CACHE_BYTES) - __init_end = .; - . = ALIGN(SECTION_ALIGN); - .text : { - _text = .; - _stext = .; - TEXT_TEXT - SCHED_TEXT - CPUIDLE_TEXT - LOCK_TEXT - KPROBES_TEXT - ENTRY_TEXT - IRQENTRY_TEXT - SOFTIRQENTRY_TEXT - *(.fixup) - _etext = .; + .rel.dyn : { + *(.rel.dyn*) } -#ifdef CONFIG_EFI - . = ALIGN(PECOFF_SECTION_ALIGNMENT); - __pecoff_text_end = .; -#endif - - INIT_DATA_SECTION(16) + __init_data_end = .; + __init_end = .; /* Start of data section */ _sdata = .; @@ -105,10 +120,6 @@ SECTIONS BSS_SECTION(PAGE_SIZE, PAGE_SIZE, 0) - .rel.dyn : { - *(.rel.dyn*) - } - #ifdef CONFIG_EFI . = ALIGN(PECOFF_SECTION_ALIGNMENT); __pecoff_data_virt_size = ABSOLUTE(. - __pecoff_text_end); diff --git a/arch/riscv/lib/Makefile b/arch/riscv/lib/Makefile index 47e7a8204460..ac6171e9c19e 100644 --- a/arch/riscv/lib/Makefile +++ b/arch/riscv/lib/Makefile @@ -2,5 +2,6 @@ lib-y += delay.o lib-y += memcpy.o lib-y += memset.o +lib-y += memmove.o lib-$(CONFIG_MMU) += uaccess.o lib-$(CONFIG_64BIT) += tishift.o diff --git a/arch/riscv/lib/memmove.S b/arch/riscv/lib/memmove.S new file mode 100644 index 000000000000..07d1d2152ba5 --- /dev/null +++ b/arch/riscv/lib/memmove.S @@ -0,0 +1,64 @@ +/* SPDX-License-Identifier: GPL-2.0 */ + +#include <linux/linkage.h> +#include <asm/asm.h> + +ENTRY(__memmove) +WEAK(memmove) + move t0, a0 + move t1, a1 + + beq a0, a1, exit_memcpy + beqz a2, exit_memcpy + srli t2, a2, 0x2 + + slt t3, a0, a1 + beqz t3, do_reverse + + andi a2, a2, 0x3 + li t4, 1 + beqz t2, byte_copy + +word_copy: + lw t3, 0(a1) + addi t2, t2, -1 + addi a1, a1, 4 + sw t3, 0(a0) + addi a0, a0, 4 + bnez t2, word_copy + beqz a2, exit_memcpy + j byte_copy + +do_reverse: + add a0, a0, a2 + add a1, a1, a2 + andi a2, a2, 0x3 + li t4, -1 + beqz t2, reverse_byte_copy + +reverse_word_copy: + addi a1, a1, -4 + addi t2, t2, -1 + lw t3, 0(a1) + addi a0, a0, -4 + sw t3, 0(a0) + bnez t2, reverse_word_copy + beqz a2, exit_memcpy + +reverse_byte_copy: + addi a0, a0, -1 + addi a1, a1, -1 + +byte_copy: + lb t3, 0(a1) + addi a2, a2, -1 + sb t3, 0(a0) + add a1, a1, t4 + add a0, a0, t4 + bnez a2, byte_copy + +exit_memcpy: + move a0, t0 + move a1, t1 + ret +END(__memmove) diff --git a/arch/riscv/mm/init.c b/arch/riscv/mm/init.c index 8e577f14f120..13ba533f462b 100644 --- a/arch/riscv/mm/init.c +++ b/arch/riscv/mm/init.c @@ -13,6 +13,7 @@ #include <linux/of_fdt.h> #include <linux/libfdt.h> #include <linux/set_memory.h> +#include <linux/dma-map-ops.h> #include <asm/fixmap.h> #include <asm/tlbflush.h> @@ -41,13 +42,14 @@ struct pt_alloc_ops { #endif }; +static phys_addr_t dma32_phys_limit __ro_after_init; + static void __init zone_sizes_init(void) { unsigned long max_zone_pfns[MAX_NR_ZONES] = { 0, }; #ifdef CONFIG_ZONE_DMA32 - max_zone_pfns[ZONE_DMA32] = PFN_DOWN(min(4UL * SZ_1G, - (unsigned long) PFN_PHYS(max_low_pfn))); + max_zone_pfns[ZONE_DMA32] = PFN_DOWN(dma32_phys_limit); #endif max_zone_pfns[ZONE_NORMAL] = max_low_pfn; @@ -181,6 +183,7 @@ void __init setup_bootmem(void) max_pfn = PFN_DOWN(memblock_end_of_DRAM()); max_low_pfn = max_pfn; + dma32_phys_limit = min(4UL * SZ_1G, (unsigned long)PFN_PHYS(max_low_pfn)); set_max_mapnr(max_low_pfn); #ifdef CONFIG_BLK_DEV_INITRD @@ -194,6 +197,7 @@ void __init setup_bootmem(void) memblock_reserve(dtb_early_pa, fdt_totalsize(dtb_early_va)); early_init_fdt_scan_reserved_mem(); + dma_contiguous_reserve(dma32_phys_limit); memblock_allow_resize(); memblock_dump_all(); } @@ -618,48 +622,33 @@ static inline void setup_vm_final(void) #endif /* CONFIG_MMU */ #ifdef CONFIG_STRICT_KERNEL_RWX -void mark_rodata_ro(void) +void protect_kernel_text_data(void) { - unsigned long text_start = (unsigned long)_text; - unsigned long text_end = (unsigned long)_etext; + unsigned long text_start = (unsigned long)_start; + unsigned long init_text_start = (unsigned long)__init_text_begin; + unsigned long init_data_start = (unsigned long)__init_data_begin; unsigned long rodata_start = (unsigned long)__start_rodata; unsigned long data_start = (unsigned long)_data; unsigned long max_low = (unsigned long)(__va(PFN_PHYS(max_low_pfn))); - set_memory_ro(text_start, (text_end - text_start) >> PAGE_SHIFT); - set_memory_ro(rodata_start, (data_start - rodata_start) >> PAGE_SHIFT); + set_memory_ro(text_start, (init_text_start - text_start) >> PAGE_SHIFT); + set_memory_ro(init_text_start, (init_data_start - init_text_start) >> PAGE_SHIFT); + set_memory_nx(init_data_start, (rodata_start - init_data_start) >> PAGE_SHIFT); + /* rodata section is marked readonly in mark_rodata_ro */ set_memory_nx(rodata_start, (data_start - rodata_start) >> PAGE_SHIFT); set_memory_nx(data_start, (max_low - data_start) >> PAGE_SHIFT); - - debug_checkwx(); } -#endif -static void __init resource_init(void) +void mark_rodata_ro(void) { - struct memblock_region *region; - - for_each_mem_region(region) { - struct resource *res; - - res = memblock_alloc(sizeof(struct resource), SMP_CACHE_BYTES); - if (!res) - panic("%s: Failed to allocate %zu bytes\n", __func__, - sizeof(struct resource)); + unsigned long rodata_start = (unsigned long)__start_rodata; + unsigned long data_start = (unsigned long)_data; - if (memblock_is_nomap(region)) { - res->name = "reserved"; - res->flags = IORESOURCE_MEM; - } else { - res->name = "System RAM"; - res->flags = IORESOURCE_SYSTEM_RAM | IORESOURCE_BUSY; - } - res->start = __pfn_to_phys(memblock_region_memory_base_pfn(region)); - res->end = __pfn_to_phys(memblock_region_memory_end_pfn(region)) - 1; + set_memory_ro(rodata_start, (data_start - rodata_start) >> PAGE_SHIFT); - request_resource(&iomem_resource, res); - } + debug_checkwx(); } +#endif void __init paging_init(void) { @@ -667,7 +656,6 @@ void __init paging_init(void) sparse_init(); setup_zero_page(); zone_sizes_init(); - resource_init(); } #ifdef CONFIG_SPARSEMEM_VMEMMAP diff --git a/arch/riscv/mm/pageattr.c b/arch/riscv/mm/pageattr.c index 87ba5a68bbb8..5e49e4b4a4cc 100644 --- a/arch/riscv/mm/pageattr.c +++ b/arch/riscv/mm/pageattr.c @@ -128,6 +128,12 @@ static int __set_memory(unsigned long addr, int numpages, pgprot_t set_mask, return ret; } +int set_memory_rw_nx(unsigned long addr, int numpages) +{ + return __set_memory(addr, numpages, __pgprot(_PAGE_READ | _PAGE_WRITE), + __pgprot(_PAGE_EXEC)); +} + int set_memory_ro(unsigned long addr, int numpages) { return __set_memory(addr, numpages, __pgprot(_PAGE_READ), diff --git a/arch/s390/Kconfig b/arch/s390/Kconfig index f795eebf648f..e84bdd15150b 100644 --- a/arch/s390/Kconfig +++ b/arch/s390/Kconfig @@ -150,6 +150,7 @@ config S390 select HAVE_FUTEX_CMPXCHG if FUTEX select HAVE_GCC_PLUGINS select HAVE_GENERIC_VDSO + select HAVE_IRQ_EXIT_ON_IRQ_STACK select HAVE_KERNEL_BZIP2 select HAVE_KERNEL_GZIP select HAVE_KERNEL_LZ4 diff --git a/arch/s390/boot/string.c b/arch/s390/boot/string.c index b11e8108773a..faccb33b462c 100644 --- a/arch/s390/boot/string.c +++ b/arch/s390/boot/string.c @@ -3,6 +3,7 @@ #include <linux/kernel.h> #include <linux/errno.h> #undef CONFIG_KASAN +#undef CONFIG_KASAN_GENERIC #include "../lib/string.c" int strncmp(const char *cs, const char *ct, size_t count) diff --git a/arch/s390/include/asm/delay.h b/arch/s390/include/asm/delay.h index 4a08379cd1eb..21a8fe18fe66 100644 --- a/arch/s390/include/asm/delay.h +++ b/arch/s390/include/asm/delay.h @@ -13,14 +13,12 @@ #ifndef _S390_DELAY_H #define _S390_DELAY_H -void udelay_enable(void); -void __ndelay(unsigned long long nsecs); -void __udelay(unsigned long long usecs); -void udelay_simple(unsigned long long usecs); +void __ndelay(unsigned long nsecs); +void __udelay(unsigned long usecs); void __delay(unsigned long loops); -#define ndelay(n) __ndelay((unsigned long long) (n)) -#define udelay(n) __udelay((unsigned long long) (n)) -#define mdelay(n) __udelay((unsigned long long) (n) * 1000) +#define ndelay(n) __ndelay((unsigned long)(n)) +#define udelay(n) __udelay((unsigned long)(n)) +#define mdelay(n) __udelay((unsigned long)(n) * 1000) #endif /* defined(_S390_DELAY_H) */ diff --git a/arch/s390/include/asm/kvm_host.h b/arch/s390/include/asm/kvm_host.h index 463c24e26000..74f9a036bab2 100644 --- a/arch/s390/include/asm/kvm_host.h +++ b/arch/s390/include/asm/kvm_host.h @@ -459,6 +459,7 @@ struct kvm_vcpu_stat { u64 diagnose_308; u64 diagnose_500; u64 diagnose_other; + u64 pfault_sync; }; #define PGM_OPERATION 0x01 diff --git a/arch/s390/include/asm/processor.h b/arch/s390/include/asm/processor.h index 6b7269f51f83..2058a435add4 100644 --- a/arch/s390/include/asm/processor.h +++ b/arch/s390/include/asm/processor.h @@ -16,14 +16,12 @@ #define CIF_NOHZ_DELAY 2 /* delay HZ disable for a tick */ #define CIF_FPU 3 /* restore FPU registers */ -#define CIF_IGNORE_IRQ 4 /* ignore interrupt (for udelay) */ #define CIF_ENABLED_WAIT 5 /* in enabled wait state */ #define CIF_MCCK_GUEST 6 /* machine check happening in guest */ #define CIF_DEDICATED_CPU 7 /* this CPU is dedicated */ #define _CIF_NOHZ_DELAY BIT(CIF_NOHZ_DELAY) #define _CIF_FPU BIT(CIF_FPU) -#define _CIF_IGNORE_IRQ BIT(CIF_IGNORE_IRQ) #define _CIF_ENABLED_WAIT BIT(CIF_ENABLED_WAIT) #define _CIF_MCCK_GUEST BIT(CIF_MCCK_GUEST) #define _CIF_DEDICATED_CPU BIT(CIF_DEDICATED_CPU) @@ -293,11 +291,6 @@ static inline unsigned long __rewind_psw(psw_t psw, unsigned long ilc) } /* - * Function to stop a processor until the next interrupt occurs - */ -void enabled_wait(void); - -/* * Function to drop a processor into disabled wait state */ static __always_inline void __noreturn disabled_wait(void) diff --git a/arch/s390/kernel/entry.S b/arch/s390/kernel/entry.S index 1f4659203f8c..f1ba197b10c0 100644 --- a/arch/s390/kernel/entry.S +++ b/arch/s390/kernel/entry.S @@ -414,6 +414,7 @@ ENTRY(system_call) mvc __PT_PSW(16,%r11),__LC_SVC_OLD_PSW mvc __PT_INT_CODE(4,%r11),__LC_SVC_ILC stg %r14,__PT_FLAGS(%r11) + xc __SF_BACKCHAIN(8,%r15),__SF_BACKCHAIN(%r15) ENABLE_INTS .Lsysc_do_svc: # clear user controlled register to prevent speculative use @@ -430,7 +431,6 @@ ENTRY(system_call) jnl .Lsysc_nr_ok slag %r8,%r1,3 .Lsysc_nr_ok: - xc __SF_BACKCHAIN(8,%r15),__SF_BACKCHAIN(%r15) stg %r2,__PT_ORIG_GPR2(%r11) stg %r7,STACK_FRAME_OVERHEAD(%r15) lg %r9,0(%r8,%r10) # get system call add. @@ -699,8 +699,8 @@ ENTRY(pgm_check_handler) mvc __THREAD_per_address(8,%r14),__LC_PER_ADDRESS mvc __THREAD_per_cause(2,%r14),__LC_PER_CODE mvc __THREAD_per_paid(1,%r14),__LC_PER_ACCESS_ID -6: RESTORE_SM_CLEAR_PER - xc __SF_BACKCHAIN(8,%r15),__SF_BACKCHAIN(%r15) +6: xc __SF_BACKCHAIN(8,%r15),__SF_BACKCHAIN(%r15) + RESTORE_SM_CLEAR_PER larl %r1,pgm_check_table llgh %r10,__PT_INT_CODE+2(%r11) nill %r10,0x007f @@ -731,8 +731,8 @@ ENTRY(pgm_check_handler) # PER event in supervisor state, must be kprobes # .Lpgm_kprobe: - RESTORE_SM_CLEAR_PER xc __SF_BACKCHAIN(8,%r15),__SF_BACKCHAIN(%r15) + RESTORE_SM_CLEAR_PER lgr %r2,%r11 # pass pointer to pt_regs brasl %r14,do_per_trap j .Lpgm_return @@ -778,10 +778,8 @@ ENTRY(io_int_handler) .Lio_skip_asce: mvc __PT_INT_CODE(12,%r11),__LC_SUBCHANNEL_ID xc __PT_FLAGS(8,%r11),__PT_FLAGS(%r11) - TSTMSK __LC_CPU_FLAGS,_CIF_IGNORE_IRQ - jo .Lio_restore - TRACE_IRQS_OFF xc __SF_BACKCHAIN(8,%r15),__SF_BACKCHAIN(%r15) + TRACE_IRQS_OFF .Lio_loop: lgr %r2,%r11 # pass pointer to pt_regs lghi %r3,IO_INTERRUPT @@ -966,10 +964,8 @@ ENTRY(ext_int_handler) mvc __PT_INT_PARM(4,%r11),__LC_EXT_PARAMS mvc __PT_INT_PARM_LONG(8,%r11),0(%r1) xc __PT_FLAGS(8,%r11),__PT_FLAGS(%r11) - TSTMSK __LC_CPU_FLAGS,_CIF_IGNORE_IRQ - jo .Lio_restore - TRACE_IRQS_OFF xc __SF_BACKCHAIN(8,%r15),__SF_BACKCHAIN(%r15) + TRACE_IRQS_OFF lgr %r2,%r11 # pass pointer to pt_regs lghi %r3,EXT_INTERRUPT brasl %r14,do_IRQ diff --git a/arch/s390/kernel/idle.c b/arch/s390/kernel/idle.c index 2b85096964f8..a5d4d80d6ede 100644 --- a/arch/s390/kernel/idle.c +++ b/arch/s390/kernel/idle.c @@ -9,7 +9,6 @@ #include <linux/kernel.h> #include <linux/kernel_stat.h> -#include <linux/kprobes.h> #include <linux/notifier.h> #include <linux/init.h> #include <linux/cpu.h> @@ -21,22 +20,19 @@ static DEFINE_PER_CPU(struct s390_idle_data, s390_idle); -void enabled_wait(void) +void arch_cpu_idle(void) { struct s390_idle_data *idle = this_cpu_ptr(&s390_idle); unsigned long long idle_time; - unsigned long psw_mask, flags; - + unsigned long psw_mask; /* Wait for external, I/O or machine check interrupt. */ psw_mask = PSW_KERNEL_BITS | PSW_MASK_WAIT | PSW_MASK_DAT | PSW_MASK_IO | PSW_MASK_EXT | PSW_MASK_MCHECK; clear_cpu_flag(CIF_NOHZ_DELAY); - raw_local_irq_save(flags); - /* Call the assembler magic in entry.S */ + /* psw_idle() returns with interrupts disabled. */ psw_idle(idle, psw_mask); - raw_local_irq_restore(flags); /* Account time spent with enabled wait psw loaded as idle time. */ raw_write_seqcount_begin(&idle->seqcount); @@ -46,8 +42,8 @@ void enabled_wait(void) idle->idle_count++; account_idle_time(cputime_to_nsecs(idle_time)); raw_write_seqcount_end(&idle->seqcount); + raw_local_irq_enable(); } -NOKPROBE_SYMBOL(enabled_wait); static ssize_t show_idle_count(struct device *dev, struct device_attribute *attr, char *buf) @@ -120,12 +116,6 @@ void arch_cpu_idle_enter(void) { } -void arch_cpu_idle(void) -{ - enabled_wait(); - raw_local_irq_enable(); -} - void arch_cpu_idle_exit(void) { } diff --git a/arch/s390/kernel/ipl.c b/arch/s390/kernel/ipl.c index 98b3aca1de8e..7a21eca498aa 100644 --- a/arch/s390/kernel/ipl.c +++ b/arch/s390/kernel/ipl.c @@ -1512,7 +1512,7 @@ static void diag308_dump(void *dump_block) while (1) { if (diag308(DIAG308_LOAD_NORMAL_DUMP, NULL) != 0x302) break; - udelay_simple(USEC_PER_SEC); + udelay(USEC_PER_SEC); } } diff --git a/arch/s390/kernel/setup.c b/arch/s390/kernel/setup.c index 1f16a03be995..1fbed91c73bc 100644 --- a/arch/s390/kernel/setup.c +++ b/arch/s390/kernel/setup.c @@ -335,7 +335,6 @@ int __init arch_early_irq_init(void) if (!stack) panic("Couldn't allocate async stack"); S390_lowcore.async_stack = stack + STACK_INIT_OFFSET; - udelay_enable(); return 0; } diff --git a/arch/s390/kernel/syscalls/syscall.tbl b/arch/s390/kernel/syscalls/syscall.tbl index 28c168000483..d443423495e5 100644 --- a/arch/s390/kernel/syscalls/syscall.tbl +++ b/arch/s390/kernel/syscalls/syscall.tbl @@ -443,3 +443,4 @@ 438 common pidfd_getfd sys_pidfd_getfd sys_pidfd_getfd 439 common faccessat2 sys_faccessat2 sys_faccessat2 440 common process_madvise sys_process_madvise sys_process_madvise +441 common epoll_pwait2 sys_epoll_pwait2 compat_sys_epoll_pwait2 diff --git a/arch/s390/kvm/guestdbg.c b/arch/s390/kvm/guestdbg.c index 394a5f53805b..3765c4223bf9 100644 --- a/arch/s390/kvm/guestdbg.c +++ b/arch/s390/kvm/guestdbg.c @@ -184,7 +184,7 @@ static int __import_wp_info(struct kvm_vcpu *vcpu, if (wp_info->len < 0 || wp_info->len > MAX_WP_SIZE) return -EINVAL; - wp_info->old_data = kmalloc(bp_data->len, GFP_KERNEL); + wp_info->old_data = kmalloc(bp_data->len, GFP_KERNEL_ACCOUNT); if (!wp_info->old_data) return -ENOMEM; /* try to backup the original value */ @@ -234,7 +234,7 @@ int kvm_s390_import_bp_data(struct kvm_vcpu *vcpu, if (nr_wp > 0) { wp_info = kmalloc_array(nr_wp, sizeof(*wp_info), - GFP_KERNEL); + GFP_KERNEL_ACCOUNT); if (!wp_info) { ret = -ENOMEM; goto error; @@ -243,7 +243,7 @@ int kvm_s390_import_bp_data(struct kvm_vcpu *vcpu, if (nr_bp > 0) { bp_info = kmalloc_array(nr_bp, sizeof(*bp_info), - GFP_KERNEL); + GFP_KERNEL_ACCOUNT); if (!bp_info) { ret = -ENOMEM; goto error; @@ -349,7 +349,7 @@ static struct kvm_hw_wp_info_arch *any_wp_changed(struct kvm_vcpu *vcpu) if (!wp_info || !wp_info->old_data || wp_info->len <= 0) continue; - temp = kmalloc(wp_info->len, GFP_KERNEL); + temp = kmalloc(wp_info->len, GFP_KERNEL_ACCOUNT); if (!temp) continue; diff --git a/arch/s390/kvm/intercept.c b/arch/s390/kvm/intercept.c index e7a7c499a73f..72b25b7cc6ae 100644 --- a/arch/s390/kvm/intercept.c +++ b/arch/s390/kvm/intercept.c @@ -398,7 +398,7 @@ int handle_sthyi(struct kvm_vcpu *vcpu) if (!kvm_s390_pv_cpu_is_protected(vcpu) && (addr & ~PAGE_MASK)) return kvm_s390_inject_program_int(vcpu, PGM_SPECIFICATION); - sctns = (void *)get_zeroed_page(GFP_KERNEL); + sctns = (void *)get_zeroed_page(GFP_KERNEL_ACCOUNT); if (!sctns) return -ENOMEM; diff --git a/arch/s390/kvm/interrupt.c b/arch/s390/kvm/interrupt.c index 2f177298c663..e3183bd05910 100644 --- a/arch/s390/kvm/interrupt.c +++ b/arch/s390/kvm/interrupt.c @@ -1792,7 +1792,7 @@ struct kvm_s390_interrupt_info *kvm_s390_get_io_int(struct kvm *kvm, goto out; } gisa_out: - tmp_inti = kzalloc(sizeof(*inti), GFP_KERNEL); + tmp_inti = kzalloc(sizeof(*inti), GFP_KERNEL_ACCOUNT); if (tmp_inti) { tmp_inti->type = KVM_S390_INT_IO(1, 0, 0, 0); tmp_inti->io.io_int_word = isc_to_int_word(isc); @@ -2015,7 +2015,7 @@ int kvm_s390_inject_vm(struct kvm *kvm, struct kvm_s390_interrupt_info *inti; int rc; - inti = kzalloc(sizeof(*inti), GFP_KERNEL); + inti = kzalloc(sizeof(*inti), GFP_KERNEL_ACCOUNT); if (!inti) return -ENOMEM; @@ -2414,7 +2414,7 @@ static int enqueue_floating_irq(struct kvm_device *dev, return -EINVAL; while (len >= sizeof(struct kvm_s390_irq)) { - inti = kzalloc(sizeof(*inti), GFP_KERNEL); + inti = kzalloc(sizeof(*inti), GFP_KERNEL_ACCOUNT); if (!inti) return -ENOMEM; @@ -2462,7 +2462,7 @@ static int register_io_adapter(struct kvm_device *dev, if (dev->kvm->arch.adapters[adapter_info.id] != NULL) return -EINVAL; - adapter = kzalloc(sizeof(*adapter), GFP_KERNEL); + adapter = kzalloc(sizeof(*adapter), GFP_KERNEL_ACCOUNT); if (!adapter) return -ENOMEM; @@ -3290,7 +3290,7 @@ int kvm_s390_gib_init(u8 nisc) goto out; } - gib = (struct kvm_s390_gib *)get_zeroed_page(GFP_KERNEL | GFP_DMA); + gib = (struct kvm_s390_gib *)get_zeroed_page(GFP_KERNEL_ACCOUNT | GFP_DMA); if (!gib) { rc = -ENOMEM; goto out; diff --git a/arch/s390/kvm/kvm-s390.c b/arch/s390/kvm/kvm-s390.c index 425d3d75320b..dbafd057ca6a 100644 --- a/arch/s390/kvm/kvm-s390.c +++ b/arch/s390/kvm/kvm-s390.c @@ -60,6 +60,7 @@ struct kvm_stats_debugfs_item debugfs_entries[] = { VCPU_STAT("userspace_handled", exit_userspace), VCPU_STAT("exit_null", exit_null), + VCPU_STAT("pfault_sync", pfault_sync), VCPU_STAT("exit_validity", exit_validity), VCPU_STAT("exit_stop_request", exit_stop_request), VCPU_STAT("exit_external_request", exit_external_request), @@ -1254,7 +1255,7 @@ static int kvm_s390_set_processor(struct kvm *kvm, struct kvm_device_attr *attr) ret = -EBUSY; goto out; } - proc = kzalloc(sizeof(*proc), GFP_KERNEL); + proc = kzalloc(sizeof(*proc), GFP_KERNEL_ACCOUNT); if (!proc) { ret = -ENOMEM; goto out; @@ -1416,7 +1417,7 @@ static int kvm_s390_get_processor(struct kvm *kvm, struct kvm_device_attr *attr) struct kvm_s390_vm_cpu_processor *proc; int ret = 0; - proc = kzalloc(sizeof(*proc), GFP_KERNEL); + proc = kzalloc(sizeof(*proc), GFP_KERNEL_ACCOUNT); if (!proc) { ret = -ENOMEM; goto out; @@ -1444,7 +1445,7 @@ static int kvm_s390_get_machine(struct kvm *kvm, struct kvm_device_attr *attr) struct kvm_s390_vm_cpu_machine *mach; int ret = 0; - mach = kzalloc(sizeof(*mach), GFP_KERNEL); + mach = kzalloc(sizeof(*mach), GFP_KERNEL_ACCOUNT); if (!mach) { ret = -ENOMEM; goto out; @@ -1812,7 +1813,7 @@ static long kvm_s390_get_skeys(struct kvm *kvm, struct kvm_s390_skeys *args) if (args->count < 1 || args->count > KVM_S390_SKEYS_MAX) return -EINVAL; - keys = kvmalloc_array(args->count, sizeof(uint8_t), GFP_KERNEL); + keys = kvmalloc_array(args->count, sizeof(uint8_t), GFP_KERNEL_ACCOUNT); if (!keys) return -ENOMEM; @@ -1857,7 +1858,7 @@ static long kvm_s390_set_skeys(struct kvm *kvm, struct kvm_s390_skeys *args) if (args->count < 1 || args->count > KVM_S390_SKEYS_MAX) return -EINVAL; - keys = kvmalloc_array(args->count, sizeof(uint8_t), GFP_KERNEL); + keys = kvmalloc_array(args->count, sizeof(uint8_t), GFP_KERNEL_ACCOUNT); if (!keys) return -ENOMEM; @@ -2625,7 +2626,7 @@ static void sca_dispose(struct kvm *kvm) int kvm_arch_init_vm(struct kvm *kvm, unsigned long type) { - gfp_t alloc_flags = GFP_KERNEL; + gfp_t alloc_flags = GFP_KERNEL_ACCOUNT; int i, rc; char debug_name[16]; static unsigned long sca_offset; @@ -2670,7 +2671,7 @@ int kvm_arch_init_vm(struct kvm *kvm, unsigned long type) BUILD_BUG_ON(sizeof(struct sie_page2) != 4096); kvm->arch.sie_page2 = - (struct sie_page2 *) get_zeroed_page(GFP_KERNEL | GFP_DMA); + (struct sie_page2 *) get_zeroed_page(GFP_KERNEL_ACCOUNT | GFP_DMA); if (!kvm->arch.sie_page2) goto out_err; @@ -2900,7 +2901,7 @@ static int sca_switch_to_extended(struct kvm *kvm) if (kvm->arch.use_esca) return 0; - new_sca = alloc_pages_exact(sizeof(*new_sca), GFP_KERNEL|__GFP_ZERO); + new_sca = alloc_pages_exact(sizeof(*new_sca), GFP_KERNEL_ACCOUNT | __GFP_ZERO); if (!new_sca) return -ENOMEM; @@ -3133,7 +3134,7 @@ void kvm_s390_vcpu_unsetup_cmma(struct kvm_vcpu *vcpu) int kvm_s390_vcpu_setup_cmma(struct kvm_vcpu *vcpu) { - vcpu->arch.sie_block->cbrlo = get_zeroed_page(GFP_KERNEL); + vcpu->arch.sie_block->cbrlo = get_zeroed_page(GFP_KERNEL_ACCOUNT); if (!vcpu->arch.sie_block->cbrlo) return -ENOMEM; return 0; @@ -3243,7 +3244,7 @@ int kvm_arch_vcpu_create(struct kvm_vcpu *vcpu) int rc; BUILD_BUG_ON(sizeof(struct sie_page) != 4096); - sie_page = (struct sie_page *) get_zeroed_page(GFP_KERNEL); + sie_page = (struct sie_page *) get_zeroed_page(GFP_KERNEL_ACCOUNT); if (!sie_page) return -ENOMEM; @@ -4109,6 +4110,7 @@ static int vcpu_post_run(struct kvm_vcpu *vcpu, int exit_reason) current->thread.gmap_pfault = 0; if (kvm_arch_setup_async_pf(vcpu)) return 0; + vcpu->stat.pfault_sync++; return kvm_arch_fault_in_page(vcpu, current->thread.gmap_addr, 1); } return vcpu_post_run_fault_in_sie(vcpu); diff --git a/arch/s390/kvm/priv.c b/arch/s390/kvm/priv.c index cd74989ce0b0..9928f785c677 100644 --- a/arch/s390/kvm/priv.c +++ b/arch/s390/kvm/priv.c @@ -879,7 +879,7 @@ static int handle_stsi(struct kvm_vcpu *vcpu) switch (fc) { case 1: /* same handling for 1 and 2 */ case 2: - mem = get_zeroed_page(GFP_KERNEL); + mem = get_zeroed_page(GFP_KERNEL_ACCOUNT); if (!mem) goto out_no_data; if (stsi((void *) mem, fc, sel1, sel2)) @@ -888,7 +888,7 @@ static int handle_stsi(struct kvm_vcpu *vcpu) case 3: if (sel1 != 2 || sel2 != 2) goto out_no_data; - mem = get_zeroed_page(GFP_KERNEL); + mem = get_zeroed_page(GFP_KERNEL_ACCOUNT); if (!mem) goto out_no_data; handle_stsi_3_2_2(vcpu, (void *) mem); diff --git a/arch/s390/kvm/pv.c b/arch/s390/kvm/pv.c index f5847f9dec7c..813b6e93dc83 100644 --- a/arch/s390/kvm/pv.c +++ b/arch/s390/kvm/pv.c @@ -60,7 +60,7 @@ int kvm_s390_pv_create_cpu(struct kvm_vcpu *vcpu, u16 *rc, u16 *rrc) if (kvm_s390_pv_cpu_get_handle(vcpu)) return -EINVAL; - vcpu->arch.pv.stor_base = __get_free_pages(GFP_KERNEL, + vcpu->arch.pv.stor_base = __get_free_pages(GFP_KERNEL_ACCOUNT, get_order(uv_info.guest_cpu_stor_len)); if (!vcpu->arch.pv.stor_base) return -ENOMEM; @@ -72,7 +72,7 @@ int kvm_s390_pv_create_cpu(struct kvm_vcpu *vcpu, u16 *rc, u16 *rrc) uvcb.stor_origin = (u64)vcpu->arch.pv.stor_base; /* Alloc Secure Instruction Data Area Designation */ - vcpu->arch.sie_block->sidad = __get_free_page(GFP_KERNEL | __GFP_ZERO); + vcpu->arch.sie_block->sidad = __get_free_page(GFP_KERNEL_ACCOUNT | __GFP_ZERO); if (!vcpu->arch.sie_block->sidad) { free_pages(vcpu->arch.pv.stor_base, get_order(uv_info.guest_cpu_stor_len)); @@ -120,7 +120,7 @@ static int kvm_s390_pv_alloc_vm(struct kvm *kvm) struct kvm_memory_slot *memslot; kvm->arch.pv.stor_var = NULL; - kvm->arch.pv.stor_base = __get_free_pages(GFP_KERNEL, get_order(base)); + kvm->arch.pv.stor_base = __get_free_pages(GFP_KERNEL_ACCOUNT, get_order(base)); if (!kvm->arch.pv.stor_base) return -ENOMEM; diff --git a/arch/s390/kvm/vsie.c b/arch/s390/kvm/vsie.c index 4f3cbf6003a9..c5d0a58b2c29 100644 --- a/arch/s390/kvm/vsie.c +++ b/arch/s390/kvm/vsie.c @@ -1234,7 +1234,7 @@ static struct vsie_page *get_vsie_page(struct kvm *kvm, unsigned long addr) mutex_lock(&kvm->arch.vsie.mutex); if (kvm->arch.vsie.page_count < nr_vcpus) { - page = alloc_page(GFP_KERNEL | __GFP_ZERO | GFP_DMA); + page = alloc_page(GFP_KERNEL_ACCOUNT | __GFP_ZERO | GFP_DMA); if (!page) { mutex_unlock(&kvm->arch.vsie.mutex); return ERR_PTR(-ENOMEM); @@ -1336,7 +1336,7 @@ out_put: void kvm_s390_vsie_init(struct kvm *kvm) { mutex_init(&kvm->arch.vsie.mutex); - INIT_RADIX_TREE(&kvm->arch.vsie.addr_to_page, GFP_KERNEL); + INIT_RADIX_TREE(&kvm->arch.vsie.addr_to_page, GFP_KERNEL_ACCOUNT); } /* Destroy the vsie data structures. To be called when a vm is destroyed. */ diff --git a/arch/s390/lib/delay.c b/arch/s390/lib/delay.c index 68d61f2835df..f289afeb3f31 100644 --- a/arch/s390/lib/delay.c +++ b/arch/s390/lib/delay.c @@ -19,13 +19,6 @@ #include <asm/div64.h> #include <asm/idle.h> -static DEFINE_STATIC_KEY_FALSE(udelay_ready); - -void __init udelay_enable(void) -{ - static_branch_enable(&udelay_ready); -} - void __delay(unsigned long loops) { /* @@ -39,105 +32,25 @@ void __delay(unsigned long loops) } EXPORT_SYMBOL(__delay); -static void __udelay_disabled(unsigned long long usecs) +static void delay_loop(unsigned long delta) { - unsigned long cr0, cr0_new, psw_mask; - struct s390_idle_data idle; - u64 end; + unsigned long end; - end = get_tod_clock() + (usecs << 12); - __ctl_store(cr0, 0, 0); - cr0_new = cr0 & ~CR0_IRQ_SUBCLASS_MASK; - cr0_new |= (1UL << (63 - 52)); /* enable clock comparator irq */ - __ctl_load(cr0_new, 0, 0); - psw_mask = __extract_psw() | PSW_MASK_EXT | PSW_MASK_WAIT; - set_clock_comparator(end); - set_cpu_flag(CIF_IGNORE_IRQ); - psw_idle(&idle, psw_mask); - trace_hardirqs_off(); - clear_cpu_flag(CIF_IGNORE_IRQ); - set_clock_comparator(S390_lowcore.clock_comparator); - __ctl_load(cr0, 0, 0); + end = get_tod_clock_monotonic() + delta; + while (!tod_after(get_tod_clock_monotonic(), end)) + cpu_relax(); } -static void __udelay_enabled(unsigned long long usecs) +void __udelay(unsigned long usecs) { - u64 clock_saved, end; - - end = get_tod_clock_fast() + (usecs << 12); - do { - clock_saved = 0; - if (tod_after(S390_lowcore.clock_comparator, end)) { - clock_saved = local_tick_disable(); - set_clock_comparator(end); - } - enabled_wait(); - if (clock_saved) - local_tick_enable(clock_saved); - } while (get_tod_clock_fast() < end); -} - -/* - * Waits for 'usecs' microseconds using the TOD clock comparator. - */ -void __udelay(unsigned long long usecs) -{ - unsigned long flags; - - if (!static_branch_likely(&udelay_ready)) { - udelay_simple(usecs); - return; - } - - preempt_disable(); - local_irq_save(flags); - if (in_irq()) { - __udelay_disabled(usecs); - goto out; - } - if (in_softirq()) { - if (raw_irqs_disabled_flags(flags)) - __udelay_disabled(usecs); - else - __udelay_enabled(usecs); - goto out; - } - if (raw_irqs_disabled_flags(flags)) { - local_bh_disable(); - __udelay_disabled(usecs); - _local_bh_enable(); - goto out; - } - __udelay_enabled(usecs); -out: - local_irq_restore(flags); - preempt_enable(); + delay_loop(usecs << 12); } EXPORT_SYMBOL(__udelay); -/* - * Simple udelay variant. To be used on startup and reboot - * when the interrupt handler isn't working. - */ -void udelay_simple(unsigned long long usecs) -{ - u64 end; - - end = get_tod_clock_fast() + (usecs << 12); - while (get_tod_clock_fast() < end) - cpu_relax(); -} - -void __ndelay(unsigned long long nsecs) +void __ndelay(unsigned long nsecs) { - u64 end; - nsecs <<= 9; do_div(nsecs, 125); - end = get_tod_clock_fast() + nsecs; - if (nsecs & ~0xfffUL) - __udelay(nsecs >> 12); - while (get_tod_clock_fast() < end) - barrier(); + delay_loop(nsecs); } EXPORT_SYMBOL(__ndelay); diff --git a/arch/s390/lib/test_unwind.c b/arch/s390/lib/test_unwind.c index 7c988994931f..dcd8946255be 100644 --- a/arch/s390/lib/test_unwind.c +++ b/arch/s390/lib/test_unwind.c @@ -9,12 +9,12 @@ #include <linux/kallsyms.h> #include <linux/kthread.h> #include <linux/module.h> +#include <linux/timer.h> #include <linux/slab.h> #include <linux/string.h> #include <linux/kprobes.h> #include <linux/wait.h> #include <asm/irq.h> -#include <asm/delay.h> #define BT_BUF_SIZE (PAGE_SIZE * 4) @@ -205,12 +205,15 @@ static noinline int unwindme_func3(struct unwindme *u) /* This function must appear in the backtrace. */ static noinline int unwindme_func2(struct unwindme *u) { + unsigned long flags; int rc; if (u->flags & UWM_SWITCH_STACK) { - preempt_disable(); + local_irq_save(flags); + local_mcck_disable(); rc = CALL_ON_STACK(unwindme_func3, S390_lowcore.nodat_stack, 1, u); - preempt_enable(); + local_mcck_enable(); + local_irq_restore(flags); return rc; } else { return unwindme_func3(u); @@ -223,31 +226,27 @@ static noinline int unwindme_func1(void *u) return unwindme_func2((struct unwindme *)u); } -static void unwindme_irq_handler(struct ext_code ext_code, - unsigned int param32, - unsigned long param64) +static void unwindme_timer_fn(struct timer_list *unused) { struct unwindme *u = READ_ONCE(unwindme); - if (u && u->task == current) { + if (u) { unwindme = NULL; u->task = NULL; u->ret = unwindme_func1(u); + complete(&u->task_ready); } } +static struct timer_list unwind_timer; + static int test_unwind_irq(struct unwindme *u) { - preempt_disable(); - if (register_external_irq(EXT_IRQ_CLK_COMP, unwindme_irq_handler)) { - pr_info("Couldn't register external interrupt handler"); - return -1; - } - u->task = current; unwindme = u; - udelay(1); - unregister_external_irq(EXT_IRQ_CLK_COMP, unwindme_irq_handler); - preempt_enable(); + init_completion(&u->task_ready); + timer_setup(&unwind_timer, unwindme_timer_fn, 0); + mod_timer(&unwind_timer, jiffies + 1); + wait_for_completion(&u->task_ready); return u->ret; } diff --git a/arch/s390/mm/gmap.c b/arch/s390/mm/gmap.c index 64795d034926..9bb2c7512cd5 100644 --- a/arch/s390/mm/gmap.c +++ b/arch/s390/mm/gmap.c @@ -2,7 +2,7 @@ /* * KVM guest address space mapping code * - * Copyright IBM Corp. 2007, 2016, 2018 + * Copyright IBM Corp. 2007, 2020 * Author(s): Martin Schwidefsky <schwidefsky@de.ibm.com> * David Hildenbrand <david@redhat.com> * Janosch Frank <frankja@linux.vnet.ibm.com> @@ -56,19 +56,19 @@ static struct gmap *gmap_alloc(unsigned long limit) atype = _ASCE_TYPE_REGION1; etype = _REGION1_ENTRY_EMPTY; } - gmap = kzalloc(sizeof(struct gmap), GFP_KERNEL); + gmap = kzalloc(sizeof(struct gmap), GFP_KERNEL_ACCOUNT); if (!gmap) goto out; INIT_LIST_HEAD(&gmap->crst_list); INIT_LIST_HEAD(&gmap->children); INIT_LIST_HEAD(&gmap->pt_list); - INIT_RADIX_TREE(&gmap->guest_to_host, GFP_KERNEL); - INIT_RADIX_TREE(&gmap->host_to_guest, GFP_ATOMIC); - INIT_RADIX_TREE(&gmap->host_to_rmap, GFP_ATOMIC); + INIT_RADIX_TREE(&gmap->guest_to_host, GFP_KERNEL_ACCOUNT); + INIT_RADIX_TREE(&gmap->host_to_guest, GFP_ATOMIC | __GFP_ACCOUNT); + INIT_RADIX_TREE(&gmap->host_to_rmap, GFP_ATOMIC | __GFP_ACCOUNT); spin_lock_init(&gmap->guest_table_lock); spin_lock_init(&gmap->shadow_lock); refcount_set(&gmap->ref_count, 1); - page = alloc_pages(GFP_KERNEL, CRST_ALLOC_ORDER); + page = alloc_pages(GFP_KERNEL_ACCOUNT, CRST_ALLOC_ORDER); if (!page) goto out_free; page->index = 0; @@ -309,7 +309,7 @@ static int gmap_alloc_table(struct gmap *gmap, unsigned long *table, unsigned long *new; /* since we dont free the gmap table until gmap_free we can unlock */ - page = alloc_pages(GFP_KERNEL, CRST_ALLOC_ORDER); + page = alloc_pages(GFP_KERNEL_ACCOUNT, CRST_ALLOC_ORDER); if (!page) return -ENOMEM; new = (unsigned long *) page_to_phys(page); @@ -594,7 +594,7 @@ int __gmap_link(struct gmap *gmap, unsigned long gaddr, unsigned long vmaddr) if (pmd_large(*pmd) && !gmap->mm->context.allow_gmap_hpage_1m) return -EFAULT; /* Link gmap segment table entry location to page table. */ - rc = radix_tree_preload(GFP_KERNEL); + rc = radix_tree_preload(GFP_KERNEL_ACCOUNT); if (rc) return rc; ptl = pmd_lock(mm, pmd); @@ -1218,11 +1218,11 @@ static int gmap_protect_rmap(struct gmap *sg, unsigned long raddr, vmaddr = __gmap_translate(parent, paddr); if (IS_ERR_VALUE(vmaddr)) return vmaddr; - rmap = kzalloc(sizeof(*rmap), GFP_KERNEL); + rmap = kzalloc(sizeof(*rmap), GFP_KERNEL_ACCOUNT); if (!rmap) return -ENOMEM; rmap->raddr = raddr; - rc = radix_tree_preload(GFP_KERNEL); + rc = radix_tree_preload(GFP_KERNEL_ACCOUNT); if (rc) { kfree(rmap); return rc; @@ -1741,7 +1741,7 @@ int gmap_shadow_r2t(struct gmap *sg, unsigned long saddr, unsigned long r2t, BUG_ON(!gmap_is_shadow(sg)); /* Allocate a shadow region second table */ - page = alloc_pages(GFP_KERNEL, CRST_ALLOC_ORDER); + page = alloc_pages(GFP_KERNEL_ACCOUNT, CRST_ALLOC_ORDER); if (!page) return -ENOMEM; page->index = r2t & _REGION_ENTRY_ORIGIN; @@ -1825,7 +1825,7 @@ int gmap_shadow_r3t(struct gmap *sg, unsigned long saddr, unsigned long r3t, BUG_ON(!gmap_is_shadow(sg)); /* Allocate a shadow region second table */ - page = alloc_pages(GFP_KERNEL, CRST_ALLOC_ORDER); + page = alloc_pages(GFP_KERNEL_ACCOUNT, CRST_ALLOC_ORDER); if (!page) return -ENOMEM; page->index = r3t & _REGION_ENTRY_ORIGIN; @@ -1909,7 +1909,7 @@ int gmap_shadow_sgt(struct gmap *sg, unsigned long saddr, unsigned long sgt, BUG_ON(!gmap_is_shadow(sg) || (sgt & _REGION3_ENTRY_LARGE)); /* Allocate a shadow segment table */ - page = alloc_pages(GFP_KERNEL, CRST_ALLOC_ORDER); + page = alloc_pages(GFP_KERNEL_ACCOUNT, CRST_ALLOC_ORDER); if (!page) return -ENOMEM; page->index = sgt & _REGION_ENTRY_ORIGIN; @@ -2116,7 +2116,7 @@ int gmap_shadow_page(struct gmap *sg, unsigned long saddr, pte_t pte) parent = sg->parent; prot = (pte_val(pte) & _PAGE_PROTECT) ? PROT_READ : PROT_WRITE; - rmap = kzalloc(sizeof(*rmap), GFP_KERNEL); + rmap = kzalloc(sizeof(*rmap), GFP_KERNEL_ACCOUNT); if (!rmap) return -ENOMEM; rmap->raddr = (saddr & PAGE_MASK) | _SHADOW_RMAP_PGTABLE; @@ -2128,7 +2128,7 @@ int gmap_shadow_page(struct gmap *sg, unsigned long saddr, pte_t pte) rc = vmaddr; break; } - rc = radix_tree_preload(GFP_KERNEL); + rc = radix_tree_preload(GFP_KERNEL_ACCOUNT); if (rc) break; rc = -EAGAIN; diff --git a/arch/sh/boards/of-generic.c b/arch/sh/boards/of-generic.c index bffbe69b2236..921d76fc3358 100644 --- a/arch/sh/boards/of-generic.c +++ b/arch/sh/boards/of-generic.c @@ -6,10 +6,10 @@ */ #include <linux/of.h> +#include <linux/of_clk.h> #include <linux/of_fdt.h> #include <linux/clocksource.h> #include <linux/irqchip.h> -#include <linux/clk-provider.h> #include <asm/machvec.h> #include <asm/rtc.h> diff --git a/arch/sh/kernel/syscalls/syscall.tbl b/arch/sh/kernel/syscalls/syscall.tbl index 783738448ff5..9df40ac0ebc0 100644 --- a/arch/sh/kernel/syscalls/syscall.tbl +++ b/arch/sh/kernel/syscalls/syscall.tbl @@ -443,3 +443,4 @@ 438 common pidfd_getfd sys_pidfd_getfd 439 common faccessat2 sys_faccessat2 440 common process_madvise sys_process_madvise +441 common epoll_pwait2 sys_epoll_pwait2 diff --git a/arch/sparc/kernel/syscalls/syscall.tbl b/arch/sparc/kernel/syscalls/syscall.tbl index 78160260991b..40d8c7cd8298 100644 --- a/arch/sparc/kernel/syscalls/syscall.tbl +++ b/arch/sparc/kernel/syscalls/syscall.tbl @@ -486,3 +486,4 @@ 438 common pidfd_getfd sys_pidfd_getfd 439 common faccessat2 sys_faccessat2 440 common process_madvise sys_process_madvise +441 common epoll_pwait2 sys_epoll_pwait2 compat_sys_epoll_pwait2 diff --git a/arch/um/Kconfig b/arch/um/Kconfig index 43333e36e0ba..34d302d1a07f 100644 --- a/arch/um/Kconfig +++ b/arch/um/Kconfig @@ -15,6 +15,7 @@ config UML select HAVE_DEBUG_KMEMLEAK select HAVE_DEBUG_BUGVERBOSE select NO_DMA + select ARCH_HAS_SET_MEMORY select GENERIC_IRQ_SHOW select GENERIC_CPU_DEVICES select HAVE_GCC_PLUGINS @@ -191,3 +192,8 @@ config UML_TIME_TRAVEL_SUPPORT endmenu source "arch/um/drivers/Kconfig" + +config ARCH_SUSPEND_POSSIBLE + def_bool y + +source "kernel/power/Kconfig" diff --git a/arch/um/drivers/chan_user.c b/arch/um/drivers/chan_user.c index 4d80526a4236..d8845d4aac6a 100644 --- a/arch/um/drivers/chan_user.c +++ b/arch/um/drivers/chan_user.c @@ -26,10 +26,10 @@ int generic_read(int fd, char *c_out, void *unused) n = read(fd, c_out, sizeof(*c_out)); if (n > 0) return n; - else if (errno == EAGAIN) - return 0; else if (n == 0) return -EIO; + else if (errno == EAGAIN) + return 0; return -errno; } diff --git a/arch/um/drivers/line.c b/arch/um/drivers/line.c index 14ad9f495fe6..1c70a31e7c5b 100644 --- a/arch/um/drivers/line.c +++ b/arch/um/drivers/line.c @@ -262,19 +262,25 @@ static irqreturn_t line_write_interrupt(int irq, void *data) int line_setup_irq(int fd, int input, int output, struct line *line, void *data) { const struct line_driver *driver = line->driver; - int err = 0; + int err; - if (input) + if (input) { err = um_request_irq(driver->read_irq, fd, IRQ_READ, line_interrupt, IRQF_SHARED, driver->read_irq_name, data); - if (err) - return err; - if (output) + if (err < 0) + return err; + } + + if (output) { err = um_request_irq(driver->write_irq, fd, IRQ_WRITE, line_write_interrupt, IRQF_SHARED, driver->write_irq_name, data); - return err; + if (err < 0) + return err; + } + + return 0; } static int line_activate(struct tty_port *port, struct tty_struct *tty) @@ -608,7 +614,6 @@ static void free_winch(struct winch *winch) winch->fd = -1; if (fd != -1) os_close_file(fd); - list_del(&winch->list); __free_winch(&winch->work); } @@ -709,6 +714,8 @@ static void unregister_winch(struct tty_struct *tty) winch = list_entry(ele, struct winch, list); wtty = tty_port_tty_get(winch->port); if (wtty == tty) { + list_del(&winch->list); + spin_unlock(&winch_handler_lock); free_winch(winch); break; } @@ -719,14 +726,17 @@ static void unregister_winch(struct tty_struct *tty) static void winch_cleanup(void) { - struct list_head *ele, *next; struct winch *winch; spin_lock(&winch_handler_lock); + while ((winch = list_first_entry_or_null(&winch_handlers, + struct winch, list))) { + list_del(&winch->list); + spin_unlock(&winch_handler_lock); - list_for_each_safe(ele, next, &winch_handlers) { - winch = list_entry(ele, struct winch, list); free_winch(winch); + + spin_lock(&winch_handler_lock); } spin_unlock(&winch_handler_lock); diff --git a/arch/um/drivers/mconsole_kern.c b/arch/um/drivers/mconsole_kern.c index a2e680f7d39f..6d00af25ec6b 100644 --- a/arch/um/drivers/mconsole_kern.c +++ b/arch/um/drivers/mconsole_kern.c @@ -738,7 +738,7 @@ static int __init mconsole_init(void) err = um_request_irq(MCONSOLE_IRQ, sock, IRQ_READ, mconsole_interrupt, IRQF_SHARED, "mconsole", (void *)sock); - if (err) { + if (err < 0) { printk(KERN_ERR "Failed to get IRQ for management console\n"); goto out; } diff --git a/arch/um/drivers/net_kern.c b/arch/um/drivers/net_kern.c index 1802cf4ef5a5..2fc0b038ff8a 100644 --- a/arch/um/drivers/net_kern.c +++ b/arch/um/drivers/net_kern.c @@ -160,7 +160,7 @@ static int uml_net_open(struct net_device *dev) err = um_request_irq(dev->irq, lp->fd, IRQ_READ, uml_net_interrupt, IRQF_SHARED, dev->name, dev); - if (err != 0) { + if (err < 0) { printk(KERN_ERR "uml_net_open: failed to get irq(%d)\n", err); err = -ENETUNREACH; goto out_close; diff --git a/arch/um/drivers/port_kern.c b/arch/um/drivers/port_kern.c index a47ca5376d9d..efa8b7304090 100644 --- a/arch/um/drivers/port_kern.c +++ b/arch/um/drivers/port_kern.c @@ -100,7 +100,7 @@ static int port_accept(struct port_list *port) .port = port }); if (um_request_irq(TELNETD_IRQ, socket[0], IRQ_READ, pipe_interrupt, - IRQF_SHARED, "telnetd", conn)) { + IRQF_SHARED, "telnetd", conn) < 0) { printk(KERN_ERR "port_accept : failed to get IRQ for " "telnetd\n"); goto out_free; @@ -182,7 +182,7 @@ void *port_data(int port_num) } if (um_request_irq(ACCEPT_IRQ, fd, IRQ_READ, port_interrupt, - IRQF_SHARED, "port", port)) { + IRQF_SHARED, "port", port) < 0) { printk(KERN_ERR "Failed to get IRQ for port %d\n", port_num); goto out_close; } diff --git a/arch/um/drivers/random.c b/arch/um/drivers/random.c index ce115fce52f0..433a3f8f2ef3 100644 --- a/arch/um/drivers/random.c +++ b/arch/um/drivers/random.c @@ -11,6 +11,7 @@ #include <linux/fs.h> #include <linux/interrupt.h> #include <linux/miscdevice.h> +#include <linux/hw_random.h> #include <linux/delay.h> #include <linux/uaccess.h> #include <init.h> @@ -18,9 +19,8 @@ #include <os.h> /* - * core module and version information + * core module information */ -#define RNG_VERSION "1.0.0" #define RNG_MODULE_NAME "hw_random" /* Changed at init time, in the non-modular case, and at module load @@ -28,88 +28,36 @@ * protects against a module being loaded twice at the same time. */ static int random_fd = -1; -static DECLARE_WAIT_QUEUE_HEAD(host_read_wait); +static struct hwrng hwrng = { 0, }; +static DECLARE_COMPLETION(have_data); -static int rng_dev_open (struct inode *inode, struct file *filp) +static int rng_dev_read(struct hwrng *rng, void *buf, size_t max, bool block) { - /* enforce read-only access to this chrdev */ - if ((filp->f_mode & FMODE_READ) == 0) - return -EINVAL; - if ((filp->f_mode & FMODE_WRITE) != 0) - return -EINVAL; + int ret; - return 0; -} - -static atomic_t host_sleep_count = ATOMIC_INIT(0); - -static ssize_t rng_dev_read (struct file *filp, char __user *buf, size_t size, - loff_t *offp) -{ - u32 data; - int n, ret = 0, have_data; - - while (size) { - n = os_read_file(random_fd, &data, sizeof(data)); - if (n > 0) { - have_data = n; - while (have_data && size) { - if (put_user((u8) data, buf++)) { - ret = ret ? : -EFAULT; - break; - } - size--; - ret++; - have_data--; - data >>= 8; - } - } - else if (n == -EAGAIN) { - DECLARE_WAITQUEUE(wait, current); - - if (filp->f_flags & O_NONBLOCK) - return ret ? : -EAGAIN; - - atomic_inc(&host_sleep_count); + for (;;) { + ret = os_read_file(random_fd, buf, max); + if (block && ret == -EAGAIN) { add_sigio_fd(random_fd); - add_wait_queue(&host_read_wait, &wait); - set_current_state(TASK_INTERRUPTIBLE); + ret = wait_for_completion_killable(&have_data); - schedule(); - remove_wait_queue(&host_read_wait, &wait); + ignore_sigio_fd(random_fd); + deactivate_fd(random_fd, RANDOM_IRQ); - if (atomic_dec_and_test(&host_sleep_count)) { - ignore_sigio_fd(random_fd); - deactivate_fd(random_fd, RANDOM_IRQ); - } + if (ret < 0) + break; + } else { + break; } - else - return n; - - if (signal_pending (current)) - return ret ? : -ERESTARTSYS; } - return ret; -} - -static const struct file_operations rng_chrdev_ops = { - .owner = THIS_MODULE, - .open = rng_dev_open, - .read = rng_dev_read, - .llseek = noop_llseek, -}; -/* rng_init shouldn't be called more than once at boot time */ -static struct miscdevice rng_miscdev = { - HWRNG_MINOR, - RNG_MODULE_NAME, - &rng_chrdev_ops, -}; + return ret != -EAGAIN ? ret : 0; +} static irqreturn_t random_interrupt(int irq, void *data) { - wake_up(&host_read_wait); + complete(&have_data); return IRQ_HANDLED; } @@ -126,18 +74,19 @@ static int __init rng_init (void) goto out; random_fd = err; - err = um_request_irq(RANDOM_IRQ, random_fd, IRQ_READ, random_interrupt, 0, "random", NULL); - if (err) + if (err < 0) goto err_out_cleanup_hw; - sigio_broken(random_fd, 1); + sigio_broken(random_fd); + hwrng.name = RNG_MODULE_NAME; + hwrng.read = rng_dev_read; + hwrng.quality = 1024; - err = misc_register (&rng_miscdev); + err = hwrng_register(&hwrng); if (err) { - printk (KERN_ERR RNG_MODULE_NAME ": misc device register " - "failed\n"); + pr_err(RNG_MODULE_NAME " registering failed (%d)\n", err); goto err_out_cleanup_hw; } out: @@ -161,8 +110,8 @@ static void cleanup(void) static void __exit rng_cleanup(void) { + hwrng_unregister(&hwrng); os_close_file(random_fd); - misc_deregister (&rng_miscdev); } module_init (rng_init); diff --git a/arch/um/drivers/ubd_kern.c b/arch/um/drivers/ubd_kern.c index eae8c83364f7..13b1fe694b90 100644 --- a/arch/um/drivers/ubd_kern.c +++ b/arch/um/drivers/ubd_kern.c @@ -47,18 +47,25 @@ /* Max request size is determined by sector mask - 32K */ #define UBD_MAX_REQUEST (8 * sizeof(long)) +struct io_desc { + char *buffer; + unsigned long length; + unsigned long sector_mask; + unsigned long long cow_offset; + unsigned long bitmap_words[2]; +}; + struct io_thread_req { struct request *req; int fds[2]; unsigned long offsets[2]; unsigned long long offset; - unsigned long length; - char *buffer; int sectorsize; - unsigned long sector_mask; - unsigned long long cow_offset; - unsigned long bitmap_words[2]; int error; + + int desc_cnt; + /* io_desc has to be the last element of the struct */ + struct io_desc io_desc[]; }; @@ -148,6 +155,7 @@ struct ubd { /* name (and fd, below) of the file opened for writing, either the * backing or the cow file. */ char *file; + char *serial; int count; int fd; __u64 size; @@ -173,6 +181,7 @@ struct ubd { #define DEFAULT_UBD { \ .file = NULL, \ + .serial = NULL, \ .count = 0, \ .fd = -1, \ .size = -1, \ @@ -265,7 +274,7 @@ static int ubd_setup_common(char *str, int *index_out, char **error_out) { struct ubd *ubd_dev; struct openflags flags = global_openflags; - char *backing_file; + char *file, *backing_file, *serial; int n, err = 0, i; if(index_out) *index_out = -1; @@ -361,24 +370,27 @@ static int ubd_setup_common(char *str, int *index_out, char **error_out) goto out; break_loop: - backing_file = strchr(str, ','); + file = strsep(&str, ",:"); + if (*file == '\0') + file = NULL; - if (backing_file == NULL) - backing_file = strchr(str, ':'); + backing_file = strsep(&str, ",:"); + if (*backing_file == '\0') + backing_file = NULL; - if(backing_file != NULL){ - if(ubd_dev->no_cow){ - *error_out = "Can't specify both 'd' and a cow file"; - goto out; - } - else { - *backing_file = '\0'; - backing_file++; - } + serial = strsep(&str, ",:"); + if (*serial == '\0') + serial = NULL; + + if (backing_file && ubd_dev->no_cow) { + *error_out = "Can't specify both 'd' and a cow file"; + goto out; } + err = 0; - ubd_dev->file = str; + ubd_dev->file = file; ubd_dev->cow.file = backing_file; + ubd_dev->serial = serial; ubd_dev->boot_openflags = flags; out: mutex_unlock(&ubd_lock); @@ -399,7 +411,7 @@ static int ubd_setup(char *str) __setup("ubd", ubd_setup); __uml_help(ubd_setup, -"ubd<n><flags>=<filename>[(:|,)<filename2>]\n" +"ubd<n><flags>=<filename>[(:|,)<filename2>][(:|,)<serial>]\n" " This is used to associate a device with a file in the underlying\n" " filesystem. When specifying two filenames, the first one is the\n" " COW name and the second is the backing file name. As separator you can\n" @@ -422,6 +434,12 @@ __uml_help(ubd_setup, " UMLs and file locking will be turned off - this is appropriate for a\n" " cluster filesystem and inappropriate at almost all other times.\n\n" " 't' will disable trim/discard support on the device (enabled by default).\n\n" +" An optional device serial number can be exposed using the serial parameter\n" +" on the cmdline which is exposed as a sysfs entry. This is particularly\n" +" useful when a unique number should be given to the device. Note when\n" +" specifying a label, the filename2 must be also presented. It can be\n" +" an empty string, in which case the backing file is not used:\n" +" ubd0=File,,Serial\n" ); static int udb_setup(char *str) @@ -525,12 +543,7 @@ static void ubd_handler(void) blk_queue_max_write_zeroes_sectors(io_req->req->q, 0); blk_queue_flag_clear(QUEUE_FLAG_DISCARD, io_req->req->q); } - if ((io_req->error) || (io_req->buffer == NULL)) - blk_mq_end_request(io_req->req, io_req->error); - else { - if (!blk_update_request(io_req->req, io_req->error, io_req->length)) - __blk_mq_end_request(io_req->req, io_req->error); - } + blk_mq_end_request(io_req->req, io_req->error); kfree(io_req); } } @@ -866,6 +879,41 @@ static void ubd_device_release(struct device *dev) *ubd_dev = ((struct ubd) DEFAULT_UBD); } +static ssize_t serial_show(struct device *dev, + struct device_attribute *attr, char *buf) +{ + struct gendisk *disk = dev_to_disk(dev); + struct ubd *ubd_dev = disk->private_data; + + if (!ubd_dev) + return 0; + + return sprintf(buf, "%s", ubd_dev->serial); +} + +static DEVICE_ATTR_RO(serial); + +static struct attribute *ubd_attrs[] = { + &dev_attr_serial.attr, + NULL, +}; + +static umode_t ubd_attrs_are_visible(struct kobject *kobj, + struct attribute *a, int n) +{ + return a->mode; +} + +static const struct attribute_group ubd_attr_group = { + .attrs = ubd_attrs, + .is_visible = ubd_attrs_are_visible, +}; + +static const struct attribute_group *ubd_attr_groups[] = { + &ubd_attr_group, + NULL, +}; + static int ubd_disk_register(int major, u64 size, int unit, struct gendisk **disk_out) { @@ -897,7 +945,7 @@ static int ubd_disk_register(int major, u64 size, int unit, disk->private_data = &ubd_devs[unit]; disk->queue = ubd_devs[unit].queue; - device_add_disk(parent, disk, NULL); + device_add_disk(parent, disk, ubd_attr_groups); *disk_out = disk; return 0; @@ -946,6 +994,7 @@ static int ubd_add(int n, char **error_out) blk_queue_write_cache(ubd_dev->queue, true, false); blk_queue_max_segments(ubd_dev->queue, MAX_SG); + blk_queue_segment_boundary(ubd_dev->queue, PAGE_SIZE - 1); err = ubd_disk_register(UBD_MAJOR, ubd_dev->size, n, &ubd_gendisk[n]); if(err){ *error_out = "Failed to register device"; @@ -1192,7 +1241,7 @@ static int __init ubd_driver_init(void){ /* Letting ubd=sync be like using ubd#s= instead of ubd#= is * enough. So use anyway the io thread. */ } - stack = alloc_stack(0, 0); + stack = alloc_stack(0); io_pid = start_io_thread(stack + PAGE_SIZE - sizeof(void *), &thread_fd); if(io_pid < 0){ @@ -1204,7 +1253,7 @@ static int __init ubd_driver_init(void){ } err = um_request_irq(UBD_IRQ, thread_fd, IRQ_READ, ubd_intr, 0, "ubd", ubd_devs); - if(err != 0) + if(err < 0) printk(KERN_ERR "um_request_irq failed - errno = %d\n", -err); return 0; } @@ -1289,37 +1338,74 @@ static void cowify_bitmap(__u64 io_offset, int length, unsigned long *cow_mask, *cow_offset += bitmap_offset; } -static void cowify_req(struct io_thread_req *req, unsigned long *bitmap, +static void cowify_req(struct io_thread_req *req, struct io_desc *segment, + unsigned long offset, unsigned long *bitmap, __u64 bitmap_offset, __u64 bitmap_len) { - __u64 sector = req->offset >> SECTOR_SHIFT; + __u64 sector = offset >> SECTOR_SHIFT; int i; - if (req->length > (sizeof(req->sector_mask) * 8) << SECTOR_SHIFT) + if (segment->length > (sizeof(segment->sector_mask) * 8) << SECTOR_SHIFT) panic("Operation too long"); if (req_op(req->req) == REQ_OP_READ) { - for (i = 0; i < req->length >> SECTOR_SHIFT; i++) { + for (i = 0; i < segment->length >> SECTOR_SHIFT; i++) { if(ubd_test_bit(sector + i, (unsigned char *) bitmap)) ubd_set_bit(i, (unsigned char *) - &req->sector_mask); + &segment->sector_mask); } + } else { + cowify_bitmap(offset, segment->length, &segment->sector_mask, + &segment->cow_offset, bitmap, bitmap_offset, + segment->bitmap_words, bitmap_len); } - else cowify_bitmap(req->offset, req->length, &req->sector_mask, - &req->cow_offset, bitmap, bitmap_offset, - req->bitmap_words, bitmap_len); } -static int ubd_queue_one_vec(struct blk_mq_hw_ctx *hctx, struct request *req, - u64 off, struct bio_vec *bvec) +static void ubd_map_req(struct ubd *dev, struct io_thread_req *io_req, + struct request *req) +{ + struct bio_vec bvec; + struct req_iterator iter; + int i = 0; + unsigned long byte_offset = io_req->offset; + int op = req_op(req); + + if (op == REQ_OP_WRITE_ZEROES || op == REQ_OP_DISCARD) { + io_req->io_desc[0].buffer = NULL; + io_req->io_desc[0].length = blk_rq_bytes(req); + } else { + rq_for_each_segment(bvec, req, iter) { + BUG_ON(i >= io_req->desc_cnt); + + io_req->io_desc[i].buffer = + page_address(bvec.bv_page) + bvec.bv_offset; + io_req->io_desc[i].length = bvec.bv_len; + i++; + } + } + + if (dev->cow.file) { + for (i = 0; i < io_req->desc_cnt; i++) { + cowify_req(io_req, &io_req->io_desc[i], byte_offset, + dev->cow.bitmap, dev->cow.bitmap_offset, + dev->cow.bitmap_len); + byte_offset += io_req->io_desc[i].length; + } + + } +} + +static struct io_thread_req *ubd_alloc_req(struct ubd *dev, struct request *req, + int desc_cnt) { - struct ubd *dev = hctx->queue->queuedata; struct io_thread_req *io_req; - int ret; + int i; - io_req = kmalloc(sizeof(struct io_thread_req), GFP_ATOMIC); + io_req = kmalloc(sizeof(*io_req) + + (desc_cnt * sizeof(struct io_desc)), + GFP_ATOMIC); if (!io_req) - return -ENOMEM; + return NULL; io_req->req = req; if (dev->cow.file) @@ -1327,26 +1413,41 @@ static int ubd_queue_one_vec(struct blk_mq_hw_ctx *hctx, struct request *req, else io_req->fds[0] = dev->fd; io_req->error = 0; - - if (bvec != NULL) { - io_req->buffer = page_address(bvec->bv_page) + bvec->bv_offset; - io_req->length = bvec->bv_len; - } else { - io_req->buffer = NULL; - io_req->length = blk_rq_bytes(req); - } - io_req->sectorsize = SECTOR_SIZE; io_req->fds[1] = dev->fd; - io_req->cow_offset = -1; - io_req->offset = off; - io_req->sector_mask = 0; + io_req->offset = (u64) blk_rq_pos(req) << SECTOR_SHIFT; io_req->offsets[0] = 0; io_req->offsets[1] = dev->cow.data_offset; - if (dev->cow.file) - cowify_req(io_req, dev->cow.bitmap, - dev->cow.bitmap_offset, dev->cow.bitmap_len); + for (i = 0 ; i < desc_cnt; i++) { + io_req->io_desc[i].sector_mask = 0; + io_req->io_desc[i].cow_offset = -1; + } + + return io_req; +} + +static int ubd_submit_request(struct ubd *dev, struct request *req) +{ + int segs = 0; + struct io_thread_req *io_req; + int ret; + int op = req_op(req); + + if (op == REQ_OP_FLUSH) + segs = 0; + else if (op == REQ_OP_WRITE_ZEROES || op == REQ_OP_DISCARD) + segs = 1; + else + segs = blk_rq_nr_phys_segments(req); + + io_req = ubd_alloc_req(dev, req, segs); + if (!io_req) + return -ENOMEM; + + io_req->desc_cnt = segs; + if (segs) + ubd_map_req(dev, io_req, req); ret = os_write_file(thread_fd, &io_req, sizeof(io_req)); if (ret != sizeof(io_req)) { @@ -1357,22 +1458,6 @@ static int ubd_queue_one_vec(struct blk_mq_hw_ctx *hctx, struct request *req, return ret; } -static int queue_rw_req(struct blk_mq_hw_ctx *hctx, struct request *req) -{ - struct req_iterator iter; - struct bio_vec bvec; - int ret; - u64 off = (u64)blk_rq_pos(req) << SECTOR_SHIFT; - - rq_for_each_segment(bvec, req, iter) { - ret = ubd_queue_one_vec(hctx, req, off, &bvec); - if (ret < 0) - return ret; - off += bvec.bv_len; - } - return 0; -} - static blk_status_t ubd_queue_rq(struct blk_mq_hw_ctx *hctx, const struct blk_mq_queue_data *bd) { @@ -1385,17 +1470,12 @@ static blk_status_t ubd_queue_rq(struct blk_mq_hw_ctx *hctx, spin_lock_irq(&ubd_dev->lock); switch (req_op(req)) { - /* operations with no lentgth/offset arguments */ case REQ_OP_FLUSH: - ret = ubd_queue_one_vec(hctx, req, 0, NULL); - break; case REQ_OP_READ: case REQ_OP_WRITE: - ret = queue_rw_req(hctx, req); - break; case REQ_OP_DISCARD: case REQ_OP_WRITE_ZEROES: - ret = ubd_queue_one_vec(hctx, req, (u64)blk_rq_pos(req) << 9, NULL); + ret = ubd_submit_request(ubd_dev, req); break; default: WARN_ON_ONCE(1); @@ -1483,22 +1563,22 @@ static int map_error(int error_code) * will result in unpredictable behaviour and/or crashes. */ -static int update_bitmap(struct io_thread_req *req) +static int update_bitmap(struct io_thread_req *req, struct io_desc *segment) { int n; - if(req->cow_offset == -1) + if (segment->cow_offset == -1) return map_error(0); - n = os_pwrite_file(req->fds[1], &req->bitmap_words, - sizeof(req->bitmap_words), req->cow_offset); - if (n != sizeof(req->bitmap_words)) + n = os_pwrite_file(req->fds[1], &segment->bitmap_words, + sizeof(segment->bitmap_words), segment->cow_offset); + if (n != sizeof(segment->bitmap_words)) return map_error(-n); return map_error(0); } -static void do_io(struct io_thread_req *req) +static void do_io(struct io_thread_req *req, struct io_desc *desc) { char *buf = NULL; unsigned long len; @@ -1513,21 +1593,20 @@ static void do_io(struct io_thread_req *req) return; } - nsectors = req->length / req->sectorsize; + nsectors = desc->length / req->sectorsize; start = 0; do { - bit = ubd_test_bit(start, (unsigned char *) &req->sector_mask); + bit = ubd_test_bit(start, (unsigned char *) &desc->sector_mask); end = start; while((end < nsectors) && - (ubd_test_bit(end, (unsigned char *) - &req->sector_mask) == bit)) + (ubd_test_bit(end, (unsigned char *) &desc->sector_mask) == bit)) end++; off = req->offset + req->offsets[bit] + start * req->sectorsize; len = (end - start) * req->sectorsize; - if (req->buffer != NULL) - buf = &req->buffer[start * req->sectorsize]; + if (desc->buffer != NULL) + buf = &desc->buffer[start * req->sectorsize]; switch (req_op(req->req)) { case REQ_OP_READ: @@ -1567,7 +1646,8 @@ static void do_io(struct io_thread_req *req) start = end; } while(start < nsectors); - req->error = update_bitmap(req); + req->offset += len; + req->error = update_bitmap(req, desc); } /* Changed in start_io_thread, which is serialized by being called only @@ -1600,8 +1680,13 @@ int io_thread(void *arg) } for (count = 0; count < n/sizeof(struct io_thread_req *); count++) { + struct io_thread_req *req = (*io_req_buffer)[count]; + int i; + io_count++; - do_io((*io_req_buffer)[count]); + for (i = 0; !req->error && i < req->desc_cnt; i++) + do_io(req, &(req->io_desc[i])); + } written = 0; diff --git a/arch/um/drivers/vector_kern.c b/arch/um/drivers/vector_kern.c index 555203e3e7b4..47a02e60898d 100644 --- a/arch/um/drivers/vector_kern.c +++ b/arch/um/drivers/vector_kern.c @@ -1196,9 +1196,9 @@ static int vector_net_close(struct net_device *dev) /* TX tasklet */ -static void vector_tx_poll(unsigned long data) +static void vector_tx_poll(struct tasklet_struct *t) { - struct vector_private *vp = (struct vector_private *)data; + struct vector_private *vp = from_tasklet(vp, t, tx_poll); vp->estats.tx_kicks++; vector_send(vp->tx_queue); @@ -1271,7 +1271,7 @@ static int vector_net_open(struct net_device *dev) irq_rr + VECTOR_BASE_IRQ, vp->fds->rx_fd, IRQ_READ, vector_rx_interrupt, IRQF_SHARED, dev->name, dev); - if (err != 0) { + if (err < 0) { netdev_err(dev, "vector_open: failed to get rx irq(%d)\n", err); err = -ENETUNREACH; goto out_close; @@ -1286,7 +1286,7 @@ static int vector_net_open(struct net_device *dev) irq_rr + VECTOR_BASE_IRQ, vp->fds->tx_fd, IRQ_WRITE, vector_tx_interrupt, IRQF_SHARED, dev->name, dev); - if (err != 0) { + if (err < 0) { netdev_err(dev, "vector_open: failed to get tx irq(%d)\n", err); err = -ENETUNREACH; @@ -1629,7 +1629,7 @@ static void vector_eth_configure( }); dev->features = dev->hw_features = (NETIF_F_SG | NETIF_F_FRAGLIST); - tasklet_init(&vp->tx_poll, vector_tx_poll, (unsigned long)vp); + tasklet_setup(&vp->tx_poll, vector_tx_poll); INIT_WORK(&vp->reset_tx, vector_reset_tx); timer_setup(&vp->tl, vector_timer_expire, 0); diff --git a/arch/um/drivers/virtio_uml.c b/arch/um/drivers/virtio_uml.c index a6c4bb6c2c01..27e92d3881ff 100644 --- a/arch/um/drivers/virtio_uml.c +++ b/arch/um/drivers/virtio_uml.c @@ -33,11 +33,6 @@ #include <os.h> #include "vhost_user.h" -/* Workaround due to a conflict between irq_user.h and irqreturn.h */ -#ifdef IRQ_NONE -#undef IRQ_NONE -#endif - #define MAX_SUPPORTED_QUEUE_SIZE 256 #define to_virtio_uml_device(_vdev) \ @@ -55,7 +50,7 @@ struct virtio_uml_device { struct platform_device *pdev; spinlock_t sock_lock; - int sock, req_fd; + int sock, req_fd, irq; u64 features; u64 protocol_features; u8 status; @@ -409,12 +404,14 @@ static int vhost_user_init_slave_req(struct virtio_uml_device *vu_dev) return rc; vu_dev->req_fd = req_fds[0]; - rc = um_request_irq(VIRTIO_IRQ, vu_dev->req_fd, IRQ_READ, + rc = um_request_irq(UM_IRQ_ALLOC, vu_dev->req_fd, IRQ_READ, vu_req_interrupt, IRQF_SHARED, vu_dev->pdev->name, vu_dev); - if (rc) + if (rc < 0) goto err_close; + vu_dev->irq = rc; + rc = vhost_user_send_no_payload_fd(vu_dev, VHOST_USER_SET_SLAVE_REQ_FD, req_fds[1]); if (rc) @@ -423,7 +420,7 @@ static int vhost_user_init_slave_req(struct virtio_uml_device *vu_dev) goto out; err_free_irq: - um_free_irq(VIRTIO_IRQ, vu_dev); + um_free_irq(vu_dev->irq, vu_dev); err_close: os_close_file(req_fds[0]); out: @@ -802,7 +799,11 @@ static void vu_del_vq(struct virtqueue *vq) struct virtio_uml_vq_info *info = vq->priv; if (info->call_fd >= 0) { - um_free_irq(VIRTIO_IRQ, vq); + struct virtio_uml_device *vu_dev; + + vu_dev = to_virtio_uml_device(vq->vdev); + + um_free_irq(vu_dev->irq, vq); os_close_file(info->call_fd); } @@ -852,9 +853,9 @@ static int vu_setup_vq_call_fd(struct virtio_uml_device *vu_dev, return rc; info->call_fd = call_fds[0]; - rc = um_request_irq(VIRTIO_IRQ, info->call_fd, IRQ_READ, + rc = um_request_irq(vu_dev->irq, info->call_fd, IRQ_READ, vu_interrupt, IRQF_SHARED, info->name, vq); - if (rc) + if (rc < 0) goto close_both; rc = vhost_user_set_vring_call(vu_dev, vq->index, call_fds[1]); @@ -864,7 +865,7 @@ static int vu_setup_vq_call_fd(struct virtio_uml_device *vu_dev, goto out; release_irq: - um_free_irq(VIRTIO_IRQ, vq); + um_free_irq(vu_dev->irq, vq); close_both: os_close_file(call_fds[0]); out: @@ -969,7 +970,7 @@ static struct virtqueue *vu_setup_vq(struct virtio_device *vdev, error_setup: if (info->call_fd >= 0) { - um_free_irq(VIRTIO_IRQ, vq); + um_free_irq(vu_dev->irq, vq); os_close_file(info->call_fd); } error_call: @@ -1078,7 +1079,7 @@ static void virtio_uml_release_dev(struct device *d) /* might not have been opened due to not negotiating the feature */ if (vu_dev->req_fd >= 0) { - um_free_irq(VIRTIO_IRQ, vu_dev); + um_free_irq(vu_dev->irq, vu_dev); os_close_file(vu_dev->req_fd); } diff --git a/arch/um/drivers/xterm.c b/arch/um/drivers/xterm.c index fc7f1e746703..87ca4a47cd66 100644 --- a/arch/um/drivers/xterm.c +++ b/arch/um/drivers/xterm.c @@ -18,6 +18,7 @@ struct xterm_chan { int pid; int helper_pid; + int chan_fd; char *title; int device; int raw; @@ -33,6 +34,7 @@ static void *xterm_init(char *str, int device, const struct chan_opts *opts) return NULL; *data = ((struct xterm_chan) { .pid = -1, .helper_pid = -1, + .chan_fd = -1, .device = device, .title = opts->xterm_title, .raw = opts->raw } ); @@ -149,6 +151,7 @@ static int xterm_open(int input, int output, int primary, void *d, goto out_kill; } + data->chan_fd = fd; new = xterm_fd(fd, &data->helper_pid); if (new < 0) { err = new; @@ -206,6 +209,8 @@ static void xterm_close(int fd, void *d) os_kill_process(data->helper_pid, 0); data->helper_pid = -1; + if (data->chan_fd != -1) + os_close_file(data->chan_fd); os_close_file(fd); } diff --git a/arch/um/drivers/xterm_kern.c b/arch/um/drivers/xterm_kern.c index d64ef6d0d463..50f11b7b4774 100644 --- a/arch/um/drivers/xterm_kern.c +++ b/arch/um/drivers/xterm_kern.c @@ -51,7 +51,7 @@ int xterm_fd(int socket, int *pid_out) err = um_request_irq(XTERM_IRQ, socket, IRQ_READ, xterm_interrupt, IRQF_SHARED, "xterm", data); - if (err) { + if (err < 0) { printk(KERN_ERR "xterm_fd : failed to get IRQ for xterm, " "err = %d\n", err); ret = err; diff --git a/arch/um/include/asm/irq.h b/arch/um/include/asm/irq.h index 42c6205e2dc4..547bff7b3a89 100644 --- a/arch/um/include/asm/irq.h +++ b/arch/um/include/asm/irq.h @@ -17,21 +17,20 @@ #define TELNETD_IRQ 12 #define XTERM_IRQ 13 #define RANDOM_IRQ 14 -#define VIRTIO_IRQ 15 #ifdef CONFIG_UML_NET_VECTOR -#define VECTOR_BASE_IRQ (VIRTIO_IRQ + 1) +#define VECTOR_BASE_IRQ (RANDOM_IRQ + 1) #define VECTOR_IRQ_SPACE 8 -#define LAST_IRQ (VECTOR_IRQ_SPACE + VECTOR_BASE_IRQ - 1) +#define UM_FIRST_DYN_IRQ (VECTOR_IRQ_SPACE + VECTOR_BASE_IRQ) #else -#define LAST_IRQ VIRTIO_IRQ +#define UM_FIRST_DYN_IRQ (RANDOM_IRQ + 1) #endif -#define NR_IRQS (LAST_IRQ + 1) +#define NR_IRQS 64 #endif diff --git a/arch/um/include/asm/pgtable.h b/arch/um/include/asm/pgtable.h index def376194dce..39376bb63abf 100644 --- a/arch/um/include/asm/pgtable.h +++ b/arch/um/include/asm/pgtable.h @@ -55,12 +55,15 @@ extern unsigned long end_iomem; #define _PAGE_CHG_MASK (PAGE_MASK | _PAGE_ACCESSED | _PAGE_DIRTY) #define __PAGE_KERNEL_EXEC \ (_PAGE_PRESENT | _PAGE_RW | _PAGE_DIRTY | _PAGE_ACCESSED) +#define __PAGE_KERNEL_RO \ + (_PAGE_PRESENT | _PAGE_DIRTY | _PAGE_ACCESSED) #define PAGE_NONE __pgprot(_PAGE_PROTNONE | _PAGE_ACCESSED) #define PAGE_SHARED __pgprot(_PAGE_PRESENT | _PAGE_RW | _PAGE_USER | _PAGE_ACCESSED) #define PAGE_COPY __pgprot(_PAGE_PRESENT | _PAGE_USER | _PAGE_ACCESSED) #define PAGE_READONLY __pgprot(_PAGE_PRESENT | _PAGE_USER | _PAGE_ACCESSED) #define PAGE_KERNEL __pgprot(_PAGE_PRESENT | _PAGE_RW | _PAGE_DIRTY | _PAGE_ACCESSED) #define PAGE_KERNEL_EXEC __pgprot(__PAGE_KERNEL_EXEC) +#define PAGE_KERNEL_RO __pgprot(__PAGE_KERNEL_RO) /* * The i386 can't do page protection for execute, and considers that