diff options
Diffstat (limited to 'arch/x86')
147 files changed, 2383 insertions, 1056 deletions
diff --git a/arch/x86/boot/Makefile b/arch/x86/boot/Makefile index e2839b5c246c..6539c50fb9aa 100644 --- a/arch/x86/boot/Makefile +++ b/arch/x86/boot/Makefile @@ -87,7 +87,7 @@ $(obj)/vmlinux.bin: $(obj)/compressed/vmlinux FORCE SETUP_OBJS = $(addprefix $(obj)/,$(setup-y)) -sed-zoffset := -e 's/^\([0-9a-fA-F]*\) [ABCDGRSTVW] \(startup_32\|startup_64\|efi32_stub_entry\|efi64_stub_entry\|efi_pe_entry\|input_data\|_end\|_ehead\|_text\|z_.*\)$$/\#define ZO_\2 0x\1/p' +sed-zoffset := -e 's/^\([0-9a-fA-F]*\) [a-zA-Z] \(startup_32\|startup_64\|efi32_stub_entry\|efi64_stub_entry\|efi_pe_entry\|input_data\|_end\|_ehead\|_text\|z_.*\)$$/\#define ZO_\2 0x\1/p' quiet_cmd_zoffset = ZOFFSET $@ cmd_zoffset = $(NM) $< | sed -n $(sed-zoffset) > $@ diff --git a/arch/x86/boot/compressed/acpi.c b/arch/x86/boot/compressed/acpi.c index 15255f388a85..c4ff6580cfeb 100644 --- a/arch/x86/boot/compressed/acpi.c +++ b/arch/x86/boot/compressed/acpi.c @@ -386,7 +386,13 @@ int count_immovable_mem_regions(void) table = table_addr + sizeof(struct acpi_table_srat); while (table + sizeof(struct acpi_subtable_header) < table_end) { + sub_table = (struct acpi_subtable_header *)table; + if (!sub_table->length) { + debug_putstr("Invalid zero length SRAT subtable.\n"); + return 0; + } + if (sub_table->type == ACPI_SRAT_TYPE_MEMORY_AFFINITY) { struct acpi_srat_mem_affinity *ma; diff --git a/arch/x86/boot/compressed/head_32.S b/arch/x86/boot/compressed/head_32.S index 37380c0d5999..c6c4b877f3d2 100644 --- a/arch/x86/boot/compressed/head_32.S +++ b/arch/x86/boot/compressed/head_32.S @@ -49,16 +49,17 @@ * Position Independent Executable (PIE) so that linker won't optimize * R_386_GOT32X relocation to its fixed symbol address. Older * linkers generate R_386_32 relocations against locally defined symbols, - * _bss, _ebss, _got and _egot, in PIE. It isn't wrong, just less + * _bss, _ebss, _got, _egot and _end, in PIE. It isn't wrong, just less * optimal than R_386_RELATIVE. But the x86 kernel fails to properly handle * R_386_32 relocations when relocating the kernel. To generate - * R_386_RELATIVE relocations, we mark _bss, _ebss, _got and _egot as + * R_386_RELATIVE relocations, we mark _bss, _ebss, _got, _egot and _end as * hidden: */ .hidden _bss .hidden _ebss .hidden _got .hidden _egot + .hidden _end __HEAD ENTRY(startup_32) @@ -106,7 +107,7 @@ ENTRY(startup_32) notl %eax andl %eax, %ebx cmpl $LOAD_PHYSICAL_ADDR, %ebx - jge 1f + jae 1f #endif movl $LOAD_PHYSICAL_ADDR, %ebx 1: diff --git a/arch/x86/boot/compressed/head_64.S b/arch/x86/boot/compressed/head_64.S index fafb75c6c592..0ad88e343ec5 100644 --- a/arch/x86/boot/compressed/head_64.S +++ b/arch/x86/boot/compressed/head_64.S @@ -42,6 +42,7 @@ .hidden _ebss .hidden _got .hidden _egot + .hidden _end __HEAD .code32 @@ -106,7 +107,7 @@ ENTRY(startup_32) notl %eax andl %eax, %ebx cmpl $LOAD_PHYSICAL_ADDR, %ebx - jge 1f + jae 1f #endif movl $LOAD_PHYSICAL_ADDR, %ebx 1: @@ -244,6 +245,11 @@ ENTRY(efi32_stub_entry) leal efi32_config(%ebp), %eax movl %eax, efi_config(%ebp) + /* Disable paging */ + movl %cr0, %eax + btrl $X86_CR0_PG_BIT, %eax + movl %eax, %cr0 + jmp startup_32 ENDPROC(efi32_stub_entry) #endif @@ -292,7 +298,7 @@ ENTRY(startup_64) notq %rax andq %rax, %rbp cmpq $LOAD_PHYSICAL_ADDR, %rbp - jge 1f + jae 1f #endif movq $LOAD_PHYSICAL_ADDR, %rbp 1: diff --git a/arch/x86/boot/compressed/kaslr_64.c b/arch/x86/boot/compressed/kaslr_64.c index 748456c365f4..9557c5a15b91 100644 --- a/arch/x86/boot/compressed/kaslr_64.c +++ b/arch/x86/boot/compressed/kaslr_64.c @@ -29,9 +29,6 @@ #define __PAGE_OFFSET __PAGE_OFFSET_BASE #include "../../mm/ident_map.c" -/* Used by pgtable.h asm code to force instruction serialization. */ -unsigned long __force_order; - /* Used to track our page table allocation area. */ struct alloc_pgt_data { unsigned char *pgt_buf; diff --git a/arch/x86/crypto/aes_ctrby8_avx-x86_64.S b/arch/x86/crypto/aes_ctrby8_avx-x86_64.S index 5f6a5af9c489..77043a82da51 100644 --- a/arch/x86/crypto/aes_ctrby8_avx-x86_64.S +++ b/arch/x86/crypto/aes_ctrby8_avx-x86_64.S @@ -127,10 +127,6 @@ ddq_add_8: /* generate a unique variable for ddq_add_x */ -.macro setddq n - var_ddq_add = ddq_add_\n -.endm - /* generate a unique variable for xmm register */ .macro setxdata n var_xdata = %xmm\n @@ -140,9 +136,7 @@ ddq_add_8: .macro club name, id .altmacro - .if \name == DDQ_DATA - setddq %\id - .elseif \name == XDATA + .if \name == XDATA setxdata %\id .endif .noaltmacro @@ -165,9 +159,8 @@ ddq_add_8: .set i, 1 .rept (by - 1) - club DDQ_DATA, i club XDATA, i - vpaddq var_ddq_add(%rip), xcounter, var_xdata + vpaddq (ddq_add_1 + 16 * (i - 1))(%rip), xcounter, var_xdata vptest ddq_low_msk(%rip), var_xdata jnz 1f vpaddq ddq_high_add_1(%rip), var_xdata, var_xdata @@ -180,8 +173,7 @@ ddq_add_8: vmovdqa 1*16(p_keys), xkeyA vpxor