the same diff --git a/arch/um/include/asm/set_memory.h b/arch/um/include/asm/set_memory.h new file mode 100644 index 000000000000..24266c63720d --- /dev/null +++ b/arch/um/include/asm/set_memory.h @@ -0,0 +1 @@ +#include <asm-generic/set_memory.h> diff --git a/arch/um/include/linux/time-internal.h b/arch/um/include/linux/time-internal.h index f3b03d39a854..68e45e950137 100644 --- a/arch/um/include/linux/time-internal.h +++ b/arch/um/include/linux/time-internal.h @@ -28,7 +28,7 @@ struct time_travel_event { extern enum time_travel_mode time_travel_mode; -void time_travel_sleep(unsigned long long duration); +void time_travel_sleep(void); static inline void time_travel_set_event_fn(struct time_travel_event *e, @@ -60,7 +60,7 @@ struct time_travel_event { #define time_travel_mode TT_MODE_OFF -static inline void time_travel_sleep(unsigned long long duration) +static inline void time_travel_sleep(void) { } diff --git a/arch/um/include/shared/common-offsets.h b/arch/um/include/shared/common-offsets.h index 4e99fe05576a..16a51a8c800f 100644 --- a/arch/um/include/shared/common-offsets.h +++ b/arch/um/include/shared/common-offsets.h @@ -40,3 +40,6 @@ DEFINE(UML_CONFIG_UML_X86, CONFIG_UML_X86); #ifdef CONFIG_64BIT DEFINE(UML_CONFIG_64BIT, CONFIG_64BIT); #endif +#ifdef CONFIG_UML_TIME_TRAVEL_SUPPORT +DEFINE(UML_CONFIG_UML_TIME_TRAVEL_SUPPORT, CONFIG_UML_TIME_TRAVEL_SUPPORT); +#endif diff --git a/arch/um/include/shared/irq_kern.h b/arch/um/include/shared/irq_kern.h index 7cd1a10c6244..7807de593bda 100644 --- a/arch/um/include/shared/irq_kern.h +++ b/arch/um/include/shared/irq_kern.h @@ -8,11 +8,12 @@ #include <linux/interrupt.h> #include <asm/ptrace.h> +#include "irq_user.h" -extern int um_request_irq(unsigned int irq, int fd, int type, - irq_handler_t handler, - unsigned long irqflags, const char * devname, - void *dev_id); -void um_free_irq(unsigned int irq, void *dev); -#endif +#define UM_IRQ_ALLOC -1 +int um_request_irq(int irq, int fd, enum um_irq_type type, + irq_handler_t handler, unsigned long irqflags, + const char *devname, void *dev_id); +void um_free_irq(int irq, void *dev_id); +#endif diff --git a/arch/um/include/shared/irq_user.h b/arch/um/include/shared/irq_user.h index 107751dce153..07239e801a5b 100644 --- a/arch/um/include/shared/irq_user.h +++ b/arch/um/include/shared/irq_user.h @@ -9,25 +9,12 @@ #include <sysdep/ptrace.h> #include <stdbool.h> -struct irq_fd { - struct irq_fd *next; - void *id; - int fd; - int type; - int irq; - int events; - bool active; - bool pending; - bool purge; +enum um_irq_type { + IRQ_READ, + IRQ_WRITE, + NUM_IRQ_TYPES, }; -#define IRQ_READ 0 -#define IRQ_WRITE 1 -#define IRQ_NONE 2 -#define MAX_IRQ_TYPE (IRQ_NONE + 1) - - - struct siginfo; extern void sigio_handler(int sig, struct siginfo *unused_si, struct uml_pt_regs *regs); extern void free_irq_by_fd(int fd); diff --git a/arch/um/include/shared/kern_util.h b/arch/um/include/shared/kern_util.h index ccafb62e8cce..d8c279e3312f 100644 --- a/arch/um/include/shared/kern_util.h +++ b/arch/um/include/shared/kern_util.h @@ -19,7 +19,7 @@ extern int kmalloc_ok; #define UML_ROUND_UP(addr) \ ((((unsigned long) addr) + PAGE_SIZE - 1) & PAGE_MASK) -extern unsigned long alloc_stack(int order, int atomic); +extern unsigned long alloc_stack(int atomic); extern void free_stack(unsigned long stack, int order); struct pt_regs; @@ -39,6 +39,8 @@ extern int is_syscall(unsigned long addr); extern void timer_handler(int sig, struct siginfo *unused_si, struct uml_pt_regs *regs); +extern void uml_pm_wake(void); + extern int start_uml(void); extern void paging_init(void); @@ -66,5 +68,6 @@ extern void bus_handler(int sig, struct siginfo *si, struct uml_pt_regs *regs); extern void winch(int sig, struct siginfo *unused_si, struct uml_pt_regs *regs); extern void fatal_sigsegv(void) __attribute__ ((noreturn)); +void um_idle_sleep(void); #endif diff --git a/arch/um/include/shared/os.h b/arch/um/include/shared/os.h index f467d28fc0b4..13d86f94cf0f 100644 --- a/arch/um/include/shared/os.h +++ b/arch/um/include/shared/os.h @@ -233,6 +233,7 @@ extern void timer_set_signal_handler(void); extern void set_sigstack(void *sig_stack, int size); extern void remove_sigstack(void); extern void set_handler(int sig); +extern void send_sigio_to_self(void); extern int change_sig(int signal, int on); extern void block_signals(void); extern void unblock_signals(void); @@ -241,6 +242,7 @@ extern int set_signals(int enable); extern int set_signals_trace(int enable); extern int os_is_signal_stack(void); extern void deliver_alarm(void); +extern void register_pm_wake_signal(void); /* util.c */ extern void stack_protections(unsigned long address); @@ -256,7 +258,7 @@ extern void os_warn(const char *fmt, ...) __attribute__ ((format (printf, 1, 2))); /* time.c */ -extern void os_idle_sleep(unsigned long long nsecs); +extern void os_idle_sleep(void); extern int os_timer_create(void); extern int os_timer_set_interval(unsigned long long nsecs); extern int os_timer_one_shot(unsigned long long nsecs); @@ -299,19 +301,29 @@ extern void reboot_skas(void); extern int os_waiting_for_events_epoll(void); extern void *os_epoll_get_data_pointer(int index); extern int os_epoll_triggered(int index, int events); -extern int os_event_mask(int irq_type); +extern int os_event_mask(enum um_irq_type irq_type); extern int os_setup_epoll(void); extern int os_add_epoll_fd(int events, int fd, void *data); extern int os_mod_epoll_fd(int events, int fd, void *data); extern int os_del_epoll_fd(int fd); extern void os_set_ioignore(void); extern void os_close_epoll_fd(void); +extern void um_irqs_suspend(void); +extern void um_irqs_resume(void); /* sigio.c */ extern int add_sigio_fd(int fd); extern int ignore_sigio_fd(int fd); -extern void maybe_sigio_broken(int fd, int read); -extern void sigio_broken(int fd, int read); +extern void maybe_sigio_broken(int fd); +extern void sigio_broken(int fd); +/* + * unlocked versions for IRQ controller code. + * + * This is safe because it's used at suspend/resume and nothing + * else is running. + */ +extern int __add_sigio_fd(int fd); +extern int __ignore_sigio_fd(int fd); /* prctl.c */ extern int os_arch_prctl(int pid, int option, unsigned long *arg2); @@ -330,4 +342,7 @@ extern void unblock_signals_trace(void); extern void um_trace_signals_on(void); extern void um_trace_signals_off(void); +/* time-travel */ +extern void deliver_time_travel_irqs(void); + #endif diff --git a/arch/um/kernel/irq.c b/arch/um/kernel/irq.c index 3577118bb4a5..3741d2380060 100644 --- a/arch/um/kernel/irq.c +++ b/arch/um/kernel/irq.c @@ -19,27 +19,40 @@ #include <kern_util.h> #include <os.h> #include <irq_user.h> +#include <irq_kern.h> +#include <as-layout.h> extern void free_irqs(void); /* When epoll triggers we do not know why it did so * we can also have different IRQs for read and write. - * This is why we keep a small irq_fd array for each fd - + * This is why we keep a small irq_reg array for each fd - * one entry per IRQ type */ +struct irq_reg { + void *id; + int irq; + /* it's cheaper to store this than to query it */ + int events; + bool active; + bool pending; + bool wakeup; +}; struct irq_entry { - struct irq_entry *next; + struct list_head list; int fd; - struct irq_fd *irq_array[MAX_IRQ_TYPE + 1]; + struct irq_reg reg[NUM_IRQ_TYPES]; + bool suspended; + bool sigio_workaround; }; -static struct irq_entry *active_fds; - static DEFINE_SPINLOCK(irq_lock); +static LIST_HEAD(active_fds); +static DECLARE_BITMAP(irqs_allocated, NR_IRQS); -static void irq_io_loop(struct irq_fd *irq, struct uml_pt_regs *regs) +static void irq_io_loop(struct irq_reg *irq, struct uml_pt_regs *regs) { /* * irq->active guards against reentry @@ -49,23 +62,27 @@ static void irq_io_loop(struct irq_fd *irq, struct uml_pt_regs *regs) */ if (irq->active) { irq->active = false; + do { irq->pending = false; do_IRQ(irq->irq, regs); - } while (irq->pending && (!irq->purge)); - if (!irq->purge) - irq->active = true; + } while (irq->pending); + + irq->active = true; } else { irq->pending = true; } } +void sigio_handler_suspend(int sig, struct siginfo *unused_si, struct uml_pt_regs *regs) +{ + /* nothing */ +} + void sigio_handler(int sig, struct siginfo *unused_si, struct uml_pt_regs *regs) { struct irq_entry *irq_entry; - struct irq_fd *irq; - - int n, i, j; + int n, i; while (1) { /* This is now lockless - epoll keeps back-referencesto the irqs @@ -84,21 +101,18 @@ void sigio_handler(int sig, struct siginfo *unused_si, struct uml_pt_regs *regs) } for (i = 0; i < n ; i++) { - /* Epoll back reference is the entry with 3 irq_fd - * leaves - one for each irq type. - */ - irq_entry = (struct irq_entry *) - os_epoll_get_data_pointer(i); - for (j = 0; j < MAX_IRQ_TYPE ; j++) { - irq = irq_entry->irq_array[j]; - if (irq == NULL) + enum um_irq_type t; + + irq_entry = os_epoll_get_data_pointer(i); + + for (t = 0; t < NUM_IRQ_TYPES; t++) { + int events = irq_entry->reg[t].events; + + if (!events) continue; - if (os_epoll_triggered(i, irq->events) > 0) - irq_io_loop(irq, regs); - if (irq->purge) { - irq_entry->irq_array[j] = NULL; - kfree(irq); - } + + if (os_epoll_triggered(i, events) > 0) + irq_io_loop(&irq_entry->reg[t], regs); } } } @@ -106,32 +120,59 @@ void sigio_handler(int sig, struct siginfo *unused_si, struct uml_pt_regs *regs) free_irqs(); } -static int assign_epoll_events_to_irq(struct irq_entry *irq_entry) +static struct irq_entry *get_irq_entry_by_fd(int fd) { - int i; - int events = 0; - struct irq_fd *irq; + struct irq_entry *walk; - for (i = 0; i < MAX_IRQ_TYPE ; i++) { - irq = irq_entry->irq_array[i]; - if (irq != NULL) - events = irq->events | events; - } - if (events > 0) { - /* os_add_epoll will call os_mod_epoll if this already exists */ - return os_add_epoll_fd(events, irq_entry->fd, irq_entry); + lockdep_assert_held(&irq_lock); + + list_for_each_entry(walk, &active_fds, list) { + if (walk->fd == fd) + return walk; } - /* No events - delete */ - return os_del_epoll_fd(irq_entry->fd); + + return NULL; } +static void free_irq_entry(struct irq_entry *to_free, bool remove) +{ + if (!to_free) + return; + + if (remove) + os_del_epoll_fd(to_free->fd); + list_del(&to_free->list); + kfree(to_free); +} + +static bool update_irq_entry(struct irq_entry *entry) +{ + enum um_irq_type i; + int events = 0; + + for (i = 0; i < NUM_IRQ_TYPES; i++) + events |= entry->reg[i].events; + + if (events) { + /* will modify (instead of add) if needed */ + os_add_epoll_fd(events, entry->fd, entry); + return true; + } + + os_del_epoll_fd(entry->fd); + return false; +} +static void update_or_free_irq_entry(struct irq_entry *entry) +{ + if (!update_irq_entry(entry)) + free_irq_entry(entry, false); +} -static int activate_fd(int irq, int fd, int type, void *dev_id) +static int activate_fd(int irq, int fd, enum um_irq_type type, void *dev_id) { - struct irq_fd *new_fd; struct irq_entry *irq_entry; - int i, err, events; + int err, events = os_event_mask(type); unsigned long flags; err = os_set_fd_async(fd); @@ -139,73 +180,34 @@ static int activate_fd(int irq, int fd, int type, void *dev_id) goto out; spin_lock_irqsave(&irq_lock, flags); - - /* Check if we have an entry for this fd */ - - err = -EBUSY; - for (irq_entry = active_fds; - irq_entry != NULL; irq_entry = irq_entry->next) { - if (irq_entry->fd == fd) - break; - } - - if (irq_entry == NULL) { - /* This needs to be atomic as it may be called from an - * IRQ context. - */ - irq_entry = kmalloc(sizeof(struct irq_entry), GFP_ATOMIC); - if (irq_entry == NULL) { - printk(KERN_ERR - "Failed to allocate new IRQ entry\n"); + irq_entry = get_irq_entry_by_fd(fd); + if (irq_entry) { + /* cannot register the same FD twice with the same type */ + if (WARN_ON(irq_entry->reg[type].events)) { + err = -EALREADY; goto out_unlock; } - irq_entry->fd = fd; - for (i = 0; i < MAX_IRQ_TYPE; i++) - irq_entry->irq_array[i] = NULL; - irq_entry->next = active_fds; - active_fds = irq_entry; - } - - /* Check if we are trying to re-register an interrupt for a - * particular fd - */ - if (irq_entry->irq_array[type] != NULL) { - printk(KERN_ERR - "Trying to reregister IRQ %d FD %d TYPE %d ID %p\n", - irq, fd, type, dev_id - ); - goto out_unlock; + /* temporarily disable to avoid IRQ-side locking */ + os_del_epoll_fd(fd); } else { - /* New entry for this fd */ - - err = -ENOMEM; - new_fd = kmalloc(sizeof(struct irq_fd), GFP_ATOMIC); - if (new_fd == NULL) + irq_entry = kzalloc(sizeof(*irq_entry), GFP_ATOMIC); + if (!irq_entry) { + err = -ENOMEM; goto out_unlock; - - events = os_event_mask(type); - - *new_fd = ((struct irq_fd) { - .id = dev_id, - .irq = irq, - .type = type, - .events = events, - .active = true, - .pending = false, - .purge = false - }); - /* Turn off any IO on this fd - allows us to - * avoid locking the IRQ loop - */ - os_del_epoll_fd(irq_entry->fd); - irq_entry->irq_array[type] = new_fd; + } + irq_entry->fd = fd; + list_add_tail(&irq_entry->list, &active_fds); + maybe_sigio_broken(fd); } - /* Turn back IO on with the correct (new) IO event mask */ - assign_epoll_events_to_irq(irq_entry); + irq_entry->reg[type].id = dev_id; + irq_entry->reg[type].irq = irq; + irq_entry->reg[type].active = true; + irq_entry->reg[type].events = events; + + WARN_ON(!update_irq_entry(irq_entry)); spin_unlock_irqrestore(&irq_lock, flags); - maybe_sigio_broken(fd, (type != IRQ_NONE)); return 0; out_unlock: @@ -215,104 +217,10 @@ out: } /* - * Walk the IRQ list and dispose of any unused entries. - * Should be done under irq_lock. + * Remove the entry or entries for a specific FD, if you + * don't want to remove all the possible entries then use + * um_free_irq() or deactivate_fd() instead. */ - -static void garbage_collect_irq_entries(void) -{ - int i; - bool reap; - struct irq_entry *walk; - struct irq_entry *previous = NULL; - struct irq_entry *to_free; - - if (active_fds == NULL) - return; - walk = active_fds; - while (walk != NULL) { - reap = true; - for (i = 0; i < MAX_IRQ_TYPE ; i++) { - if (walk->irq_array[i] != NULL) { - reap = false; - break; - } - } - if (reap) { - if (previous == NULL) - active_fds = walk->next; - else - previous->next = walk->next; - to_free = walk; - } else { - to_free = NULL; - } - walk = walk->next; - kfree(to_free); - } -} - -/* - * Walk the IRQ list and get the descriptor for our FD - */ - -static struct irq_entry *get_irq_entry_by_fd(int fd) -{ - struct irq_entry *walk = active_fds; - - while (walk != NULL) { - if (walk->fd == fd) - return walk; - walk = walk->next; - } - return NULL; -} - - -/* - * Walk the IRQ list and dispose of an entry for a specific - * device, fd and number. Note - if sharing an IRQ for read - * and writefor the same FD it will be disposed in either case. - * If this behaviour is undesirable use different IRQ ids. - */ - -#define IGNORE_IRQ 1 -#define IGNORE_DEV (1<<1) - -static void do_free_by_irq_and_dev( - struct irq_entry *irq_entry, - unsigned int irq, - void *dev, - int flags -) -{ - int i; - struct irq_fd *to_free; - - for (i = 0; i < MAX_IRQ_TYPE ; i++) { - if (irq_entry->irq_array[i] != NULL) { - if ( - ((flags & IGNORE_IRQ) || - (irq_entry->irq_array[i]->irq == irq)) && - ((flags & IGNORE_DEV) || - (irq_entry->irq_array[i]->id == dev)) - ) { - /* Turn off any IO on this fd - allows us to - * avoid locking the IRQ loop - */ - os_del_epoll_fd(irq_entry->fd); - to_free = irq_entry->irq_array[i]; - irq_entry->irq_array[i] = NULL; - assign_epoll_events_to_irq(irq_entry); - if (to_free->active) - to_free->purge = true; - else - kfree(to_free); - } - } - } -} - void free_irq_by_fd(int fd) { struct irq_entry *to_free; @@ -320,58 +228,64 @@ void free_irq_by_fd(int fd) spin_lock_irqsave(&irq_lock, flags); to_free = get_irq_entry_by_fd(fd); - if (to_free != NULL) { - do_free_by_irq_and_dev( - to_free, - -1, - NULL, - IGNORE_IRQ | IGNORE_DEV - ); - } - garbage_collect_irq_entries(); + free_irq_entry(to_free, true); spin_unlock_irqrestore(&irq_lock, flags); } EXPORT_SYMBOL(free_irq_by_fd); static void free_irq_by_irq_and_dev(unsigned int irq, void *dev) { - struct irq_entry *to_free; + struct irq_entry *entry; unsigned long flags; spin_lock_irqsave(&irq_lock, flags); - to_free = active_fds; - while (to_free != NULL) { - do_free_by_irq_and_dev( - to_free, - irq, - dev, - 0 - ); - to_free = to_free->next; + list_for_each_entry(entry, &active_fds, list) { + enum um_irq_type i; + + for (i = 0; i < NUM_IRQ_TYPES; i++) { + struct irq_reg *reg = &entry->reg[i]; + + if (!reg->events) + continue; + if (reg->irq != irq) + continue; + if (reg->id != dev) + continue; + + os_del_epoll_fd(entry->fd); + reg->events = 0; + update_or_free_irq_entry(entry); + goto out; + } } - garbage_collect_irq_entries(); +out: spin_unlock_irqrestore(&irq_lock, flags); } - void deactivate_fd(int fd, int irqnum) { - struct irq_entry *to_free; + struct irq_entry *entry; unsigned long flags; + enum um_irq_type i; os_del_epoll_fd(fd); + spin_lock_irqsave(&irq_lock, flags); - to_free = get_irq_entry_by_fd(fd); - if (to_free != NULL) { - do_free_by_irq_and_dev( - to_free, - irqnum, - NULL, - IGNORE_DEV - ); + entry = get_irq_entry_by_fd(fd); + if (!entry) + goto out; + + for (i = 0; i < NUM_IRQ_TYPES; i++) { + if (!entry->reg[i].events) + continue; + if (entry->reg[i].irq == irqnum) + entry->reg[i].events = 0; } - garbage_collect_irq_entries(); + + update_or_free_irq_entry(entry); +out: spin_unlock_irqrestore(&irq_lock, flags); + ignore_sigio_fd(fd); } EXPORT_SYMBOL(deactivate_fd); @@ -384,24 +298,17 @@ EXPORT_SYMBOL(deactivate_fd); */ int deactivate_all_fds(void) { - struct irq_entry *to_free; + struct irq_entry *entry; /* Stop IO. The IRQ loop has no lock so this is our * only way of making sure we are safe to dispose * of all IRQ handlers */ os_set_ioignore(); - to_free = active_fds; - while (to_free != NULL) { - do_free_by_irq_and_dev( - to_free, - -1, - NULL, - IGNORE_IRQ | IGNORE_DEV - ); - to_free = to_free->next; - } - /* don't garbage collect - we can no longer call kfree() here */ + + /* we can no longer call kfree() here so just deactivate */ + list_for_each_entry(entry, &active_fds, list) + os_del_epoll_fd(entry->fd); os_close_epoll_fd(); return 0; } @@ -421,31 +328,146 @@ unsigned int do_IRQ(int irq, struct uml_pt_regs *regs) return 1; } -void um_free_irq(unsigned int irq, void *dev) +void um_free_irq(int irq, void *dev) { + if (WARN(irq < 0 || irq > NR_IRQS, "freeing invalid irq %d", irq)) + return; + free_irq_by_irq_and_dev(irq, dev); free_irq(irq, dev); + clear_bit(irq, irqs_allocated); } EXPORT_SYMBOL(um_free_irq); -int um_request_irq(unsigned int irq, int fd, int type, - irq_handler_t handler, - unsigned long irqflags, const char * devname, - void *dev_id) +int um_request_irq(int irq, int fd, enum um_irq_type type, + irq_handler_t handler, unsigned long irqflags, + const char *devname, void *dev_id) { int err; + if (irq == UM_IRQ_ALLOC) { + int i; + + for (i = UM_FIRST_DYN_IRQ; i < NR_IRQS; i++) { + if (!test_and_set_bit(i, irqs_allocated)) { + irq = i; + break; + } + } + } + + if (irq < 0) + return -ENOSPC; + if (fd != -1) { err = activate_fd(irq, fd, type, dev_id); if (err) - return err; + goto error; } - return request_irq(irq, handler, irqflags, devname, dev_id); -} + err = request_irq(irq, handler, irqflags, devname, dev_id); + if (err < 0) + goto error; + return irq; +error: + clear_bit(irq, irqs_allocated); + return err; +} EXPORT_SYMBOL(um_request_irq); +#ifdef CONFIG_PM_SLEEP +void um_irqs_suspend(void) +{ + struct irq_entry *entry; + unsigned long flags; + + sig_info[SIGIO] = sigio_handler_suspend; + + spin_lock_irqsave(&irq_lock, flags); + list_for_each_entry(entry, &active_fds, list) { + enum um_irq_type t; + bool wake = false; + + for (t = 0; t < NUM_IRQ_TYPES; t++) { + if (!entry->reg[t].events) + continue; + + /* + * For the SIGIO_WRITE_IRQ, which is used to handle the + * SIGIO workaround thread, we need special handling: + * enable wake for it itself, but below we tell it about + * any FDs that should be suspended. + */ + if (entry->reg[t].wakeup || + entry->reg[t].irq == SIGIO_WRITE_IRQ) { + wake = true; + break; + } + } + + if (!wake) { + entry->suspended = true; + os_clear_fd_async(entry->fd); + entry->sigio_workaround = + !__ignore_sigio_fd(entry->fd); + } + } + spin_unlock_irqrestore(&irq_lock, flags); +} + +void um_irqs_resume(void) +{ + struct irq_entry *entry; + unsigned long flags; + + spin_lock_irqsave(&irq_lock, flags); + list_for_each_entry(entry, &active_fds, list) { + if (entry->suspended) { + int err = os_set_fd_async(entry->fd); + + WARN(err < 0, "os_set_fd_async returned %d\n", err); + entry->suspended = false; + + if (entry->sigio_workaround) { + err = __add_sigio_fd(entry->fd); + WARN(err < 0, "add_sigio_returned %d\n", err); + } + } + } + spin_unlock_irqrestore(&irq_lock, flags); + + sig_info[SIGIO] = sigio_handler; + send_sigio_to_self(); +} + +static int normal_irq_set_wake(struct irq_data *d, unsigned int on) +{ + struct irq_entry *entry; + unsigned long flags; + + spin_lock_irqsave(&irq_lock, flags); + list_for_each_entry(entry, &active_fds, list) { + enum um_irq_type t; + + for (t = 0; t < NUM_IRQ_TYPES; t++) { + if (!entry->reg[t].events) + continue; + + if (entry->reg[t].irq != d->irq) + continue; + entry->reg[t].wakeup = on; + goto unlock; + } + } +unlock: + spin_unlock_irqrestore(&irq_lock, flags); + return 0; +} +#else +#define normal_irq_set_wake NULL +#endif + /* * irq_chip must define at least enable/disable and ack when * the edge handler is used. @@ -454,7 +476,7 @@ static void dummy(struct irq_data *d) { } -/* This is used for everything else than the timer. */ +/* This is used for everything other than the timer. */ static struct irq_chip normal_irq_type = { .name = "SIGIO", .irq_disable = dummy, @@ -462,10 +484,11 @@ static struct irq_chip normal_irq_type = { .irq_ack = dummy, .irq_mask = dummy, .irq_unmask = dummy, + .irq_set_wake = normal_irq_set_wake, }; -static struct irq_chip SIGVTALRM_irq_type = { - .name = "SIGVTALRM", +static struct irq_chip alarm_irq_type = { + .name = "SIGALRM", .irq_disable = dummy, .irq_enable = dummy, .irq_ack = dummy, @@ -477,10 +500,9 @@ void __init init_IRQ(void) { int i; - irq_set_chip_and_handler(TIMER_IRQ, &SIGVTALRM_irq_type, handle_edge_irq); - + irq_set_chip_and_handler(TIMER_IRQ, &alarm_irq_type, handle_edge_irq); - for (i = 1; i <= LAST_IRQ; i++) + for (i = 1; i < NR_IRQS; i++) irq_set_chip_and_handler(i, &normal_irq_type, handle_edge_irq); /* Initialize EPOLL Loop */ os_setup_epoll(); diff --git a/arch/um/kernel/process.c b/arch/um/kernel/process.c index 0fcdc374a9a1..2a986ece5478 100644 --- a/arch/um/kernel/process.c +++ b/arch/um/kernel/process.c @@ -32,6 +32,7 @@ #include <os.h> #include <skas.h> #include <linux/time-internal.h> +#include <asm/set_memory.h> /* * This is a per-cpu array. A processor only modifies its entry and it only @@ -62,16 +63,18 @@ void free_stack(unsigned long stack, int order) free_pages(stack, order); } -unsigned long alloc_stack(int order, int atomic) +unsigned long alloc_stack(int atomic) { - unsigned long page; + unsigned long addr; gfp_t flags = GFP_KERNEL; if (atomic) flags = GFP_ATOMIC; - page = __get_free_pages(flags, order); + addr = __get_free_pages(flags, 1); - return page; + set_memory_ro(addr, 1); + + return addr + PAGE_SIZE; } static inline void set_current(struct task_struct *task) @@ -203,15 +206,12 @@ void initial_thread_cb(void (*proc)(void *), void *arg) kmalloc_ok = save_kmalloc_ok; } -static void um_idle_sleep(void) +void um_idle_sleep(void) { - unsigned long long duration = UM_NSEC_PER_SEC; - - if (time_travel_mode != TT_MODE_OFF) { - time_travel_sleep(duration); - } else { - os_idle_sleep(duration); - } + if (time_travel_mode != TT_MODE_OFF) + time_travel_sleep(); + else + os_idle_sleep(); } void arch_cpu_idle(void) diff --git a/arch/um/kernel/sigio.c b/arch/um/kernel/sigio.c index d1cffc2a7f21..5085a50c3b8c 100644 --- a/arch/um/kernel/sigio.c +++ b/arch/um/kernel/sigio.c @@ -25,7 +25,7 @@ int write_sigio_irq(int fd) err = um_request_irq(SIGIO_WRITE_IRQ, fd, IRQ_READ, sigio_interrupt, 0, "write sigio", NULL); - if (err) { + if (err < 0) { printk(KERN_ERR "write_sigio_irq : um_request_irq failed, " "err = %d\n", err); return -1; diff --git a/arch/um/kernel/time.c b/arch/um/kernel/time.c index 3d109ff3309b..f4db89b5b5a6 100644 --- a/arch/um/kernel/time.c +++ b/arch/um/kernel/time.c @@ -31,6 +31,7 @@ static bool time_travel_start_set; static unsigned long long time_travel_start; static unsigned long long time_travel_time; static LIST_HEAD(time_travel_events); +static LIST_HEAD(time_travel_irqs); static unsigned long long time_travel_timer_interval; static unsigned long long time_travel_next_event; static struct time_travel_event time_travel_timer_event; @@ -46,6 +47,9 @@ static void time_travel_set_time(unsigned long long ns) if (unlikely(ns < time_travel_time)) panic("time-travel: time goes backwards %lld -> %lld\n", time_travel_time, ns); + else if (unlikely(ns >= S64_MAX)) + panic("The system was going to sleep forever, aborting"); + time_travel_time = ns; } @@ -180,6 +184,14 @@ static void time_travel_ext_update_request(unsigned long long time) time == time_travel_ext_prev_request) return; + /* + * if we're running and are allowed to run past the request + * then we don't need to update it either + */ + if (!time_travel_ext_waiting && time_travel_ext_free_until_valid && + time < time_travel_ext_free_until) + return; + time_travel_ext_prev_request = time; time_travel_ext_prev_request_valid = true; time_travel_ext_req(UM_TIMETRAVEL_REQUEST, time); @@ -187,7 +199,13 @@ static void time_travel_ext_update_request(unsigned long long time) void __time_travel_propagate_time(void) { + static unsigned long long last_propagated; + + if (last_propagated == time_travel_time) + return; + time_travel_ext_req(UM_TIMETRAVEL_UPDATE, time_travel_time); + last_propagated = time_travel_time; } EXPORT_SYMBOL_GPL(__time_travel_propagate_time); @@ -214,6 +232,7 @@ static void time_travel_ext_wait(bool idle) }; time_travel_ext_prev_request_valid = false; + time_travel_ext_free_until_valid = false; time_travel_ext_waiting++; time_travel_ext_req(UM_TIMETRAVEL_WAIT, -1); @@ -260,11 +279,6 @@ static void __time_travel_add_event(struct time_travel_event *e, struct time_travel_event *tmp; bool inserted = false; - if (WARN(time_travel_mode == TT_MODE_BASIC && - e != &time_travel_timer_event, - "only timer events can be handled in basic mode")) - return; - if (e->pending) return; @@ -311,6 +325,35 @@ void time_travel_periodic_timer(struct time_travel_event *e) deliver_alarm(); } +void deliver_time_travel_irqs(void) +{ + struct time_travel_event *e; + unsigned long flags; + + /* + * Don't do anything for most cases. Note that because here we have + * to disable IRQs (and re-enable later) we'll actually recurse at + * the end of the function, so this is strictly necessary. + */ + if (likely(list_empty(&time_travel_irqs))) + return; + + local_irq_save(flags); + irq_enter(); + while ((e = list_first_entry_or_null(&time_travel_irqs, + struct time_travel_event, + list))) { + WARN(e->time != time_travel_time, + "time moved from %lld to %lld before IRQ delivery\n", + time_travel_time, e->time); + list_del(&e->list); + e->pending = false; + e->fn(e); + } + irq_exit(); + local_irq_restore(flags); +} + static void time_travel_deliver_event(struct time_travel_event *e) { if (e == &time_travel_timer_event) { @@ -319,6 +362,14 @@ static void time_travel_deliver_event(struct time_travel_event *e) * by itself, so must handle it specially here */ e->fn(e); + } else if (irqs_disabled()) { + list_add_tail(&e->list, &time_travel_irqs); + /* + * set pending again, it was set to false when the + * event was deleted from the original list, but + * now it's still pending until we deliver the IRQ. + */ + e->pending = true; } else { unsigned long flags; @@ -404,9 +455,14 @@ static void time_travel_oneshot_timer(struct time_travel_event *e) deliver_alarm(); } -void time_travel_sleep(unsigned long long duration) +void time_travel_sleep(void) { - unsigned long long next = time_travel_time + duration; + /* + * Wait "forever" (using S64_MAX because there are some potential + * wrapping issues, especially with the current TT_MODE_EXTERNAL + * controller application. + */ + unsigned long long next = S64_MAX; if (time_travel_mode == TT_MODE_BASIC) os_timer_disable(); @@ -483,6 +539,7 @@ invalid_number: #define time_travel_start_set 0 #define time_travel_start 0 #define time_travel_time 0 +#define time_travel_ext_waiting 0 static inline void time_travel_update_time(unsigned long long ns, bool retearly) { @@ -628,7 +685,8 @@ static u64 timer_read(struct clocksource *cs) * "what do I do next" and onstack event we use to know when * to return from time_travel_update_time(). */ - if (!irqs_disabled() && !in_interrupt() && !in_softirq()) + if (!irqs_disabled() && !in_interrupt() && !in_softirq() && + !time_travel_ext_waiting) time_travel_update_time(time_travel_time + TIMER_MULTIPLIER, false); @@ -673,10 +731,8 @@ void read_persistent_clock64(struct timespec64 *ts) { long long nsecs; - if (time_travel_start_set) + if (time_travel_mode != TT_MODE_OFF) nsecs = time_travel_start + time_travel_time; - else if (time_travel_mode == TT_MODE_EXTERNAL) - nsecs = time_travel_ext_req(UM_TIMETRAVEL_GET_TOD, -1); else nsecs = os_persistent_clock_emulation(); @@ -686,6 +742,25 @@ void read_persistent_clock64(struct timespec64 *ts) void __init time_init(void) { +#ifdef CONFIG_UML_TIME_TRAVEL_SUPPORT + switch (time_travel_mode) { + case TT_MODE_EXTERNAL: + time_travel_start = time_travel_ext_req(UM_TIMETRAVEL_GET_TOD, -1); + /* controller gave us the *current* time, so adjust by that */ + time_travel_ext_get_time(); + time_travel_start -= time_travel_time; + break; + case TT_MODE_INFCPU: + case TT_MODE_BASIC: + if (!time_travel_start_set) + time_travel_start = os_persistent_clock_emulation(); + break; + case TT_MODE_OFF: + /* we just read the host clock with os_persistent_clock_emulation() */ + break; + } +#endif + timer_set_signal_handler(); late_time_init = um_timer_setup; } diff --git a/arch/um/kernel/tlb.c b/arch/um/kernel/tlb.c index 61776790cd67..437d1f1cc5ec 100644 --- a/arch/um/kernel/tlb.c +++ b/arch/um/kernel/tlb.c @@ -608,3 +608,57 @@ void force_flush_all(void) vma = vma->vm_next; } } + +struct page_change_data { + unsigned int set_mask, clear_mask; +}; + +static int change_page_range(pte_t *ptep, unsigned long addr, void *data) +{ + struct page_change_data *cdata = data; + pte_t pte = READ_ONCE(*ptep); + + pte_clear_bits(pte, cdata->clear_mask); + pte_set_bits(pte, cdata->set_mask); + + set_pte(ptep, pte); + return 0; +} + +static int change_memory(unsigned long start, unsigned long pages, + unsigned int set_mask, unsigned int clear_mask) +{ + unsigned long size = pages * PAGE_SIZE; + struct page_change_data data; + int ret; + + data.set_mask = set_mask; + data.clear_mask = clear_mask; + + ret = apply_to_page_range(&init_mm, start, size, change_page_range, + &data); + + flush_tlb_kernel_range(start, start + size); + + return ret; +} + +int set_memory_ro(unsigned long addr, int numpages) +{ + return change_memory(addr, numpages, 0, _PAGE_RW); +} + +int set_memory_rw(unsigned long addr, int numpages) +{ + return change_memory(addr, numpages, _PAGE_RW, 0); +} + +int set_memory_nx(unsigned long addr, int numpages) +{ + return -EOPNOTSUPP; +} + +int set_memory_x(unsigned long addr, int numpages) +{ + return -EOPNOTSUPP; +} diff --git a/arch/um/kernel/um_arch.c b/arch/um/kernel/um_arch.c index 76b37297b7d4..31d356b1ffd8 100644 --- a/arch/um/kernel/um_arch.c +++ b/arch/um/kernel/um_arch.c @@ -13,6 +13,7 @@ #include <linux/sched.h> #include <linux/sched/task.h> #include <linux/kmsg_dump.h> +#include <linux/suspend.h> #include <asm/processor.h> #include <asm/sections.h> @@ -377,3 +378,69 @@ void *text_poke(void *addr, const void *opcode, size_t len) void text_poke_sync(void) { } + +void uml_pm_wake(void) +{ + pm_system_wakeup(); +} + +#ifdef CONFIG_PM_SLEEP +static int um_suspend_valid(suspend_state_t state) +{ + return state == PM_SUSPEND_MEM; +} + +static int um_suspend_prepare(void) +{ + um_irqs_suspend(); + return 0; +} + +static int um_suspend_enter(suspend_state_t state) +{ + if (WARN_ON(state != PM_SUSPEND_MEM)) + return -EINVAL; + + /* + * This is identical to the idle sleep, but we've just + * (during suspend) turned off all interrupt sources + * except for the ones we want, so now we can only wake + * up on something we actually want to wake up on. All + * timing has also been suspended. + */ + um_idle_sleep(); + return 0; +} + +static void um_suspend_finish(void) +{ + um_irqs_resume(); +} + +const struct platform_suspend_ops um_suspend_ops = { + .valid = um_suspend_valid, + .prepare = um_suspend_prepare, + .enter = um_suspend_enter, + .finish = um_suspend_finish, +}; + +static int init_pm_wake_signal(void) +{ + /* + * In external time-travel mode we can't use signals to wake up + * since that would mess with the scheduling. We'll have to do + * some additional work to support wakeup on virtio devices or + * similar, perhaps implementing a fake RTC controller that can + * trigger wakeup (and request the appropriate scheduling from + * the external scheduler when going to suspend.) + */ + if (time_travel_mode != TT_MODE_EXTERNAL) + register_pm_wake_signal(); + + suspend_set_ops(&um_suspend_ops); + + return 0; +} + +late_initcall(init_pm_wake_signal); +#endif diff --git a/arch/um/os-Linux/Makefile b/arch/um/os-Linux/Makefile index 839915b8c31c..77ac50baa3f8 100644 --- a/arch/um/os-Linux/Makefile +++ b/arch/um/os-Linux/Makefile @@ -10,6 +10,8 @@ obj-y = execvp.o file.o helper.o irq.o main.o mem.o process.o \ registers.o sigio.o signal.o start_up.o time.o tty.o \ umid.o user_syms.o util.o drivers/ skas/ +CFLAGS_signal.o += -Wframe-larger-than=4096 + obj-$(CONFIG_ARCH_REUSE_HOST_VSYSCALL_AREA) += elf_aux.o USER_OBJS := $(user-objs-y) elf_aux.o execvp.o file.o helper.o irq.o \ diff --git a/arch/um/os-Linux/helper.c b/arch/um/os-Linux/helper.c index 9fa6e4187d4f..feb48d796e00 100644 --- a/arch/um/os-Linux/helper.c +++ b/arch/um/os-Linux/helper.c @@ -45,7 +45,7 @@ int run_helper(void (*pre_exec)(void *), void *pre_data, char **argv) unsigned long stack, sp; int pid, fds[2], ret, n; - stack = alloc_stack(0, __cant_sleep()); + stack = alloc_stack(__cant_sleep()); if (stack == 0) return -ENOMEM; @@ -116,7 +116,7 @@ int run_helper_thread(int (*proc)(void *), void *arg, unsigned int flags, unsigned long stack, sp; int pid, status, err; - stack = alloc_stack(0, __cant_sleep()); + stack = alloc_stack(__cant_sleep()); if (stack == 0) return -ENOMEM; diff --git a/arch/um/os-Linux/irq.c b/arch/um/os-Linux/irq.c index d508310ee5e1..98ea910ef87c 100644 --- a/arch/um/os-Linux/irq.c +++ b/arch/um/os-Linux/irq.c @@ -45,10 +45,10 @@ int os_epoll_triggered(int index, int events) * access to the right includes/defines for EPOLL constants. */ -int os_event_mask(int irq_type) +int os_event_mask(enum um_irq_type irq_type) { if (irq_type == IRQ_READ) - return EPOLLIN | EPOLLPRI; + return EPOLLIN | EPOLLPRI | EPOLLERR | EPOLLHUP | EPOLLRDHUP; if (irq_type == IRQ_WRITE) return EPOLLOUT; return 0; diff --git a/arch/um/os-Linux/sigio.c b/arch/um/os-Linux/sigio.c index 75558080d0bf..6597ea1986ff 100644 --- a/arch/um/os-Linux/sigio.c +++ b/arch/um/os-Linux/sigio.c @@ -164,45 +164,55 @@ static void update_thread(void) set_signals_trace(flags); } -int add_sigio_fd(int fd) +int __add_sigio_fd(int fd) { struct pollfd *p; - int err = 0, i, n; + int err, i, n; - sigio_lock(); for (i = 0; i < all_sigio_fds.used; i++) { if (all_sigio_fds.poll[i].fd == fd) break; } if (i == all_sigio_fds.used) - goto out; + return -ENOSPC; p = &all_sigio_fds.poll[i]; for (i = 0; i < current_poll.used; i++) { if (current_poll.poll[i].fd == fd) - goto out; + return 0; } n = current_poll.used; err = need_poll(&next_poll, n + 1); if (err) - goto out; + return err; memcpy(next_poll.poll, current_poll.poll, current_poll.used * sizeof(struct pollfd)); next_poll.poll[n] = *p; next_poll.used = n + 1; update_thread(); - out: + + return 0; +} + + +int add_sigio_fd(int fd) +{ + int err; + + sigio_lock(); + err = __add_sigio_fd(fd); sigio_unlock(); + return err; } -int ignore_sigio_fd(int fd) +int __ignore_sigio_fd(int fd) { struct pollfd *p; - int err = 0, i, n = 0; + int err, i, n = 0; /* * This is called from exitcalls elsewhere in UML - if @@ -212,17 +222,16 @@ int ignore_sigio_fd(int fd) if (write_sigio_pid == -1) return -EIO; - sigio_lock(); for (i = 0; i < current_poll.used; i++) { if (current_poll.poll[i].fd == fd) break; } if (i == current_poll.used) - goto out; + return -ENOENT; err = need_poll(&next_poll, current_poll.used - 1); if (err) - goto out; + return err; for (i = 0; i < current_poll.used; i++) { p = ¤t_poll.poll[i]; @@ -232,8 +241,18 @@ int ignore_sigio_fd(int fd) next_poll.used = current_poll.used - 1; update_thread(); - out: + + return 0; +} + +int ignore_sigio_fd(int fd) +{ + int err; + + sigio_lock(); + err = __ignore_sigio_fd(fd); sigio_unlock(); + return err; } @@ -336,7 +355,7 @@ out_close1: close(l_write_sigio_fds[1]); } -void sigio_broken(int fd, int read) +void sigio_broken(int fd) { int err; @@ -352,7 +371,7 @@ void sigio_broken(int fd, int read) all_sigio_fds.poll[all_sigio_fds.used++] = ((struct pollfd) { .fd = fd, - .events = read ? POLLIN : POLLOUT, + .events = POLLIN, .revents = 0 }); out: sigio_unlock(); @@ -360,17 +379,16 @@ out: /* Changed during early boot */ static int pty_output_sigio; -static int pty_close_sigio; -void maybe_sigio_broken(int fd, int read) +void maybe_sigio_broken(int fd) { if (!isatty(fd)) return; - if ((read || pty_output_sigio) && (!read || pty_close_sigio)) + if (pty_output_sigio) return; - sigio_broken(fd, read); + sigio_broken(fd); } static void sigio_cleanup(void) @@ -514,19 +532,6 @@ static void tty_output(int master, int slave) printk(UM_KERN_CONT "tty_output : read failed, err = %d\n", n); } -static void tty_close(int master, int slave) -{ - printk(UM_KERN_INFO "Checking that host ptys support SIGIO on " - "close..."); - - close(slave); - if (got_sigio) { - printk(UM_KERN_CONT "Yes\n"); - pty_close_sigio = 1; - } else - printk(UM_KERN_CONT "No, enabling workaround\n"); -} - static void __init check_sigio(void) { if ((access("/dev/ptmx", R_OK) < 0) && @@ -536,7 +541,6 @@ static void __init check_sigio(void) return; } check_one_sigio(tty_output); - check_one_sigio(tty_close); } /* Here because it only does the SIGIO testing for now */ diff --git a/arch/um/os-Linux/signal.c b/arch/um/os-Linux/signal.c index b58bc68cbe64..96f511d1aabe 100644 --- a/arch/um/os-Linux/signal.c +++ b/arch/um/os-Linux/signal.c @@ -136,6 +136,16 @@ void set_sigstack(void *sig_stack, int size) panic("enabling signal stack failed, errno = %d\n", errno); } +static void sigusr1_handler(int sig, struct siginfo *unused_si, mcontext_t *mc) +{ + uml_pm_wake(); +} + +void register_pm_wake_signal(void) +{ + set_handler(SIGUSR1); +} + static void (*handlers[_NSIG])(int sig, struct siginfo *si, mcontext_t *mc) = { [SIGSEGV] = sig_handler, [SIGBUS] = sig_handler, @@ -145,7 +155,9 @@ static void (*handlers[_NSIG])(int sig, struct siginfo *si, mcontext_t *mc) = { [SIGIO] = sig_handler, [SIGWINCH] = sig_handler, - [SIGALRM] = timer_alarm_handler + [SIGALRM] = timer_alarm_handler, + + [SIGUSR1] = sigusr1_handler, }; static void hard_handler(int sig, siginfo_t *si, void *p) @@ -222,6 +234,11 @@ void set_handler(int sig) panic("sigprocmask failed - errno = %d\n", errno); } +void send_sigio_to_self(void) +{ + kill(os_getpid(), SIGIO); +} + int change_sig(int signal, int on) { sigset_t sigset; @@ -254,6 +271,9 @@ void unblock_signals(void) return; signals_enabled = 1; +#ifdef UML_CONFIG_UML_TIME_TRAVEL_SUPPORT + deliver_time_travel_irqs(); +#endif /* * We loop because the IRQ handler returns with interrupts off. So, diff --git a/arch/um/os-Linux/skas/process.c b/arch/um/os-Linux/skas/process.c index 4fb877b99dde..0621d521208e 100644 --- a/arch/um/os-Linux/skas/process.c +++ b/arch/um/os-Linux/skas/process.c @@ -400,7 +400,20 @@ void userspace(struct uml_pt_regs *regs, unsigned long *aux_fp_regs) if (WIFSTOPPED(status)) { int sig = WSTOPSIG(status); - ptrace(PTRACE_GETSIGINFO, pid, 0, (struct siginfo *)&si); + /* These signal handlers need the si argument. + * The SIGIO and SIGALARM handlers which constitute the + * majority of invocations, do not use it. + */ + switch (sig) { + case SIGSEGV: + case SIGTRAP: + case SIGILL: + case SIGBUS: + case SIGFPE: + case SIGWINCH: + ptrace(PTRACE_GETSIGINFO, pid, 0, (struct siginfo *)&si); + break; + } switch (sig) { case SIGSEGV: diff --git a/arch/um/os-Linux/time.c b/arch/um/os-Linux/time.c index 90f6de224c70..a61cbf73a179 100644 --- a/arch/um/os-Linux/time.c +++ b/arch/um/os-Linux/time.c @@ -7,6 +7,7 @@ */ #include <stddef.h> +#include <unistd.h> #include <errno.h> #include <signal.h> #include <time.h> @@ -99,19 +100,9 @@ long long os_nsecs(void) } /** - * os_idle_sleep() - sleep for a given time of nsecs - * @nsecs: nanoseconds to sleep + * os_idle_sleep() - sleep until interrupted */ -void os_idle_sleep(unsigned long long nsecs) +void os_idle_sleep(void) { - struct timespec ts = { - .tv_sec = nsecs / UM_NSEC_PER_SEC, - .tv_nsec = nsecs % UM_NSEC_PER_SEC - }; - - /* - * Relay the signal if clock_nanosleep is interrupted. - */ - if (clock_nanosleep(CLOCK_MONOTONIC, 0, &ts, NULL)) - deliver_alarm(); + pause(); } diff --git a/arch/um/os-Linux/umid.c b/arch/um/os-Linux/umid.c index 1d7558dac75f..a3dd61521d24 100644 --- a/arch/um/os-Linux/umid.c +++ b/arch/um/os-Linux/umid.c @@ -137,20 +137,13 @@ static inline int is_umdir_used(char *dir) { char pid[sizeof("nnnnnnnnn")], *end, *file; int dead, fd, p, n, err; - size_t filelen; + size_t filelen = strlen(dir) + sizeof("/pid") + 1; - err = asprintf(&file, "%s/pid", dir); - if (err < 0) - return 0; - - filelen = strlen(file); + file = malloc(filelen); + if (!file) + return -ENOMEM; - n = snprintf(file, filelen, "%s/pid", dir); - if (n >= filelen) { - printk(UM_KERN_ERR "is_umdir_used - pid filename too long\n"); - err = -E2BIG; - goto out; - } + snprintf(file, filelen, "%s/pid", dir); dead = 0; fd = open(file, O_RDONLY); diff --git a/arch/x86/boot/compressed/misc.h b/arch/x86/boot/compressed/misc.h index d9a631c5973c..901ea5ebec22 100644 --- a/arch/x86/boot/compressed/misc.h +++ b/arch/x86/boot/compressed/misc.h @@ -12,6 +12,7 @@ #undef CONFIG_PARAVIRT_XXL #undef CONFIG_PARAVIRT_SPINLOCKS #undef CONFIG_KASAN +#undef CONFIG_KASAN_GENERIC /* cpu_feature_enabled() cannot be used this early */ #define USE_EARLY_PGTABLE_L5 diff --git a/arch/x86/entry/syscalls/syscall_32.tbl b/arch/x86/entry/syscalls/syscall_32.tbl index 0d0667a9fbd7..874aeacde2dd 100644 --- a/arch/x86/entry/syscalls/syscall_32.tbl +++ b/arch/x86/entry/syscalls/syscall_32.tbl @@ -445,3 +445,4 @@ 438 i386 pidfd_getfd sys_pidfd_getfd 439 i386 faccessat2 sys_faccessat2 440 i386 process_madvise sys_process_madvise +441 i386 epoll_pwait2 sys_epoll_pwait2 compat_sys_epoll_pwait2 diff --git a/arch/x86/entry/syscalls/syscall_64.tbl b/arch/x86/entry/syscalls/syscall_64.tbl index 379819244b91..78672124d28b 100644 --- a/arch/x86/entry/syscalls/syscall_64.tbl +++ b/arch/x86/entry/syscalls/syscall_64.tbl @@ -362,6 +362,7 @@ 438 common pidfd_getfd sys_pidfd_getfd 439 common faccessat2 sys_faccessat2 440 common process_madvise sys_process_madvise +441 common epoll_pwait2 sys_epoll_pwait2 # # Due to a historical design error, certain syscalls are numbered differently diff --git a/arch/x86/include/asm/cpufeatures.h b/arch/x86/include/asm/cpufeatures.h index f5ef2d5b9231..84b887825f12 100644 --- a/arch/x86/include/asm/cpufeatures.h +++ b/arch/x86/include/asm/cpufeatures.h @@ -237,6 +237,7 @@ #define X86_FEATURE_VMCALL ( 8*32+18) /* "" Hypervisor supports the VMCALL instruction */ #define X86_FEATURE_VMW_VMMCALL ( 8*32+19) /* "" VMware prefers VMMCALL hypercall instruction */ #define X86_FEATURE_SEV_ES ( 8*32+20) /* AMD Secure Encrypted Virtualization - Encrypted State */ +#define X86_FEATURE_VM_PAGE_FLUSH ( 8*32+21) /* "" VM Page Flush MSR is supported */ /* Intel-defined CPU features, CPUID level 0x00000007:0 (EBX), word 9 */ #define X86_FEATURE_FSGSBASE ( 9*32+ 0) /* RDFSBASE, WRFSBASE, RDGSBASE, WRGSBASE instructions*/ @@ -376,6 +377,7 @@ #define X86_FEATURE_TSXLDTRK (18*32+16) /* TSX Suspend Load Address Tracking */ #define X86_FEATURE_PCONFIG (18*32+18) /* Intel PCONFIG */ #define X86_FEATURE_ARCH_LBR (18*32+19) /* Intel ARCH LBR */ +#define X86_FEATURE_AVX512_FP16 (18*32+23) /* AVX512 FP16 */ #define X86_FEATURE_SPEC_CTRL (18*32+26) /* "" Speculation Control (IBRS + IBPB) */ #define X86_FEATURE_INTEL_STIBP (18*32+27) /* "" Single Thread Indirect Branch Predictors */ #define X86_FEATURE_FLUSH_L1D (18*32+28) /* Flush L1D cache */ diff --git a/arch/x86/include/asm/kvm_host.h b/arch/x86/include/asm/kvm_host.h index 7e5f33a0d0e2..3ab7b46087b7 100644 --- a/arch/x86/include/asm/kvm_host.h +++ b/arch/x86/include/asm/kvm_host.h @@ -614,6 +614,7 @@ struct kvm_vcpu_arch { struct kvm_pio_request pio; void *pio_data; + void *guest_ins_data; u8 event_exit_inst_len; @@ -805,6 +806,9 @@ struct kvm_vcpu_arch { */ bool enforce; } pv_cpuid; + + /* Protected Guests */ + bool guest_state_protected; }; struct kvm_lpage_info { @@ -1088,7 +1092,7 @@ struct kvm_x86_ops { void (*hardware_disable)(void); void (*hardware_unsetup)(void); bool (*cpu_has_accelerated_tpr)(void); - bool (*has_emulated_msr)(u32 index); + bool (*has_emulated_msr)(struct kvm *kvm, u32 index); void (*vcpu_after_set_cpuid)(struct kvm_vcpu *vcpu); unsigned int vm_size; @@ -1115,7 +1119,8 @@ struct kvm_x86_ops { struct kvm_segment *var, int seg); void (*get_cs_db_l_bits)(struct kvm_vcpu *vcpu, int *db, int *l); void (*set_cr0)(struct kvm_vcpu *vcpu, unsigned long cr0); - int (*set_cr4)(struct kvm_vcpu *vcpu, unsigned long cr4); + bool (*is_valid_cr4)(struct kvm_vcpu *vcpu, unsigned long cr0); + void (*set_cr4)(struct kvm_vcpu *vcpu, unsigned long cr4); int (*set_efer)(struct kvm_vcpu *vcpu, u64 efer); void (*get_idt)(struct kvm_vcpu *vcpu, struct desc_ptr *dt); void (*set_idt)(struct kvm_vcpu *vcpu, struct desc_ptr *dt); @@ -1231,6 +1236,7 @@ struct kvm_x86_ops { void (*enable_log_dirty_pt_masked)(struct kvm *kvm, struct kvm_memory_slot *slot, gfn_t offset, unsigned long mask); + int (*cpu_dirty_log_size)(void); /* pmu operations of sub-arch */ const struct kvm_pmu_ops *pmu_ops; @@ -1280,6 +1286,7 @@ struct kvm_x86_ops { void (*migrate_timers)(struct kvm_vcpu *vcpu); void (*msr_filter_changed)(struct kvm_vcpu *vcpu); + int (*complete_emulated_msr)(struct kvm_vcpu *vcpu, int err); }; struct kvm_x86_nested_ops { @@ -1470,6 +1477,10 @@ void kvm_vcpu_deliver_sipi_vector(struct kvm_vcpu *vcpu, u8 vector); int kvm_task_switch(struct kvm_vcpu *vcpu, u16 tss_selector, int idt_index, int reason, bool has_error_code, u32 error_code); +void kvm_free_guest_fpu(struct kvm_vcpu *vcpu); + +void kvm_post_set_cr0(struct kvm_vcpu *vcpu, unsigned long old_cr0, unsigned long cr0); +void kvm_post_set_cr4(struct kvm_vcpu *vcpu, unsigned long old_cr4, unsigned long cr4); int kvm_set_cr0(struct kvm_vcpu *vcpu, unsigned long cr0); int kvm_set_cr3(struct kvm_vcpu *vcpu, unsigned long cr3); int kvm_set_cr4(struct kvm_vcpu *vcpu, unsigned long cr4); @@ -1696,7 +1707,8 @@ void __kvm_request_immediate_exit(struct kvm_vcpu *vcpu); int kvm_is_in_guest(void); -int __x86_set_memory_region(struct kvm *kvm, int id, gpa_t gpa, u32 size); +void __user *__x86_set_memory_region(struct kvm *kvm, int id, gpa_t gpa, + u32 size); bool kvm_vcpu_is_reset_bsp(struct kvm_vcpu *vcpu); bool kvm_vcpu_is_bsp(struct kvm_vcpu *vcpu); @@ -1743,4 +1755,6 @@ static inline int kvm_cpu_get_apicid(int mps_cpu) #define GET_SMSTATE(type, buf, offset) \ (*(type *)((buf) + (offset) - 0x7e00)) +int kvm_cpu_dirty_log_size(void); + #endif /* _ASM_X86_KVM_HOST_H */ diff --git a/arch/x86/include/asm/msr-index.h b/arch/x86/include/asm/msr-index.h index 2b5fc9accec4..546d6ecf0a35 100644 --- a/arch/x86/include/asm/msr-index.h +++ b/arch/x86/include/asm/msr-index.h @@ -472,6 +472,7 @@ #define MSR_AMD64_ICIBSEXTDCTL 0xc001103c #define MSR_AMD64_IBSOPDATA4 0xc001103d #define MSR_AMD64_IBS_REG_COUNT_MAX 8 /* includes MSR_AMD64_IBSBRTARGET */ +#define MSR_AMD64_VM_PAGE_FLUSH 0xc001011e #define MSR_AMD64_SEV_ES_GHCB 0xc0010130 #define MSR_AMD64_SEV 0xc0010131 #define MSR_AMD64_SEV_ENABLED_BIT 0 diff --git a/arch/x86/include/asm/svm.h b/arch/x86/include/asm/svm.h index 71d630bb5e08..1c561945b426 100644 --- a/arch/x86/include/asm/svm.h +++ b/arch/x86/include/asm/svm.h @@ -98,6 +98,16 @@ enum { INTERCEPT_MWAIT_COND, INTERCEPT_XSETBV, INTERCEPT_RDPRU, + TRAP_EFER_WRITE, + TRAP_CR0_WRITE, + TRAP_CR1_WRITE, + TRAP_CR2_WRITE, + TRAP_CR3_WRITE, + TRAP_CR4_WRITE, + TRAP_CR5_WRITE, + TRAP_CR6_WRITE, + TRAP_CR7_WRITE, + TRAP_CR8_WRITE, /* Byte offset 014h (word 5) */ INTERCEPT_INVLPGB = 160, INTERCEPT_INVLPGB_ILLEGAL, @@ -130,7 +140,7 @@ struct __attribute__ ((__packed__)) vmcb_control_area { u32 exit_int_info_err; u64 nested_ctl; u64 avic_vapic_bar; - u8 reserved_4[8]; + u64 ghcb_gpa; u32 event_inj; u32 event_inj_err; u64 nested_cr3; @@ -144,6 +154,8 @@ struct __attribute__ ((__packed__)) vmcb_control_area { u8 reserved_6[8]; /* Offset 0xe8 */ u64 avic_logical_id; /* Offset 0xf0 */ u64 avic_physical_id; /* Offset 0xf8 */ + u8 reserved_7[8]; + u64 vmsa_pa; /* Used for an SEV-ES guest */ }; @@ -178,7 +190,8 @@ struct __attribute__ ((__packed__)) vmcb_control_area { #define LBR_CTL_ENABLE_MASK BIT_ULL(0) #define VIRTUAL_VMLOAD_VMSAVE_ENABLE_MASK BIT_ULL(1) -#define SVM_INTERRUPT_SHADOW_MASK 1 +#define SVM_INTERRUPT_SHADOW_MASK BIT_ULL(0) +#define SVM_GUEST_INTERRUPT_MASK BIT_ULL(1) #define SVM_IOIO_STR_SHIFT 2 #define SVM_IOIO_REP_SHIFT 3 @@ -197,6 +210,7 @@ struct __attribute__ ((__packed__)) vmcb_control_area { #define SVM_NESTED_CTL_NP_ENABLE BIT(0) #define SVM_NESTED_CTL_SEV_ENABLE BIT(1) +#define SVM_NESTED_CTL_SEV_ES_ENABLE BIT(2) struct vmcb_seg { u16 selector; @@ -220,7 +234,8 @@ struct vmcb_save_area { u8 cpl; u8 reserved_2[4]; u64 efer; - u8 reserved_3[112]; + u8 reserved_3[104]; + u64 xss; /* Valid for SEV-ES only */ u64 cr4; u64 cr3; u64 cr0; @@ -251,9 +266,12 @@ struct vmcb_save_area { /* * The following part of the save area is valid only for - * SEV-ES guests when referenced through the GHCB. + * SEV-ES guests when referenced through the GHCB or for + * saving to the host save area. */ - u8 reserved_7[104]; + u8 reserved_7[80]; + u32 pkru; + u8 reserved_7a[20]; u64 reserved_8; /* rax already available at 0x01f8 */ u64 rcx; u64 rdx; @@ -294,7 +312,7 @@ struct ghcb { #define EXPECTED_VMCB_SAVE_AREA_SIZE 1032 -#define EXPECTED_VMCB_CONTROL_AREA_SIZE 256 +#define EXPECTED_VMCB_CONTROL_AREA_SIZE 272 #define EXPECTED_GHCB_SIZE PAGE_SIZE static inline void __unused_size_checks(void) @@ -379,6 +397,16 @@ struct vmcb { (unsigned long *)&ghcb->save.valid_bitmap); \ } \ \ + static inline u64 ghcb_get_##field(struct ghcb *ghcb) \ + { \ + return ghcb->save.field; \ + } \ + \ + static inline u64 ghcb_get_##field##_if_valid(struct ghcb *ghcb) \ + { \ + return ghcb_##field##_is_valid(ghcb) ? ghcb->save.field : 0; \ + } \ + \ static inline void ghcb_set_##field(struct ghcb *ghcb, u64 value) \ { \ __set_bit(GHCB_BITMAP_IDX(field), \ diff --git a/arch/x86/include/asm/vmx.h b/arch/x86/include/asm/vmx.h index f8ba5289ecb0..38ca445a8429 100644 --- a/arch/x86/include/asm/vmx.h +++ b/arch/x86/include/asm/vmx.h @@ -113,6 +113,7 @@ #define VMX_MISC_PREEMPTION_TIMER_RATE_MASK 0x0000001f #define VMX_MISC_SAVE_EFER_LMA 0x00000020 #define VMX_MISC_ACTIVITY_HLT 0x00000040 +#define VMX_MISC_ACTIVITY_WAIT_SIPI 0x00000100 #define VMX_MISC_ZERO_LEN_INS 0x40000000 #define VMX_MISC_MSR_LIST_MULTIPLIER 512 diff --git a/arch/x86/include/asm/xen/page.h b/arch/x86/include/asm/xen/page.h index 5941e18edd5a..1a162e559753 100644 --- a/arch/x86/include/asm/xen/page.h +++ b/arch/x86/include/asm/xen/page.h @@ -355,7 +355,7 @@ unsigned long arbitrary_virt_to_mfn(void *vaddr); void make_lowmem_page_readonly(void *vaddr); void make_lowmem_page_readwrite(void *vaddr); -#define xen_remap(cookie, size) ioremap((cookie), (size)); +#define xen_remap(cookie, size) ioremap((cookie), (size)) #define xen_unmap(cookie) iounmap((cookie)) static inline bool xen_arch_need_swiotlb(struct device *dev, diff --git a/arch/x86/include/uapi/asm/kvm.h b/arch/x86/include/uapi/asm/kvm.h index 89e5f3d1bba8..8e76d3701db3 100644 --- a/arch/x86/include/uapi/asm/kvm.h +++ b/arch/x86/include/uapi/asm/kvm.h @@ -12,6 +12,7 @@ #define KVM_PIO_PAGE_OFFSET 1 #define KVM_COALESCED_MMIO_PAGE_OFFSET 2 +#define KVM_DIRTY_LOG_PAGE_OFFSET 64 #define DE_VECTOR 0 #define DB_VECTOR 1 diff --git a/arch/x86/include/uapi/asm/svm.h b/arch/x86/include/uapi/asm/svm.h index f1d8307454e0..554f75fe013c 100644 --- a/arch/x86/include/uapi/asm/svm.h +++ b/arch/x86/include/uapi/asm/svm.h @@ -77,10 +77,28 @@ #define SVM_EXIT_MWAIT_COND 0x08c #define SVM_EXIT_XSETBV 0x08d #define SVM_EXIT_RDPRU 0x08e +#define SVM_EXIT_EFER_WRITE_TRAP 0x08f +#define SVM_EXIT_CR0_WRITE_TRAP 0x090 +#define SVM_EXIT_CR1_WRITE_TRAP 0x091 +#define SVM_EXIT_CR2_WRITE_TRAP 0x092 +#define SVM_EXIT_CR3_WRITE_TRAP 0x093 +#define SVM_EXIT_CR4_WRITE_TRAP 0x094 +#define SVM_EXIT_CR5_WRITE_TRAP 0x095 +#define SVM_EXIT_CR6_WRITE_TRAP 0x096 +#define SVM_EXIT_CR7_WRITE_TRAP 0x097 +#define SVM_EXIT_CR8_WRITE_TRAP 0x098 +#define SVM_EXIT_CR9_WRITE_TRAP 0x099 +#define SVM_EXIT_CR10_WRITE_TRAP 0x09a +#define SVM_EXIT_CR11_WRITE_TRAP 0x09b +#define SVM_EXIT_CR12_WRITE_TRAP 0x09c +#define SVM_EXIT_CR13_WRITE_TRAP 0x09d +#define SVM_EXIT_CR14_WRITE_TRAP 0x09e +#define SVM_EXIT_CR15_WRITE_TRAP 0x09f #define SVM_EXIT_INVPCID 0x0a2 #define SVM_EXIT_NPF 0x400 #define SVM_EXIT_AVIC_INCOMPLETE_IPI 0x401 #define SVM_EXIT_AVIC_UNACCELERATED_ACCESS 0x402 +#define SVM_EXIT_VMGEXIT 0x403 /* SEV-ES software-defined VMGEXIT events */ #define SVM_VMGEXIT_MMIO_READ 0x80000001 @@ -183,10 +201,20 @@ { SVM_EXIT_MONITOR, "monitor" }, \ { SVM_EXIT_MWAIT, "mwait" }, \ { SVM_EXIT_XSETBV, "xsetbv" }, \ + { SVM_EXIT_EFER_WRITE_TRAP, "write_efer_trap" }, \ + { SVM_EXIT_CR0_WRITE_TRAP, "write_cr0_trap" }, \ + { SVM_EXIT_CR4_WRITE_TRAP, "write_cr4_trap" }, \ + { SVM_EXIT_CR8_WRITE_TRAP, "write_cr8_trap" }, \ { SVM_EXIT_INVPCID, "invpcid" }, \ { SVM_EXIT_NPF, "npf" }, \ { SVM_EXIT_AVIC_INCOMPLETE_IPI, "avic_incomplete_ipi" }, \ { SVM_EXIT_AVIC_UNACCELERATED_ACCESS, "avic_unaccelerated_access" }, \ + { SVM_EXIT_VMGEXIT, "vmgexit" }, \ + { SVM_VMGEXIT_MMIO_READ, "vmgexit_mmio_read" }, \ + { SVM_VMGEXIT_MMIO_WRITE, "vmgexit_mmio_write" }, \ + { SVM_VMGEXIT_NMI_COMPLETE, "vmgexit_nmi_complete" }, \ + { SVM_VMGEXIT_AP_HLT_LOOP, "vmgexit_ap_hlt_loop" }, \ + { SVM_VMGEXIT_AP_JUMP_TABLE, "vmgexit_ap_jump_table" }, \ { SVM_EXIT_ERR, "invalid_guest_state" } diff --git a/arch/x86/include/uapi/asm/vmx.h b/arch/x86/include/uapi/asm/vmx.h index b8ff9e8ac0d5..ada955c5ebb6 100644 --- a/arch/x86/include/uapi/asm/vmx.h +++ b/arch/x86/include/uapi/asm/vmx.h @@ -32,6 +32,7 @@ #define EXIT_REASON_EXTERNAL_INTERRUPT 1 #define EXIT_REASON_TRIPLE_FAULT 2 #define EXIT_REASON_INIT_SIGNAL 3 +#define EXIT_REASON_SIPI_SIGNAL 4 #define EXIT_REASON_INTERRUPT_WINDOW 7 #define EXIT_REASON_NMI_WINDOW 8 @@ -94,6 +95,7 @@ { EXIT_REASON_EXTERNAL_INTERRUPT, "EXTERNAL_INTERRUPT" }, \ { EXIT_REASON_TRIPLE_FAULT, "TRIPLE_FAULT" }, \ { EXIT_REASON_INIT_SIGNAL, "INIT_SIGNAL" }, \ + { EXIT_REASON_SIPI_SIGNAL, "SIPI_SIGNAL" }, \ { EXIT_REASON_INTERRUPT_WINDOW, "INTERRUPT_WINDOW" }, \ { EXIT_REASON_NMI_WINDOW, "NMI_WINDOW" }, \ { EXIT_REASON_TASK_SWITCH, "TASK_SWITCH" }, \ diff --git a/arch/x86/kernel/acpi/wakeup_64.S b/arch/x86/kernel/acpi/wakeup_64.S index c8daa92f38dc..5d3a0b8fd379 100644 --- a/arch/x86/kernel/acpi/wakeup_64.S +++ b/arch/x86/kernel/acpi/wakeup_64.S @@ -112,7 +112,7 @@ SYM_FUNC_START(do_suspend_lowlevel) movq pt_regs_r14(%rax), %r14 movq pt_regs_r15(%rax), %r15 -#ifdef CONFIG_KASAN +#if defined(CONFIG_KASAN) && CONFIG_KASAN_STACK /* * The suspend path may have poisoned some areas deeper in the stack, * which we now need to unpoison. diff --git a/arch/x86/kernel/cpu/cpuid-deps.c b/arch/x86/kernel/cpu/cpuid-deps.c index d502241995a3..42af31b64c2c 100644 --- a/arch/x86/kernel/cpu/cpuid-deps.c +++ b/arch/x86/kernel/cpu/cpuid-deps.c @@ -69,6 +69,7 @@ static const struct cpuid_dep cpuid_deps[] = { { X86_FEATURE_CQM_MBM_TOTAL, X86_FEATURE_CQM_LLC }, { X86_FEATURE_CQM_MBM_LOCAL, X86_FEATURE_CQM_LLC }, { X86_FEATURE_AVX512_BF16, X86_FEATURE_AVX512VL }, + { X86_FEATURE_AVX512_FP16, X86_FEATURE_AVX512BW }, { X86_FEATURE_ENQCMD, X86_FEATURE_XSAVES }, { X86_FEATURE_PER_THREAD_MBA, X86_FEATURE_MBA }, {} diff --git a/arch/x86/kernel/cpu/scattered.c b/arch/x86/kernel/cpu/scattered.c index 866c9a9bcdee..236924930bf0 100644 --- a/arch/x86/kernel/cpu/scattered.c +++ b/arch/x86/kernel/cpu/scattered.c @@ -44,6 +44,7 @@ static const struct cpuid_bit cpuid_bits[] = { { X86_FEATURE_SEV, CPUID_EAX, 1, 0x8000001f, 0 }, { X86_FEATURE_SEV_ES, CPUID_EAX, 3, 0x8000001f, 0 }, { X86_FEATURE_SME_COHERENT, CPUID_EAX, 10, 0x8000001f, 0 }, + { X86_FEATURE_VM_PAGE_FLUSH, CPUID_EAX, 2, 0x8000001f, 0 }, { 0, 0, 0, 0, 0 } }; diff --git a/arch/x86/kernel/cpu/vmware.c b/arch/x86/kernel/cpu/vmware.c index 924571fe5864..c6ede3b3d302 100644 --- a/arch/x86/kernel/cpu/vmware.c +++ b/arch/x86/kernel/cpu/vmware.c @@ -501,12 +501,12 @@ static bool vmware_sev_es_hcall_finish(struct ghcb *ghcb, struct pt_regs *regs) ghcb_rbp_is_valid(ghcb))) return false; - regs->bx = ghcb->save.rbx; - regs->cx = ghcb->save.rcx; - regs->dx = ghcb->save.rdx; - regs->si = ghcb->save.rsi; - regs->di = ghcb->save.rdi; - regs->bp = ghcb->save.rbp; + regs->bx = ghcb_get_rbx(ghcb); + regs->cx = ghcb_get_rcx(ghcb); + regs->dx = ghcb_get_rdx(ghcb); + regs->si = ghcb_get_rsi(ghcb); + regs->di = ghcb_get_rdi(ghcb); + regs->bp = ghcb_get_rbp(ghcb); return true; } diff --git a/arch/x86/kernel/kvmclock.c b/arch/x86/kernel/kvmclock.c index 34b18f6eeb2c..aa593743acf6 100644 --- a/arch/x86/kernel/kvmclock.c +++ b/arch/x86/kernel/kvmclock.c @@ -44,7 +44,6 @@ static int __init parse_no_kvmclock_vsyscall(char *arg) early_param("no-kvmclock-vsyscall", parse_no_kvmclock_vsyscall); /* Aligned to page sizes to match whats mapped via vsyscalls to userspace */ -#define HV_CLOCK_SIZE (sizeof(struct pvclock_vsyscall_time_info) * NR_CPUS) #define HVC_BOOT_ARRAY_SIZE \ (PAGE_SIZE / sizeof(struct pvclock_vsyscall_time_info)) diff --git a/arch/x86/kernel/traps.c b/arch/x86/kernel/traps.c index fb55981f2a0d..7f5aec758f0e 100644 --- a/arch/x86/kernel/traps.c +++ b/arch/x86/kernel/traps.c @@ -303,11 +303,12 @@ DEFINE_IDTENTRY_ERRORCODE(exc_alignment_check) local_irq_enable(); if (handle_user_split_lock(regs, error_code)) - return; + goto out; do_trap(X86_TRAP_AC, SIGBUS, "alignment check", regs, error_code, BUS_ADRALN, NULL); +out: local_irq_disable(); } diff --git a/arch/x86/kvm/Kconfig b/arch/x86/kvm/Kconfig index f92dfd8ef10d..7ac592664c52 100644 --- a/arch/x86/kvm/Kconfig +++ b/arch/x86/kvm/Kconfig @@ -100,7 +100,8 @@ config KVM_AMD_SEV depends on KVM_AMD && X86_64 depends on CRYPTO_DEV_SP_PSP && !(KVM_AMD=y && CRYPTO_DEV_CCP_DD=m) help - Provides support for launching Encrypted VMs on AMD processors. + Provides support for launching Encrypted VMs (SEV) and Encrypted VMs + with Encrypted State (SEV-ES) on AMD processors. config KVM_MMU_AUDIT bool "Audit KVM MMU" diff --git a/arch/x86/kvm/Makefile b/arch/x86/kvm/Makefile index b804444e16d4..4bd14ab01323 100644 --- a/arch/x86/kvm/Makefile +++ b/arch/x86/kvm/Makefile @@ -10,7 +10,8 @@ endif KVM := ../../../virt/kvm kvm-y += $(KVM)/kvm_main.o $(KVM)/coalesced_mmio.o \ - $(KVM)/eventfd.o $(KVM)/irqchip.o $(KVM)/vfio.o + $(KVM)/eventfd.o $(KVM)/irqchip.o $(KVM)/vfio.o \ + $(KVM)/dirty_ring.o kvm-$(CONFIG_KVM_ASYNC_PF) += $(KVM)/async_pf.o kvm-y += x86.o emulate.o i8259.o irq.o lapic.o \ diff --git a/arch/x86/kvm/cpuid.c b/arch/x86/kvm/cpuid.c index 83637a2ff605..13036cf0b912 100644 --- a/arch/x86/kvm/cpuid.c +++ b/arch/x86/kvm/cpuid.c @@ -146,6 +146,7 @@ void kvm_update_cpuid_runtime(struct kvm_vcpu *vcpu) MSR_IA32_MISC_ENABLE_MWAIT); } } +EXPORT_SYMBOL_GPL(kvm_update_cpuid_runtime); static void kvm_vcpu_after_set_cpuid(struct kvm_vcpu *vcpu) { @@ -418,7 +419,7 @@ void kvm_set_cpu_caps(void) F(AVX512_4VNNIW) | F(AVX512_4FMAPS) | F(SPEC_CTRL) | F(SPEC_CTRL_SSBD) | F(ARCH_CAPABILITIES) | F(INTEL_STIBP) | F(MD_CLEAR) | F(AVX512_VP2INTERSECT) | F(FSRM) | - F(SERIALIZE) | F(TSXLDTRK) + F(SERIALIZE) | F(TSXLDTRK) | F(AVX512_FP16) ); /* TSC_ADJUST and ARCH_CAPABILITIES are emulated in software. */ diff --git a/arch/x86/kvm/cpuid.h b/arch/x86/kvm/cpuid.h index f7a6e8f83783..dc921d76e42e 100644 --- a/arch/x86/kvm/cpuid.h +++ b/arch/x86/kvm/cpuid.h @@ -264,6 +264,20 @@ static inline int guest_cpuid_stepping(struct kvm_vcpu *vcpu) return x86_stepping(best->eax); } +static inline bool guest_has_spec_ctrl_msr(struct kvm_vcpu *vcpu) +{ + return (guest_cpuid_has(vcpu, X86_FEATURE_SPEC_CTRL) || + guest_cpuid_has(vcpu, X86_FEATURE_AMD_STIBP) || + guest_cpuid_has(vcpu, X86_FEATURE_AMD_IBRS) || + guest_cpuid_has(vcpu, X86_FEATURE_AMD_SSBD)); +} + +static inline bool guest_has_pred_cmd_msr(struct kvm_vcpu *vcpu) +{ + return (guest_cpuid_has(vcpu, X86_FEATURE_SPEC_CTRL) || + guest_cpuid_has(vcpu, X86_FEATURE_AMD_IBPB)); +} + static inline bool supports_cpuid_fault(struct kvm_vcpu *vcpu) { return vcpu->arch.msr_platform_info & MSR_PLATFORM_INFO_CPUID_FAULT; diff --git a/arch/x86/kvm/hyperv.c b/arch/x86/kvm/hyperv.c index 5c7c4060b45c..922c69dcca4d 100644 --- a/arch/x86/kvm/hyperv.c +++ b/arch/x86/kvm/hyperv.c @@ -1951,8 +1951,8 @@ int kvm_vm_ioctl_hv_eventfd(struct kvm *kvm, struct kvm_hyperv_eventfd *args) return kvm_hv_eventfd_assign(kvm, args->conn_id, args->fd); } -int kvm_vcpu_ioctl_get_hv_cpuid(struct kvm_vcpu *vcpu, struct kvm_cpuid2 *cpuid, - struct kvm_cpuid_entry2 __user *entries) +int kvm_get_hv_cpuid(struct kvm_vcpu *vcpu, struct kvm_cpuid2 *cpuid, + struct kvm_cpuid_entry2 __user *entries) { uint16_t evmcs_ver = 0; struct kvm_cpuid_entry2 cpuid_entries[] = { @@ -2037,7 +2037,7 @@ int kvm_vcpu_ioctl_get_hv_cpuid(struct kvm_vcpu *vcpu, struct kvm_cpuid2 *cpuid, * Direct Synthetic timers only make sense with in-kernel * LAPIC */ - if (lapic_in_kernel(vcpu)) + if (!vcpu || lapic_in_kernel(vcpu)) ent->edx |= HV_STIMER_DIRECT_MODE_AVAILABLE; break; diff --git a/arch/x86/kvm/hyperv.h b/arch/x86/kvm/hyperv.h index e68c6c2e9649..6d7def2b0aad 100644 --- a/arch/x86/kvm/hyperv.h +++ b/arch/x86/kvm/hyperv.h @@ -126,7 +126,7 @@ void kvm_hv_setup_tsc_page(struct kvm *kvm, void kvm_hv_init_vm(struct kvm *kvm); void kvm_hv_destroy_vm(struct kvm *kvm); int kvm_vm_ioctl_hv_eventfd(struct kvm *kvm, struct kvm_hyperv_eventfd *args); -int kvm_vcpu_ioctl_get_hv_cpuid(struct kvm_vcpu *vcpu, struct kvm_cpuid2 *cpuid, - struct kvm_cpuid_entry2 __user *entries); +int kvm_get_hv_cpuid(struct kvm_vcpu *vcpu, struct kvm_cpuid2 *cpuid, + struct kvm_cpuid_entry2 __user *entries); #endif diff --git a/arch/x86/kvm/kvm_cache_regs.h b/arch/x86/kvm/kvm_cache_regs.h index a889563ad02d..f15bc16de07c 100644 --- a/arch/x86/kvm/kvm_cache_regs.h +++ b/arch/x86/kvm/kvm_cache_regs.h @@ -9,6 +9,31 @@ (X86_CR4_PVI | X86_CR4_DE | X86_CR4_PCE | X86_CR4_OSFXSR \ | X86_CR4_OSXMMEXCPT | X86_CR4_PGE | X86_CR4_TSD | X86_CR4_FSGSBASE) +static inline bool kvm_register_is_available(struct kvm_vcpu *vcpu, + enum kvm_reg reg) +{ + return test_bit(reg, (unsigned long *)&vcpu->arch.regs_avail); +} + +static inline bool kvm_register_is_dirty(struct kvm_vcpu *vcpu, + enum kvm_reg reg) +{ + return test_bit(reg, (unsigned long *)&vcpu->arch.regs_dirty); +} + +static inline void kvm_register_mark_available(struct kvm_vcpu *vcpu, + enum kvm_reg reg) +{ + __set_bit(reg, (unsigned long *)&vcpu->arch.regs_avail); +} + +static inline void kvm_register_mark_dirty(struct kvm_vcpu *vcpu, + enum kvm_reg reg) +{ + __set_bit(reg, (unsigned long *)&vcpu->arch.regs_avail); + __set_bit(reg, (unsigned long *)&vcpu->arch.regs_dirty); +} + #define BUILD_KVM_GPR_ACCESSORS(lname, uname) \ static __always_inline unsigned long kvm_##lname##_read(struct kvm_vcpu *vcpu)\ { \ @@ -18,6 +43,7 @@ static __always_inline void kvm_##lname##_write(struct kvm_vcpu *vcpu, \ unsigned long val) \ { \ vcpu->arch.regs[VCPU_REGS_##uname] = val; \ + kvm_register_mark_dirty(vcpu, VCPU_REGS_##uname); \ } BUILD_KVM_GPR_ACCESSORS(rax, RAX) BUILD_KVM_GPR_ACCESSORS(rbx, RBX) @@ -37,31 +63,6 @@ BUILD_KVM_GPR_ACCESSORS(r14, R14) BUILD_KVM_GPR_ACCESSORS(r15, R15) #endif -static inline bool kvm_register_is_available(struct kvm_vcpu *vcpu, - enum kvm_reg reg) -{ - return test_bit(reg, (unsigned long *)&vcpu->arch.regs_avail); -} - -static inline bool kvm_register_is_dirty(struct kvm_vcpu *vcpu, - enum kvm_reg reg) -{ - return test_bit(reg, (unsigned long *)&vcpu->arch.regs_dirty); -} - -static inline void kvm_register_mark_available(struct kvm_vcpu *vcpu, - enum kvm_reg reg) -{ - __set_bit(reg, (unsigned long *)&vcpu->arch.regs_avail); -} - -static inline void kvm_register_mark_dirty(struct kvm_vcpu *vcpu, - enum kvm_reg reg) -{ - __set_bit(reg, (unsigned long *)&vcpu->arch.regs_avail); - __set_bit(reg, (unsigned long *)&vcpu->arch.regs_dirty); -} - static inline unsigned long kvm_register_read(struct kvm_vcpu *vcpu, int reg) { if (WARN_ON_ONCE((unsigned int)reg >= NR_VCPU_REGS)) diff --git a/arch/x86/kvm/lapic.c b/arch/x86/kvm/lapic.c index 86c33d53c90a..3136e05831cf 100644 --- a/arch/x86/kvm/lapic.c +++ b/arch/x86/kvm/lapic.c @@ -2843,14 +2843,35 @@ void kvm_apic_accept_events(struct kvm_vcpu *vcpu) { struct kvm_lapic *apic = vcpu->arch.apic; u8 sipi_vector; + int r; unsigned long pe; - if (!lapic_in_kernel(vcpu) || !apic->pending_events) + if (!lapic_in_kernel(vcpu)) return; /* + * Read pending events before calling the check_events + * callback. + */ + pe = smp_load_acquire(&apic->pending_events); + if (!pe) + return; + + if (is_guest_mode(vcpu)) { + r = kvm_x86_ops.nested_ops->check_events(vcpu); + if (r < 0) + return; + /* + * If an event has happened and caused a vmexit, + * we know INITs are latched and therefore + * we will not incorrectly deliver an APIC + * event instead of a vmexit. + */ + } + + /* * INITs are latched while CPU is in specific states - * (SMM, VMX non-root mode, SVM with GIF=0). + * (SMM, VMX root mode, SVM with GIF=0). * Because a CPU cannot be in these states immediately * after it has processed an INIT signal (and thus in * KVM_MP_STATE_INIT_RECEIVED state), just eat SIPIs @@ -2858,26 +2879,28 @@ void kvm_apic_accept_events(struct kvm_vcpu *vcpu) */ if (kvm_vcpu_latch_init(vcpu)) { WARN_ON_ONCE(vcpu->arch.mp_state == KVM_MP_STATE_INIT_RECEIVED); - if (test_bit(KVM_APIC_SIPI, &apic->pending_events)) + if (test_bit(KVM_APIC_SIPI, &pe)) clear_bit(KVM_APIC_SIPI, &apic->pending_events); return; } - pe = xchg(&apic->pending_events, 0); if (test_bit(KVM_APIC_INIT, &pe)) { + clear_bit(KVM_APIC_INIT, &apic->pending_events); kvm_vcpu_reset(vcpu, true); if (kvm_vcpu_is_bsp(apic->vcpu)) vcpu->arch.mp_state = KVM_MP_STATE_RUNNABLE; else vcpu->arch.mp_state = KVM_MP_STATE_INIT_RECEIVED; } - if (test_bit(KVM_APIC_SIPI, &pe) && - vcpu->arch.mp_state == KVM_MP_STATE_INIT_RECEIVED) { - /* evaluate pending_events before reading the vector */ - smp_rmb(); - sipi_vector = apic->sipi_vector; - kvm_vcpu_deliver_sipi_vector(vcpu, sipi_vector); - vcpu->arch.mp_state = KVM_MP_STATE_RUNNABLE; + if (test_bit(KVM_APIC_SIPI, &pe)) { + clear_bit(KVM_APIC_SIPI, &apic->pending_events); + if (vcpu->arch.mp_state == KVM_MP_STATE_INIT_RECEIVED) { + /* evaluate pending_events before reading the vector */ + smp_rmb(); + sipi_vector = apic->sipi_vector; + kvm_vcpu_deliver_sipi_vector(vcpu, sipi_vector); + vcpu->arch.mp_state = KVM_MP_STATE_RUNNABLE; + } } } diff --git a/arch/x86/kvm/mmu/mmu.c b/arch/x86/kvm/mmu/mmu.c index 7a6ae9e90bd7..c478904af518 100644 --- a/arch/x86/kvm/mmu/mmu.c +++ b/arch/x86/kvm/mmu/mmu.c @@ -820,7 +820,7 @@ gfn_to_memslot_dirty_bitmap(struct kvm_vcpu *vcpu, gfn_t gfn, slot = kvm_vcpu_gfn_to_memslot(vcpu, gfn); if (!slot || slot->flags & KVM_MEMSLOT_INVALID) return NULL; - if (no_dirty_log && slot->dirty_bitmap) + if (no_dirty_log && kvm_slot_dirty_track_enabled(slot)) return NULL; return slot; @@ -1289,6 +1289,14 @@ void kvm_arch_mmu_enable_log_dirty_pt_masked(struct kvm *kvm, kvm_mmu_write_protect_pt_masked(kvm, slot, gfn_offset, mask); } +int kvm_cpu_dirty_log_size(void) +{ + if (kvm_x86_ops.cpu_dirty_log_size) + return kvm_x86_ops.cpu_dirty_log_size(); + + return 0; +} + bool kvm_mmu_slot_gfn_write_protect(struct kvm *kvm, struct kvm_memory_slot *slot, u64 gfn) { diff --git a/arch/x86/kvm/mmu/mmutrace.h b/arch/x86/kvm/mmu/mmutrace.h index 213699b27b44..e798489b56b5 100644 --- a/arch/x86/kvm/mmu/mmutrace.h +++ b/arch/x86/kvm/mmu/mmutrace.h @@ -381,6 +381,35 @@ TRACE_EVENT( ) ); +TRACE_EVENT( + kvm_tdp_mmu_spte_changed, + TP_PROTO(int as_id, gfn_t gfn, int level, u64 old_spte, u64 new_spte), + TP_ARGS(as_id, gfn, level, old_spte, new_spte), + + TP_STRUCT__entry( + __field(u64, gfn) + __field(u64, old_spte) + __field(u64, new_spte) + /* Level cannot be larger than 5 on x86, so it fits in a u8. */ + __field(u8, level) + /* as_id can only be 0 or 1 x86, so it fits in a u8. */ + __field(u8, as_id) + ), + + TP_fast_assign( + __entry->gfn = gfn; + __entry->old_spte = old_spte; + __entry->new_spte = new_spte; + __entry->level = level; + __entry->as_id = as_id; + ), + + TP_printk("as id %d gfn %llx level %d old_spte %llx new_spte %llx", + __entry->as_id, __entry->gfn, __entry->level, + __entry->old_spte, __entry->new_spte + ) +); + #endif /* _TRACE_KVMMMU_H */ #undef TRACE_INCLUDE_PATH diff --git a/arch/x86/kvm/mmu/tdp_mmu.c b/arch/x86/kvm/mmu/tdp_mmu.c index 84c8f06bec26..4bd2f1dc0172 100644 --- a/arch/x86/kvm/mmu/tdp_mmu.c +++ b/arch/x86/kvm/mmu/tdp_mmu.c @@ -7,6 +7,8 @@ #include "tdp_mmu.h" #include "spte.h" +#include <trace/events/kvm.h> + #ifdef CONFIG_X86_64 static bool __read_mostly tdp_mmu_enabled = false; module_param_named(tdp_mmu, tdp_mmu_enabled, bool, 0644); @@ -108,6 +110,8 @@ static struct kvm_mmu_page *alloc_tdp_mmu_page(struct kvm_vcpu *vcpu, gfn_t gfn, sp->gfn = gfn; sp->tdp_mmu_page = true; + trace_kvm_mmu_get_page(sp, true); + return sp; } @@ -185,7 +189,7 @@ static void handle_changed_spte_dirty_log(struct kvm *kvm, int as_id, gfn_t gfn, if ((!is_writable_pte(old_spte) || pfn_changed) && is_writable_pte(new_spte)) { slot = __gfn_to_memslot(__kvm_memslots(kvm, as_id), gfn); - mark_page_dirty_in_slot(slot, gfn); + mark_page_dirty_in_slot(kvm, slot, gfn); } } @@ -244,6 +248,8 @@ static void __handle_changed_spte(struct kvm *kvm, int as_id, gfn_t gfn, if (old_spte == new_spte) return; + trace_kvm_tdp_mmu_spte_changed(as_id, gfn, level, old_spte, new_spte); + /* * The only times a SPTE should be changed from a non-present to * non-present state is when an MMIO entry is installed/modified/ @@ -278,6 +284,8 @@ static void __handle_changed_spte(struct kvm *kvm, int as_id, gfn_t gfn, pt = spte_to_child_pt(old_spte, level); sp = sptep_to_sp(pt); + trace_kvm_mmu_prepare_zap_page(sp); + list_del(&sp->link); if (sp->lpage_disallowed) @@ -480,11 +488,13 @@ static int tdp_mmu_map_handle_target_level(struct kvm_vcpu *vcpu, int write, if (unlikely(is_noslot_pfn(pfn))) { new_spte = make_mmio_spte(vcpu, iter->gfn, ACC_ALL); trace_mark_mmio_spte(iter->sptep, iter->gfn, new_spte); - } else + } else { make_spte_ret = make_spte(vcpu, ACC_ALL, iter->level, iter->gfn, pfn, iter->old_spte, prefault, true, map_writable, !shadow_accessed_mask, &new_spte); + trace_kvm_mmu_set_spte(iter->level, iter->gfn, iter->sptep); + } if (new_spte == iter->old_spte) ret = RET_PF_SPURIOUS; @@ -698,6 +708,8 @@ static int age_gfn_range(struct kvm *kvm, struct kvm_memory_slot *slot, tdp_mmu_set_spte_no_acc_track(kvm, &iter, new_spte); young = 1; + + trace_kvm_age_page(iter.gfn, iter.level, slot, young); } return young; diff --git a/arch/x86/kvm/mtrr.c b/arch/x86/kvm/mtrr.c index 7f0059aa30e1..f472fdb6ae7e 100644 --- a/arch/x86/kvm/mtrr.c +++ b/arch/x86/kvm/mtrr.c @@ -84,12 +84,8 @@ bool kvm_mtrr_valid(struct kvm_vcpu *vcpu, u32 msr, u64 data) } else /* MTRR mask */ mask |= 0x7ff; - if (data & mask) { - kvm_inject_gp(vcpu, 0); - return false; - } - return true; + return (data & mask) == 0; } EXPORT_SYMBOL_GPL(kvm_mtrr_valid); diff --git a/arch/x86/kvm/svm/avic.c b/arch/x86/kvm/svm/avic.c index 8c550999ace0..0ef84d57b72e 100644 --- a/arch/x86/kvm/svm/avic.c +++ b/arch/x86/kvm/svm/avic.c @@ -233,7 +233,8 @@ static u64 *avic_get_physical_id_entry(struct kvm_vcpu *vcpu, */ static int avic_update_access_page(struct kvm *kvm, bool activate) { - int ret = 0; + void __user *ret; + int r = 0; mutex_lock(&kvm->slots_lock); /* @@ -249,13 +250,15 @@ static int avic_update_access_page(struct kvm *kvm, bool activate) APIC_ACCESS_PAGE_PRIVATE_MEMSLOT, APIC_DEFAULT_PHYS_BASE, activate ? PAGE_SIZE : 0); - if (ret) + if (IS_ERR(ret)) { + r = PTR_ERR(ret); goto out; + } kvm->arch.apic_access_page_done = activate; out: mutex_unlock(&kvm->slots_lock); - return ret; + return r; } static int avic_init_backing_page(struct kvm_vcpu *vcpu) diff --git a/arch/x86/kvm/svm/nested.c b/arch/x86/kvm/svm/nested.c index 9e4c226dbf7d..b0b667456b2e 100644 --- a/arch/x86/kvm/svm/nested.c +++ b/arch/x86/kvm/svm/nested.c @@ -254,7 +254,7 @@ static bool nested_vmcb_checks(struct vcpu_svm *svm, struct vmcb *vmcb12) (vmcb12->save.cr3 & MSR_CR3_LONG_MBZ_MASK)) return false; } - if (kvm_valid_cr4(&svm->vcpu, vmcb12->save.cr4)) + if (!kvm_is_valid_cr4(&svm->vcpu, vmcb12->save.cr4)) return false; return nested_vmcb_check_controls(&vmcb12->control); @@ -381,7 +381,7 @@ static void nested_prepare_vmcb_save(struct vcpu_svm *svm, struct vmcb *vmcb12) svm->vmcb->save.ds = vmcb12->save.ds; svm->vmcb->save.gdtr = vmcb12->save.gdtr; svm->vmcb->save.idtr = vmcb12->save.idtr; - kvm_set_rflags(&svm->vcpu, vmcb12->save.rflags); + kvm_set_rflags(&svm->vcpu, vmcb12->save.rflags | X86_EFLAGS_FIXED); svm_set_efer(&svm->vcpu, vmcb12->save.efer); svm_set_cr0(&svm->vcpu, vmcb12->save.cr0); svm_set_cr4(&svm->vcpu, vmcb12->save.cr4); @@ -394,8 +394,8 @@ static void nested_prepare_vmcb_save(struct vcpu_svm *svm, struct vmcb *vmcb12) svm->vmcb->save.rax = vmcb12->save.rax; svm->vmcb->save.rsp = vmcb12->save.rsp; svm->vmcb->save.rip = vmcb12->save.rip; - svm->vmcb->save.dr7 = vmcb12->save.dr7; - svm->vcpu.arch.dr6 = vmcb12->save.dr6; + svm->vmcb->save.dr7 = vmcb12->save.dr7 | DR7_FIXED_1; + svm->vcpu.arch.dr6 = vmcb12->save.dr6 | DR6_FIXED_1 | DR6_RTM; svm->vmcb->save.cpl = vmcb12->save.cpl; } @@ -660,13 +660,14 @@ int nested_svm_vmexit(struct vcpu_svm *svm) svm->vmcb->save.gdtr = hsave->save.gdtr; svm->vmcb->save.idtr = hsave->save.idtr; kvm_set_rflags(&svm->vcpu, hsave->save.rflags); + kvm_set_rflags(&svm->vcpu, hsave->save.rflags | X86_EFLAGS_FIXED); svm_set_efer(&svm->vcpu, hsave->save.efer); svm_set_cr0(&svm->vcpu, hsave->save.cr0 | X86_CR0_PE); svm_set_cr4(&svm->vcpu, hsave->save.cr4); kvm_rax_write(&svm->vcpu, hsave->save.rax); kvm_rsp_write(&svm->vcpu, hsave->save.rsp); kvm_rip_write(&svm->vcpu, hsave->save.rip); - svm->vmcb->save.dr7 = 0; + svm->vmcb->save.dr7 = DR7_FIXED_1; svm->vmcb->save.cpl = 0; svm->vmcb->control.exit_int_info = 0; diff --git a/arch/x86/kvm/svm/sev.c b/arch/x86/kvm/svm/sev.c index 566f4d18185b..9858d5ae9ddd 100644 --- a/arch/x86/kvm/svm/sev.c +++ b/arch/x86/kvm/svm/sev.c @@ -14,10 +14,20 @@ #include <linux/psp-sev.h> #include <linux/pagemap.h> #include <linux/swap.h> +#include <linux/processor.h> +#include <linux/trace_events.h> +#include <asm/fpu/internal.h> + +#include <asm/trapnr.h> #include "x86.h" #include "svm.h" +#include "cpuid.h" +#include "trace.h" + +#define __ex(x) __kvm_handle_fault_on_reboot(x) +static u8 sev_enc_bit; static int sev_flush_asids(void); static DECLARE_RWSEM(sev_deactivate_lock); static DEFINE_MUTEX(sev_bitmap_lock); @@ -25,7 +35,6 @@ unsigned int max_sev_asid; static unsigned int min_sev_asid; static unsigned long *sev_asid_bitmap; static unsigned long *sev_reclaim_asid_bitmap; -#define __sme_page_pa(x) __sme_set(page_to_pfn(x) << PAGE_SHIFT) struct enc_region { struct list_head list; @@ -57,19 +66,19 @@ static int sev_flush_asids(void) } /* Must be called with the sev_bitmap_lock held */ -static bool __sev_recycle_asids(void) +static bool __sev_recycle_asids(int min_asid, int max_asid) { int pos; /* Check if there are any ASIDs to reclaim before performing a flush */ - pos = find_next_bit(sev_reclaim_asid_bitmap, - max_sev_asid, min_sev_asid - 1); - if (pos >= max_sev_asid) + pos = find_next_bit(sev_reclaim_asid_bitmap, max_sev_asid, min_asid); + if (pos >= max_asid) return false; if (sev_flush_asids()) return false; + /* 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); @@ -77,20 +86,23 @@ static bool __sev_recycle_asids(void) return true; } -static int sev_asid_new(void) +static int sev_asid_new(struct kvm_sev_info *sev) { + int pos, min_asid, max_asid; bool retry = true; - int pos; mutex_lock(&sev_bitmap_lock); /* - * SEV-enabled guest must use asid from min_sev_asid to max_sev_asid. + * 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; + 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_sev_asid - 1); - if (pos >= max_sev_asid) { - if (retry && __sev_recycle_asids()) { + pos = find_next_zero_bit(sev_asid_bitmap, max_sev_asid, min_asid); + if (pos >= max_asid) { + if (retry && __sev_recycle_asids(min_asid, max_asid)) { retry = false; goto again; } @@ -172,7 +184,7 @@ static int sev_guest_init(struct kvm *kvm, struct kvm_sev_cmd *argp) if (unlikely(sev->active)) return ret; - asid = sev_asid_new(); + asid = sev_asid_new(sev); if (asid < 0) return ret; @@ -191,6 +203,16 @@ e_free: return ret; } +static int sev_es_guest_init(struct kvm *kvm, struct kvm_sev_cmd *argp) +{ + if (!sev_es) + return -ENOTTY; + + to_kvm_svm(kvm)->sev_info.es_active = true; + + return sev_guest_init(kvm, argp); +} + static int sev_bind_asid(struct kvm *kvm, unsigned int handle, int *error) { struct sev_data_activate *data; @@ -490,6 +512,96 @@ e_free: return ret; } +static int sev_es_sync_vmsa(struct vcpu_svm *svm) +{ + struct vmcb_save_area *save = &svm->vmcb->save; + + /* Check some debug related fields before encrypting the VMSA */ + if (svm->vcpu.guest_debug || (save->dr7 & ~DR7_FIXED_1)) + return -EINVAL; + + /* Sync registgers */ + save->rax = svm->vcpu.arch.regs[VCPU_REGS_RAX]; + save->rbx = svm->vcpu.arch.regs[VCPU_REGS_RBX]; + save->rcx = svm->vcpu.arch.regs[VCPU_REGS_RCX]; + save->rdx = svm->vcpu.arch.regs[VCPU_REGS_RDX]; + save->rsp = svm->vcpu.arch.regs[VCPU_REGS_RSP]; + save->rbp = svm->vcpu.arch.regs[VCPU_REGS_RBP]; + save->rsi = svm->vcpu.arch.regs[VCPU_REGS_RSI]; + save->rdi = svm->vcpu.arch.regs[VCPU_REGS_RDI]; +#ifdef CONFIG_X86_64 + save->r8 = svm->vcpu.arch.regs[VCPU_REGS_R8]; + save->r9 = svm->vcpu.arch.regs[VCPU_REGS_R9]; + save->r10 = svm->vcpu.arch.regs[VCPU_REGS_R10]; + save->r11 = svm->vcpu.arch.regs[VCPU_REGS_R11]; + save->r12 = svm->vcpu.arch.regs[VCPU_REGS_R12]; + save->r13 = svm->vcpu.arch.regs[VCPU_REGS_R13]; + save->r14 = svm->vcpu.arch.regs[VCPU_REGS_R14]; + save->r15 = svm->vcpu.arch.regs[VCPU_REGS_R15]; +#endif + save->rip = svm->vcpu.arch.regs[VCPU_REGS_RIP]; + + /* Sync some non-GPR registers before encrypting */ + save->xcr0 = svm->vcpu.arch.xcr0; + save->pkru = svm->vcpu.arch.pkru; + save->xss = svm->vcpu.arch.ia32_xss; + + /* + * SEV-ES will use a VMSA that is pointed to by the VMCB, not + * the traditional VMSA that is part of the VMCB. Copy the + * traditional VMSA as it has been built so far (in prep + * for LAUNCH_UPDATE_VMSA) to be the initial SEV-ES state. + */ + memcpy(svm->vmsa, save, sizeof(*save)); + + return 0; +} + +static int sev_launch_update_vmsa(struct kvm *kvm, struct kvm_sev_cmd *argp) +{ + struct kvm_sev_info *sev = &to_kvm_svm(kvm)->sev_info; + struct sev_data_launch_update_vmsa *vmsa; + int i, ret; + + if (!sev_es_guest(kvm)) + return -ENOTTY; + + vmsa = kzalloc(sizeof(*vmsa), GFP_KERNEL); + if (!vmsa) + return -ENOMEM; + + for (i = 0; i < kvm->created_vcpus; i++) { + struct vcpu_svm *svm = to_svm(kvm->vcpus[i]); + + /* Perform some pre-encryption checks against the VMSA */ + ret = sev_es_sync_vmsa(svm); + if (ret) + goto e_free; + + /* + * The LAUNCH_UPDATE_VMSA command will perform in-place + * encryption of the VMSA memory content (i.e it will write + * the same memory region with the guest's key), so invalidate + * it first. + */ + clflush_cache_range(svm->vmsa, PAGE_SIZE); + + vmsa->handle = sev->handle; + vmsa->address = __sme_pa(svm->vmsa); + vmsa->len = PAGE_SIZE; + ret = sev_issue_cmd(kvm, SEV_CMD_LAUNCH_UPDATE_VMSA, vmsa, + &argp->error); + if (ret) + goto e_free; + + svm->vcpu.arch.guest_state_protected = true; + } + +e_free: + kfree(vmsa); + return ret; +} + static int sev_launch_measure(struct kvm *kvm, struct kvm_sev_cmd *argp) { void __user *measure = (void __user *)(uintptr_t)argp->data; @@ -932,7 +1044,7 @@ int svm_mem_enc_op(struct kvm *kvm, void __user *argp) struct kvm_sev_cmd sev_cmd; int r; - if (!svm_sev_enabled()) + if (!svm_sev_enabled() || !sev) return -ENOTTY; if (!argp) @@ -947,12 +1059,18 @@ int svm_mem_enc_op(struct kvm *kvm, void __user *argp) case KVM_SEV_INIT: r = sev_guest_init(kvm, &sev_cmd); break; + case KVM_SEV_ES_INIT: + r = sev_es_guest_init(kvm, &sev_cmd); + break; case KVM_SEV_LAUNCH_START: r = sev_launch_start(kvm, &sev_cmd); break; case KVM_SEV_LAUNCH_UPDATE_DATA: r = sev_launch_update_data(kvm, &sev_cmd); break; + case KVM_SEV_LAUNCH_UPDATE_VMSA: + r = sev_launch_update_vmsa(kvm, &sev_cmd); + break; case KVM_SEV_LAUNCH_MEASURE: r = sev_launch_measure(kvm, &sev_cmd); break; @@ -1125,49 +1243,61 @@ void sev_vm_destroy(struct kvm *kvm) sev_asid_free(sev->asid); } -int __init sev_hardware_setup(void) +void __init sev_hardware_setup(void) { - struct sev_user_data_status *status; - int rc; + unsigned int eax, ebx, ecx, edx; + bool sev_es_supported = false; + bool sev_supported = false; + + /* Does the CPU support SEV? */ + if (!boot_cpu_has(X86_FEATURE_SEV)) + goto out; + + /* Retrieve SEV CPUID information */ + cpuid(0x8000001f, &eax, &ebx, &ecx, &edx); + + /* Set encryption bit location for SEV-ES guests */ + sev_enc_bit = ebx & 0x3f; /* Maximum number of encrypted guests supported simultaneously */ - max_sev_asid = cpuid_ecx(0x8000001F); + max_sev_asid = ecx; if (!svm_sev_enabled()) - return 1; + goto out; /* Minimum ASID value that should be used for SEV guest */ - min_sev_asid = cpuid_edx(0x8000001F); + min_sev_asid = edx; /* Initialize SEV ASID bitmaps */ sev_asid_bitmap = bitmap_zalloc(max_sev_asid, GFP_KERNEL); if (!sev_asid_bitmap) - return 1; + goto out; sev_reclaim_asid_bitmap = bitmap_zalloc(max_sev_asid, GFP_KERNEL); if (!sev_reclaim_asid_bitmap) - return 1; + goto out; - status = kmalloc(sizeof(*status), GFP_KERNEL); - if (!status) - return 1; + pr_info("SEV supported: %u ASIDs\n", max_sev_asid - min_sev_asid + 1); + sev_supported = true; - /* - * Check SEV platform status. - * - * PLATFORM_STATUS can be called in any state, if we failed to query - * the PLATFORM status then either PSP firmware does not support SEV - * feature or SEV firmware is dead. - */ - rc = sev_platform_status(status, NULL); - if (rc) - goto err; + /* SEV-ES support requested? */ + if (!sev_es) + goto out; - pr_info("SEV supported\n"); + /* Does the CPU support SEV-ES? */ + if (!boot_cpu_has(X86_FEATURE_SEV_ES)) + goto out; -err: - kfree(status); - return rc; + /* Has the system been allocated ASIDs for SEV-ES? */ + if (min_sev_asid == 1) + goto out; + + pr_info("SEV-ES supported: %u ASIDs\n", min_sev_asid - 1); + sev_es_supported = true; + +out: + sev = sev_supported; + sev_es = sev_es_supported; } void sev_hardware_teardown(void) @@ -1181,13 +1311,329 @@ void sev_hardware_teardown(void) sev_flush_asids(); } +/* + * Pages used by hardware to hold guest encrypted state must be flushed before + * returning them to the system. + */ +static void sev_flush_guest_memory(struct vcpu_svm *svm, void *va, + unsigned long len) +{ + /* + * If hardware enforced cache coherency for encrypted mappings of the + * same physical page is supported, nothing to do. + */ + if (boot_cpu_has(X86_FEATURE_SME_COHERENT)) + return; + + /* + * If the VM Page Flush MSR is supported, use it to flush the page + * (using the page virtual address and the guest ASID). + */ + if (boot_cpu_has(X86_FEATURE_VM_PAGE_FLUSH)) { + struct kvm_sev_info *sev; + unsigned long va_start; + u64 start, stop; + + /* Align start and stop to page boundaries. */ + va_start = (unsigned long)va; + start = (u64)va_start & PAGE_MASK; + stop = PAGE_ALIGN((u64)va_start + len); + + if (start < stop) { + sev = &to_kvm_svm(svm->vcpu.kvm)->sev_info; + + while (start < stop) { + wrmsrl(MSR_AMD64_VM_PAGE_FLUSH, + start | sev->asid); + + start += PAGE_SIZE; + } + + return; + } + + WARN(1, "Address overflow, using WBINVD\n"); + } + + /* + * Hardware should always have one of the above features, + * but if not, use WBINVD and issue a warning. + */ + WARN_ONCE(1, "Using WBINVD to flush guest memory\n"); + wbinvd_on_all_cpus(); +} + +void sev_free_vcpu(struct kvm_vcpu *vcpu) +{ + struct vcpu_svm *svm; + + if (!sev_es_guest(vcpu->kvm)) + return; + + svm = to_svm(vcpu); + + if (vcpu->arch.guest_state_protected) + sev_flush_guest_memory(svm, svm->vmsa, PAGE_SIZE); + __free_page(virt_to_page(svm->vmsa)); + + if (svm->ghcb_sa_free) + kfree(svm->ghcb_sa); +} + +static void dump_ghcb(struct vcpu_svm *svm) +{ + struct ghcb *ghcb = svm->ghcb; + unsigned int nbits; + + /* Re-use the dump_invalid_vmcb module parameter */ + if (!dump_invalid_vmcb) { + pr_warn_ratelimited("set kvm_amd.dump_invalid_vmcb=1 to dump internal KVM state.\n"); + return; + } + + nbits = sizeof(ghcb->save.valid_bitmap) * 8; + + pr_err("GHCB (GPA=%016llx):\n", svm->vmcb->control.ghcb_gpa); + pr_err("%-20s%016llx is_valid: %u\n", "sw_exit_code", + ghcb->save.sw_exit_code, ghcb_sw_exit_code_is_valid(ghcb)); + pr_err("%-20s%016llx is_valid: %u\n", "sw_exit_info_1", + ghcb->save.sw_exit_info_1, ghcb_sw_exit_info_1_is_valid(ghcb)); + pr_err("%-20s%016llx is_valid: %u\n", "sw_exit_info_2", + ghcb->save.sw_exit_info_2, ghcb_sw_exit_info_2_is_valid(ghcb)); + pr_err("%-20s%016llx is_valid: %u\n", "sw_scratch", + ghcb->save.sw_scratch, ghcb_sw_scratch_is_valid(ghcb)); + pr_err("%-20s%*pb\n", "valid_bitmap", nbits, ghcb->save.valid_bitmap); +} + +static void sev_es_sync_to_ghcb(struct vcpu_svm *svm) +{ + struct kvm_vcpu *vcpu = &svm->vcpu; + struct ghcb *ghcb = svm->ghcb; + + /* + * The GHCB protocol so far allows for the following data + * to be returned: + * GPRs RAX, RBX, RCX, RDX + * + * Copy their values to the GHCB if they are dirty. + */ + if (kvm_register_is_dirty(vcpu, VCPU_REGS_RAX)) + ghcb_set_rax(ghcb, vcpu->arch.regs[VCPU_REGS_RAX]); + if (kvm_register_is_dirty(vcpu, VCPU_REGS_RBX)) + ghcb_set_rbx(ghcb, vcpu->arch.regs[VCPU_REGS_RBX]); + if (kvm_register_is_dirty(vcpu, VCPU_REGS_RCX)) + ghcb_set_rcx(ghcb, vcpu->arch.regs[VCPU_REGS_RCX]); + if (kvm_register_is_dirty(vcpu, VCPU_REGS_RDX)) + ghcb_set_rdx(ghcb, vcpu->arch.regs[VCPU_REGS_RDX]); +} + +static void sev_es_sync_from_ghcb(struct vcpu_svm *svm) +{ + struct vmcb_control_area *control = &svm->vmcb->control; + struct kvm_vcpu *vcpu = &svm->vcpu; + struct ghcb *ghcb = svm->ghcb; + u64 exit_code; + + /* + * The GHCB protocol so far allows for the following data + * to be supplied: + * GPRs RAX, RBX, RCX, RDX + * XCR0 + * CPL + * + * VMMCALL allows the guest to provide extra registers. KVM also + * expects RSI for hypercalls, so include that, too. + * + * Copy their values to the appropriate location if supplied. + */ + memset(vcpu->arch.regs, 0, sizeof(vcpu->arch.regs)); + + vcpu->arch.regs[VCPU_REGS_RAX] = ghcb_get_rax_if_valid(ghcb); + vcpu->arch.regs[VCPU_REGS_RBX] = ghcb_get_rbx_if_valid(ghcb); + vcpu->arch.regs[VCPU_REGS_RCX] = ghcb_get_rcx_if_valid(ghcb); + vcpu->arch.regs[VCPU_REGS_RDX] = ghcb_get_rdx_if_valid(ghcb); + vcpu->arch.regs[VCPU_REGS_RSI] = ghcb_get_rsi_if_valid(ghcb); + + svm->vmcb->save.cpl = ghcb_get_cpl_if_valid(ghcb); + + if (ghcb_xcr0_is_valid(ghcb)) { + vcpu->arch.xcr0 = ghcb_get_xcr0(ghcb); + kvm_update_cpuid_runtime(vcpu); + } + + /* Copy the GHCB exit information into the VMCB fields */ + exit_code = ghcb_get_sw_exit_code(ghcb); + control->exit_code = lower_32_bits(exit_code); + control->exit_code_hi = upper_32_bits(exit_code); + control->exit_info_1 = ghcb_get_sw_exit_info_1(ghcb); + control->exit_info_2 = ghcb_get_sw_exit_info_2(ghcb); + + /* Clear the valid entries fields */ + memset(ghcb->save.valid_bitmap, 0, sizeof(ghcb->save.valid_bitmap)); +} + +static int sev_es_validate_vmgexit(struct vcpu_svm *svm) +{ + struct kvm_vcpu *vcpu; + struct ghcb *ghcb; + u64 exit_code = 0; + + ghcb = svm->ghcb; + + /* Only GHCB Usage code 0 is supported */ + if (ghcb->ghcb_usage) + goto vmgexit_err; + + /* + * Retrieve the exit code now even though is may not be marked valid + * as it could help with debugging. + */ + exit_code = ghcb_get_sw_exit_code(ghcb); + + if (!ghcb_sw_exit_code_is_valid(ghcb) || + !ghcb_sw_exit_info_1_is_valid(ghcb) || + !ghcb_sw_exit_info_2_is_valid(ghcb)) + goto vmgexit_err; + + switch (ghcb_get_sw_exit_code(ghcb)) { + case SVM_EXIT_READ_DR7: + break; + case SVM_EXIT_WRITE_DR7: + if (!ghcb_rax_is_valid(ghcb)) + goto vmgexit_err; + break; + case SVM_EXIT_RDTSC: + break; + case SVM_EXIT_RDPMC: + if (!ghcb_rcx_is_valid(ghcb)) + goto vmgexit_err; + break; + case SVM_EXIT_CPUID: + if (!ghcb_rax_is_valid(ghcb) || + !ghcb_rcx_is_valid(ghcb)) + goto vmgexit_err; + if (ghcb_get_rax(ghcb) == 0xd) + if (!ghcb_xcr0_is_valid(ghcb)) + goto vmgexit_err; + break; + case SVM_EXIT_INVD: + break; + case SVM_EXIT_IOIO: + if (ghcb_get_sw_exit_info_1(ghcb) & SVM_IOIO_STR_MASK) { + if (!ghcb_sw_scratch_is_valid(ghcb)) + goto vmgexit_err; + } else { + if (!(ghcb_get_sw_exit_info_1(ghcb) & SVM_IOIO_TYPE_MASK)) + if (!ghcb_rax_is_valid(ghcb)) + goto vmgexit_err; + } + break; + case SVM_EXIT_MSR: + if (!ghcb_rcx_is_valid(ghcb)) + goto vmgexit_err; + if (ghcb_get_sw_exit_info_1(ghcb)) { + if (!ghcb_rax_is_valid(ghcb) || + !ghcb_rdx_is_valid(ghcb)) + goto vmgexit_err; + } + break; + case SVM_EXIT_VMMCALL: + if (!ghcb_rax_is_valid(ghcb) || + !ghcb_cpl_is_valid(ghcb)) + goto vmgexit_err; + break; + case SVM_EXIT_RDTSCP: + break; + case SVM_EXIT_WBINVD: + break; + case SVM_EXIT_MONITOR: + if (!ghcb_rax_is_valid(ghcb) || + !ghcb_rcx_is_valid(ghcb) || + !ghcb_rdx_is_valid(ghcb)) + goto vmgexit_err; + break; + case SVM_EXIT_MWAIT: + if (!ghcb_rax_is_valid(ghcb) || + !ghcb_rcx_is_valid(ghcb)) + goto vmgexit_err; + break; + case SVM_VMGEXIT_MMIO_READ: + case SVM_VMGEXIT_MMIO_WRITE: + if (!ghcb_sw_scratch_is_valid(ghcb)) + goto vmgexit_err; + break; + case SVM_VMGEXIT_NMI_COMPLETE: + case SVM_VMGEXIT_AP_JUMP_TABLE: + case SVM_VMGEXIT_UNSUPPORTED_EVENT: + break; + default: + goto vmgexit_err; + } + + return 0; + +vmgexit_err: + vcpu = &svm->vcpu; + + if (ghcb->ghcb_usage) { + vcpu_unimpl(vcpu, "vmgexit: ghcb usage %#x is not valid\n", + ghcb->ghcb_usage); + } else { + vcpu_unimpl(vcpu, "vmgexit: exit reason %#llx is not valid\n", + exit_code); + dump_ghcb(svm); + } + + vcpu->run->exit_reason = KVM_EXIT_INTERNAL_ERROR; + vcpu->run->internal.suberror = KVM_INTERNAL_ERROR_UNEXPECTED_EXIT_REASON; + vcpu->run->internal.ndata = 2; + vcpu->run->internal.data[0] = exit_code; + vcpu->run->internal.data[1] = vcpu->arch.last_vmentry_cpu; + + return -EINVAL; +} + +static void pre_sev_es_run(struct vcpu_svm *svm) +{ + if (!svm->ghcb) + return; + + if (svm->ghcb_sa_free) { + /* + * The scratch area lives outside the GHCB, so there is a + * buffer that, depending on the operation performed, may + * need to be synced, then freed. + */ + if (svm->ghcb_sa_sync) { + kvm_write_guest(svm->vcpu.kvm, + ghcb_get_sw_scratch(svm->ghcb), + svm->ghcb_sa, svm->ghcb_sa_len); + svm->ghcb_sa_sync = false; + } + + kfree(svm->ghcb_sa); + svm->ghcb_sa = NULL; + svm->ghcb_sa_free = false; + } + + trace_kvm_vmgexit_exit(svm->vcpu.vcpu_id, svm->ghcb); + + sev_es_sync_to_ghcb(svm); + + kvm_vcpu_unmap(&svm->vcpu, &svm->ghcb_map, true); + svm->ghcb = NULL; +} + void pre_sev_run(struct vcpu_svm *svm, int cpu) { struct svm_cpu_data *sd = per_cpu(svm_data, cpu); int asid = sev_get_asid(svm->vcpu.kvm); + /* Perform any SEV-ES pre-run actions */ + pre_sev_es_run(svm); + /* Assign the asid allocated with this SEV guest */ - svm->vmcb->control.asid = asid; + svm->asid = asid; /* * Flush guest TLB: @@ -1203,3 +1649,394 @@ void pre_sev_run(struct vcpu_svm *svm, int cpu) svm->vmcb->control.tlb_ctl = TLB_CONTROL_FLUSH_ASID; vmcb_mark_dirty(svm->vmcb, VMCB_ASID); } + +#define GHCB_SCRATCH_AREA_LIMIT (16ULL * PAGE_SIZE) +static bool setup_vmgexit_scratch(struct vcpu_svm *svm, bool sync, u64 len) +{ + struct vmcb_control_area *control = &svm->vmcb->control; + struct ghcb *ghcb = svm->ghcb; + u64 ghcb_scratch_beg, ghcb_scratch_end; + u64 scratch_gpa_beg, scratch_gpa_end; + void *scratch_va; + + scratch_gpa_beg = ghcb_get_sw_scratch(ghcb); + if (!scratch_gpa_beg) { + pr_err("vmgexit: scratch gpa not provided\n"); + return false; + } + + scratch_gpa_end = scratch_gpa_beg + len; + if (scratch_gpa_end < scratch_gpa_beg) { + pr_err("vmgexit: scratch length (%#llx) not valid for scratch address (%#llx)\n", + len, scratch_gpa_beg); + return false; + } + + if ((scratch_gpa_beg & PAGE_MASK) == control->ghcb_gpa) { + /* Scratch area begins within GHCB */ + ghcb_scratch_beg = control->ghcb_gpa + + offsetof(struct ghcb, shared_buffer); + ghcb_scratch_end = control->ghcb_gpa + + offsetof(struct ghcb, reserved_1); + + /* + * If the scratch area begins within the GHCB, it must be + * completely contained in the GHCB shared buffer area. + */ + if (scratch_gpa_beg < ghcb_scratch_beg || + scratch_gpa_end > ghcb_scratch_end) { + pr_err("vmgexit: scratch area is outside of GHCB shared buffer area (%#llx - %#llx)\n", + scratch_gpa_beg, scratch_gpa_end); + return false; + } + + scratch_va = (void *)svm->ghcb; + scratch_va += (scratch_gpa_beg - control->ghcb_gpa); + } else { + /* + * The guest memory must be read into a kernel buffer, so + * limit the size + */ + if (len > GHCB_SCRATCH_AREA_LIMIT) { + pr_err("vmgexit: scratch area exceeds KVM limits (%#llx requested, %#llx limit)\n", + len, GHCB_SCRATCH_AREA_LIMIT); + return false; + } + scratch_va = kzalloc(len, GFP_KERNEL); + if (!scratch_va) + return false; + + if (kvm_read_guest(svm->vcpu.kvm, scratch_gpa_beg, scratch_va, len)) { + /* Unable to copy scratch area from guest */ + pr_err("vmgexit: kvm_read_guest for scratch area failed\n"); + + kfree(scratch_va); + return false; + } + + /* + * The scratch area is outside the GHCB. The operation will + * dictate whether the buffer needs to be synced before running + * the vCPU next time (i.e. a read was requested so the data + * must be written back to the guest memory). + */ + svm->ghcb_sa_sync = sync; + svm->ghcb_sa_free = true; + } + + svm->ghcb_sa = scratch_va; + svm->ghcb_sa_len = len; + + return true; +} + +static void set_ghcb_msr_bits(struct vcpu_svm *svm, u64 value, u64 mask, + unsigned int pos) +{ + svm->vmcb->control.ghcb_gpa &= ~(mask << pos); + svm->vmcb->control.ghcb_gpa |= (value & mask) << pos; +} + +static u64 get_ghcb_msr_bits(struct vcpu_svm *svm, u64 mask, unsigned int pos) +{ + return (svm->vmcb->control.ghcb_gpa >> pos) & mask; +} + +static void set_ghcb_msr(struct vcpu_svm *svm, u64 value) +{ + svm->vmcb->control.ghcb_gpa = value; +} + +static int sev_handle_vmgexit_msr_protocol(struct vcpu_svm *svm) +{ + struct vmcb_control_area *control = &svm->vmcb->control; + struct kvm_vcpu *vcpu = &svm->vcpu; + u64 ghcb_info; + int ret = 1; + + ghcb_info = control->ghcb_gpa & GHCB_MSR_INFO_MASK; + + trace_kvm_vmgexit_msr_protocol_enter(svm->vcpu.vcpu_id, + control->ghcb_gpa); + + switch (ghcb_info) { + case GHCB_MSR_SEV_INFO_REQ: + set_ghcb_msr(svm, GHCB_MSR_SEV_INFO(GHCB_VERSION_MAX, + GHCB_VERSION_MIN, + sev_enc_bit)); + break; + case GHCB_MSR_CPUID_REQ: { + u64 cpuid_fn, cpuid_reg, cpuid_value; + + cpuid_fn = get_ghcb_msr_bits(svm, + GHCB_MSR_CPUID_FUNC_MASK, + GHCB_MSR_CPUID_FUNC_POS); + + /* Initialize the registers needed by the CPUID intercept */ + vcpu->arch.regs[VCPU_REGS_RAX] = cpuid_fn; + vcpu->arch.regs[VCPU_REGS_RCX] = 0; + + ret = svm_invoke_exit_handler(svm, SVM_EXIT_CPUID); + if (!ret) { + ret = -EINVAL; + break; + } + + cpuid_reg = get_ghcb_msr_bits(svm, + GHCB_MSR_CPUID_REG_MASK, + GHCB_MSR_CPUID_REG_POS); + if (cpuid_reg == 0) + cpuid_value = vcpu->arch.regs[VCPU_REGS_RAX]; + else if (cpuid_reg == 1) + cpuid_value = vcpu->arch.regs[VCPU_REGS_RBX]; + else if (cpuid_reg == 2) + cpuid_value = vcpu->arch.regs[VCPU_REGS_RCX]; + else + cpuid_value = vcpu->arch.regs[VCPU_REGS_RDX]; + + set_ghcb_msr_bits(svm, cpuid_value, + GHCB_MSR_CPUID_VALUE_MASK, + GHCB_MSR_CPUID_VALUE_POS); + + set_ghcb_msr_bits(svm, GHCB_MSR_CPUID_RESP, + GHCB_MSR_INFO_MASK, + GHCB_MSR_INFO_POS); + break; + } + case GHCB_MSR_TERM_REQ: { + u64 reason_set, reason_code; + + reason_set = get_ghcb_msr_bits(svm, + GHCB_MSR_TERM_REASON_SET_MASK, + GHCB_MSR_TERM_REASON_SET_POS); + reason_code = get_ghcb_msr_bits(svm, + GHCB_MSR_TERM_REASON_MASK, + GHCB_MSR_TERM_REASON_POS); + pr_info("SEV-ES guest requested termination: %#llx:%#llx\n", + reason_set, reason_code); + fallthrough; + } + default: + ret = -EINVAL; + } + + trace_kvm_vmgexit_msr_protocol_exit(svm->vcpu.vcpu_id, + control->ghcb_gpa, ret); + + return ret; +} + +int sev_handle_vmgexit(struct vcpu_svm *svm) +{ + struct vmcb_control_area *control = &svm->vmcb->control; + u64 ghcb_gpa, exit_code; + struct ghcb *ghcb; + int ret; + + /* Validate the GHCB */ + ghcb_gpa = control->ghcb_gpa; + if (ghcb_gpa & GHCB_MSR_INFO_MASK) + return sev_handle_vmgexit_msr_protocol(svm); + + if (!ghcb_gpa) { + vcpu_unimpl(&svm->vcpu, "vmgexit: GHCB gpa is not set\n"); + return -EINVAL; + } + + if (kvm_vcpu_map(&svm->vcpu, ghcb_gpa >> PAGE_SHIFT, &svm->ghcb_map)) { + /* Unable to map GHCB from guest */ + vcpu_unimpl(&svm->vcpu, "vmgexit: error mapping GHCB [%#llx] from guest\n", + ghcb_gpa); + return -EINVAL; + } + + svm->ghcb = svm->ghcb_map.hva; + ghcb = svm->ghcb_map.hva; + + trace_kvm_vmgexit_enter(svm->vcpu.vcpu_id, ghcb); + + exit_code = ghcb_get_sw_exit_code(ghcb); + + ret = sev_es_validate_vmgexit(svm); + if (ret) + return ret; + + sev_es_sync_from_ghcb(svm); + ghcb_set_sw_exit_info_1(ghcb, 0); + ghcb_set_sw_exit_info_2(ghcb, 0); + + ret = -EINVAL; + switch (exit_code) { + case SVM_VMGEXIT_MMIO_READ: + if (!setup_vmgexit_scratch(svm, true, control->exit_info_2)) + break; + + ret = kvm_sev_es_mmio_read(&svm->vcpu, + control->exit_info_1, + control->exit_info_2, + svm->ghcb_sa); + break; + case SVM_VMGEXIT_MMIO_WRITE: + if (!setup_vmgexit_scratch(svm, false, control->exit_info_2)) + break; + + ret = kvm_sev_es_mmio_write(&svm->vcpu, + control->exit_info_1, + control->exit_info_2, + svm->ghcb_sa); + break; + case SVM_VMGEXIT_NMI_COMPLETE: + ret = svm_invoke_exit_handler(svm, SVM_EXIT_IRET); + break; + case SVM_VMGEXIT_AP_JUMP_TABLE: { + struct kvm_sev_info *sev = &to_kvm_svm(svm->vcpu.kvm)->sev_info; + + switch (control->exit_info_1) { + case 0: + /* Set AP jump table address */ + sev->ap_jump_table = control->exit_info_2; + break; + case 1: + /* Get AP jump table address */ + ghcb_set_sw_exit_info_2(ghcb, sev->ap_jump_table); + break; + default: + pr_err("svm: vmgexit: unsupported AP jump table request - exit_info_1=%#llx\n", + control->exit_info_1); + ghcb_set_sw_exit_info_1(ghcb, 1); + ghcb_set_sw_exit_info_2(ghcb, + X86_TRAP_UD | + SVM_EVTINJ_TYPE_EXEPT | + SVM_EVTINJ_VALID); + } + + ret = 1; + break; + } + case SVM_VMGEXIT_UNSUPPORTED_EVENT: + vcpu_unimpl(&svm->vcpu, + "vmgexit: unsupported event - exit_info_1=%#llx, exit_info_2=%#llx\n", + control->exit_info_1, control->exit_info_2); + break; + default: + ret = svm_invoke_exit_handler(svm, exit_code); + } + + return ret; +} + +int sev_es_string_io(struct vcpu_svm *svm, int size, unsigned int port, int in) +{ + if (!setup_vmgexit_scratch(svm, in, svm->vmcb->control.exit_info_2)) + return -EINVAL; + + return kvm_sev_es_string_io(&svm->vcpu, size, port, + svm->ghcb_sa, svm->ghcb_sa_len, in); +} + +void sev_es_init_vmcb(struct vcpu_svm *svm) +{ + struct kvm_vcpu *vcpu = &svm->vcpu; + + svm->vmcb->control.nested_ctl |= SVM_NESTED_CTL_SEV_ES_ENABLE; + svm->vmcb->control.virt_ext |= LBR_CTL_ENABLE_MASK; + + /* + * An SEV-ES guest requires a VMSA area that is a separate from the + * VMCB page. Do not include the encryption mask on the VMSA physical + * address since hardware will access it using the guest key. + */ + svm->vmcb->control.vmsa_pa = __pa(svm->vmsa); + + /* Can't intercept CR register access, HV can't modify CR registers */ + svm_clr_intercept(svm, INTERCEPT_CR0_READ); + svm_clr_intercept(svm, INTERCEPT_CR4_READ); + svm_clr_intercept(svm, INTERCEPT_CR8_READ); + svm_clr_intercept(svm, INTERCEPT_CR0_WRITE); + svm_clr_intercept(svm, INTERCEPT_CR4_WRITE); + svm_clr_intercept(svm, INTERCEPT_CR8_WRITE); + + svm_clr_intercept(svm, INTERCEPT_SELECTIVE_CR0); + + /* Track EFER/CR register changes */ + svm_set_intercept(svm, TRAP_EFER_WRITE); + svm_set_intercept(svm, TRAP_CR0_WRITE); + svm_set_intercept(svm, TRAP_CR4_WRITE); + svm_set_intercept(svm, TRAP_CR8_WRITE); + + /* No support for enable_vmware_backdoor */ + clr_exception_intercept(svm, GP_VECTOR); + + /* Can't intercept XSETBV, HV can't modify XCR0 directly */ + svm_clr_intercept(svm, INTERCEPT_XSETBV); + + /* Clear intercepts on selected MSRs */ + set_msr_interception(vcpu, svm->msrpm, MSR_EFER, 1, 1); + set_msr_interception(vcpu, svm->msrpm, MSR_IA32_CR_PAT, 1, 1); + set_msr_interception(vcpu, svm->msrpm, MSR_IA32_LASTBRANCHFROMIP, 1, 1); + set_msr_interception(vcpu, svm->msrpm, MSR_IA32_LASTBRANCHTOIP, 1, 1); + set_msr_interception(vcpu, svm->msrpm, MSR_IA32_LASTINTFROMIP, 1, 1); + set_msr_interception(vcpu, svm->msrpm, MSR_IA32_LASTINTTOIP, 1, 1); +} + +void sev_es_create_vcpu(struct vcpu_svm *svm) +{ + /* + * Set the GHCB MSR value as per the GHCB specification when creating + * a vCPU for an SEV-ES guest. + */ + set_ghcb_msr(svm, GHCB_MSR_SEV_INFO(GHCB_VERSION_MAX, + GHCB_VERSION_MIN, + sev_enc_bit)); +} + +void sev_es_vcpu_load(struct vcpu_svm *svm, int cpu) +{ + struct svm_cpu_data *sd = per_cpu(svm_data, cpu); + struct vmcb_save_area *hostsa; + unsigned int i; + + /* + * As an SEV-ES guest, hardware will restore the host state on VMEXIT, + * of which one step is to perform a VMLOAD. Since hardware does not + * perform a VMSAVE on VMRUN, the host savearea must be updated. + */ + asm volatile(__ex("vmsave") : : "a" (__sme_page_pa(sd->save_area)) : "memory"); + + /* + * Certain MSRs are restored on VMEXIT, only save ones that aren't + * restored. + */ + for (i = 0; i < NR_HOST_SAVE_USER_MSRS; i++) { + if (host_save_user_msrs[i].sev_es_restored) + continue; + + rdmsrl(host_save_user_msrs[i].index, svm->host_user_msrs[i]); + } + + /* XCR0 is restored on VMEXIT, save the current host value */ + hostsa = (struct vmcb_save_area *)(page_address(sd->save_area) + 0x400); + hostsa->xcr0 = xgetbv(XCR_XFEATURE_ENABLED_MASK); + + /* PKRU is restored on VMEXIT, save the curent host value */ + hostsa->pkru = read_pkru(); + + /* MSR_IA32_XSS is restored on VMEXIT, save the currnet host value */ + hostsa->xss = host_xss; +} + +void sev_es_vcpu_put(struct vcpu_svm *svm) +{ + unsigned int i; + + /* + * Certain MSRs are restored on VMEXIT and were saved with vmsave in + * sev_es_vcpu_load() above. Only restore ones that weren't. + */ + for (i = 0; i < NR_HOST_SAVE_USER_MSRS; i++) { + if (host_save_user_msrs[i].sev_es_restored) + continue; + + wrmsrl(host_save_user_msrs[i].index, svm->host_user_msrs[i]); + } +} diff --git a/arch/x86/kvm/svm/svm.c b/arch/x86/kvm/svm/svm.c index da7eb4aaf44f..cce0143a6f80 100644 --- a/arch/x86/kvm/svm/svm.c +++ b/arch/x86/kvm/svm/svm.c @@ -33,9 +33,9 @@ #include <asm/debugreg.h> #include <asm/kvm_para.h> #include <asm/irq_remapping.h> -#include <asm/mce.h> #include <asm/spec-ctrl.h> #include <asm/cpu_device_id.h> +#include <asm/traps.h> #include <asm/virtext.h> #include "trace.h" @@ -90,7 +90,7 @@ static DEFINE_PER_CPU(u64, current_tsc_ratio); static const struct svm_direct_access_msrs { u32 index; /* Index of the MSR */ - bool always; /* True if intercept is always on */ + bool always; /* True if intercept is initially cleared */ } direct_access_msrs[MAX_DIRECT_ACCESS_MSRS] = { { .index = MSR_STAR, .always = true }, { .index = MSR_IA32_SYSENTER_CS, .always = true }, @@ -108,6 +108,9 @@ static const struct svm_direct_access_msrs { { .index = MSR_IA32_LASTBRANCHTOIP, .always = false }, { .index = MSR_IA32_LASTINTFROMIP, .always = false }, { .index = MSR_IA32_LASTINTTOIP, .always = false }, + { .index = MSR_EFER, .always = false }, + { .index = MSR_IA32_CR_PAT, .always = false }, + { .index = MSR_AMD64_SEV_ES_GHCB, .always = true }, { .index = MSR_INVALID, .always = false }, }; @@ -187,10 +190,14 @@ static int vgif = true; module_param(vgif, int, 0444); /* enable/disable SEV support */ -static int sev = IS_ENABLED(CONFIG_AMD_MEM_ENCRYPT_ACTIVE_BY_DEFAULT); +int sev = IS_ENABLED(CONFIG_AMD_MEM_ENCRYPT_ACTIVE_BY_DEFAULT); module_param(sev, int, 0444); -static bool __read_mostly dump_invalid_vmcb = 0; +/* enable/disable SEV-ES support */ +int sev_es = IS_ENABLED(CONFIG_AMD_MEM_ENCRYPT_ACTIVE_BY_DEFAULT); +module_param(sev_es, int, 0444); + +bool __read_mostly dump_invalid_vmcb; module_param(dump_invalid_vmcb, bool, 0644); static u8 rsm_ins_bytes[] = "\x0f\xaa"; @@ -336,6 +343,13 @@ static int skip_emulated_instruction(struct kvm_vcpu *vcpu) { struct vcpu_svm *svm = to_svm(vcpu); + /* + * SEV-ES does not expose the next RIP. The RIP update is controlled by + * the type of exit and the #VC handler in the guest. + */ + if (sev_es_guest(vcpu->kvm)) + goto done; + if (nrips && svm->vmcb->control.next_rip != 0) { WARN_ON_ONCE(!static_cpu_has(X86_FEATURE_NRIPS)); svm->next_rip = svm->vmcb->control.next_rip; @@ -347,6 +361,8 @@ static int skip_emulated_instruction(struct kvm_vcpu *vcpu) } else { kvm_rip_write(vcpu, svm->next_rip); } + +done: svm_set_interrupt_shadow(vcpu, 0); return 1; @@ -484,7 +500,7 @@ static int svm_hardware_enable(void) wrmsrl(MSR_EFER, efer | EFER_SVME); - wrmsrl(MSR_VM_HSAVE_PA, page_to_pfn(sd->save_area) << PAGE_SHIFT); + wrmsrl(MSR_VM_HSAVE_PA, __sme_page_pa(sd->save_area)); if (static_cpu_has(X86_FEATURE_TSCRATEMSR)) { wrmsrl(MSR_AMD64_TSC_RATIO, TSC_RATIO_DEFAULT); @@ -552,6 +568,7 @@ static int svm_cpu_init(int cpu) sd->save_area = alloc_page(GFP_KERNEL); if (!sd->save_area) goto free_cpu_data; + clear_page(page_address(sd->save_area)); if (svm_sev_enabled()) { sd->sev_vmcbs = kmalloc_array(max_sev_asid + 1, @@ -662,8 +679,8 @@ static void set_msr_interception_bitmap(struct kvm_vcpu *vcpu, u32 *msrpm, msrpm[offset] = tmp; } -static void set_msr_interception(struct kvm_vcpu *vcpu, u32 *msrpm, u32 msr, - int read, int write) +void set_msr_interception(struct kvm_vcpu *vcpu, u32 *msrpm, u32 msr, + int read, int write) { set_shadow_msr_intercept(vcpu, msr, read, write); set_msr_interception_bitmap(vcpu, msrpm, msr, read, write); @@ -959,15 +976,11 @@ static __init int svm_hardware_setup(void) kvm_enable_efer_bits(EFER_SVME | EFER_LMSLE); } - if (sev) { - if (boot_cpu_has(X86_FEATURE_SEV) && - IS_ENABLED(CONFIG_KVM_AMD_SEV)) { - r = sev_hardware_setup(); - if (r) - sev = false; - } else { - sev = false; - } + if (IS_ENABLED(CONFIG_KVM_AMD_SEV) && sev) { + sev_hardware_setup(); + } else { + sev = false; + sev_es = false; } svm_adjust_mmio_mask(); @@ -1215,6 +1228,7 @@ static void init_vmcb(struct vcpu_svm *svm) save->cr4 = 0; } svm->asid_generation = 0; + svm->asid = 0; svm->nested.vmcb12_gpa = 0; svm->vcpu.arch.hflags = 0; @@ -1252,6 +1266,11 @@ static void init_vmcb(struct vcpu_svm *svm) if (sev_guest(svm->vcpu.kvm)) { svm->vmcb->control.nested_ctl |= SVM_NESTED_CTL_SEV_ENABLE; clr_exception_intercept(svm, UD_VECTOR); + + if (sev_es_guest(svm->vcpu.kvm)) { + /* Perform SEV-ES specific VMCB updates */ + sev_es_init_vmcb(svm); + } } vmcb_mark_all_dirty(svm->vmcb); @@ -1288,6 +1307,7 @@ static int svm_create_vcpu(struct kvm_vcpu *vcpu) { struct vcpu_svm *svm; struct page *vmcb_page; + struct page *vmsa_page = NULL; int err; BUILD_BUG_ON(offsetof(struct vcpu_svm, vcpu) != 0); @@ -1298,9 +1318,27 @@ static int svm_create_vcpu(struct kvm_vcpu *vcpu) if (!vmcb_page) goto out; + if (sev_es_guest(svm->vcpu.kvm)) { + /* + * SEV-ES guests require a separate VMSA page used to contain + * the encrypted register state of the guest. + */ + vmsa_page = alloc_page(GFP_KERNEL_ACCOUNT | __GFP_ZERO); + if (!vmsa_page) + goto error_free_vmcb_page; + + /* + * SEV-ES guests maintain an encrypted version of their FPU + * state which is restored and saved on VMRUN and VMEXIT. + * Free the fpu structure to prevent KVM from attempting to + * access the FPU state. + */ + kvm_free_guest_fpu(vcpu); + } + err = avic_init_vcpu(svm); if (err) - goto error_free_vmcb_page; + goto error_free_vmsa_page; /* We initialize this flag to true to make sure that the is_running * bit would be set the first time the vcpu is loaded. @@ -1311,21 +1349,32 @@ static int svm_create_vcpu(struct kvm_vcpu *vcpu) svm->msrpm = svm_vcpu_alloc_msrpm(); if (!svm->msrpm) { err = -ENOMEM; - goto error_free_vmcb_page; + goto error_free_vmsa_page; } svm_vcpu_init_msrpm(vcpu, svm->msrpm); svm->vmcb = page_address(vmcb_page); svm->vmcb_pa = __sme_set(page_to_pfn(vmcb_page) << PAGE_SHIFT); + + if (vmsa_page) + svm->vmsa = page_address(vmsa_page); + svm->asid_generation = 0; init_vmcb(svm); svm_init_osvw(vcpu); vcpu->arch.microcode_version = 0x01000065; + if (sev_es_guest(svm->vcpu.kvm)) + /* Perform SEV-ES specific VMCB creation updates */ + sev_es_create_vcpu(svm); + return 0; +error_free_vmsa_page: + if (vmsa_page) + __free_page(vmsa_page); error_free_vmcb_page: __free_page(vmcb_page); out: @@ -1353,6 +1402,8 @@ static void svm_free_vcpu(struct kvm_vcpu *vcpu) svm_free_nested(svm); + sev_free_vcpu(vcpu); + __free_page(pfn_to_page(__sme_clr(svm->vmcb_pa) >> PAGE_SHIFT)); __free_pages(virt_to_page(svm->msrpm), MSRPM_ALLOC_ORDER); } @@ -1368,15 +1419,20 @@ static void svm_vcpu_load(struct kvm_vcpu *vcpu, int cpu) vmcb_mark_all_dirty(svm->vmcb); } + if (sev_es_guest(svm->vcpu.kvm)) { + sev_es_vcpu_load(svm, cpu); + } else { #ifdef CONFIG_X86_64 - rdmsrl(MSR_GS_BASE, to_svm(vcpu)->host.gs_base); + rdmsrl(MSR_GS_BASE, to_svm(vcpu)->host.gs_base); #endif - savesegment(fs, svm->host.fs); - savesegment(gs, svm->host.gs); - svm->host.ldt = kvm_read_ldt(); + savesegment(fs, svm->host.fs); + savesegment(gs, svm->host.gs); + svm->host.ldt = kvm_read_ldt(); - for (i = 0; i < NR_HOST_SAVE_USER_MSRS; i++) - rdmsrl(host_save_user_msrs[i], svm->host_user_msrs[i]); + for (i = 0; i < NR_HOST_SAVE_USER_MSRS; i++) + rdmsrl(host_save_user_msrs[i].index, + svm->host_user_msrs[i]); + } if (static_cpu_has(X86_FEATURE_TSCRATEMSR)) { u64 tsc_ratio = vcpu->arch.tsc_scaling_ratio; @@ -1404,18 +1460,24 @@ static void svm_vcpu_put(struct kvm_vcpu *vcpu) avic_vcpu_put(vcpu); ++vcpu->stat.host_state_reload; - kvm_load_ldt(svm->host.ldt); + if (sev_es_guest(svm->vcpu.kvm)) { + sev_es_vcpu_put(svm); + } else { + kvm_load_ldt(svm->host.ldt); #ifdef CONFIG_X86_64 - loadsegment(fs, svm->host.fs); - wrmsrl(MSR_KERNEL_GS_BASE, current->thread.gsbase); - load_gs_index(svm->host.gs); + loadsegment(fs, svm->host.fs); + wrmsrl(MSR_KERNEL_GS_BASE, current->thread.gsbase); + load_gs_index(svm->host.gs); #else #ifdef CONFIG_X86_32_LAZY_GS - loadsegment(gs, svm->host.gs); + loadsegment(gs, svm->host.gs); #endif #endif - for (i = 0; i < NR_HOST_SAVE_USER_MSRS; i++) - wrmsrl(host_save_user_msrs[i], svm->host_user_msrs[i]); + + for (i = 0; i < NR_HOST_SAVE_USER_MSRS; i++) + wrmsrl(host_save_user_msrs[i].index, + svm->host_user_msrs[i]); + } } static unsigned long svm_get_rflags(struct kvm_vcpu *vcpu) @@ -1633,9 +1695,18 @@ static void svm_set_gdt(struct kvm_vcpu *vcpu, struct desc_ptr *dt) static void update_cr0_intercept(struct vcpu_svm *svm) { - ulong gcr0 = svm->vcpu.arch.cr0; - u64 *hcr0 = &svm->vmcb->save.cr0; + ulong gcr0; + u64 *hcr0; + /* + * SEV-ES guests must always keep the CR intercepts cleared. CR + * tracking is done using the CR write traps. + */ + if (sev_es_guest(svm->vcpu.kvm)) + return; + + gcr0 = svm->vcpu.arch.cr0; + hcr0 = &svm->vmcb->save.cr0; *hcr0 = (*hcr0 & ~SVM_CR0_SELECTIVE_MASK) | (gcr0 & SVM_CR0_SELECTIVE_MASK); @@ -1655,7 +1726,7 @@ void svm_set_cr0(struct kvm_vcpu *vcpu, unsigned long cr0) struct vcpu_svm *svm = to_svm(vcpu); #ifdef CONFIG_X86_64 - if (vcpu->arch.efer & EFER_LME) { + if (vcpu->arch.efer & EFER_LME && !vcpu->arch.guest_state_protected) { if (!is_paging(vcpu) && (cr0 & X86_CR0_PG)) { vcpu->arch.efer |= EFER_LMA; svm->vmcb->save.efer |= EFER_LMA | EFER_LME; @@ -1684,13 +1755,15 @@ void svm_set_cr0(struct kvm_vcpu *vcpu, unsigned long cr0) update_cr0_intercept(svm); } -int svm_set_cr4(struct kvm_vcpu *vcpu, unsigned long cr4) +static bool svm_is_valid_cr4(struct kvm_vcpu *vcpu, unsigned long cr4) { - unsigned long host_cr4_mce = cr4_read_shadow() & X86_CR4_MCE; - unsigned long old_cr4 = to_svm(vcpu)->vmcb->save.cr4; + return true; +} - if (cr4 & X86_CR4_VMXE) - return 1; +void svm_set_cr4(struct kvm_vcpu *vcpu, unsigned long cr4) +{ + unsigned long host_cr4_mce = cr4_read_shadow() & X86_CR4_MCE; + unsigned long old_cr4 = vcpu->arch.cr4; if (npt_enabled && ((old_cr4 ^ cr4) & X86_CR4_PGE)) svm_flush_tlb(vcpu); @@ -1701,7 +1774,9 @@ int svm_set_cr4(struct kvm_vcpu *vcpu, unsigned long cr4) cr4 |= host_cr4_mce; to_svm(vcpu)->vmcb->save.cr4 = cr4; vmcb_mark_dirty(to_svm(vcpu)->vmcb, VMCB_CR); - return 0; + + if ((cr4 ^ old_cr4) & (X86_CR4_OSXSAVE | X86_CR4_PKE)) + kvm_update_cpuid_runtime(vcpu); } static void svm_set_segment(struct kvm_vcpu *vcpu, @@ -1753,18 +1828,20 @@ static void new_asid(struct vcpu_svm *svm, struct svm_cpu_data *sd) ++sd->asid_generation; sd->next_asid = sd->min_asid; svm->vmcb->control.tlb_ctl = TLB_CONTROL_FLUSH_ALL_ASID; + vmcb_mark_dirty(svm->vmcb, VMCB_ASID); } svm->asid_generation = sd->asid_generation; - svm->vmcb->control.asid = sd->next_asid++; - - vmcb_mark_dirty(svm->vmcb, VMCB_ASID); + svm->asid = sd->next_asid++; } static void svm_set_dr6(struct vcpu_svm *svm, unsigned long value) { struct vmcb *vmcb = svm->vmcb; + if (svm->vcpu.arch.guest_state_protected) + return; + if (unlikely(value != vmcb->save.dr6)) { vmcb->save.dr6 = value; vmcb_mark_dirty(vmcb, VMCB_DR); @@ -1775,6 +1852,9 @@ static void svm_sync_dirty_debug_regs(struct kvm_vcpu *vcpu) { struct vcpu_svm *svm = to_svm(vcpu); + if (vcpu->arch.guest_state_protected) + return; + get_debugreg(vcpu->arch.db[0], 0); get_debugreg(vcpu->arch.db[1], 1); get_debugreg(vcpu->arch.db[2], 2); @@ -1793,6 +1873,9 @@ static void svm_set_dr7(struct kvm_vcpu *vcpu, unsigned long value) { struct vcpu_svm *svm = to_svm(vcpu); + if (vcpu->arch.guest_state_protected) + return; + svm->vmcb->save.dr7 = value; vmcb_mark_dirty(svm->vmcb, VMCB_DR); } @@ -1931,25 +2014,6 @@ static bool is_erratum_383(void) return true; } -/* - * Trigger machine check on the host. We assume all the MSRs are already set up - * by the CPU and that we still run on the same CPU as the MCE occurred on. - * We pass a fake environment to the machine check handler because we want - * the guest to be always treated like user space, no matter what context - * it used internally. - */ -static void kvm_machine_check(void) -{ -#if defined(CONFIG_X86_MCE) - struct pt_regs regs = { - .cs = 3, /* Fake ring 3 no matter what the guest ran on */ - .flags = X86_EFLAGS_IF, - }; - - do_machine_check(®s); -#endif -} - static void svm_handle_mce(struct vcpu_svm *svm) { if (is_erratum_383()) { @@ -1981,6 +2045,13 @@ static int shutdown_interception(struct vcpu_svm *svm) struct kvm_run *kvm_run = svm->vcpu.run; /* + * The VM save area has already been encrypted so it + * cannot be reinitialized - just terminate. + */ + if (sev_es_guest(svm->vcpu.kvm)) + return -EINVAL; + + /* * VMCB is undefined after a SHUTDOWN intercept * so reinitialize it. */ @@ -2001,11 +2072,16 @@ static int io_interception(struct vcpu_svm *svm) ++svm->vcpu.stat.io_exits; string = (io_info & SVM_IOIO_STR_MASK) != 0; in = (io_info & SVM_IOIO_TYPE_MASK) != 0; - if (string) - return kvm_emulate_instruction(vcpu, 0); - port = io_info >> 16; size = (io_info & SVM_IOIO_SIZE_MASK) >> SVM_IOIO_SIZE_SHIFT; + + if (string) { + if (sev_es_guest(vcpu->kvm)) + return sev_es_string_io(svm, size, port, in); + else + return kvm_emulate_instruction(vcpu, 0); + } + svm->next_rip = svm->vmcb->control.exit_info_2; return kvm_fast_pio(&svm->vcpu, size, port, in); @@ -2269,9 +2345,11 @@ static int cpuid_interception(struct vcpu_svm *svm) static int iret_interception(struct vcpu_svm *svm) { ++svm->vcpu.stat.nmi_window_exits; - svm_clr_intercept(svm, INTERCEPT_IRET); svm->vcpu.arch.hflags |= HF_IRET_MASK; - svm->nmi_iret_rip = kvm_rip_read(&svm->vcpu); + if (!sev_es_guest(svm->vcpu.kvm)) { + svm_clr_intercept(svm, INTERCEPT_IRET); + svm->nmi_iret_rip = kvm_rip_read(&svm->vcpu); + } kvm_make_request(KVM_REQ_EVENT, &svm->vcpu); return 1; } @@ -2408,6 +2486,41 @@ static int cr_interception(struct vcpu_svm *svm) return kvm_complete_insn_gp(&svm->vcpu, err); } +static int cr_trap(struct vcpu_svm *svm) +{ + struct kvm_vcpu *vcpu = &svm->vcpu; + unsigned long old_value, new_value; + unsigned int cr; + int ret = 0; + + new_value = (unsigned long)svm->vmcb->control.exit_info_1; + + cr = svm->vmcb->control.exit_code - SVM_EXIT_CR0_WRITE_TRAP; + switch (cr) { + case 0: + old_value = kvm_read_cr0(vcpu); + svm_set_cr0(vcpu, new_value); + + kvm_post_set_cr0(vcpu, old_value, new_value); + break; + case 4: + old_value = kvm_read_cr4(vcpu); + svm_set_cr4(vcpu, new_value); + + kvm_post_set_cr4(vcpu, old_value, new_value); + break; + case 8: + ret = kvm_set_cr8(&svm->vcpu, new_value); + break; + default: + WARN(1, "unhandled CR%d write trap", cr); + kvm_queue_exception(vcpu, UD_VECTOR); + return 1; + } + + return kvm_complete_insn_gp(vcpu, ret); +} + static int dr_interception(struct vcpu_svm *svm) { int reg, dr; @@ -2461,6 +2574,25 @@ static int cr8_write_interception(struct vcpu_svm *svm) return 0; } +static int efer_trap(struct vcpu_svm *svm) +{ + struct msr_data msr_info; + int ret; + + /* + * Clear the EFER_SVME bit from EFER. The SVM code always sets this + * bit in svm_set_efer(), but __kvm_valid_efer() checks it against + * whether the guest has X86_FEATURE_SVM - this avoids a failure if + * the guest doesn't have X86_FEATURE_SVM. + */ + msr_info.host_initiated = false; + msr_info.index = MSR_EFER; + msr_info.data = svm->vmcb->control.exit_info_1 & ~EFER_SVME; + ret = kvm_set_msr_common(&svm->vcpu, &msr_info); + + return kvm_complete_insn_gp(&svm->vcpu, ret); +} + static int svm_get_msr_feature(struct kvm_msr_entry *msr) { msr->data = 0; @@ -2543,10 +2675,7 @@ static int svm_get_msr(struct kvm_vcpu *vcpu, struct msr_data *msr_info) break; case MSR_IA32_SPEC_CTRL: if (!msr_info->host_initiated && - !guest_cpuid_has(vcpu, X86_FEATURE_SPEC_CTRL) && - !guest_cpuid_has(vcpu, X86_FEATURE_AMD_STIBP) && - !guest_cpuid_has(vcpu, X86_FEATURE_AMD_IBRS) && - !guest_cpuid_has(vcpu, X86_FEATURE_AMD_SSBD)) + !guest_has_spec_ctrl_msr(vcpu)) return 1; msr_info->data = svm->spec_ctrl; @@ -2584,6 +2713,20 @@ static int svm_get_msr(struct kvm_vcpu *vcpu, struct msr_data *msr_info) return 0; } +static int svm_complete_emulated_msr(struct kvm_vcpu *vcpu, int err) +{ + struct vcpu_svm *svm = to_svm(vcpu); + if (!sev_es_guest(svm->vcpu.kvm) || !err) + return kvm_complete_insn_gp(&svm->vcpu, err); + + ghcb_set_sw_exit_info_1(svm->ghcb, 1); + ghcb_set_sw_exit_info_2(svm->ghcb, + X86_TRAP_GP | + SVM_EVTINJ_TYPE_EXEPT | + SVM_EVTINJ_VALID); + return 1; +} + static int rdmsr_interception(struct vcpu_svm *svm) { return kvm_emulate_rdmsr(&svm->vcpu); @@ -2630,10 +2773,7 @@ static int svm_set_msr(struct kvm_vcpu *vcpu, struct msr_data *msr) break; case MSR_IA32_SPEC_CTRL: if (!msr->host_initiated && - !guest_cpuid_has(vcpu, X86_FEATURE_SPEC_CTRL) && - !guest_cpuid_has(vcpu, X86_FEATURE_AMD_STIBP) && - !guest_cpuid_has(vcpu, X86_FEATURE_AMD_IBRS) && - !guest_cpuid_has(vcpu, X86_FEATURE_AMD_SSBD)) + !guest_has_spec_ctrl_msr(vcpu)) return 1; if (kvm_spec_ctrl_test_value(data)) @@ -2658,12 +2798,12 @@ static int svm_set_msr(struct kvm_vcpu *vcpu, struct msr_data *msr) break; case MSR_IA32_PRED_CMD: if (!msr->host_initiated && - !guest_cpuid_has(vcpu, X86_FEATURE_AMD_IBPB)) + !guest_has_pred_cmd_msr(vcpu)) return 1; if (data & ~PRED_CMD_IBPB) return 1; - if (!boot_cpu_has(X86_FEATURE_AMD_IBPB)) + if (!boot_cpu_has(X86_FEATURE_IBPB)) return 1; if (!data) break; @@ -2805,7 +2945,14 @@ static int interrupt_window_interception(struct vcpu_svm *svm) static int pause_interception(struct vcpu_svm *svm) { struct kvm_vcpu *vcpu = &svm->vcpu; - bool in_kernel = (svm_get_cpl(vcpu) == 0); + bool in_kernel; + + /* + * CPL is not made available for an SEV-ES guest, therefore + * vcpu->arch.preempted_in_kernel can never be true. Just + * set in_kernel to false as well. + */ + in_kernel = !sev_es_guest(svm->vcpu.kvm) && svm_get_cpl(vcpu) == 0; if (!kvm_pause_in_guest(vcpu->kvm)) grow_ple_window(vcpu); @@ -2920,11 +3067,16 @@ static int (*const svm_exit_handlers[])(struct vcpu_svm *svm) = { [SVM_EXIT_MWAIT] = mwait_interception, [SVM_EXIT_XSETBV] = xsetbv_interception, [SVM_EXIT_RDPRU] = rdpru_interception, + [SVM_EXIT_EFER_WRITE_TRAP] = efer_trap, + [SVM_EXIT_CR0_WRITE_TRAP] = cr_trap, + [SVM_EXIT_CR4_WRITE_TRAP] = cr_trap, + [SVM_EXIT_CR8_WRITE_TRAP] = cr_trap, [SVM_EXIT_INVPCID] = invpcid_interception, [SVM_EXIT_NPF] = npf_interception, [SVM_EXIT_RSM] = rsm_interception, [SVM_EXIT_AVIC_INCOMPLETE_IPI] = avic_incomplete_ipi_interception, [SVM_EXIT_AVIC_UNACCELERATED_ACCESS] = avic_unaccelerated_access_interception, + [SVM_EXIT_VMGEXIT] = sev_handle_vmgexit, }; static void dump_vmcb(struct kvm_vcpu *vcpu) @@ -2966,6 +3118,7 @@ static void dump_vmcb(struct kvm_vcpu *vcpu) pr_err("%-20s%lld\n", "nested_ctl:", control->nested_ctl); pr_err("%-20s%016llx\n", "nested_cr3:", control->nested_cr3); pr_err("%-20s%016llx\n", "avic_vapic_bar:", control->avic_vapic_bar); + pr_err("%-20s%016llx\n", "ghcb:", control->ghcb_gpa); pr_err("%-20s%08x\n", "event_inj:", control->event_inj); pr_err("%-20s%08x\n", "event_inj_err:", control->event_inj_err); pr_err("%-20s%lld\n", "virt_ext:", control->virt_ext); @@ -2973,6 +3126,7 @@ static void dump_vmcb(struct kvm_vcpu *vcpu) pr_err("%-20s%016llx\n", "avic_backing_page:", control->avic_backing_page); pr_err("%-20s%016llx\n", "avic_logical_id:", control->avic_logical_id); pr_err("%-20s%016llx\n", "avic_physical_id:", control->avic_physical_id); + pr_err("%-20s%016llx\n", "vmsa_pa:", control->vmsa_pa); pr_err("VMCB State Save Area:\n"); pr_err("%-5s s: %04x a: %04x l: %08x b: %016llx\n", "es:", @@ -3045,6 +3199,43 @@ 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) +{ + if (exit_code < ARRAY_SIZE(svm_exit_handlers) && + svm_exit_handlers[exit_code]) + return 0; + + vcpu_unimpl(vcpu, "svm: unexpected exit reason 0x%llx\n", exit_code); + dump_vmcb(vcpu); + vcpu->run->exit_reason = KVM_EXIT_INTERNAL_ERROR; + vcpu->run->internal.suberror = KVM_INTERNAL_ERROR_UNEXPECTED_EXIT_REASON; + vcpu->run->internal.ndata = 2; + vcpu->run->internal.data[0] = exit_code; + vcpu->run->internal.data[1] = vcpu->arch.last_vmentry_cpu; + + return -EINVAL; +} + +int svm_invoke_exit_handler(struct vcpu_svm *svm, u64 exit_code) +{ + if (svm_handle_invalid_exit(&svm->vcpu, exit_code)) + return 0; + +#ifdef CONFIG_RETPOLINE + if (exit_code == SVM_EXIT_MSR) + return msr_interception(svm); + else if (exit_code == SVM_EXIT_VINTR) + return interrupt_window_interception(svm); + else if (exit_code == SVM_EXIT_INTR) + return intr_interception(svm); + else if (exit_code == SVM_EXIT_HLT) + return halt_interception(svm); + else if (exit_code == SVM_EXIT_NPF) + return npf_interception(svm); +#endif + return svm_exit_handlers[exit_code](svm); +} + static void svm_get_exit_info(struct kvm_vcpu *vcpu, u64 *info1, u64 *info2, u32 *intr_info, u32 *error_code) { @@ -3068,10 +3259,13 @@ static int handle_exit(struct kvm_vcpu *vcpu, fastpath_t exit_fastpath) trace_kvm_exit(exit_code, vcpu, KVM_ISA_SVM); - if (!svm_is_intercept(svm, INTERCEPT_CR0_WRITE)) - vcpu->arch.cr0 = svm->vmcb->save.cr0; - if (npt_enabled) - vcpu->arch.cr3 = svm->vmcb->save.cr3; + /* SEV-ES guests must use the CR write traps to track CR registers. */ + if (!sev_es_guest(vcpu->kvm)) { + if (!svm_is_intercept(svm, INTERCEPT_CR0_WRITE)) + vcpu->arch.cr0 = svm->vmcb->save.cr0; + if (npt_enabled) + vcpu->arch.cr3 = svm->vmcb->save.cr3; + } if (is_guest_mode(vcpu)) { int vmexit; @@ -3108,32 +3302,7 @@ static int handle_exit(struct kvm_vcpu *vcpu, fastpath_t exit_fastpath) if (exit_fastpath != EXIT_FASTPATH_NONE) return 1; - if (exit_code >= ARRAY_SIZE(svm_exit_handlers) - || !svm_exit_handlers[exit_code]) { - vcpu_unimpl(vcpu, "svm: unexpected exit reason 0x%x\n", exit_code); - dump_vmcb(vcpu); - vcpu->run->exit_reason = KVM_EXIT_INTERNAL_ERROR; - vcpu->run->internal.suberror = - KVM_INTERNAL_ERROR_UNEXPECTED_EXIT_REASON; - vcpu->run->internal.ndata = 2; - vcpu->run->internal.data[0] = exit_code; - vcpu->run->internal.data[1] = vcpu->arch.last_vmentry_cpu; - return 0; - } - -#ifdef CONFIG_RETPOLINE - if (exit_code == SVM_EXIT_MSR) - return msr_interception(svm); - else if (exit_code == SVM_EXIT_VINTR) - return interrupt_window_interception(svm); - else if (exit_code == SVM_EXIT_INTR) - return intr_interception(svm); - else if (exit_code == SVM_EXIT_HLT) - return halt_interception(svm); - else if (exit_code == SVM_EXIT_NPF) - return npf_interception(svm); -#endif - return svm_exit_handlers[exit_code](svm); + return svm_invoke_exit_handler(svm, exit_code); } static void reload_tss(struct kvm_vcpu *vcpu) @@ -3162,7 +3331,8 @@ static void svm_inject_nmi(struct kvm_vcpu *vcpu) svm->vmcb->control.event_inj = SVM_EVTINJ_VALID | SVM_EVTINJ_TYPE_NMI; vcpu->arch.hflags |= HF_NMI_MASK; - svm_set_intercept(svm, INTERCEPT_IRET); + if (!sev_es_guest(svm->vcpu.kvm)) + svm_set_intercept(svm, INTERCEPT_IRET); ++vcpu->stat.nmi_injections; } @@ -3183,6 +3353,13 @@ static void update_cr8_intercept(struct kvm_vcpu *vcpu, int tpr, int irr) { struct vcpu_svm *svm = to_svm(vcpu); + /* + * SEV-ES guests must always keep the CR intercepts cleared. CR + * tracking is done using the CR write traps. + */ + if (sev_es_guest(vcpu->kvm)) + return; + if (nested_svm_virtualize_tpr(vcpu)) return; @@ -3239,10 +3416,12 @@ static void svm_set_nmi_mask(struct kvm_vcpu *vcpu, bool masked) if (masked) { svm->vcpu.arch.hflags |= HF_NMI_MASK; - svm_set_intercept(svm, INTERCEPT_IRET); + if (!sev_es_guest(svm->vcpu.kvm)) + svm_set_intercept(svm, INTERCEPT_IRET); } else { svm->vcpu.arch.hflags &= ~HF_NMI_MASK; - svm_clr_intercept(svm, INTERCEPT_IRET); + if (!sev_es_guest(svm->vcpu.kvm)) + svm_clr_intercept(svm, INTERCEPT_IRET); } } @@ -3254,7 +3433,14 @@ bool svm_interrupt_blocked(struct kvm_vcpu *vcpu) if (!gif_set(svm)) return true; - if (is_guest_mode(vcpu)) { + if (sev_es_guest(svm->vcpu.kvm)) { + /* + * SEV-ES guests to not expose RFLAGS. Use the VMCB interrupt mask + * bit to determine the state of the IF flag. + */ + if (!(vmcb->control.int_state & SVM_GUEST_INTERRUPT_MASK)) + return true; + } else if (is_guest_mode(vcpu)) { /* As long as interrupts are being delivered... */ if ((svm->nested.ctl.int_ctl & V_INTR_MASKING_MASK) ? !