xkey0, xdata0, xdata0 - club DDQ_DATA, by - vpaddq var_ddq_add(%rip), xcounter, xcounter + vpaddq (ddq_add_1 + 16 * (by - 1))(%rip), xcounter, xcounter vptest ddq_low_msk(%rip), xcounter jnz 1f vpaddq ddq_high_add_1(%rip), xcounter, xcounter diff --git a/arch/x86/crypto/aesni-intel_asm.S b/arch/x86/crypto/aesni-intel_asm.S index e40bdf024ba7..9afeb58c910e 100644 --- a/arch/x86/crypto/aesni-intel_asm.S +++ b/arch/x86/crypto/aesni-intel_asm.S @@ -266,7 +266,7 @@ ALL_F: .octa 0xffffffffffffffffffffffffffffffff PSHUFB_XMM %xmm2, %xmm0 movdqu %xmm0, CurCount(%arg2) # ctx_data.current_counter = iv - PRECOMPUTE \SUBKEY, %xmm1, %xmm2, %xmm3, %xmm4, %xmm5, %xmm6, %xmm7, + PRECOMPUTE \SUBKEY, %xmm1, %xmm2, %xmm3, %xmm4, %xmm5, %xmm6, %xmm7 movdqu HashKey(%arg2), %xmm13 CALC_AAD_HASH %xmm13, \AAD, \AADLEN, %xmm0, %xmm1, %xmm2, %xmm3, \ @@ -978,7 +978,7 @@ _initial_blocks_done\@: * arg1, %arg3, %arg4 are used as pointers only, not modified * %r11 is the data offset value */ -.macro GHASH_4_ENCRYPT_4_PARALLEL_ENC TMP1 TMP2 TMP3 TMP4 TMP5 \ +.macro GHASH_4_ENCRYPT_4_PARALLEL_enc TMP1 TMP2 TMP3 TMP4 TMP5 \ TMP6 XMM0 XMM1 XMM2 XMM3 XMM4 XMM5 XMM6 XMM7 XMM8 operation movdqa \XMM1, \XMM5 @@ -1186,7 +1186,7 @@ aes_loop_par_enc_done\@: * arg1, %arg3, %arg4 are used as pointers only, not modified * %r11 is the data offset value */ -.macro GHASH_4_ENCRYPT_4_PARALLEL_DEC TMP1 TMP2 TMP3 TMP4 TMP5 \ +.macro GHASH_4_ENCRYPT_4_PARALLEL_dec TMP1 TMP2 TMP3 TMP4 TMP5 \ TMP6 XMM0 XMM1 XMM2 XMM3 XMM4 XMM5 XMM6 XMM7 XMM8 operation movdqa \XMM1, \XMM5 diff --git a/arch/x86/crypto/nhpoly1305-avx2-glue.c b/arch/x86/crypto/nhpoly1305-avx2-glue.c index f7567cbd35b6..80fcb85736e1 100644 --- a/arch/x86/crypto/nhpoly1305-avx2-glue.c +++ b/arch/x86/crypto/nhpoly1305-avx2-glue.c @@ -29,7 +29,7 @@ static int nhpoly1305_avx2_update(struct shash_desc *desc, return crypto_nhpoly1305_update(desc, src, srclen); do { - unsigned int n = min_t(unsigned int, srclen, PAGE_SIZE); + unsigned int n = min_t(unsigned int, srclen, SZ_4K); kernel_fpu_begin(); crypto_nhpoly1305_update_helper(desc, src, n, _nh_avx2); diff --git a/arch/x86/crypto/nhpoly1305-sse2-glue.c b/arch/x86/crypto/nhpoly1305-sse2-glue.c index a661ede3b5cf..cc6b7c1a2705 100644 --- a/arch/x86/crypto/nhpoly1305-sse2-glue.c +++ b/arch/x86/crypto/nhpoly1305-sse2-glue.c @@ -29,7 +29,7 @@ static int nhpoly1305_sse2_update(struct shash_desc *desc, return crypto_nhpoly1305_update(desc, src, srclen); do { - unsigned int n = min_t(unsigned int, srclen, PAGE_SIZE); + unsigned int n = min_t(unsigned int, srclen, SZ_4K); kernel_fpu_begin(); crypto_nhpoly1305_update_helper(desc, src, n, _nh_sse2); diff --git a/arch/x86/entry/calling.h b/arch/x86/entry/calling.h index 515c0ceeb4a3..b3f121478738 100644 --- a/arch/x86/entry/calling.h +++ b/arch/x86/entry/calling.h @@ -98,13 +98,6 @@ For 32-bit we have the following conventions - kernel is built with #define SIZEOF_PTREGS 21*8 .macro PUSH_AND_CLEAR_REGS rdx=%rdx rax=%rax save_ret=0 - /* - * Push registers and sanitize registers of values that a - * speculation attack might otherwise want to exploit. The - * lower registers are likely clobbered well before they - * could be put to use in a speculative execution gadget. - * Interleave XOR with PUSH for better uop scheduling: - */ .if \save_ret pushq %rsi /* pt_regs->si */ movq 8(%rsp), %rsi /* temporarily store the return address in %rsi */ @@ -114,34 +107,43 @@ For 32-bit we have the following conventions - kernel is built with pushq %rsi /* pt_regs->si */ .endif pushq \rdx /* pt_regs->dx */ - xorl %edx, %edx /* nospec dx */ pushq %rcx /* pt_regs->cx */ - xorl %ecx, %ecx /* nospec cx */ pushq \rax /* pt_regs->ax */ pushq %r8 /* pt_regs->r8 */ - xorl %r8d, %r8d /* nospec r8 */ pushq %r9 /* pt_regs->r9 */ - xorl %r9d, %r9d /* nospec r9 */ pushq %r10 /* pt_regs->r10 */ - xorl %r10d, %r10d /* nospec r10 */ pushq %r11 /* pt_regs->r11 */ - xorl %r11d, %r11d /* nospec r11*/ pushq %rbx /* pt_regs->rbx */ - xorl %ebx, %ebx /* nospec rbx*/ pushq %rbp /* pt_regs->rbp */ - xorl %ebp, %ebp /* nospec rbp*/ pushq %r12 /* pt_regs->r12 */ - xorl %r12d, %r12d /* nospec r12*/ pushq %r13 /* pt_regs->r13 */ - xorl %r13d, %r13d /* nospec r13*/ pushq %r14 /* pt_regs->r14 */ - xorl %r14d, %r14d /* nospec r14*/ pushq %r15 /* pt_regs->r15 */ - xorl %r15d, %r15d /* nospec r15*/ UNWIND_HINT_REGS + .if \save_ret pushq %rsi /* return address on top of stack */ .endif + + /* + * Sanitize registers of values that a speculation attack might + * otherwise want to exploit. The lower registers are likely clobbered + * well before they could be put to use in a speculative execution + * gadget. + */ + xorl %edx, %edx /* nospec dx */ + xorl %ecx, %ecx /* nospec cx */ + xorl %r8d, %r8d /* nospec r8 */ + xorl %r9d, %r9d /* nospec r9 */ + xorl %r10d, %r10d /* nospec r10 */ + xorl %r11d, %r11d /* nospec r11 */ + xorl %ebx, %ebx /* nospec rbx */ + xorl %ebp, %ebp /* nospec rbp */ + xorl %r12d, %r12d /* nospec r12 */ + xorl %r13d, %r13d /* nospec r13 */ + xorl %r14d, %r14d /* nospec r14 */ + xorl %r15d, %r15d /* nospec r15 */ + .endm .macro POP_REGS pop_rdi=1 skip_r11rcx=0 diff --git a/arch/x86/entry/common.c b/arch/x86/entry/common.c index 2418804e66b4..73c216d73417 100644 --- a/arch/x86/entry/common.c +++ b/arch/x86/entry/common.c @@ -290,15 +290,16 @@ __visible void do_syscall_64(unsigned long nr, struct pt_regs *regs) if (READ_ONCE(ti->flags) & _TIF_WORK_SYSCALL_ENTRY) nr = syscall_trace_enter(regs); - /* - * NB: Native and x32 syscalls are dispatched from the same - * table. The only functional difference is the x32 bit in - * regs->orig_ax, which changes the behavior of some syscalls. - */ - nr &= __SYSCALL_MASK; if (likely(nr < NR_syscalls)) { nr = array_index_nospec(nr, NR_syscalls); regs->ax = sys_call_table[nr](regs); +#ifdef CONFIG_X86_X32_ABI + } else if (likely((nr & __X32_SYSCALL_BIT) && + (nr & ~__X32_SYSCALL_BIT) < X32_NR_syscalls)) { + nr = array_index_nospec(nr & ~__X32_SYSCALL_BIT, + X32_NR_syscalls); + regs->ax = x32_sys_call_table[nr](regs); +#endif } syscall_return_slowpath(regs); diff --git a/arch/x86/entry/entry_32.S b/arch/x86/entry/entry_32.S index 1153e510cedd..e5530e74b738 100644 --- a/arch/x86/entry/entry_32.S +++ b/arch/x86/entry/entry_32.S @@ -1647,6 +1647,7 @@ ENTRY(int3) END(int3) ENTRY(general_protection) + ASM_CLAC pushl $do_general_protection jmp common_exception END(general_protection) diff --git a/arch/x86/entry/entry_64.S b/arch/x86/entry/entry_64.S index 7d81e14b6226..b83feb7d9464 100644 --- a/arch/x86/entry/entry_64.S +++ b/arch/x86/entry/entry_64.S @@ -249,7 +249,6 @@ GLOBAL(entry_SYSCALL_64_after_hwframe) */ syscall_return_via_sysret: /* rcx and r11 are already restored (see code above) */ - UNWIND_HINT_EMPTY POP_REGS pop_rdi=0 skip_r11rcx=1 /* @@ -258,6 +257,7 @@ syscall_return_via_sysret: */ movq %rsp, %rdi movq PER_CPU_VAR(cpu_tss_rw + TSS_sp0), %rsp + UNWIND_HINT_EMPTY pushq RSP-RDI(%rdi) /* RSP */ pushq (%rdi) /* RDI */ @@ -512,7 +512,7 @@ END(spurious_entries_start) * +----------------------------------------------------+ */ ENTRY(interrupt_entry) - UNWIND_HINT_FUNC + UNWIND_HINT_IRET_REGS offset=16 ASM_CLAC cld @@ -544,9 +544,9 @@ ENTRY(interrupt_entry) pushq 5*8(%rdi) /* regs->eflags */ pushq 4*8(%rdi) /* regs->cs */ pushq 3*8(%rdi) /* regs->ip */ + UNWIND_HINT_IRET_REGS pushq 2*8(%rdi) /* regs->orig_ax */ pushq 8(%rdi) /* return address */ - UNWIND_HINT_FUNC movq (%rdi), %rdi jmp 2f @@ -637,6 +637,7 @@ GLOBAL(swapgs_restore_regs_and_return_to_usermode) */ movq %rsp, %rdi movq PER_CPU_VAR(cpu_tss_rw + TSS_sp0), %rsp + UNWIND_HINT_EMPTY /* Copy the IRET frame to the trampoline stack. */ pushq 6*8(%rdi) /* SS */ @@ -1734,7 +1735,7 @@ ENTRY(rewind_stack_do_exit) movq PER_CPU_VAR(cpu_current_top_of_stack), %rax leaq -PTREGS_SIZE(%rax), %rsp - UNWIND_HINT_FUNC sp_offset=PTREGS_SIZE + UNWIND_HINT_REGS call do_exit END(rewind_stack_do_exit) diff --git a/arch/x86/entry/syscall_32.c b/arch/x86/entry/syscall_32.c index aa3336a7cb15..7d17b3addbbb 100644 --- a/arch/x86/entry/syscall_32.c +++ b/arch/x86/entry/syscall_32.c @@ -10,13 +10,11 @@ #ifdef CONFIG_IA32_EMULATION /* On X86_64, we use struct pt_regs * to pass parameters to syscalls */ #define __SYSCALL_I386(nr, sym, qual) extern asmlinkage long sym(const struct pt_regs *); - -/* this is a lie, but it does not hurt as sys_ni_syscall just returns -EINVAL */ -extern asmlinkage long sys_ni_syscall(const struct pt_regs *); - +#define __sys_ni_syscall __ia32_sys_ni_syscall #else /* CONFIG_IA32_EMULATION */ #define __SYSCALL_I386(nr, sym, qual) extern asmlinkage long sym(unsigned long, unsigned long, unsigned long, unsigned long, unsigned long, unsigned long); extern asmlinkage long sys_ni_syscall(unsigned long, unsigned long, unsigned long, unsigned long, unsigned long, unsigned long); +#define __sys_ni_syscall sys_ni_syscall #endif /* CONFIG_IA32_EMULATION */ #include <asm/syscalls_32.h> @@ -29,6 +27,6 @@ __visible const sys_call_ptr_t ia32_sys_call_table[__NR_syscall_compat_max+1] = * Smells like a compiler bug -- it doesn't work * when the & below is removed. */ - [0 ... __NR_syscall_compat_max] = &sys_ni_syscall, + [0 ... __NR_syscall_compat_max] = &__sys_ni_syscall, #include <asm/syscalls_32.h> }; diff --git a/arch/x86/entry/syscall_64.c b/arch/x86/entry/syscall_64.c index d5252bc1e380..adf619a856e8 100644 --- a/arch/x86/entry/syscall_64.c +++ b/arch/x86/entry/syscall_64.c @@ -4,22 +4,53 @@ #include <linux/linkage.h> #include <linux/sys.h> #include <linux/cache.h> +#include <linux/syscalls.h> #include <asm/asm-offsets.h> #include <asm/syscall.h> -/* this is a lie, but it does not hurt as sys_ni_syscall just returns -EINVAL */ -extern asmlinkage long sys_ni_syscall(const struct pt_regs *); +extern asmlinkage long sys_ni_syscall(void); + +SYSCALL_DEFINE0(ni_syscall) +{ + return sys_ni_syscall(); +} + #define __SYSCALL_64(nr, sym, qual) extern asmlinkage long sym(const struct pt_regs *); +#define __SYSCALL_X32(nr, sym, qual) __SYSCALL_64(nr, sym, qual) #include <asm/syscalls_64.h> #undef __SYSCALL_64 +#undef __SYSCALL_X32 #define __SYSCALL_64(nr, sym, qual) [nr] = sym, +#define __SYSCALL_X32(nr, sym, qual) asmlinkage const sys_call_ptr_t sys_call_table[__NR_syscall_max+1] = { /* * Smells like a compiler bug -- it doesn't work * when the & below is removed. */ - [0 ... __NR_syscall_max] = &sys_ni_syscall, + [0 ... __NR_syscall_max] = &__x64_sys_ni_syscall, +#include <asm/syscalls_64.h> +}; + +#undef __SYSCALL_64 +#undef __SYSCALL_X32 + +#ifdef CONFIG_X86_X32_ABI + +#define __SYSCALL_64(nr, sym, qual) +#define __SYSCALL_X32(nr, sym, qual) [nr] = sym, + +asmlinkage const sys_call_ptr_t x32_sys_call_table[__NR_syscall_x32_max+1] = { + /* + * Smells like a compiler bug -- it doesn't work + * when the & below is removed. + */ + [0 ... __NR_syscall_x32_max] = &__x64_sys_ni_syscall, #include <asm/syscalls_64.h> }; + +#undef __SYSCALL_64 +#undef __SYSCALL_X32 + +#endif diff --git a/arch/x86/entry/syscalls/syscall_32.tbl b/arch/x86/entry/syscalls/syscall_32.tbl index ad968b7bac72..8e5a3cc5eba2 100644 --- a/arch/x86/entry/syscalls/syscall_32.tbl +++ b/arch/x86/entry/syscalls/syscall_32.tbl @@ -124,13 +124,13 @@ 110 i386 iopl sys_iopl __ia32_sys_iopl 111 i386 vhangup sys_vhangup __ia32_sys_vhangup 112 i386 idle -113 i386 vm86old sys_vm86old sys_ni_syscall +113 i386 vm86old sys_vm86old __ia32_sys_ni_syscall 114 i386 wait4 sys_wait4 __ia32_compat_sys_wait4 115 i386 swapoff sys_swapoff __ia32_sys_swapoff 116 i386 sysinfo sys_sysinfo __ia32_compat_sys_sysinfo 117 i386 ipc sys_ipc __ia32_compat_sys_ipc 118 i386 fsync sys_fsync __ia32_sys_fsync -119 i386 sigreturn sys_sigreturn sys32_sigreturn +119 i386 sigreturn sys_sigreturn __ia32_compat_sys_sigreturn 120 i386 clone sys_clone __ia32_compat_sys_x86_clone 121 i386 setdomainname sys_setdomainname __ia32_sys_setdomainname 122 i386 uname sys_newuname __ia32_sys_newuname @@ -177,20 +177,20 @@ 163 i386 mremap sys_mremap __ia32_sys_mremap 164 i386 setresuid sys_setresuid16 __ia32_sys_setresuid16 165 i386 getresuid sys_getresuid16 __ia32_sys_getresuid16 -166 i386 vm86 sys_vm86 sys_ni_syscall +166 i386 vm86 sys_vm86 __ia32_sys_ni_syscall 167 i386 query_module 168 i386 poll sys_poll __ia32_sys_poll 169 i386 nfsservctl 170 i386 setresgid sys_setresgid16 __ia32_sys_setresgid16 171 i386 getresgid sys_getresgid16 __ia32_sys_getresgid16 172 i386 prctl sys_prctl __ia32_sys_prctl -173 i386 rt_sigreturn sys_rt_sigreturn sys32_rt_sigreturn +173 i386 rt_sigreturn sys_rt_sigreturn __ia32_compat_sys_rt_sigreturn 174 i386 rt_sigaction sys_rt_sigaction __ia32_compat_sys_rt_sigaction -175 i386 rt_sigprocmask sys_rt_sigprocmask __ia32_sys_rt_sigprocmask +175 i386 rt_sigprocmask sys_rt_sigprocmask __ia32_compat_sys_rt_sigprocmask 176 i386 rt_sigpending sys_rt_sigpending __ia32_compat_sys_rt_sigpending 177 i386 rt_sigtimedwait sys_rt_sigtimedwait_time32 __ia32_compat_sys_rt_sigtimedwait_time32 178 i386 rt_sigqueueinfo sys_rt_sigqueueinfo __ia32_compat_sys_rt_sigqueueinfo -179 i386 rt_sigsuspend sys_rt_sigsuspend __ia32_sys_rt_sigsuspend +179 i386 rt_sigsuspend sys_rt_sigsuspend __ia32_compat_sys_rt_sigsuspend 180 i386 pread64 sys_pread64 __ia32_compat_sys_x86_pread 181 i386 pwrite64 sys_pwrite64 __ia32_compat_sys_x86_pwrite 182 i386 chown sys_chown16 __ia32_sys_chown16 diff --git a/arch/x86/entry/syscalls/syscalltbl.sh b/arch/x86/entry/syscalls/syscalltbl.sh index 94fcd1951aca..1af2be39e7d9 100644 --- a/arch/x86/entry/syscalls/syscalltbl.sh +++ b/arch/x86/entry/syscalls/syscalltbl.sh @@ -1,13 +1,13 @@ -#!/bin/sh +#!/bin/bash # SPDX-License-Identifier: GPL-2.0 in="$1" out="$2" syscall_macro() { - abi="$1" - nr="$2" - entry="$3" + local abi="$1" + local nr="$2" + local entry="$3" # Entry can be either just a function name or "function/qualifier" real_entry="${entry%%/*}" @@ -21,14 +21,14 @@ syscall_macro() { } emit() { - abi="$1" - nr="$2" - entry="$3" - compat="$4" - umlentry="" + local abi="$1" + local nr="$2" + local entry="$3" + local compat="$4" + local umlentry="" - if [ "$abi" = "64" -a -n "$compat" ]; then - echo "a compat entry for a 64-bit syscall makes no sense" >&2 + if [ "$abi" != "I386" -a -n "$compat" ]; then + echo "a compat entry ($abi: $compat) for a 64-bit syscall makes no sense" >&2 exit 1 fi @@ -62,14 +62,17 @@ grep '^[0-9]' "$in" | sort -n | ( while read nr abi name entry compat; do abi=`echo "$abi" | tr '[a-z]' '[A-Z]'` if [ "$abi" = "COMMON" -o "$abi" = "64" ]; then - # COMMON is the same as 64, except that we don't expect X32 - # programs to use it. Our expectation has nothing to do with - # any generated code, so treat them the same. emit 64 "$nr" "$entry" "$compat" + if [ "$abi" = "COMMON" ]; then + # COMMON means that this syscall exists in the same form for + # 64-bit and X32. + echo "#ifdef