(svm->nested.hsave->save.rflags & X86_EFLAGS_IF) @@ -3413,8 +3599,9 @@ static void svm_complete_interrupts(struct vcpu_svm *svm) * If we've made progress since setting HF_IRET_MASK, we've * executed an IRET and can allow NMI injection. */ - if ((svm->vcpu.arch.hflags & HF_IRET_MASK) - && kvm_rip_read(&svm->vcpu) != svm->nmi_iret_rip) { + if ((svm->vcpu.arch.hflags & HF_IRET_MASK) && + (sev_es_guest(svm->vcpu.kvm) || + kvm_rip_read(&svm->vcpu) != svm->nmi_iret_rip)) { svm->vcpu.arch.hflags &= ~(HF_NMI_MASK | HF_IRET_MASK); kvm_make_request(KVM_REQ_EVENT, &svm->vcpu); } @@ -3437,6 +3624,12 @@ static void svm_complete_interrupts(struct vcpu_svm *svm) break; case SVM_EXITINTINFO_TYPE_EXEPT: /* + * Never re-inject a #VC exception. + */ + if (vector == X86_TRAP_VC) + break; + + /* * In case of software exceptions, do not reinject the vector, * but re-execute the instruction instead. Rewind RIP first * if we emulated INT3 before. @@ -3509,16 +3702,20 @@ static noinstr void svm_vcpu_enter_exit(struct kvm_vcpu *vcpu, guest_enter_irqoff(); lockdep_hardirqs_on(CALLER_ADDR0); - __svm_vcpu_run(svm->vmcb_pa, (unsigned long *)&svm->vcpu.arch.regs); + if (sev_es_guest(svm->vcpu.kvm)) { + __svm_sev_es_vcpu_run(svm->vmcb_pa); + } else { + __svm_vcpu_run(svm->vmcb_pa, (unsigned long *)&svm->vcpu.arch.regs); #ifdef CONFIG_X86_64 - native_wrmsrl(MSR_GS_BASE, svm->host.gs_base); + native_wrmsrl(MSR_GS_BASE, svm->host.gs_base); #else - loadsegment(fs, svm->host.fs); + loadsegment(fs, svm->host.fs); #ifndef CONFIG_X86_32_LAZY_GS - loadsegment(gs, svm->host.gs); + loadsegment(gs, svm->host.gs); #endif #endif + } /* * VMEXIT disables interrupts (host state), but tracing and lockdep @@ -3568,6 +3765,10 @@ static __no_kcsan fastpath_t svm_vcpu_run(struct kvm_vcpu *vcpu) sync_lapic_to_cr8(vcpu); + if (unlikely(svm->asid != svm->vmcb->control.asid)) { + svm->vmcb->control.asid = svm->asid; + vmcb_mark_dirty(svm->vmcb, VMCB_ASID); + } svm->vmcb->save.cr2 = vcpu->arch.cr2; /* @@ -3612,14 +3813,17 @@ static __no_kcsan fastpath_t svm_vcpu_run(struct kvm_vcpu *vcpu) if (unlikely(!msr_write_intercepted(vcpu, MSR_IA32_SPEC_CTRL))) svm->spec_ctrl = native_read_msr(MSR_IA32_SPEC_CTRL); - reload_tss(vcpu); + if (!sev_es_guest(svm->vcpu.kvm)) + reload_tss(vcpu); x86_spec_ctrl_restore_host(svm->spec_ctrl, svm->virt_spec_ctrl); - vcpu->arch.cr2 = svm->vmcb->save.cr2; - vcpu->arch.regs[VCPU_REGS_RAX] = svm->vmcb->save.rax; - vcpu->arch.regs[VCPU_REGS_RSP] = svm->vmcb->save.rsp; - vcpu->arch.regs[VCPU_REGS_RIP] = svm->vmcb->save.rip; + if (!sev_es_guest(svm->vcpu.kvm)) { + vcpu->arch.cr2 = svm->vmcb->save.cr2; + vcpu->arch.regs[VCPU_REGS_RAX] = svm->vmcb->save.rax; + vcpu->arch.regs[VCPU_REGS_RSP] = svm->vmcb->save.rsp; + vcpu->arch.regs[VCPU_REGS_RIP] = svm->vmcb->save.rip; + } if (unlikely(svm->vmcb->control.exit_code == SVM_EXIT_NMI)) kvm_before_interrupt(&svm->vcpu); @@ -3722,12 +3926,21 @@ static bool svm_cpu_has_accelerated_tpr(void) return false; } -static bool svm_has_emulated_msr(u32 index) +/* + * The kvm parameter can be NULL (module initialization, or invocation before + * VM creation). Be sure to check the kvm parameter before using it. + */ +static bool svm_has_emulated_msr(struct kvm *kvm, u32 index) { switch (index) { case MSR_IA32_MCG_EXT_CTL: case MSR_IA32_VMX_BASIC ... MSR_IA32_VMX_VMFUNC: return false; + case MSR_IA32_SMBASE: + /* SEV-ES guests do not support SMM, so report false */ + if (kvm && sev_es_guest(kvm)) + return false; + break; default: break; } @@ -4086,6 +4299,12 @@ static bool svm_can_emulate_instruction(struct kvm_vcpu *vcpu, void *insn, int i unsigned long cr4; /* + * When the guest is an SEV-ES guest, emulation is not possible. + */ + if (sev_es_guest(vcpu->kvm)) + return false; + + /* * Detect and workaround Errata 1096 Fam_17h_00_0Fh. * * Errata: @@ -4217,6 +4436,7 @@ static struct kvm_x86_ops svm_x86_ops __initdata = { .get_cpl = svm_get_cpl, .get_cs_db_l_bits = kvm_get_cs_db_l_bits, .set_cr0 = svm_set_cr0, + .is_valid_cr4 = svm_is_valid_cr4, .set_cr4 = svm_set_cr4, .set_efer = svm_set_efer, .get_idt = svm_get_idt, @@ -4305,6 +4525,7 @@ static struct kvm_x86_ops svm_x86_ops __initdata = { .apic_init_signal_blocked = svm_apic_init_signal_blocked, .msr_filter_changed = svm_msr_filter_changed, + .complete_emulated_msr = svm_complete_emulated_msr, }; static struct kvm_x86_init_ops svm_init_ops __initdata = { diff --git a/arch/x86/kvm/svm/svm.h b/arch/x86/kvm/svm/svm.h index 1d853fe4c778..5431e6335e2e 100644 --- a/arch/x86/kvm/svm/svm.h +++ b/arch/x86/kvm/svm/svm.h @@ -17,21 +17,32 @@ #include <linux/kvm_types.h> #include <linux/kvm_host.h> +#include <linux/bits.h> #include <asm/svm.h> -static const u32 host_save_user_msrs[] = { +#define __sme_page_pa(x) __sme_set(page_to_pfn(x) << PAGE_SHIFT) + +static const struct svm_host_save_msrs { + u32 index; /* Index of the MSR */ + bool sev_es_restored; /* True if MSR is restored on SEV-ES VMEXIT */ +} host_save_user_msrs[] = { #ifdef CONFIG_X86_64 - MSR_STAR, MSR_LSTAR, MSR_CSTAR, MSR_SYSCALL_MASK, MSR_KERNEL_GS_BASE, - MSR_FS_BASE, + { .index = MSR_STAR, .sev_es_restored = true }, + { .index = MSR_LSTAR, .sev_es_restored = true }, + { .index = MSR_CSTAR, .sev_es_restored = true }, + { .index = MSR_SYSCALL_MASK, .sev_es_restored = true }, + { .index = MSR_KERNEL_GS_BASE, .sev_es_restored = true }, + { .index = MSR_FS_BASE, .sev_es_restored = true }, #endif - MSR_IA32_SYSENTER_CS, MSR_IA32_SYSENTER_ESP, MSR_IA32_SYSENTER_EIP, - MSR_TSC_AUX, + { .index = MSR_IA32_SYSENTER_CS, .sev_es_restored = true }, + { .index = MSR_IA32_SYSENTER_ESP, .sev_es_restored = true }, + { .index = MSR_IA32_SYSENTER_EIP, .sev_es_restored = true }, + { .index = MSR_TSC_AUX, .sev_es_restored = false }, }; - #define NR_HOST_SAVE_USER_MSRS ARRAY_SIZE(host_save_user_msrs) -#define MAX_DIRECT_ACCESS_MSRS 15 +#define MAX_DIRECT_ACCESS_MSRS 18 #define MSRPM_OFFSETS 16 extern u32 msrpm_offsets[MSRPM_OFFSETS] __read_mostly; extern bool npt_enabled; @@ -61,11 +72,13 @@ enum { struct kvm_sev_info { bool active; /* SEV enabled guest */ + bool es_active; /* SEV-ES enabled guest */ unsigned int asid; /* ASID used for this guest */ unsigned int handle; /* SEV firmware handle */ int fd; /* SEV device fd */ unsigned long pages_locked; /* Number of pages locked */ struct list_head regions_list; /* List of registered regions */ + u64 ap_jump_table; /* SEV-ES AP Jump Table address */ }; struct kvm_svm { @@ -106,6 +119,7 @@ struct vcpu_svm { struct vmcb *vmcb; unsigned long vmcb_pa; struct svm_cpu_data *svm_data; + u32 asid; uint64_t asid_generation; uint64_t sysenter_esp; uint64_t sysenter_eip; @@ -166,6 +180,17 @@ struct vcpu_svm { DECLARE_BITMAP(read, MAX_DIRECT_ACCESS_MSRS); DECLARE_BITMAP(write, MAX_DIRECT_ACCESS_MSRS); } shadow_msr_intercept; + + /* SEV-ES support */ + struct vmcb_save_area *vmsa; + struct ghcb *ghcb; + struct kvm_host_map ghcb_map; + + /* SEV-ES scratch area support */ + void *ghcb_sa; + u64 ghcb_sa_len; + bool ghcb_sa_sync; + bool ghcb_sa_free; }; struct svm_cpu_data { @@ -193,6 +218,28 @@ static inline struct kvm_svm *to_kvm_svm(struct kvm *kvm) return container_of(kvm, struct kvm_svm, kvm); } +static inline bool sev_guest(struct kvm *kvm) +{ +#ifdef CONFIG_KVM_AMD_SEV + struct kvm_sev_info *sev = &to_kvm_svm(kvm)->sev_info; + + return sev->active; +#else + return false; +#endif +} + +static inline bool sev_es_guest(struct kvm *kvm) +{ +#ifdef CONFIG_KVM_AMD_SEV + struct kvm_sev_info *sev = &to_kvm_svm(kvm)->sev_info; + + return sev_guest(kvm) && sev->es_active; +#else + return false; +#endif +} + static inline void vmcb_mark_all_dirty(struct vmcb *vmcb) { vmcb->control.clean = 0; @@ -244,21 +291,24 @@ static inline void set_dr_intercepts(struct vcpu_svm *svm) { struct vmcb *vmcb = get_host_vmcb(svm); - vmcb_set_intercept(&vmcb->control, INTERCEPT_DR0_READ); - vmcb_set_intercept(&vmcb->control, INTERCEPT_DR1_READ); - vmcb_set_intercept(&vmcb->control, INTERCEPT_DR2_READ); - vmcb_set_intercept(&vmcb->control, INTERCEPT_DR3_READ); - vmcb_set_intercept(&vmcb->control, INTERCEPT_DR4_READ); - vmcb_set_intercept(&vmcb->control, INTERCEPT_DR5_READ); - vmcb_set_intercept(&vmcb->control, INTERCEPT_DR6_READ); + if (!sev_es_guest(svm->vcpu.kvm)) { + vmcb_set_intercept(&vmcb->control, INTERCEPT_DR0_READ); + vmcb_set_intercept(&vmcb->control, INTERCEPT_DR1_READ); + vmcb_set_intercept(&vmcb->control, INTERCEPT_DR2_READ); + vmcb_set_intercept(&vmcb->control, INTERCEPT_DR3_READ); + vmcb_set_intercept(&vmcb->control, INTERCEPT_DR4_READ); + vmcb_set_intercept(&vmcb->control, INTERCEPT_DR5_READ); + vmcb_set_intercept(&vmcb->control, INTERCEPT_DR6_READ); + vmcb_set_intercept(&vmcb->control, INTERCEPT_DR0_WRITE); + vmcb_set_intercept(&vmcb->control, INTERCEPT_DR1_WRITE); + vmcb_set_intercept(&vmcb->control, INTERCEPT_DR2_WRITE); + vmcb_set_intercept(&vmcb->control, INTERCEPT_DR3_WRITE); + vmcb_set_intercept(&vmcb->control, INTERCEPT_DR4_WRITE); + vmcb_set_intercept(&vmcb->control, INTERCEPT_DR5_WRITE); + vmcb_set_intercept(&vmcb->control, INTERCEPT_DR6_WRITE); + } + vmcb_set_intercept(&vmcb->control, INTERCEPT_DR7_READ); - vmcb_set_intercept(&vmcb->control, INTERCEPT_DR0_WRITE); - vmcb_set_intercept(&vmcb->control, INTERCEPT_DR1_WRITE); - vmcb_set_intercept(&vmcb->control, INTERCEPT_DR2_WRITE); - vmcb_set_intercept(&vmcb->control, INTERCEPT_DR3_WRITE); - vmcb_set_intercept(&vmcb->control, INTERCEPT_DR4_WRITE); - vmcb_set_intercept(&vmcb->control, INTERCEPT_DR5_WRITE); - vmcb_set_intercept(&vmcb->control, INTERCEPT_DR6_WRITE); vmcb_set_intercept(&vmcb->control, INTERCEPT_DR7_WRITE); recalc_intercepts(svm); @@ -270,6 +320,12 @@ static inline void clr_dr_intercepts(struct vcpu_svm *svm) vmcb->control.intercepts[INTERCEPT_DR] = 0; + /* DR7 access must remain intercepted for an SEV-ES guest */ + if (sev_es_guest(svm->vcpu.kvm)) { + vmcb_set_intercept(&vmcb->control, INTERCEPT_DR7_READ); + vmcb_set_intercept(&vmcb->control, INTERCEPT_DR7_WRITE); + } + recalc_intercepts(svm); } @@ -351,6 +407,10 @@ static inline bool gif_set(struct vcpu_svm *svm) #define MSR_CR3_LONG_MBZ_MASK 0xfff0000000000000U #define MSR_INVALID 0xffffffffU +extern int sev; +extern int sev_es; +extern bool dump_invalid_vmcb; + u32 svm_msrpm_offset(u32 msr); u32 *svm_vcpu_alloc_msrpm(void); void svm_vcpu_init_msrpm(struct kvm_vcpu *vcpu, u32 *msrpm); @@ -358,13 +418,16 @@ void svm_vcpu_free_msrpm(u32 *msrpm); int svm_set_efer(struct kvm_vcpu *vcpu, u64 efer); void svm_set_cr0(struct kvm_vcpu *vcpu, unsigned long cr0); -int svm_set_cr4(struct kvm_vcpu *vcpu, unsigned long cr4); +void svm_set_cr4(struct kvm_vcpu *vcpu, unsigned long cr4); void svm_flush_tlb(struct kvm_vcpu *vcpu); void disable_nmi_singlestep(struct vcpu_svm *svm); bool svm_smi_blocked(struct kvm_vcpu *vcpu); bool svm_nmi_blocked(struct kvm_vcpu *vcpu); bool svm_interrupt_blocked(struct kvm_vcpu *vcpu); void svm_set_gif(struct vcpu_svm *svm, bool value); +int svm_invoke_exit_handler(struct vcpu_svm *svm, u64 exit_code); +void set_msr_interception(struct kvm_vcpu *vcpu, u32 *msrpm, u32 msr, + int read, int write); /* nested.c */ @@ -470,18 +533,42 @@ void svm_vcpu_unblocking(struct kvm_vcpu *vcpu); /* sev.c */ -extern unsigned int max_sev_asid; +#define GHCB_VERSION_MAX 1ULL +#define GHCB_VERSION_MIN 1ULL + +#define GHCB_MSR_INFO_POS 0 +#define GHCB_MSR_INFO_MASK (BIT_ULL(12) - 1) + +#define GHCB_MSR_SEV_INFO_RESP 0x001 +#define GHCB_MSR_SEV_INFO_REQ 0x002 +#define GHCB_MSR_VER_MAX_POS 48 +#define GHCB_MSR_VER_MAX_MASK 0xffff +#define GHCB_MSR_VER_MIN_POS 32 +#define GHCB_MSR_VER_MIN_MASK 0xffff +#define GHCB_MSR_CBIT_POS 24 +#define GHCB_MSR_CBIT_MASK 0xff +#define GHCB_MSR_SEV_INFO(_max, _min, _cbit) \ + ((((_max) & GHCB_MSR_VER_MAX_MASK) << GHCB_MSR_VER_MAX_POS) | \ + (((_min) & GHCB_MSR_VER_MIN_MASK) << GHCB_MSR_VER_MIN_POS) | \ + (((_cbit) & GHCB_MSR_CBIT_MASK) << GHCB_MSR_CBIT_POS) | \ + GHCB_MSR_SEV_INFO_RESP) + +#define GHCB_MSR_CPUID_REQ 0x004 +#define GHCB_MSR_CPUID_RESP 0x005 +#define GHCB_MSR_CPUID_FUNC_POS 32 +#define GHCB_MSR_CPUID_FUNC_MASK 0xffffffff +#define GHCB_MSR_CPUID_VALUE_POS 32 +#define GHCB_MSR_CPUID_VALUE_MASK 0xffffffff +#define GHCB_MSR_CPUID_REG_POS 30 +#define GHCB_MSR_CPUID_REG_MASK 0x3 + +#define GHCB_MSR_TERM_REQ 0x100 +#define GHCB_MSR_TERM_REASON_SET_POS 12 +#define GHCB_MSR_TERM_REASON_SET_MASK 0xf +#define GHCB_MSR_TERM_REASON_POS 16 +#define GHCB_MSR_TERM_REASON_MASK 0xff -static inline bool sev_guest(struct kvm *kvm) -{ -#ifdef CONFIG_KVM_AMD_SEV - struct kvm_sev_info *sev = &to_kvm_svm(kvm)->sev_info; - - return sev->active; -#else - return false; -#endif -} +extern unsigned int max_sev_asid; static inline bool svm_sev_enabled(void) { @@ -495,7 +582,19 @@ int svm_register_enc_region(struct kvm *kvm, int svm_unregister_enc_region(struct kvm *kvm, struct kvm_enc_region *range); void pre_sev_run(struct vcpu_svm *svm, int cpu); -int __init sev_hardware_setup(void); +void __init sev_hardware_setup(void); void sev_hardware_teardown(void); +void sev_free_vcpu(struct kvm_vcpu *vcpu); +int sev_handle_vmgexit(struct vcpu_svm *svm); +int sev_es_string_io(struct vcpu_svm *svm, int size, unsigned int port, int in); +void sev_es_init_vmcb(struct vcpu_svm *svm); +void sev_es_create_vcpu(struct vcpu_svm *svm); +void sev_es_vcpu_load(struct vcpu_svm *svm, int cpu); +void sev_es_vcpu_put(struct vcpu_svm *svm); + +/* vmenter.S */ + +void __svm_sev_es_vcpu_run(unsigned long vmcb_pa); +void __svm_vcpu_run(unsigned long vmcb_pa, unsigned long *regs); #endif diff --git a/arch/x86/kvm/svm/vmenter.S b/arch/x86/kvm/svm/vmenter.S index 1ec1ac40e328..6feb8c08f45a 100644 --- a/arch/x86/kvm/svm/vmenter.S +++ b/arch/x86/kvm/svm/vmenter.S @@ -168,3 +168,53 @@ SYM_FUNC_START(__svm_vcpu_run) pop %_ASM_BP ret SYM_FUNC_END(__svm_vcpu_run) + +/** + * __svm_sev_es_vcpu_run - Run a SEV-ES vCPU via a transition to SVM guest mode + * @vmcb_pa: unsigned long + */ +SYM_FUNC_START(__svm_sev_es_vcpu_run) + push %_ASM_BP +#ifdef CONFIG_X86_64 + push %r15 + push %r14 + push %r13 + push %r12 +#else + push %edi + push %esi +#endif + push %_ASM_BX + + /* Enter guest mode */ + mov %_ASM_ARG1, %_ASM_AX + sti + +1: vmrun %_ASM_AX + jmp 3f +2: cmpb $0, kvm_rebooting + jne 3f + ud2 + _ASM_EXTABLE(1b, 2b) + +3: cli + +#ifdef CONFIG_RETPOLINE + /* IMPORTANT: Stuff the RSB immediately after VM-Exit, before RET! */ + FILL_RETURN_BUFFER %_ASM_AX, RSB_CLEAR_LOOPS, X86_FEATURE_RETPOLINE +#endif + + pop %_ASM_BX + +#ifdef CONFIG_X86_64 + pop %r12 + pop %r13 + pop %r14 + pop %r15 +#else + pop %esi + pop %edi +#endif + pop %_ASM_BP + ret +SYM_FUNC_END(__svm_sev_es_vcpu_run) diff --git a/arch/x86/kvm/trace.h b/arch/x86/kvm/trace.h index aef960f90f26..2de30c20bc26 100644 --- a/arch/x86/kvm/trace.h +++ b/arch/x86/kvm/trace.h @@ -1578,6 +1578,103 @@ TRACE_EVENT(kvm_hv_syndbg_get_msr, __entry->vcpu_id, __entry->vp_index, __entry->msr, __entry->data) ); + +/* + * Tracepoint for the start of VMGEXIT processing + */ +TRACE_EVENT(kvm_vmgexit_enter, + TP_PROTO(unsigned int vcpu_id, struct ghcb *ghcb), + TP_ARGS(vcpu_id, ghcb), + + TP_STRUCT__entry( + __field(unsigned int, vcpu_id) + __field(u64, exit_reason) + __field(u64, info1) + __field(u64, info2) + ), + + TP_fast_assign( + __entry->vcpu_id = vcpu_id; + __entry->exit_reason = ghcb->save.sw_exit_code; + __entry->info1 = ghcb->save.sw_exit_info_1; + __entry->info2 = ghcb->save.sw_exit_info_2; + ), + + TP_printk("vcpu %u, exit_reason %llx, exit_info1 %llx, exit_info2 %llx", + __entry->vcpu_id, __entry->exit_reason, + __entry->info1, __entry->info2) +); + +/* + * Tracepoint for the end of VMGEXIT processing + */ +TRACE_EVENT(kvm_vmgexit_exit, + TP_PROTO(unsigned int vcpu_id, struct ghcb *ghcb), + TP_ARGS(vcpu_id, ghcb), + + TP_STRUCT__entry( + __field(unsigned int, vcpu_id) + __field(u64, exit_reason) + __field(u64, info1) + __field(u64, info2) + ), + + TP_fast_assign( + __entry->vcpu_id = vcpu_id; + __entry->exit_reason = ghcb->save.sw_exit_code; + __entry->info1 = ghcb->save.sw_exit_info_1; + __entry->info2 = ghcb->save.sw_exit_info_2; + ), + + TP_printk("vcpu %u, exit_reason %llx, exit_info1 %llx, exit_info2 %llx", + __entry->vcpu_id, __entry->exit_reason, + __entry->info1, __entry->info2) +); + +/* + * Tracepoint for the start of VMGEXIT MSR procotol processing + */ +TRACE_EVENT(kvm_vmgexit_msr_protocol_enter, + TP_PROTO(unsigned int vcpu_id, u64 ghcb_gpa), + TP_ARGS(vcpu_id, ghcb_gpa), + + TP_STRUCT__entry( + __field(unsigned int, vcpu_id) + __field(u64, ghcb_gpa) + ), + + TP_fast_assign( + __entry->vcpu_id = vcpu_id; + __entry->ghcb_gpa = ghcb_gpa; + ), + + TP_printk("vcpu %u, ghcb_gpa %016llx", + __entry->vcpu_id, __entry->ghcb_gpa) +); + +/* + * Tracepoint for the end of VMGEXIT MSR procotol processing + */ +TRACE_EVENT(kvm_vmgexit_msr_protocol_exit, + TP_PROTO(unsigned int vcpu_id, u64 ghcb_gpa, int result), + TP_ARGS(vcpu_id, ghcb_gpa, result), + + TP_STRUCT__entry( + __field(unsigned int, vcpu_id) + __field(u64, ghcb_gpa) + __field(int, result) + ), + + TP_fast_assign( + __entry->vcpu_id = vcpu_id; + __entry->ghcb_gpa = ghcb_gpa; + __entry->result = result; + ), + + TP_printk("vcpu %u, ghcb_gpa %016llx, result %d", + __entry->vcpu_id, __entry->ghcb_gpa, __entry->result) +); + #endif /* _TRACE_KVM_H */ #undef TRACE_INCLUDE_PATH diff --git a/arch/x86/kvm/vmx/evmcs.c b/arch/x86/kvm/vmx/evmcs.c index f3199bb02f22..41f24661af04 100644 --- a/arch/x86/kvm/vmx/evmcs.c +++ b/arch/x86/kvm/vmx/evmcs.c @@ -326,7 +326,6 @@ bool nested_enlightened_vmentry(struct kvm_vcpu *vcpu, u64 *evmcs_gpa) uint16_t nested_get_evmcs_version(struct kvm_vcpu *vcpu) { - struct vcpu_vmx *vmx = to_vmx(vcpu); /* * vmcs_version represents the range of supported Enlightened VMCS * versions: lower 8 bits is the minimal version, higher 8 bits is the @@ -334,7 +333,7 @@ uint16_t nested_get_evmcs_version(struct kvm_vcpu *vcpu) * KVM_EVMCS_VERSION. */ if (kvm_cpu_cap_get(X86_FEATURE_VMX) && - vmx->nested.enlightened_vmcs_enabled) + (!vcpu || to_vmx(vcpu)->nested.enlightened_vmcs_enabled)) return (KVM_EVMCS_VERSION << 8) | 1; return 0; diff --git a/arch/x86/kvm/vmx/nested.c b/arch/x86/kvm/vmx/nested.c index 89af692deb7e..e2f26564a12d 100644 --- a/arch/x86/kvm/vmx/nested.c +++ b/arch/x86/kvm/vmx/nested.c @@ -2952,7 +2952,8 @@ static int nested_vmx_check_vmcs_link_ptr(struct kvm_vcpu *vcpu, static int nested_check_guest_non_reg_state(struct vmcs12 *vmcs12) { if (CC(vmcs12->guest_activity_state != GUEST_ACTIVITY_ACTIVE && - vmcs12->guest_activity_state != GUEST_ACTIVITY_HLT)) + vmcs12->guest_activity_state != GUEST_ACTIVITY_HLT && + vmcs12->guest_activity_state != GUEST_ACTIVITY_WAIT_SIPI)) return -EINVAL; return 0; @@ -3559,19 +3560,29 @@ static int nested_vmx_run(struct kvm_vcpu *vcpu, bool launch) */ nested_cache_shadow_vmcs12(vcpu, vmcs12); - /* - * If we're entering a halted L2 vcpu and the L2 vcpu won't be - * awakened by event injection or by an NMI-window VM-exit or - * by an interrupt-window VM-exit, halt the vcpu. - */ - if ((vmcs12->guest_activity_state == GUEST_ACTIVITY_HLT) && - !(vmcs12->vm_entry_intr_info_field & INTR_INFO_VALID_MASK) && - !(vmcs12->cpu_based_vm_exec_control & CPU_BASED_NMI_WINDOW_EXITING) && - !((vmcs12->cpu_based_vm_exec_control & CPU_BASED_INTR_WINDOW_EXITING) && - (vmcs12->guest_rflags & X86_EFLAGS_IF))) { + switch (vmcs12->guest_activity_state) { + case GUEST_ACTIVITY_HLT: + /* + * If we're entering a halted L2 vcpu and the L2 vcpu won't be + * awakened by event injection or by an NMI-window VM-exit or + * by an interrupt-window VM-exit, halt the vcpu. + */ + if (!(vmcs12->vm_entry_intr_info_field & INTR_INFO_VALID_MASK) && + !nested_cpu_has(vmcs12, CPU_BASED_NMI_WINDOW_EXITING) && + !(nested_cpu_has(vmcs12, CPU_BASED_INTR_WINDOW_EXITING) && + (vmcs12->guest_rflags & X86_EFLAGS_IF))) { + vmx->nested.nested_run_pending = 0; + return kvm_vcpu_halt(vcpu); + } + break; + case GUEST_ACTIVITY_WAIT_SIPI: vmx->nested.nested_run_pending = 0; - return kvm_vcpu_halt(vcpu); + vcpu->arch.mp_state = KVM_MP_STATE_INIT_RECEIVED; + break; + default: + break; } + return 1; vmentry_failed: @@ -3797,7 +3808,20 @@ static int vmx_check_nested_events(struct kvm_vcpu *vcpu) return -EBUSY; nested_vmx_update_pending_dbg(vcpu); clear_bit(KVM_APIC_INIT, &apic->pending_events); - nested_vmx_vmexit(vcpu, EXIT_REASON_INIT_SIGNAL, 0, 0); + if (vcpu->arch.mp_state != KVM_MP_STATE_INIT_RECEIVED) + nested_vmx_vmexit(vcpu, EXIT_REASON_INIT_SIGNAL, 0, 0); + return 0; + } + + if (lapic_in_kernel(vcpu) && + test_bit(KVM_APIC_SIPI, &apic->pending_events)) { + if (block_nested_events) + return -EBUSY; + + clear_bit(KVM_APIC_SIPI, &apic->pending_events); + if (vcpu->arch.mp_state == KVM_MP_STATE_INIT_RECEIVED) + nested_vmx_vmexit(vcpu, EXIT_REASON_SIPI_SIGNAL, 0, + apic->sipi_vector & 0xFFUL); return 0; } @@ -4036,6 +4060,8 @@ static void sync_vmcs02_to_vmcs12(struct kvm_vcpu *vcpu, struct vmcs12 *vmcs12) if (vcpu->arch.mp_state == KVM_MP_STATE_HALTED) vmcs12->guest_activity_state = GUEST_ACTIVITY_HLT; + else if (vcpu->arch.mp_state == KVM_MP_STATE_INIT_RECEIVED) + vmcs12->guest_activity_state = GUEST_ACTIVITY_WAIT_SIPI; else vmcs12->guest_activity_state = GUEST_ACTIVITY_ACTIVE; @@ -4814,7 +4840,7 @@ static int handle_vmon(struct kvm_vcpu *vcpu) /* * The Intel VMX Instruction Reference lists a bunch of bits that are * prerequisite to running VMXON, most notably cr4.VMXE must be set to - * 1 (see vmx_set_cr4() for when we allow the guest to set this). + * 1 (see vmx_is_valid_cr4() for when we allow the guest to set this). * Otherwise, we should fail with #UD. But most faulting conditions * have already been checked by hardware, prior to the VM-exit for * VMXON. We do test guest cr4.VMXE because processor CR4 always has @@ -6483,7 +6509,8 @@ void nested_vmx_setup_ctls_msrs(struct nested_vmx_msrs *msrs, u32 ept_caps) msrs->misc_low |= MSR_IA32_VMX_MISC_VMWRITE_SHADOW_RO_FIELDS | VMX_MISC_EMULATED_PREEMPTION_TIMER_RATE | - VMX_MISC_ACTIVITY_HLT; + VMX_MISC_ACTIVITY_HLT | + VMX_MISC_ACTIVITY_WAIT_SIPI; msrs->misc_high = 0; /* diff --git a/arch/x86/kvm/vmx/vmenter.S b/arch/x86/kvm/vmx/vmenter.S index 90ad7a6246e3..e85aa5faa22d 100644 --- a/arch/x86/kvm/vmx/vmenter.S +++ b/arch/x86/kvm/vmx/vmenter.S @@ -132,7 +132,7 @@ SYM_FUNC_START(__vmx_vcpu_run) mov (%_ASM_SP), %_ASM_AX /* Check if vmlaunch or vmresume is needed */ - cmpb $0, %bl + testb %bl, %bl /* Load guest registers. Don't clobber flags. */ mov VCPU_RCX(%_ASM_AX), %_ASM_CX diff --git a/arch/x86/kvm/vmx/vmx.c b/arch/x86/kvm/vmx/vmx.c index 47b8357b9751..75c9c6a0a3a4 100644 --- a/arch/x86/kvm/vmx/vmx.c +++ b/arch/x86/kvm/vmx/vmx.c @@ -40,7 +40,6 @@ #include <asm/irq_remapping.h> #include <asm/kexec.h> #include <asm/perf_event.h> -#include <asm/mce.h> #include <asm/mmu_context.h> #include <asm/mshyperv.h> #include <asm/mwait.h> @@ -1826,7 +1825,7 @@ static int vmx_get_msr(struct kvm_vcpu *vcpu, struct msr_data *msr_info) break; case MSR_IA32_SPEC_CTRL: if (!msr_info->host_initiated && - !guest_cpuid_has(vcpu, X86_FEATURE_SPEC_CTRL)) + !guest_has_spec_ctrl_msr(vcpu)) return 1; msr_info->data = to_vmx(vcpu)->spec_ctrl; @@ -2028,7 +2027,7 @@ static int vmx_set_msr(struct kvm_vcpu *vcpu, struct msr_data *msr_info) break; case MSR_IA32_SPEC_CTRL: if (!msr_info->host_initiated && - !guest_cpuid_has(vcpu, X86_FEATURE_SPEC_CTRL)) + !guest_has_spec_ctrl_msr(vcpu)) return 1; if (kvm_spec_ctrl_test_value(data)) @@ -2063,12 +2062,12 @@ static int vmx_set_msr(struct kvm_vcpu *vcpu, struct msr_data *msr_info) goto find_uret_msr; case MSR_IA32_PRED_CMD: if (!msr_info->host_initiated && - !guest_cpuid_has(vcpu, X86_FEATURE_SPEC_CTRL)) + !guest_has_pred_cmd_msr(vcpu)) return 1; if (data & ~PRED_CMD_IBPB) return 1; - if (!boot_cpu_has(X86_FEATURE_SPEC_CTRL)) + if (!boot_cpu_has(X86_FEATURE_IBPB)) return 1; if (!data) break; @@ -3095,8 +3094,25 @@ static void vmx_load_mmu_pgd(struct kvm_vcpu *vcpu, unsigned long pgd, vmcs_writel(GUEST_CR3, guest_cr3); } -int vmx_set_cr4(struct kvm_vcpu *vcpu, unsigned long cr4) +static bool vmx_is_valid_cr4(struct kvm_vcpu *vcpu, unsigned long cr4) { + /* + * We operate under the default treatment of SMM, so VMX cannot be + * enabled under SMM. Note, whether or not VMXE is allowed at all is + * handled by kvm_is_valid_cr4(). + */ + if ((cr4 & X86_CR4_VMXE) && is_smm(vcpu)) + return false; + + if (to_vmx(vcpu)->nested.vmxon && !nested_cr4_valid(vcpu, cr4)) + return false; + + return true; +} + +void vmx_set_cr4(struct kvm_vcpu *vcpu, unsigned long cr4) +{ + unsigned long old_cr4 = vcpu->arch.cr4; struct vcpu_vmx *vmx = to_vmx(vcpu); /* * Pass through host's Machine Check Enable value to hw_cr4, which @@ -3123,21 +3139,6 @@ int vmx_set_cr4(struct kvm_vcpu *vcpu, unsigned long cr4) } } - if (cr4 & X86_CR4_VMXE) { - /* - * To use VMXON (and later other VMX instructions), a guest - * must first be able to turn on cr4.VMXE (see handle_vmon()). - * So basically the check on whether to allow nested VMX - * is here. We operate under the default treatment of SMM, - * so VMX cannot be enabled under SMM. - */ - if (!nested_vmx_allowed(vcpu) || is_smm(vcpu)) - return 1; - } - - if (vmx->nested.vmxon && !nested_cr4_valid(vcpu, cr4)) - return 1; - vcpu->arch.cr4 = cr4; kvm_register_mark_available(vcpu, VCPU_EXREG_CR4); @@ -3168,7 +3169,9 @@ int vmx_set_cr4(struct kvm_vcpu *vcpu, unsigned long cr4) vmcs_writel(CR4_READ_SHADOW, cr4); vmcs_writel(GUEST_CR4, hw_cr4); - return 0; + + if ((cr4 ^ old_cr4) & (X86_CR4_OSXSAVE | X86_CR4_PKE)) + kvm_update_cpuid_runtime(vcpu); } void vmx_get_segment(struct kvm_vcpu *vcpu, struct kvm_segment *var, int seg) @@ -3515,42 +3518,33 @@ bool __vmx_guest_state_valid(struct kvm_vcpu *vcpu) return true; } -static int init_rmode_tss(struct kvm *kvm) +static int init_rmode_tss(struct kvm *kvm, void __user *ua) { - gfn_t fn; - u16 data = 0; - int idx, r; + const void *zero_page = (const void *) __va(page_to_phys(ZERO_PAGE(0))); + u16 data; + int i; + + for (i = 0; i < 3; i++) { + if (__copy_to_user(ua + PAGE_SIZE * i, zero_page, PAGE_SIZE)) + return -EFAULT; + } - idx = srcu_read_lock(&kvm->srcu); - fn = to_kvm_vmx(kvm)->tss_addr >> PAGE_SHIFT; - r = kvm_clear_guest_page(kvm, fn, 0, PAGE_SIZE); - if (r < 0) - goto out; data = TSS_BASE_SIZE + TSS_REDIRECTION_SIZE; - r = kvm_write_guest_page(kvm, fn++, &data, - TSS_IOPB_BASE_OFFSET, sizeof(u16)); - if (r < 0) - goto out; - r = kvm_clear_guest_page(kvm, fn++, 0, PAGE_SIZE); - if (r < 0) - goto out; - r = kvm_clear_guest_page(kvm, fn, 0, PAGE_SIZE); - if (r < 0) - goto out; + if (__copy_to_user(ua + TSS_IOPB_BASE_OFFSET, &data, sizeof(u16))) + return -EFAULT; + data = ~0; - r = kvm_write_guest_page(kvm, fn, &data, - RMODE_TSS_SIZE - 2 * PAGE_SIZE - 1, - sizeof(u8)); -out: - srcu_read_unlock(&kvm->srcu, idx); - return r; + if (__copy_to_user(ua + RMODE_TSS_SIZE - 1, &data, sizeof(u8))) + return -EFAULT; + + return 0; } static int init_rmode_identity_map(struct kvm *kvm) { struct kvm_vmx *kvm_vmx = to_kvm_vmx(kvm); int i, r = 0; - kvm_pfn_t identity_map_pfn; + void __user *uaddr; u32 tmp; /* Protect kvm_vmx->ept_identity_pagetable_done. */ @@ -3561,24 +3555,24 @@ static int init_rmode_identity_map(struct kvm *kvm) if (!kvm_vmx->ept_identity_map_addr) kvm_vmx->ept_identity_map_addr = VMX_EPT_IDENTITY_PAGETABLE_ADDR; - identity_map_pfn = kvm_vmx->ept_identity_map_addr >> PAGE_SHIFT; - r = __x86_set_memory_region(kvm, IDENTITY_PAGETABLE_PRIVATE_MEMSLOT, - kvm_vmx->ept_identity_map_addr, PAGE_SIZE); - if (r < 0) + uaddr = __x86_set_memory_region(kvm, + IDENTITY_PAGETABLE_PRIVATE_MEMSLOT, + kvm_vmx->ept_identity_map_addr, + PAGE_SIZE); + if (IS_ERR(uaddr)) { + r = PTR_ERR(uaddr); goto out; + } - r = kvm_clear_guest_page(kvm, identity_map_pfn, 0, PAGE_SIZE); - if (r < 0) - goto out; /* Set up identity-mapping pagetable for EPT in real mode */ for (i = 0; i < PT32_ENT_PER_PAGE; i++) { tmp = (i << 22) + (_PAGE_PRESENT | _PAGE_RW | _PAGE_USER | _PAGE_ACCESSED | _PAGE_DIRTY | _PAGE_PSE); - r = kvm_write_guest_page(kvm, identity_map_pfn, - &tmp, i * sizeof(tmp), sizeof(tmp)); - if (r < 0) + if (__copy_to_user(uaddr + i * sizeof(tmp), &tmp, sizeof(tmp))) { + r = -EFAULT; goto out; + } } kvm_vmx->ept_identity_pagetable_done = true; @@ -3605,19 +3599,22 @@ static void seg_setup(int seg) static int alloc_apic_access_page(struct kvm *kvm) { struct page *page; - int r = 0; + void __user *hva; + int ret = 0; mutex_lock(&kvm->slots_lock); if (kvm->arch.apic_access_page_done) goto out; - r = __x86_set_memory_region(kvm, APIC_ACCESS_PAGE_PRIVATE_MEMSLOT, - APIC_DEFAULT_PHYS_BASE, PAGE_SIZE); - if (r) + hva = __x86_set_memory_region(kvm, APIC_ACCESS_PAGE_PRIVATE_MEMSLOT, + APIC_DEFAULT_PHYS_BASE, PAGE_SIZE); + if (IS_ERR(hva)) { + ret = PTR_ERR(hva); goto out; + } page = gfn_to_page(kvm, APIC_DEFAULT_PHYS_BASE >> PAGE_SHIFT); if (is_error_page(page)) { - r = -EFAULT; + ret = -EFAULT; goto out; } @@ -3629,7 +3626,7 @@ static int alloc_apic_access_page(struct kvm *kvm) kvm->arch.apic_access_page_done = true; out: mutex_unlock(&kvm->slots_lock); - return r; + return ret; } int allocate_vpid(void) @@ -4638,7 +4635,7 @@ static int vmx_interrupt_allowed(struct kvm_vcpu *vcpu, bool for_injection) static int vmx_set_tss_addr(struct kvm *kvm, unsigned int addr) { - int ret; + void __user *ret; if (enable_unrestricted_guest) return 0; @@ -4648,10 +4645,12 @@ static int vmx_set_tss_addr(struct kvm *kvm, unsigned int addr) PAGE_SIZE * 3); mutex_unlock(&kvm->slots_lock); - if (ret) - return ret; + if (IS_ERR(ret)) + return PTR_ERR(ret); + to_kvm_vmx(kvm)->tss_addr = addr; - return init_rmode_tss(kvm); + + return init_rmode_tss(kvm, ret); } static int vmx_set_identity_map_addr(struct kvm *kvm, u64 ident_addr) @@ -4716,25 +4715,6 @@ static int handle_rmode_exception(struct kvm_vcpu *vcpu, return 1; } -/* - * Trigger machine check on the host. We assume all the MSRs are already set up - * by the CPU and that we still run on the same CPU as the MCE occurred on. - * We pass a fake environment to the machine check handler because we want - * the guest to be always treated like user space, no matter what context - * it used internally. - */ -static void kvm_machine_check(void) -{ -#if defined(CONFIG_X86_MCE) - struct pt_regs regs = { - .cs = 3, /* Fake ring 3 no matter what the guest ran on */ - .flags = X86_EFLAGS_IF, - }; - - do_machine_check(®s); -#endif -} - static int handle_machine_check(struct kvm_vcpu *vcpu) { /* handled by vmx_vcpu_run() */ @@ -6399,7 +6379,11 @@ static void vmx_handle_exit_irqoff(struct kvm_vcpu *vcpu) handle_exception_nmi_irqoff(vmx); } -static bool vmx_has_emulated_msr(u32 index) +/* + * The kvm parameter can be NULL (module initialization, or invocation before + * VM creation). Be sure to check the kvm parameter before using it. + */ +static bool vmx_has_emulated_msr(struct kvm *kvm, u32 index) { switch (index) { case MSR_IA32_SMBASE: @@ -7558,7 +7542,7 @@ static void enable_smi_window(struct kvm_vcpu *vcpu) static bool vmx_apic_init_signal_blocked(struct kvm_vcpu *vcpu) { - return to_vmx(vcpu)->nested.vmxon; + return to_vmx(vcpu)->nested.vmxon && !is_guest_mode(vcpu); } static void vmx_migrate_timers(struct kvm_vcpu *vcpu) @@ -7587,6 +7571,11 @@ static bool vmx_check_apicv_inhibit_reasons(ulong bit) return supported & BIT(bit); } +static int vmx_cpu_dirty_log_size(void) +{ + return enable_pml ? PML_ENTITY_NUM : 0; +} + static struct kvm_x86_ops vmx_x86_ops __initdata = { .hardware_unsetup = hardware_unsetup, @@ -7616,6 +7605,7 @@ static struct kvm_x86_ops vmx_x86_ops __initdata = { .get_cpl = vmx_get_cpl, .get_cs_db_l_bits = vmx_get_cs_db_l_bits, .set_cr0 = vmx_set_cr0, + .is_valid_cr4 = vmx_is_valid_cr4, .set_cr4 = vmx_set_cr4, .set_efer = vmx_set_efer, .get_idt = vmx_get_idt, @@ -7715,6 +7705,8 @@ static struct kvm_x86_ops vmx_x86_ops __initdata = { .migrate_timers = vmx_migrate_timers, .msr_filter_changed = vmx_msr_filter_changed, + .complete_emulated_msr = kvm_complete_insn_gp, + .cpu_dirty_log_size = vmx_cpu_dirty_log_size, }; static __init int hardware_setup(void) @@ -7832,6 +7824,7 @@ static __init int hardware_setup(void) vmx_x86_ops.slot_disable_log_dirty = NULL; vmx_x86_ops.flush_log_dirty = NULL; vmx_x86_ops.enable_log_dirty_pt_masked = NULL; + vmx_x86_ops.cpu_dirty_log_size = NULL; } if (!cpu_has_vmx_preemption_timer()) diff --git a/arch/x86/kvm/vmx/vmx.h b/arch/x86/kvm/vmx/vmx.h index f6f66e5c6510..9d3a557949ac 100644 --- a/arch/x86/kvm/vmx/vmx.h +++ b/arch/x86/kvm/vmx/vmx.h @@ -321,7 +321,7 @@ u32 vmx_get_interrupt_shadow(struct kvm_vcpu *vcpu); void vmx_set_interrupt_shadow(struct kvm_vcpu *vcpu, int mask); int vmx_set_efer(struct kvm_vcpu *vcpu, u64 efer); void vmx_set_cr0(struct kvm_vcpu *vcpu, unsigned long cr0); -int vmx_set_cr4(struct kvm_vcpu *vcpu, unsigned long cr4); +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); diff --git a/arch/x86/kvm/x86.c b/arch/x86/kvm/x86.c index e545a8a613b1..3f7c1fc7a3ce 100644 --- a/arch/x86/kvm/x86.c +++ b/arch/x86/kvm/x86.c @@ -197,7 +197,8 @@ EXPORT_SYMBOL_GPL(host_efer); bool __read_mostly allow_smaller_maxphyaddr = 0; EXPORT_SYMBOL_GPL(allow_smaller_maxphyaddr); -static u64 __read_mostly host_xss; +u64 __read_mostly host_xss; +EXPORT_SYMBOL_GPL(host_xss); u64 __read_mostly supported_xss; EXPORT_SYMBOL_GPL(supported_xss); @@ -804,11 +805,29 @@ bool pdptrs_changed(struct kvm_vcpu *vcpu) } EXPORT_SYMBOL_GPL(pdptrs_changed); +void kvm_post_set_cr0(struct kvm_vcpu *vcpu, unsigned long old_cr0, unsigned long cr0) +{ + unsigned long update_bits = X86_CR0_PG | X86_CR0_WP; + + if ((cr0 ^ old_cr0) & X86_CR0_PG) { + kvm_clear_async_pf_completion_queue(vcpu); + kvm_async_pf_hash_reset(vcpu); + } + + if ((cr0 ^ old_cr0) & update_bits) + kvm_mmu_reset_context(vcpu); + + if (((cr0 ^ old_cr0) & X86_CR0_CD) && + kvm_arch_has_noncoherent_dma(vcpu->kvm) && + !kvm_check_has_quirk(vcpu->kvm, KVM_X86_QUIRK_CD_NW_CLEARED)) + kvm_zap_gfn_range(vcpu->kvm, 0, ~0ULL); +} +EXPORT_SYMBOL_GPL(kvm_post_set_cr0); + int kvm_set_cr0(struct kvm_vcpu *vcpu, unsigned long cr0) { unsigned long old_cr0 = kvm_read_cr0(vcpu); unsigned long pdptr_bits = X86_CR0_CD | X86_CR0_NW | X86_CR0_PG; - unsigned long update_bits = X86_CR0_PG | X86_CR0_WP; cr0 |= X86_CR0_ET; @@ -847,18 +866,7 @@ int kvm_set_cr0(struct kvm_vcpu *vcpu, unsigned long cr0) kvm_x86_ops.set_cr0(vcpu, cr0); - if ((cr0 ^ old_cr0) & X86_CR0_PG) { - kvm_clear_async_pf_completion_queue(vcpu); - kvm_async_pf_hash_reset(vcpu); - } - - if ((cr0 ^ old_cr0) & update_bits) - kvm_mmu_reset_context(vcpu); - - if (((cr0 ^ old_cr0) & X86_CR0_CD) && - kvm_arch_has_noncoherent_dma(vcpu->kvm) && - !kvm_check_has_quirk(vcpu->kvm, KVM_X86_QUIRK_CD_NW_CLEARED)) - kvm_zap_gfn_range(vcpu->kvm, 0, ~0ULL); + kvm_post_set_cr0(vcpu, old_cr0, cr0); return 0; } @@ -872,6 +880,9 @@ EXPORT_SYMBOL_GPL(kvm_lmsw); void kvm_load_guest_xsave_state(struct kvm_vcpu *vcpu) { + if (vcpu->arch.guest_state_protected) + return; + if (kvm_read_cr4_bits(vcpu, X86_CR4_OSXSAVE)) { if (vcpu->arch.xcr0 != host_xcr0) @@ -892,6 +903,9 @@ EXPORT_SYMBOL_GPL(kvm_load_guest_xsave_state); void kvm_load_host_xsave_state(struct kvm_vcpu *vcpu) { + if (vcpu->arch.guest_state_protected) + return; + if (static_cpu_has(X86_FEATURE_PKU) && (kvm_read_cr4_bits(vcpu, X86_CR4_PKE) || (vcpu->arch.xcr0 & XFEATURE_MASK_PKRU))) { @@ -964,26 +978,36 @@ int kvm_set_xcr(struct kvm_vcpu *vcpu, u32 index, u64 xcr) } EXPORT_SYMBOL_GPL(kvm_set_xcr); -int kvm_valid_cr4(struct kvm_vcpu *vcpu, unsigned long cr4) +bool kvm_is_valid_cr4(struct kvm_vcpu *vcpu, unsigned long cr4) { if (cr4 & cr4_reserved_bits) - return -EINVAL; + return false; if (cr4 & vcpu->arch.cr4_guest_rsvd_bits) - return -EINVAL; + return false; - return 0; + return kvm_x86_ops.is_valid_cr4(vcpu, cr4); +} +EXPORT_SYMBOL_GPL(kvm_is_valid_cr4); + +void kvm_post_set_cr4(struct kvm_vcpu *vcpu, unsigned long old_cr4, unsigned long cr4) +{ + unsigned long mmu_role_bits = X86_CR4_PGE | X86_CR4_PSE | X86_CR4_PAE | + X86_CR4_SMEP | X86_CR4_SMAP | X86_CR4_PKE; + + if (((cr4 ^ old_cr4) & mmu_role_bits) || + (!(cr4 & X86_CR4_PCIDE) && (old_cr4 & X86_CR4_PCIDE))) + kvm_mmu_reset_context(vcpu); } -EXPORT_SYMBOL_GPL(kvm_valid_cr4); +EXPORT_SYMBOL_GPL(kvm_post_set_cr4); int kvm_set_cr4(struct kvm_vcpu *vcpu, unsigned long cr4) { unsigned long old_cr4 = kvm_read_cr4(vcpu); unsigned long pdptr_bits = X86_CR4_PGE | X86_CR4_PSE | X86_CR4_PAE | X86_CR4_SMEP; - unsigned long mmu_role_bits = pdptr_bits | X86_CR4_SMAP | X86_CR4_PKE; - if (kvm_valid_cr4(vcpu, cr4)) + if (!kvm_is_valid_cr4(vcpu, cr4)) return 1; if (is_long_mode(vcpu)) { @@ -1006,15 +1030,9 @@ int kvm_set_cr4(struct kvm_vcpu *vcpu, unsigned long cr4) return 1; } - if (kvm_x86_ops.set_cr4(vcpu, cr4)) - return 1; + kvm_x86_ops.set_cr4(vcpu, cr4); - if (((cr4 ^ old_cr4) & mmu_role_bits) || - (!(cr4 & X86_CR4_PCIDE) && (old_cr4 & X86_CR4_PCIDE))) - kvm_mmu_reset_context(vcpu); - - if ((cr4 ^ old_cr4) & (X86_CR4_OSXSAVE | X86_CR4_PKE)) - kvm_update_cpuid_runtime(vcpu); + kvm_post_set_cr4(vcpu, old_cr4, cr4); return 0; } @@ -1638,27 +1656,20 @@ int kvm_set_msr(struct kvm_vcpu *vcpu, u32 index, u64 data) } EXPORT_SYMBOL_GPL(kvm_set_msr); -static int complete_emulated_msr(struct kvm_vcpu *vcpu, bool is_read) +static int complete_emulated_rdmsr(struct kvm_vcpu *vcpu) { - if (vcpu->run->msr.error) { - kvm_inject_gp(vcpu, 0); - return 1; - } else if (is_read) { + int err = vcpu->run->msr.error; + if (!err) { kvm_rax_write(vcpu, (u32)vcpu->run->msr.data); kvm_rdx_write(vcpu, vcpu->run->msr.data >> 32); } - return kvm_skip_emulated_instruction(vcpu); -} - -static int complete_emulated_rdmsr(struct kvm_vcpu *vcpu) -{ - return complete_emulated_msr(vcpu, true); + return kvm_x86_ops.complete_emulated_msr(vcpu, err); } static int complete_emulated_wrmsr(struct kvm_vcpu *vcpu) { - return complete_emulated_msr(vcpu, false); + return kvm_x86_ops.complete_emulated_msr(vcpu, vcpu->run->msr.error); } static u64 kvm_msr_reason(int r) @@ -1721,18 +1732,16 @@ int kvm_emulate_rdmsr(struct kvm_vcpu *vcpu) return 0; } - /* MSR read failed? Inject a #GP */ - if (r) { + if (!r) { + trace_kvm_msr_read(ecx, data); + + kvm_rax_write(vcpu, data & -1u); + kvm_rdx_write(vcpu, (data >> 32) & -1u); + } else { trace_kvm_msr_read_ex(ecx); - kvm_inject_gp(vcpu, 0); - return 1; } - trace_kvm_msr_read(ecx, data); - - kvm_rax_write(vcpu, data & -1u); - kvm_rdx_write(vcpu, (data >> 32) & -1u); - return kvm_skip_emulated_instruction(vcpu); + return kvm_x86_ops.complete_emulated_msr(vcpu, r); } EXPORT_SYMBOL_GPL(kvm_emulate_rdmsr); @@ -1753,15 +1762,12 @@ int kvm_emulate_wrmsr(struct kvm_vcpu *vcpu) if (r < 0) return r; - /* MSR write failed? Inject a #GP */ - if (r > 0) { + if (!r) + trace_kvm_msr_write(ecx, data); + else trace_kvm_msr_write_ex(ecx, data); - kvm_inject_gp(vcpu, 0); - return 1; - } - trace_kvm_msr_write(ecx, data); - return kvm_skip_emulated_instruction(vcpu); + return kvm_x86_ops.complete_emulated_msr(vcpu, r); } EXPORT_SYMBOL_GPL(kvm_emulate_wrmsr); @@ -3678,6 +3684,27 @@ static inline bool kvm_can_mwait_in_guest(void) boot_cpu_has(X86_FEATURE_ARAT); } +static int kvm_ioctl_get_supported_hv_cpuid(struct kvm_vcpu *vcpu, + struct kvm_cpuid2 __user *cpuid_arg) +{ + struct kvm_cpuid2 cpuid; + int r; + + r = -EFAULT; + if (copy_from_user(&cpuid, cpuid_arg, sizeof(cpuid))) + return r; + + r = kvm_get_hv_cpuid(vcpu, &cpuid, cpuid_arg->entries); + if (r) + return r; + + r = -EFAULT; + if (copy_to_user(cpuid_arg, &cpuid, sizeof(cpuid))) + return r; + + return 0; +} + int kvm_vm_ioctl_check_extension(struct kvm *kvm, long ext) { int r = 0; @@ -3714,6 +3741,7 @@ int kvm_vm_ioctl_check_extension(struct kvm *kvm, long ext) case KVM_CAP_HYPERV_TLBFLUSH: case KVM_CAP_HYPERV_SEND_IPI: case KVM_CAP_HYPERV_CPUID: + case KVM_CAP_SYS_HYPERV_CPUID: case KVM_CAP_PCI_SEGMENT: case KVM_CAP_DEBUGREGS: case KVM_CAP_X86_ROBUST_SINGLESTEP: @@ -3762,7 +3790,7 @@ int kvm_vm_ioctl_check_extension(struct kvm *kvm, long ext) * fringe case that is not enabled except via specific settings * of the module parameters. */ - r = kvm_x86_ops.has_emulated_msr(MSR_IA32_SMBASE); + r = kvm_x86_ops.has_emulated_msr(kvm, MSR_IA32_SMBASE); break; case KVM_CAP_VAPIC: r = !kvm_x86_ops.cpu_has_accelerated_tpr(); @@ -3899,6 +3927,9 @@ long kvm_arch_dev_ioctl(struct file *filp, case KVM_GET_MSRS: r = msr_io(NULL, argp, do_get_msr_feature, 1); break; + case KVM_GET_SUPPORTED_HV_CPUID: + r = kvm_ioctl_get_supported_hv_cpuid(NULL, argp); + break; default: r = -EINVAL; break; @@ -3997,7 +4028,7 @@ void kvm_arch_vcpu_put(struct kvm_vcpu *vcpu) { int idx; - if (vcpu->preempted) + if (vcpu->preempted && !vcpu->arch.guest_state_protected) vcpu->arch.preempted_in_kernel = !kvm_x86_ops.get_cpl(vcpu); /* @@ -4481,6 +4512,9 @@ static void load_xsave(struct kvm_vcpu *vcpu, u8 *src) static void kvm_vcpu_ioctl_x86_get_xsave(struct kvm_vcpu *vcpu, struct kvm_xsave *guest_xsave) { + if (!vcpu->arch.guest_fpu) + return; + if (boot_cpu_has(X86_FEATURE_XSAVE)) { memset(guest_xsave, 0, sizeof(struct kvm_xsave)); fill_xsave((u8 *) guest_xsave->region, vcpu); @@ -4498,9 +4532,14 @@ static void kvm_vcpu_ioctl_x86_get_xsave(struct kvm_vcpu *vcpu, static int kvm_vcpu_ioctl_x86_set_xsave(struct kvm_vcpu *vcpu, struct kvm_xsave *guest_xsave) { - u64 xstate_bv = - *(u64 *)&guest_xsave->region[XSAVE_HDR_OFFSET / sizeof(u32)]; - u32 mxcsr = *(u32 *)&guest_xsave->region[XSAVE_MXCSR_OFFSET / sizeof(u32)]; + u64 xstate_bv; + u32 mxcsr; + + if (!vcpu->arch.guest_fpu) + return 0; + + xstate_bv = *(u64 *)&guest_xsave->region[XSAVE_HDR_OFFSET / sizeof(u32)]; + mxcsr = *(u32 *)&guest_xsave->region[XSAVE_MXCSR_OFFSET / sizeof(u32)]; if (boot_cpu_has(X86_FEATURE_XSAVE)) { /* @@ -4977,25 +5016,9 @@ long kvm_arch_vcpu_ioctl(struct file *filp, srcu_read_unlock(&vcpu->kvm->srcu, idx); break; } - case KVM_GET_SUPPORTED_HV_CPUID: { - struct kvm_cpuid2 __user *cpuid_arg = argp; - struct kvm_cpuid2 cpuid; - - r = -EFAULT; - if (copy_from_user(&cpuid, cpuid_arg, sizeof(cpuid))) - goto out; - - r = kvm_vcpu_ioctl_get_hv_cpuid(vcpu, &cpuid, - cpuid_arg->entries); - if (r) - goto out; - - r = -EFAULT; - if (copy_to_user(cpuid_arg, &cpuid, sizeof(cpuid))) - goto out; - r = 0; + case KVM_GET_SUPPORTED_HV_CPUID: + r = kvm_ioctl_get_supported_hv_cpuid(vcpu, argp); break; - } default: r = -EINVAL; } @@ -5776,7 +5799,7 @@ static void kvm_init_msr_list(void) } for (i = 0; i < ARRAY_SIZE(emulated_msrs_all); i++) { - if (!kvm_x86_ops.has_emulated_msr(emulated_msrs_all[i])) + if (!kvm_x86_ops.has_emulated_msr(NULL, emulated_msrs_all[i])) continue; emulated_msrs[num_emulated_msrs++] = emulated_msrs_all[i]; @@ -8158,7 +8181,14 @@ static void post_kvm_run_save(struct kvm_vcpu *vcpu) { struct kvm_run *kvm_run = vcpu->run; - kvm_run->if_flag = (kvm_get_rflags(vcpu) & X86_EFLAGS_IF) != 0; + /* + * if_flag is obsolete and useless, so do not bother + * setting it for SEV-ES guests. Userspace can just + * use kvm_run->ready_for_interrupt_injection. + */ + kvm_run->if_flag = !vcpu->arch.guest_state_protected + && (kvm_get_rflags(vcpu) & X86_EFLAGS_IF) != 0; + kvm_run->flags = is_smm(vcpu) ? KVM_RUN_X86_SMM : 0; kvm_run->cr8 = kvm_get_cr8(vcpu); kvm_run->apic_base = kvm_get_apic_base(vcpu); @@ -8748,6 +8778,15 @@ static int vcpu_enter_guest(struct kvm_vcpu *vcpu) bool req_immediate_exit = false; + /* Forbid vmenter if vcpu dirty ring is soft-full */ + if (unlikely(vcpu->kvm->dirty_ring_size && + kvm_dirty_ring_soft_full(&vcpu->dirty_ring))) { + vcpu->run->exit_reason = KVM_EXIT_DIRTY_RING_FULL; + trace_kvm_dirty_ring_exit(vcpu); + r = 0; + goto out; + } + if (kvm_request_pending(vcpu)) { if (kvm_check_request(KVM_REQ_GET_NESTED_STATE_PAGES, vcpu)) { if (unlikely(!kvm_x86_ops.nested_ops->get_nested_state_pages(vcpu))) { @@ -9223,9 +9262,14 @@ static void kvm_load_guest_fpu(struct kvm_vcpu *vcpu) kvm_save_current_fpu(vcpu->arch.user_fpu); - /* PKRU is separately restored in kvm_x86_ops.run. */ - __copy_kernel_to_fpregs(&vcpu->arch.guest_fpu->state, - ~XFEATURE_MASK_PKRU); + /* + * Guests with protected state can't have it set by the hypervisor, + * so skip trying to set it. + */ + if (vcpu->arch.guest_fpu) + /* PKRU is separately restored in kvm_x86_ops.run. */ + __copy_kernel_to_fpregs(&vcpu->arch.guest_fpu->state, + ~XFEATURE_MASK_PKRU); fpregs_mark_activate(); fpregs_unlock(); @@ -9238,7 +9282,12 @@ static void kvm_put_guest_fpu(struct kvm_vcpu *vcpu) { fpregs_lock(); - kvm_save_current_fpu(vcpu->arch.guest_fpu); + /* + * Guests with protected state can't have it read by the hypervisor, + * so skip trying to save it. + */ + if (vcpu->arch.guest_fpu) + kvm_save_current_fpu(vcpu->arch.guest_fpu); copy_kernel_to_fpregs(&vcpu->arch.user_fpu->state); @@ -9417,6 +9466,9 @@ static void __get_sregs(struct kvm_vcpu *vcpu, struct kvm_sregs *sregs) { struct desc_ptr dt; + if (vcpu->arch.guest_state_protected) + goto skip_protected_regs; + kvm_get_segment(vcpu, &sregs->cs, VCPU_SREG_CS); kvm_get_segment(vcpu, &sregs->ds, VCPU_SREG_DS); kvm_get_segment(vcpu, &sregs->es, VCPU_SREG_ES); @@ -9434,9 +9486,11 @@ static void __get_sregs(struct kvm_vcpu *vcpu, struct kvm_sregs *sregs) sregs->gdt.limit = dt.size; sregs->gdt.base = dt.address; - sregs->cr0 = kvm_read_cr0(vcpu); sregs->cr2 = vcpu->arch.cr2; sregs->cr3 = kvm_read_cr3(vcpu); + +skip_protected_regs: + sregs->cr0 = kvm_read_cr0(vcpu); sregs->cr4 = kvm_read_cr4(vcpu); sregs->cr8 = kvm_get_cr8(vcpu); sregs->efer = vcpu->arch.efer; @@ -9535,7 +9589,7 @@ int kvm_task_switch(struct kvm_vcpu *vcpu, u16 tss_selector, int idt_index, } EXPORT_SYMBOL_GPL(kvm_task_switch); -static int kvm_valid_sregs(struct kvm_vcpu *vcpu, struct kvm_sregs *sregs) +static bool kvm_is_valid_sregs(struct kvm_vcpu *vcpu, struct kvm_sregs *sregs) { if ((sregs->efer & EFER_LME) && (sregs->cr0 & X86_CR0_PG)) { /* @@ -9543,31 +9597,29 @@ static int kvm_valid_sregs(struct kvm_vcpu *vcpu, struct kvm_sregs *sregs) * 64-bit mode (though maybe in a 32-bit code segment). * CR4.PAE and EFER.LMA must be set. */ - if (!(sregs->cr4 & X86_CR4_PAE) - || !(sregs->efer & EFER_LMA)) - return -EINVAL; + if (!(sregs->cr4 & X86_CR4_PAE) || !(sregs->efer & EFER_LMA)) + return false; } else { /* * Not in 64-bit mode: EFER.LMA is clear and the code * segment cannot be 64-bit. */ if (sregs->efer & EFER_LMA || sregs->cs.l) - return -EINVAL; + return false; } - return kvm_valid_cr4(vcpu, sregs->cr4); + return kvm_is_valid_cr4(vcpu, sregs->cr4); } static int __set_sregs(struct kvm_vcpu *vcpu, struct kvm_sregs *sregs) { struct msr_data apic_base_msr; int mmu_reset_needed = 0; - int cpuid_update_needed = 0; int pending_vec, max_bits, idx; struct desc_ptr dt; int ret = -EINVAL; - if (kvm_valid_sregs(vcpu, sregs)) + if (!kvm_is_valid_sregs(vcpu, sregs)) goto out; apic_base_msr.data = sregs->apic_base; @@ -9575,6 +9627,9 @@ static int __set_sregs(struct kvm_vcpu *vcpu, struct kvm_sregs *sregs) if (kvm_set_apic_base(vcpu, &apic_base_msr)) goto out; + if (vcpu->arch.guest_state_protected) + goto skip_protected_regs; + dt.size = sregs->idt.limit; dt.address = sregs->idt.base; kvm_x86_ops.set_idt(vcpu, &dt); @@ -9597,11 +9652,7 @@ static int __set_sregs(struct kvm_vcpu *vcpu, struct kvm_sregs *sregs) vcpu->arch.cr0 = sregs->cr0; mmu_reset_needed |= kvm_read_cr4(vcpu) != sregs->cr4; - cpuid_update_needed |= ((kvm_read_cr4(vcpu) ^ sregs->cr4) & - (X86_CR4_OSXSAVE | X86_CR4_PKE)); kvm_x86_ops.set_cr4(vcpu, sregs->cr4); - if (cpuid_update_needed) - kvm_update_cpuid_runtime(vcpu); idx = srcu_read_lock(&vcpu->kvm->srcu); if (is_pae_paging(vcpu)) { @@ -9613,14 +9664,6 @@ static int __set_sregs(struct kvm_vcpu *vcpu, struct kvm_sregs *sregs) if (mmu_reset_needed) kvm_mmu_reset_context(vcpu); - max_bits = KVM_NR_INTERRUPTS; - pending_vec = find_first_bit( - (const unsigned long *)sregs->interrupt_bitmap, max_bits); - if (pending_vec < max_bits) { - kvm_queue_interrupt(vcpu, pending_vec, false); - pr_debug("Set back pending irq %d\n", pending_vec); - } - kvm_set_segment(vcpu, &sregs->cs, VCPU_SREG_CS); kvm_set_segment(vcpu, &sregs->ds, VCPU_SREG_DS); kvm_set_segment(vcpu, &sregs->es, VCPU_SREG_ES); @@ -9639,6 +9682,15 @@ static int __set_sregs(struct kvm_vcpu *vcpu, struct kvm_sregs *sregs) !is_protmode(vcpu)) vcpu->arch.mp_state = KVM_MP_STATE_RUNNABLE; +skip_protected_regs: + max_bits = KVM_NR_INTERRUPTS; + pending_vec = find_first_bit( + (const unsigned long *)sregs->interrupt_bitmap, max_bits); + if (pending_vec < max_bits) { + kvm_queue_interrupt(vcpu, pending_vec, false); + pr_debug("Set back pending irq %d\n", pending_vec); + } + kvm_make_request(KVM_REQ_EVENT, vcpu); ret = 0; @@ -9663,6 +9715,9 @@ int kvm_arch_vcpu_ioctl_set_guest_debug(struct kvm_vcpu *vcpu, unsigned long rflags; int i, r; + if (vcpu->arch.guest_state_protected) + return -EINVAL; + vcpu_load(vcpu); if (dbg->control & (KVM_GUESTDBG_INJECT_DB | KVM_GUESTDBG_INJECT_BP)) { @@ -9742,6 +9797,9 @@ int kvm_arch_vcpu_ioctl_get_fpu(struct kvm_vcpu *vcpu, struct kvm_fpu *fpu) { struct fxregs_state *fxsave; + if (!vcpu->arch.guest_fpu) + return 0; + vcpu_load(vcpu); fxsave = &vcpu->arch.guest_fpu->state.fxsave; @@ -9762,6 +9820,9 @@ int kvm_arch_vcpu_ioctl_set_fpu(struct kvm_vcpu *vcpu, struct kvm_fpu *fpu) { struct fxregs_state *fxsave; + if (!vcpu->arch.guest_fpu) + return 0; + vcpu_load(vcpu); fxsave = &vcpu->arch.guest_fpu->state.fxsave; @@ -9820,6 +9881,9 @@ static int sync_regs(struct kvm_vcpu *vcpu) static void fx_init(struct kvm_vcpu *vcpu) { + if (!vcpu->arch.guest_fpu) + return; + fpstate_init(&vcpu->arch.guest_fpu->state); if (boot_cpu_has(X86_FEATURE_XSAVES)) vcpu->arch.guest_fpu->state.xsave.header.xcomp_bv = @@ -9833,6 +9897,15 @@ static void fx_init(struct kvm_vcpu *vcpu) vcpu->arch.cr0 |= X86_CR0_ET; } +void kvm_free_guest_fpu(struct kvm_vcpu *vcpu) +{ + if (vcpu->arch.guest_fpu) { + kmem_cache_free(x86_fpu_cache, vcpu->arch.guest_fpu); + vcpu->arch.guest_fpu = NULL; + } +} +EXPORT_SYMBOL_GPL(kvm_free_guest_fpu); + int kvm_arch_vcpu_precreate(struct kvm *kvm, unsigned int id) { if (kvm_check_tsc_unstable() && atomic_read(&kvm->online_vcpus) != 0) @@ -9869,7 +9942,7 @@ int kvm_arch_vcpu_create(struct kvm_vcpu *vcpu) r = -ENOMEM; - page = alloc_page(GFP_KERNEL | __GFP_ZERO); + page = alloc_page(GFP_KERNEL_ACCOUNT | __GFP_ZERO); if (!page) goto fail_free_lapic; vcpu->arch.pio_data = page_address(page); @@ -9928,7 +10001,7 @@ int kvm_arch_vcpu_create(struct kvm_vcpu *vcpu) return 0; free_guest_fpu: - kmem_cache_free(x86_fpu_cache, vcpu->arch.guest_fpu); + kvm_free_guest_fpu(vcpu); free_user_fpu: kmem_cache_free(x86_fpu_cache, vcpu->arch.user_fpu); free_emulate_ctxt: @@ -9982,7 +10055,7 @@ void kvm_arch_vcpu_destroy(struct kvm_vcpu *vcpu) kmem_cache_free(x86_emulator_cache, vcpu->arch.emulate_ctxt); free_cpumask_var(vcpu->arch.wbinvd_dirty_mask); kmem_cache_free(x86_fpu_cache, vcpu->arch.user_fpu); - kmem_cache_free(x86_fpu_cache, vcpu->arch.guest_fpu); + kvm_free_guest_fpu(vcpu); kvm_hv_vcpu_uninit(vcpu); kvm_pmu_destroy(vcpu); @@ -10030,7 +10103,7 @@ void kvm_vcpu_reset(struct kvm_vcpu *vcpu, bool init_event) kvm_async_pf_hash_reset(vcpu); vcpu->arch.apf.halted = false; - if (kvm_mpx_supported()) { + if (vcpu->arch.guest_fpu && kvm_mpx_supported()) { void *mpx_state_buffer; /* @@ -10349,7 +10422,32 @@ void kvm_arch_sync_events(struct kvm *kvm) kvm_free_pit(kvm); } -int __x86_set_memory_region(struct kvm *kvm, int id, gpa_t gpa, u32 size) +#define ERR_PTR_USR(e) ((void __user *)ERR_PTR(e)) + +/** + * __x86_set_memory_region: Setup KVM internal memory slot + * + * @kvm: the kvm pointer to the VM. + * @id: the slot ID to setup. + * @gpa: the GPA to install the slot (unused when @size == 0). + * @size: the size of the slot. Set to zero to uninstall a slot. + * + * This function helps to setup a KVM internal memory slot. Specify + * @size > 0 to install a new slot, while @size == 0 to uninstall a + * slot. The return code can be one of the following: + * + * HVA: on success (uninstall will return a bogus HVA) + * -errno: on error + * + * The caller should always use IS_ERR() to check the return value + * before use. Note, the KVM internal memory slots are guaranteed to + * remain valid and unchanged until the VM is destroyed, i.e., the + * GPA->HVA translation will not change. However, the HVA is a user + * address, i.e. its accessibility is not guaranteed, and must be + * accessed via __copy_{to,from}_user(). + */ +void __user * __x86_set_memory_region(struct kvm *kvm, int id, gpa_t gpa, + u32 size) { int i, r; unsigned long hva, old_npages; @@ -10358,12 +10456,12 @@ int __x86_set_memory_region(struct kvm *kvm, int id, gpa_t gpa, u32 size) /* Called with kvm->slots_lock held. */ if (WARN_ON(id >= KVM_MEM_SLOTS_NUM)) - return -EINVAL; + return ERR_PTR_USR(-EINVAL); slot = id_to_memslot(slots, id); if (size) { if (slot && slot->npages) - return -EEXIST; + return ERR_PTR_USR(-EEXIST); /* * MAP_SHARED to prevent internal slot pages from being moved @@ -10372,7 +10470,7 @@ int __x86_set_memory_region(struct kvm *kvm, int id, gpa_t gpa, u32 size) hva = vm_mmap(NULL, 0, size, PROT_READ | PROT_WRITE, MAP_SHARED | MAP_ANONYMOUS, 0); if (IS_ERR((void *)hva)) - return PTR_ERR((void *)hva); + return (void __user *)hva; } else { if (!slot || !slot->npages) return 0; @@ -10391,13 +10489,13 @@ int __x86_set_memory_region(struct kvm *kvm, int id, gpa_t gpa, u32 size) m.memory_size = size; r = __kvm_set_memory_region(kvm, &m); if (r < 0) - return r; + return ERR_PTR_USR(r); } if (!size) vm_munmap(hva, old_npages * PAGE_SIZE); - return 0; + return (void __user *)hva; } EXPORT_SYMBOL_GPL(__x86_set_memory_region); @@ -10754,6 +10852,10 @@ int kvm_arch_interrupt_allowed(struct kvm_vcpu *vcpu) unsigned long kvm_get_linear_rip(struct kvm_vcpu *vcpu) { + /* Can't read the RIP when guest state is protected, just return 0 */ + if (vcpu->arch.guest_state_protected) + return 0; + if (is_64_bit_mode(vcpu)) return kvm_rip_read(vcpu); return (u32)(get_segment_base(vcpu, VCPU_SREG_CS) + @@ -11263,6 +11365,179 @@ int kvm_handle_invpcid(struct kvm_vcpu *vcpu, unsigned long type, gva_t gva) } EXPORT_SYMBOL_GPL(kvm_handle_invpcid); +static int complete_sev_es_emulated_mmio(struct kvm_vcpu *vcpu) +{ + struct kvm_run *run = vcpu->run; + struct kvm_mmio_fragment *frag; + unsigned int len; + + BUG_ON(!vcpu->mmio_needed); + + /* Complete previous fragment */ + frag = &vcpu->mmio_fragments[vcpu->mmio_cur_fragment]; + len = min(8u, frag->len); + if (!vcpu->mmio_is_write) + memcpy(frag->data, run->mmio.data, len); + + if (frag->len <= 8) { + /* Switch to the next fragment. */ + frag++; + vcpu->mmio_cur_fragment++; + } else { + /* Go forward to the next mmio piece. */ + frag->data += len; + frag->gpa += len; + frag->len -= len; + } + + if (vcpu->mmio_cur_fragment >= vcpu->mmio_nr_fragments) { + vcpu->mmio_needed = 0; + + // VMG change, at this point, we're always done + // RIP has already been advanced + return 1; + } + + // More MMIO is needed + run->mmio.phys_addr = frag->gpa; + run->mmio.len = min(8u, frag->len); + run->mmio.is_write = vcpu->mmio_is_write; + if (run->mmio.is_write) + memcpy(run->mmio.data, frag->data, min(8u, frag->len)); + run->exit_reason = KVM_EXIT_MMIO; + + vcpu->arch.complete_userspace_io = complete_sev_es_emulated_mmio; + + return 0; +} + +int kvm_sev_es_mmio_write(struct kvm_vcpu *vcpu, gpa_t gpa, unsigned int bytes, + void *data) +{ + int handled; + struct kvm_mmio_fragment *frag; + + if (!data) + return -EINVAL; + + handled = write_emultor.read_write_mmio(vcpu, gpa, bytes, data); + if (handled == bytes) + return 1; + + bytes -= handled; + gpa += handled; + data += handled; + + /*TODO: Check if need to increment number of frags */ + frag = vcpu->mmio_fragments; + vcpu->mmio_nr_fragments = 1; + frag->len = bytes; + frag->gpa = gpa; + frag->data = data; + + vcpu->mmio_needed = 1; + vcpu->mmio_cur_fragment = 0; + + vcpu->run->mmio.phys_addr = gpa; + vcpu->run->mmio.len = min(8u, frag->len); + vcpu->run->mmio.is_write = 1; + memcpy(vcpu->run->mmio.data, frag->data, min(8u, frag->len)); + vcpu->run->exit_reason = KVM_EXIT_MMIO; + + vcpu->arch.complete_userspace_io = complete_sev_es_emulated_mmio; + + return 0; +} +EXPORT_SYMBOL_GPL(kvm_sev_es_mmio_write); + +int kvm_sev_es_mmio_read(struct kvm_vcpu *vcpu, gpa_t gpa, unsigned int bytes, + void *data) +{ + int handled; + struct kvm_mmio_fragment *frag; + + if (!data) + return -EINVAL; + + handled = read_emultor.read_write_mmio(vcpu, gpa, bytes, data); + if (handled == bytes) + return 1; + + bytes -= handled; + gpa += handled; + data += handled; + + /*TODO: Check if need to increment number of frags */ + frag = vcpu->mmio_fragments; + vcpu->mmio_nr_fragments = 1; + frag->len = bytes; + frag->gpa = gpa; + frag->data = data; + + vcpu->mmio_needed = 1; + vcpu->mmio_cur_fragment = 0; + + vcpu->run->mmio.phys_addr = gpa; + vcpu->run->mmio.len = min(8u, frag->len); + vcpu->run->mmio.is_write = 0; + vcpu->run->exit_reason = KVM_EXIT_MMIO; + + vcpu->arch.complete_userspace_io = complete_sev_es_emulated_mmio; + + return 0; +} +EXPORT_SYMBOL_GPL(kvm_sev_es_mmio_read); + +static int complete_sev_es_emulated_ins(struct kvm_vcpu *vcpu) +{ + memcpy(vcpu->arch.guest_ins_data, vcpu->arch.pio_data, + vcpu->arch.pio.count * vcpu->arch.pio.size); + vcpu->arch.pio.count = 0; + + return 1; +} + +static int kvm_sev_es_outs(struct kvm_vcpu *vcpu, unsigned int size, + unsigned int port, void *data, unsigned int count) +{ + int ret; + + ret = emulator_pio_out_emulated(vcpu->arch.emulate_ctxt, size, port, + data, count); + if (ret) + return ret; + + vcpu->arch.pio.count = 0; + + return 0; +} + +static int kvm_sev_es_ins(struct kvm_vcpu *vcpu, unsigned int size, + unsigned int port, void *data, unsigned int count) +{ + int ret; + + ret = emulator_pio_in_emulated(vcpu->arch.emulate_ctxt, size, port, + data, count); + if (ret) { + vcpu->arch.pio.count = 0; + } else { + vcpu->arch.guest_ins_data = data; + vcpu->arch.complete_userspace_io = complete_sev_es_emulated_ins; + } + + return 0; +} + +int kvm_sev_es_string_io(struct kvm_vcpu *vcpu, unsigned int size, + unsigned int port, void *data, unsigned int count, + int in) +{ + return in ? kvm_sev_es_ins(vcpu, size, port, data, count) + : kvm_sev_es_outs(vcpu, size, port, data, count); +} +EXPORT_SYMBOL_GPL(kvm_sev_es_string_io); + EXPORT_TRACEPOINT_SYMBOL_GPL(kvm_exit); EXPORT_TRACEPOINT_SYMBOL_GPL(kvm_fast_mmio); EXPORT_TRACEPOINT_SYMBOL_GPL(kvm_inj_virq); @@ -11285,3 +11560,7 @@ EXPORT_TRACEPOINT_SYMBOL_GPL(kvm_avic_unaccelerated_access); EXPORT_TRACEPOINT_SYMBOL_GPL(kvm_avic_incomplete_ipi); EXPORT_TRACEPOINT_SYMBOL_GPL(kvm_avic_ga_log); EXPORT_TRACEPOINT_SYMBOL_GPL(kvm_apicv_update_request); +EXPORT_TRACEPOINT_SYMBOL_GPL(kvm_vmgexit_enter); +EXPORT_TRACEPOINT_SYMBOL_GPL(kvm_vmgexit_exit); +EXPORT_TRACEPOINT_SYMBOL_GPL(kvm_vmgexit_msr_protocol_enter); +EXPORT_TRACEPOINT_SYMBOL_GPL(kvm_vmgexit_msr_protocol_exit); diff --git a/arch/x86/kvm/x86.h b/arch/x86/kvm/x86.h index e7ca622a468f..c5ee0f5ce0f1 100644 --- a/arch/x86/kvm/x86.h +++ b/arch/x86/kvm/x86.h @@ -3,6 +3,7 @@ #define ARCH_X86_KVM_X86_H #include <linux/kvm_host.h> +#include <asm/mce.h> #include <asm/pvclock.h> #include "kvm_cache_regs.h" #include "kvm_emulate.h" @@ -278,6 +279,7 @@ fastpath_t handle_fastpath_set_msr_irqoff(struct kvm_vcpu *vcpu); extern u64 host_xcr0; extern u64 supported_xcr0; +extern u64 host_xss; extern u64 supported_xss; static inline bool kvm_mpx_supported(void) @@ -366,10 +368,29 @@ static inline bool kvm_dr6_valid(u64 data) return !(data >> 32); } +/* + * Trigger machine check on the host. We assume all the MSRs are already set up + * by the CPU and that we still run on the same CPU as the MCE occurred on. + * We pass a fake environment to the machine check handler because we want + * the guest to be always treated like user space, no matter what context + * it used internally. + */ +static inline void kvm_machine_check(void) +{ +#if defined(CONFIG_X86_MCE) + struct pt_regs regs = { + .cs = 3, /* Fake ring 3 no matter what the guest ran on */ + .flags = X86_EFLAGS_IF, + }; + + do_machine_check(®s); +#endif +} + void kvm_load_guest_xsave_state(struct kvm_vcpu *vcpu); void kvm_load_host_xsave_state(struct kvm_vcpu *vcpu); int kvm_spec_ctrl_test_value(u64 value); -int kvm_valid_cr4(struct kvm_vcpu *vcpu, unsigned long cr4); +bool kvm_is_valid_cr4(struct kvm_vcpu *vcpu, unsigned long cr4); bool kvm_vcpu_exit_request(struct kvm_vcpu *vcpu); int kvm_handle_memory_failure(struct kvm_vcpu *vcpu, int r, struct x86_exception *e); @@ -407,4 +428,12 @@ bool kvm_msr_allowed(struct kvm_vcpu *vcpu, u32 index, u32 type); __reserved_bits; \ }) +int kvm_sev_es_mmio_write(struct kvm_vcpu *vcpu, gpa_t src, unsigned int bytes, + void *dst); +int kvm_sev_es_mmio_read(struct kvm_vcpu *vcpu, gpa_t src, unsigned int bytes, + void *dst); +int kvm_sev_es_string_io(struct kvm_vcpu *vcpu, unsigned int size, + unsigned int port, void *data, unsigned int count, + int in); + #endif diff --git a/arch/x86/xen/Kconfig b/arch/x86/xen/Kconfig index 218acbd5c7a0..afc1da68b06d 100644 --- a/arch/x86/xen/Kconfig +++ b/arch/x86/xen/Kconfig @@ -26,6 +26,19 @@ config XEN_PV help Support running as a Xen PV guest. +config XEN_512GB + bool "Limit Xen pv-domain memory to 512GB" + depends on XEN_PV + default y + help + Limit paravirtualized user domains to 512GB of RAM. + + The Xen tools and crash dump analysis tools might not support + pv-domains with more than 512 GB of RAM. This option controls the + default setting of the kernel to use only up to 512 GB or more. + It is always possible to change the default via specifying the + boot parameter "xen_512gb_limit". + config XEN_PV_SMP def_bool y depends on XEN_PV && SMP @@ -39,28 +52,19 @@ config XEN_DOM0 Support running as a Xen PV Dom0 guest. config XEN_PVHVM - bool "Xen PVHVM guest support" - default y - depends on XEN && PCI && X86_LOCAL_APIC - help - Support running as a Xen PVHVM guest. + def_bool y + depends on XEN && X86_LOCAL_APIC config XEN_PVHVM_SMP def_bool y depends on XEN_PVHVM && SMP -config XEN_512GB - bool "Limit Xen pv-domain memory to 512GB" - depends on XEN_PV +config XEN_PVHVM_GUEST + bool "Xen PVHVM guest support" default y + depends on XEN_PVHVM && PCI help - Limit paravirtualized user domains to 512GB of RAM. - - The Xen tools and crash dump analysis tools might not support - pv-domains with more than 512 GB of RAM. This option controls the - default setting of the kernel to use only up to 512 GB or more. - It is always possible to change the default via specifying the - boot parameter "xen_512gb_limit". + Support running as a Xen PVHVM guest. config XEN_SAVE_RESTORE bool @@ -76,7 +80,9 @@ config XEN_DEBUG_FS Enabling this option may incur a significant performance overhead. config XEN_PVH - bool "Support for running as a Xen PVH guest" + bool "Xen PVH guest support" depends on XEN && XEN_PVHVM && ACPI select PVH def_bool n + help + Support for running as a Xen PVH guest. diff --git a/arch/x86/xen/p2m.c b/arch/x86/xen/p2m.c index be4151f42611..3301875dd196 100644 --- a/arch/x86/xen/p2m.c +++ b/arch/x86/xen/p2m.c @@ -795,17 +795,7 @@ static int p2m_dump_show(struct seq_file *m, void *v) return 0; } -static int p2m_dump_open(struct inode *inode, struct file *filp) -{ - return single_open(filp, p2m_dump_show, NULL); -} - -static const struct file_operations p2m_dump_fops = { - .open = p2m_dump_open, - .read = seq_read, - .llseek = seq_lseek, - .release = single_release, -}; +DEFINE_SHOW_ATTRIBUTE(p2m_dump); static struct dentry *d_mmu_debug; diff --git a/arch/xtensa/kernel/syscalls/syscall.tbl b/arch/xtensa/kernel/syscalls/syscall.tbl index b070f272995d..46116a28eeed 100644 --- a/arch/xtensa/kernel/syscalls/syscall.tbl +++ b/arch/xtensa/kernel/syscalls/syscall.tbl @@ -411,3 +411,4 @@ 438 common pidfd_getfd sys_pidfd_getfd 439 common faccessat2 sys_faccessat2 440 common process_madvise sys_process_madvise +441 common epoll_pwait2 sys_epoll_pwait2 diff --git a/arch/xtensa/kernel/time.c b/arch/xtensa/kernel/time.c index 77971fe4cc95..e8ceb1528608 100644 --- a/arch/xtensa/kernel/time.c +++ b/arch/xtensa/kernel/time.c @@ -13,7 +13,7 @@ */ #include <linux/clk.h> -#include <linux/clk-provider.h> +#include <linux/of_clk.h> #include <linux/errno.h> #include <linux/sched.h> #include <linux/time.h> |