CONFIG_X86_X32_ABI" + emit X32 "$nr" "$entry" "$compat" + echo "#endif" + fi elif [ "$abi" = "X32" ]; then - # X32 is equivalent to 64 on an X32-compatible kernel. echo "#ifdef CONFIG_X86_X32_ABI" - emit 64 "$nr" "$entry" "$compat" + emit X32 "$nr" "$entry" "$compat" echo "#endif" elif [ "$abi" = "I386" ]; then emit "$abi" "$nr" "$entry" "$compat" diff --git a/arch/x86/entry/vdso/vdso32-setup.c b/arch/x86/entry/vdso/vdso32-setup.c index 42d4c89f990e..ddff0ca6f509 100644 --- a/arch/x86/entry/vdso/vdso32-setup.c +++ b/arch/x86/entry/vdso/vdso32-setup.c @@ -11,6 +11,7 @@ #include <linux/smp.h> #include <linux/kernel.h> #include <linux/mm_types.h> +#include <linux/elf.h> #include <asm/processor.h> #include <asm/vdso.h> diff --git a/arch/x86/events/amd/core.c b/arch/x86/events/amd/core.c index 64c3e70b0556..3ea8056148d8 100644 --- a/arch/x86/events/amd/core.c +++ b/arch/x86/events/amd/core.c @@ -246,6 +246,7 @@ static const u64 amd_f17h_perfmon_event_map[PERF_COUNT_HW_MAX] = [PERF_COUNT_HW_CPU_CYCLES] = 0x0076, [PERF_COUNT_HW_INSTRUCTIONS] = 0x00c0, [PERF_COUNT_HW_CACHE_REFERENCES] = 0xff60, + [PERF_COUNT_HW_CACHE_MISSES] = 0x0964, [PERF_COUNT_HW_BRANCH_INSTRUCTIONS] = 0x00c2, [PERF_COUNT_HW_BRANCH_MISSES] = 0x00c3, [PERF_COUNT_HW_STALLED_CYCLES_FRONTEND] = 0x0287, @@ -301,6 +302,25 @@ static inline int amd_pmu_addr_offset(int index, bool eventsel) return offset; } +/* + * AMD64 events are detected based on their event codes. + */ +static inline unsigned int amd_get_event_code(struct hw_perf_event *hwc) +{ + return ((hwc->config >> 24) & 0x0f00) | (hwc->config & 0x00ff); +} + +static inline bool amd_is_pair_event_code(struct hw_perf_event *hwc) +{ + if (!(x86_pmu.flags & PMU_FL_PAIR)) + return false; + + switch (amd_get_event_code(hwc)) { + case 0x003: return true; /* Retired SSE/AVX FLOPs */ + default: return false; + } +} + static int amd_core_hw_config(struct perf_event *event) { if (event->attr.exclude_host && event->attr.exclude_guest) @@ -319,14 +339,6 @@ static int amd_core_hw_config(struct perf_event *event) return 0; } -/* - * AMD64 events are detected based on their event codes. - */ -static inline unsigned int amd_get_event_code(struct hw_perf_event *hwc) -{ - return ((hwc->config >> 24) & 0x0f00) | (hwc->config & 0x00ff); -} - static inline int amd_is_nb_event(struct hw_perf_event *hwc) { return (hwc->config & 0xe0) == 0xe0; @@ -864,6 +876,20 @@ amd_get_event_constraints_f15h(struct cpu_hw_events *cpuc, int idx, } } +static struct event_constraint pair_constraint; + +static struct event_constraint * +amd_get_event_constraints_f17h(struct cpu_hw_events *cpuc, int idx, + struct perf_event *event) +{ + struct hw_perf_event *hwc = &event->hw; + + if (amd_is_pair_event_code(hwc)) + return &pair_constraint; + + return &unconstrained; +} + static ssize_t amd_event_sysfs_show(char *page, u64 config) { u64 event = (config & ARCH_PERFMON_EVENTSEL_EVENT) | @@ -907,33 +933,15 @@ static __initconst const struct x86_pmu amd_pmu = { static int __init amd_core_pmu_init(void) { + u64 even_ctr_mask = 0ULL; + int i; + if (!boot_cpu_has(X86_FEATURE_PERFCTR_CORE)) return 0; - /* Avoid calulating the value each time in the NMI handler */ + /* Avoid calculating the value each time in the NMI handler */ perf_nmi_window = msecs_to_jiffies(100); - switch (boot_cpu_data.x86) { - case 0x15: - pr_cont("Fam15h "); - x86_pmu.get_event_constraints = amd_get_event_constraints_f15h; - break; - case 0x17: - pr_cont("Fam17h "); - /* - * In family 17h, there are no event constraints in the PMC hardware. - * We fallback to using default amd_get_event_constraints. - */ - break; - case 0x18: - pr_cont("Fam18h "); - /* Using default amd_get_event_constraints. */ - break; - default: - pr_err("core perfctr but no constraints; unknown hardware!\n"); - return -ENODEV; - } - /* * If core performance counter extensions exists, we must use * MSR_F15H_PERF_CTL/MSR_F15H_PERF_CTR msrs. See also @@ -948,6 +956,30 @@ static int __init amd_core_pmu_init(void) */ x86_pmu.amd_nb_constraints = 0; + if (boot_cpu_data.x86 == 0x15) { + pr_cont("Fam15h "); + x86_pmu.get_event_constraints = amd_get_event_constraints_f15h; + } + if (boot_cpu_data.x86 >= 0x17) { + pr_cont("Fam17h+ "); + /* + * Family 17h and compatibles have constraints for Large + * Increment per Cycle events: they may only be assigned an + * even numbered counter that has a consecutive adjacent odd + * numbered counter following it. + */ + for (i = 0; i < x86_pmu.num_counters - 1; i += 2) + even_ctr_mask |= 1 << i; + + pair_constraint = (struct event_constraint) + __EVENT_CONSTRAINT(0, even_ctr_mask, 0, + x86_pmu.num_counters / 2, 0, + PERF_X86_EVENT_PAIR); + + x86_pmu.get_event_constraints = amd_get_event_constraints_f17h; + x86_pmu.flags |= PMU_FL_PAIR; + } + pr_cont("core perfctr, "); return 0; } diff --git a/arch/x86/events/amd/uncore.c b/arch/x86/events/amd/uncore.c index a6ea07f2aa84..4d867a752f0e 100644 --- a/arch/x86/events/amd/uncore.c +++ b/arch/x86/events/amd/uncore.c @@ -190,15 +190,12 @@ static int amd_uncore_event_init(struct perf_event *event) /* * NB and Last level cache counters (MSRs) are shared across all cores - * that share the same NB / Last level cache. Interrupts can be directed - * to a single target core, however, event counts generated by processes - * running on other cores cannot be masked out. So we do not support - * sampling and per-thread events. + * that share the same NB / Last level cache. On family 16h and below, + * Interrupts can be directed to a single target core, however, event + * counts generated by processes running on other cores cannot be masked + * out. So we do not support sampling and per-thread events via + * CAP_NO_INTERRUPT, and we do not enable counter overflow interrupts: */ - if (is_sampling_event(event) || event->attach_state & PERF_ATTACH_TASK) - return -EINVAL; - - /* and we do not enable counter overflow interrupts */ hwc->config = event->attr.config & AMD64_RAW_EVENT_MASK_NB; hwc->idx = -1; @@ -306,7 +303,7 @@ static struct pmu amd_nb_pmu = { .start = amd_uncore_start, .stop = amd_uncore_stop, .read = amd_uncore_read, - .capabilities = PERF_PMU_CAP_NO_EXCLUDE, + .capabilities = PERF_PMU_CAP_NO_EXCLUDE | PERF_PMU_CAP_NO_INTERRUPT, }; static struct pmu amd_llc_pmu = { @@ -317,7 +314,7 @@ static struct pmu amd_llc_pmu = { .start = amd_uncore_start, .stop = amd_uncore_stop, .read = amd_uncore_read, - .capabilities = PERF_PMU_CAP_NO_EXCLUDE, + .capabilities = PERF_PMU_CAP_NO_EXCLUDE | PERF_PMU_CAP_NO_INTERRUPT, }; static struct amd_uncore *amd_uncore_alloc(unsigned int cpu) diff --git a/arch/x86/events/core.c b/arch/x86/events/core.c index 3cd94a21bd53..bfcb077503e6 100644 --- a/arch/x86/events/core.c +++ b/arch/x86/events/core.c @@ -375,7 +375,7 @@ int x86_add_exclusive(unsigned int what) * LBR and BTS are still mutually exclusive. */ if (x86_pmu.lbr_pt_coexist && what == x86_lbr_exclusive_pt) - return 0; + goto out; if (!atomic_inc_not_zero(&x86_pmu.lbr_exclusive[what])) { mutex_lock(&pmc_reserve_mutex); @@ -387,6 +387,7 @@ int x86_add_exclusive(unsigned int what) mutex_unlock(&pmc_reserve_mutex); } +out: atomic_inc(&active_events); return 0; @@ -397,11 +398,15 @@ fail_unlock: void x86_del_exclusive(unsigned int what) { + atomic_dec(&active_events); + + /* + * See the comment in x86_add_exclusive(). + */ if (x86_pmu.lbr_pt_coexist && what == x86_lbr_exclusive_pt) return; atomic_dec(&x86_pmu.lbr_exclusive[what]); - atomic_dec(&active_events); } int x86_setup_perfctr(struct perf_event *event) diff --git a/arch/x86/events/intel/bts.c b/arch/x86/events/intel/bts.c index 5ee3fed881d3..741540d849f3 100644 --- a/arch/x86/events/intel/bts.c +++ b/arch/x86/events/intel/bts.c @@ -63,9 +63,17 @@ struct bts_buffer { static struct pmu bts_pmu; +static int buf_nr_pages(struct page *page) +{ + if (!PagePrivate(page)) + return 1; + + return 1 << page_private(page); +} + static size_t buf_size(struct page *page) { - return 1 << (PAGE_SHIFT + page_private(page)); + return buf_nr_pages(page) * PAGE_SIZE; } static void * @@ -83,9 +91,7 @@ bts_buffer_setup_aux(struct perf_event *event, void **pages, /* count all the high order buffers */ for (pg = 0, nbuf = 0; pg < nr_pages;) { page = virt_to_page(pages[pg]); - if (WARN_ON_ONCE(!PagePrivate(page) && nr_pages > 1)) - return NULL; - pg += 1 << page_private(page); + pg += buf_nr_pages(page); nbuf++; } @@ -109,7 +115,7 @@ bts_buffer_setup_aux(struct perf_event *event, void **pages, unsigned int __nr_pages; page = virt_to_page(pages[pg]); - __nr_pages = PagePrivate(page) ? 1 << page_private(page) : 1; + __nr_pages = buf_nr_pages(page); buf->buf[nbuf].page = page; buf->buf[nbuf].offset = offset; buf->buf[nbuf].displacement = (pad ? BTS_RECORD_SIZE - pad : 0); diff --git a/arch/x86/events/intel/core.c b/arch/x86/events/intel/core.c index 2369ea1a1db7..512bf05751c6 100644 --- a/arch/x86/events/intel/core.c +++ b/arch/x86/events/intel/core.c @@ -1891,8 +1891,8 @@ static __initconst const u64 tnt_hw_cache_extra_regs static struct extra_reg intel_tnt_extra_regs[] __read_mostly = { /* must define OFFCORE_RSP_X first, see intel_fixup_er() */ - INTEL_UEVENT_EXTRA_REG(0x01b7, MSR_OFFCORE_RSP_0, 0xffffff9fffull, RSP_0), - INTEL_UEVENT_EXTRA_REG(0x02b7, MSR_OFFCORE_RSP_1, 0xffffff9fffull, RSP_1), + INTEL_UEVENT_EXTRA_REG(0x01b7, MSR_OFFCORE_RSP_0, 0x800ff0ffffff9fffull, RSP_0), + INTEL_UEVENT_EXTRA_REG(0x02b7, MSR_OFFCORE_RSP_1, 0xff0ffffff9fffull, RSP_1), EVENT_EXTRA_END }; diff --git a/arch/x86/events/intel/ds.c b/arch/x86/events/intel/ds.c index 6601b8759c92..4e52c51c402e 100644 --- a/arch/x86/events/intel/ds.c +++ b/arch/x86/events/intel/ds.c @@ -1670,6 +1670,8 @@ intel_pmu_save_and_restart_reload(struct perf_event *event, int count) old = ((s64)(prev_raw_count << shift) >> shift); local64_add(new - old + count * period, &event->count); + local64_set(&hwc->period_left, -new); + perf_event_update_userpage(event); return 0; diff --git a/arch/x86/events/intel/uncore_snb.c b/arch/x86/events/intel/uncore_snb.c index f8431819b3e1..5c1da571a5aa 100644 --- a/arch/x86/events/intel/uncore_snb.c +++ b/arch/x86/events/intel/uncore_snb.c @@ -15,6 +15,7 @@ #define PCI_DEVICE_ID_INTEL_SKL_HQ_IMC 0x1910 #define PCI_DEVICE_ID_INTEL_SKL_SD_IMC 0x190f #define PCI_DEVICE_ID_INTEL_SKL_SQ_IMC 0x191f +#define PCI_DEVICE_ID_INTEL_SKL_E3_IMC 0x1918 #define PCI_DEVICE_ID_INTEL_KBL_Y_IMC 0x590c #define PCI_DEVICE_ID_INTEL_KBL_U_IMC 0x5904 #define PCI_DEVICE_ID_INTEL_KBL_UQ_IMC 0x5914 @@ -662,6 +663,10 @@ static const struct pci_device_id skl_uncore_pci_ids[] = { .driver_data = UNCORE_PCI_DEV_DATA(SNB_PCI_UNCORE_IMC, 0), }, { /* IMC */ + PCI_DEVICE(PCI_VENDOR_ID_INTEL, PCI_DEVICE_ID_INTEL_SKL_E3_IMC), + .driver_data = UNCORE_PCI_DEV_DATA(SNB_PCI_UNCORE_IMC, 0), + }, + { /* IMC */ PCI_DEVICE(PCI_VENDOR_ID_INTEL, PCI_DEVICE_ID_INTEL_KBL_Y_IMC), .driver_data = UNCORE_PCI_DEV_DATA(SNB_PCI_UNCORE_IMC, 0), }, @@ -802,6 +807,7 @@ static const struct imc_uncore_pci_dev desktop_imc_pci_ids[] = { IMC_DEV(SKL_HQ_IMC, &skl_uncore_pci_driver), /* 6th Gen Core H Quad Core */ IMC_DEV(SKL_SD_IMC, &skl_uncore_pci_driver), /* 6th Gen Core S Dual Core */ IMC_DEV(SKL_SQ_IMC, &skl_uncore_pci_driver), /* 6th Gen Core S Quad Core */ + IMC_DEV(SKL_E3_IMC, &skl_uncore_pci_driver), /* Xeon E3 V5 Gen Core processor */ IMC_DEV(KBL_Y_IMC, &skl_uncore_pci_driver), /* 7th Gen Core Y */ IMC_DEV(KBL_U_IMC, &skl_uncore_pci_driver), /* 7th Gen Core U */ IMC_DEV(KBL_UQ_IMC, &skl_uncore_pci_driver), /* 7th Gen Core U Quad Core */ diff --git a/arch/x86/events/perf_event.h b/arch/x86/events/perf_event.h index 4e346856ee19..134c89d815d7 100644 --- a/arch/x86/events/perf_event.h +++ b/arch/x86/events/perf_event.h @@ -76,6 +76,7 @@ static inline bool constraint_match(struct event_constraint *c, u64 ecode) #define PERF_X86_EVENT_EXCL_ACCT 0x0100 /* accounted EXCL event */ #define PERF_X86_EVENT_AUTO_RELOAD 0x0200 /* use PEBS auto-reload */ #define PERF_X86_EVENT_LARGE_PEBS 0x0400 /* use large PEBS */ +#define PERF_X86_EVENT_PAIR 0x1000 /* Large Increment per Cycle */ struct amd_nb { int nb_id; /* NorthBridge id */ @@ -726,6 +727,7 @@ do { \ #define PMU_FL_EXCL_ENABLED 0x8 /* exclusive counter active */ #define PMU_FL_PEBS_ALL 0x10 /* all events are valid PEBS events */ #define PMU_FL_TFA 0x20 /* deal with TSX force abort */ +#define PMU_FL_PAIR 0x40 /* merge counters for large incr. events */ #define EVENT_VAR(_id) event_attr_##_id #define EVENT_PTR(_id) &event_attr_##_id.attr.attr diff --git a/arch/x86/hyperv/hv_init.c b/arch/x86/hyperv/hv_init.c index dd92d8b438d4..18c3c2bb17b0 100644 --- a/arch/x86/hyperv/hv_init.c +++ b/arch/x86/hyperv/hv_init.c @@ -20,6 +20,7 @@ #include <linux/clockchips.h> #include <linux/hyperv.h> #include <linux/slab.h> +#include <linux/kernel.h> #include <linux/cpuhotplug.h> #ifdef CONFIG_HYPERV_TSCPAGE @@ -427,11 +428,14 @@ void hyperv_cleanup(void) } EXPORT_SYMBOL_GPL(hyperv_cleanup); -void hyperv_report_panic(struct pt_regs *regs, long err) +void hyperv_report_panic(struct pt_regs *regs, long err, bool in_die) { static bool panic_reported; u64 guest_id; + if (in_die && !panic_on_oops) + return; + /* * We prefer to report panic on 'die' chain as we have proper * registers to report, but if we miss it (e.g. on BUG()) we need diff --git a/arch/x86/ia32/ia32_signal.c b/arch/x86/ia32/ia32_signal.c index 629d1ee05599..08ee9e6da915 100644 --- a/arch/x86/ia32/ia32_signal.c +++ b/arch/x86/ia32/ia32_signal.c @@ -21,6 +21,7 @@ #include <linux/personality.h> #include <linux/compat.h> #include <linux/binfmts.h> +#include <linux/syscalls.h> #include <asm/ucontext.h> #include <linux/uaccess.h> #include <asm/fpu/internal.h> @@ -118,7 +119,7 @@ static int ia32_restore_sigcontext(struct pt_regs *regs, return err; } -asmlinkage long sys32_sigreturn(void) +COMPAT_SYSCALL_DEFINE0(sigreturn) { struct pt_regs *regs = current_pt_regs(); struct sigframe_ia32 __user *frame = (struct sigframe_ia32 __user *)(regs->sp-8); @@ -144,7 +145,7 @@ badframe: return 0; } -asmlinkage long sys32_rt_sigreturn(void) +COMPAT_SYSCALL_DEFINE0(rt_sigreturn) { struct pt_regs *regs = current_pt_regs(); struct rt_sigframe_ia32 __user *frame; diff --git a/arch/x86/include/asm/apic.h b/arch/x86/include/asm/apic.h index 2e599384abd8..84402de885b9 100644 --- a/arch/x86/include/asm/apic.h +++ b/arch/x86/include/asm/apic.h @@ -53,7 +53,7 @@ extern int apic_verbosity; extern int local_apic_timer_c2_ok; extern int disable_apic; -extern unsigned int lapic_timer_frequency; +extern unsigned int lapic_timer_period; extern enum apic_intr_mode_id apic_intr_mode; enum apic_intr_mode_id { @@ -448,6 +448,14 @@ static inline void ack_APIC_irq(void) apic_eoi(); } + +static inline bool lapic_vector_set_in_irr(unsigned int vector) +{ + u32 irr = apic_read(APIC_IRR + (vector / 32 * 0x10)); + + return !!(irr & (1U << (vector % 32))); +} + static inline unsigned default_get_apic_id(unsigned long x) { unsigned int ver = GET_APIC_VERSION(apic_read(APIC_LVR)); diff --git a/arch/x86/include/asm/cpu_device_id.h b/arch/x86/include/asm/cpu_device_id.h index 31c379c1da41..0c814cd9ea42 100644 --- a/arch/x86/include/asm/cpu_device_id.h +++ b/arch/x86/include/asm/cpu_device_id.h @@ -9,6 +9,36 @@ #include <linux/mod_devicetable.h> +#define X86_CENTAUR_FAM6_C7_D 0xd +#define X86_CENTAUR_FAM6_NANO 0xf + +#define X86_STEPPINGS(mins, maxs) GENMASK(maxs, mins) + +/** + * X86_MATCH_VENDOR_FAM_MODEL_STEPPINGS_FEATURE - Base macro for CPU matching + * @_vendor: The vendor name, e.g. INTEL, AMD, HYGON, ..., ANY + * The name is expanded to X86_VENDOR_@_vendor + * @_family: The family number or X86_FAMILY_ANY + * @_model: The model number, model constant or X86_MODEL_ANY + * @_steppings: Bitmask for steppings, stepping constant or X86_STEPPING_ANY + * @_feature: A X86_FEATURE bit or X86_FEATURE_ANY + * @_data: Driver specific data or NULL. The internal storage + * format is unsigned long. The supplied value, pointer + * etc. is casted to unsigned long internally. + * + * Backport version to keep the SRBDS pile consistant. No shorter variants + * required for this. + */ +#define X86_MATCH_VENDOR_FAM_MODEL_STEPPINGS_FEATURE(_vendor, _family, _model, \ + _steppings, _feature, _data) { \ + .vendor = X86_VENDOR_##_vendor, \ + .family = _family, \ + .model = _model, \ + .steppings = _steppings, \ + .feature = _feature, \ + .driver_data = (unsigned long) _data \ +} + /* * Match specific microcode revisions. * diff --git a/arch/x86/include/asm/cpufeatures.h b/arch/x86/include/asm/cpufeatures.h index 6086e00f4b97..463395d7a306 100644 --- a/arch/x86/include/asm/cpufeatures.h +++ b/arch/x86/include/asm/cpufeatures.h @@ -351,6 +351,7 @@ /* Intel-defined CPU features, CPUID level 0x00000007:0 (EDX), word 18 */ #define X86_FEATURE_AVX512_4VNNIW (18*32+ 2) /* AVX-512 Neural Network Instructions */ #define X86_FEATURE_AVX512_4FMAPS (18*32+ 3) /* AVX-512 Multiply Accumulation Single precision */ +#define X86_FEATURE_SRBDS_CTRL (18*32+ 9) /* "" SRBDS mitigation MSR available */ #define X86_FEATURE_MD_CLEAR (18*32+10) /* VERW clears CPU buffers */ #define X86_FEATURE_TSX_FORCE_ABORT (18*32+13) /* "" TSX_FORCE_ABORT */ #define X86_FEATURE_PCONFIG (18*32+18) /* Intel PCONFIG */ @@ -395,5 +396,6 @@ #define X86_BUG_SWAPGS X86_BUG(21) /* CPU is affected by speculation through SWAPGS */ #define X86_BUG_TAA X86_BUG(22) /* CPU is affected by TSX Async Abort(TAA) */ #define X86_BUG_ITLB_MULTIHIT X86_BUG(23) /* CPU may incur MCE during certain page attribute changes */ +#define X86_BUG_SRBDS X86_BUG(24) /* CPU may leak RNG bits if not mitigated */ #endif /* _ASM_X86_CPUFEATURES_H */ diff --git a/arch/x86/include/asm/crash.h b/arch/x86/include/asm/crash.h index 0acf5ee45a21..ef5638f641f2 100644 --- a/arch/x86/include/asm/crash.h +++ b/arch/x86/include/asm/crash.h @@ -2,6 +2,8 @@ #ifndef _ASM_X86_CRASH_H #define _ASM_X86_CRASH_H +struct kimage; + int crash_load_segments(struct kimage *image); int crash_copy_backup_region(struct kimage *image); int crash_setup_memmap_entries(struct kimage *image, diff --git a/arch/x86/include/asm/dma.h b/arch/x86/include/asm/dma.h index 00f7cf45e699..8e95aa4b0d17 100644 --- a/arch/x86/include/asm/dma.h +++ b/arch/x86/include/asm/dma.h @@ -74,7 +74,7 @@ #define MAX_DMA_PFN ((16UL * 1024 * 1024) >> PAGE_SHIFT) /* 4GB broken PCI/AGP hardware bus master zone */ -#define MAX_DMA32_PFN ((4UL * 1024 * 1024 * 1024) >> PAGE_SHIFT) +#define MAX_DMA32_PFN (1UL << (32 - PAGE_SHIFT)) #ifdef CONFIG_X86_32 /* The maximum address that we can perform a DMA transfer to on this platform */ diff --git a/arch/x86/include/asm/fixmap.h b/arch/x86/include/asm/fixmap.h index 9da8cccdf3fb..6a295acd3de6 100644 --- a/arch/x86/include/asm/fixmap.h +++ b/arch/x86/include/asm/fixmap.h @@ -157,7 +157,7 @@ extern pte_t *kmap_pte; extern pte_t *pkmap_page_table; void __native_set_fixmap(enum fixed_addresses idx, pte_t pte); -void native_set_fixmap(enum fixed_addresses idx, +void native_set_fixmap(unsigned /* enum fixed_addresses */ idx, phys_addr_t phys, pgprot_t flags); #ifndef CONFIG_PARAVIRT_XXL diff --git a/arch/x86/include/asm/fpu/internal.h b/arch/x86/include/asm/fpu/internal.h index 44c48e34d799..00eac7f1529b 100644 --- a/arch/x86/include/asm/fpu/internal.h +++ b/arch/x86/include/asm/fpu/internal.h @@ -619,6 +619,11 @@ static inline void switch_fpu_finish(struct fpu *new_fpu) * MXCSR and XCR definitions: */ +static inline void ldmxcsr(u32 mxcsr) +{ + asm volatile("ldmxcsr %0" :: "m" (mxcsr)); +} + extern unsigned int mxcsr_feature_mask; #define XCR_XFEATURE_ENABLED_MASK 0x00000000 diff --git a/arch/x86/include/asm/kvm_host.h b/arch/x86/include/asm/kvm_host.h index 4512200c33d2..c58b42c1011c 100644 --- a/arch/x86/include/asm/kvm_host.h +++ b/arch/x86/include/asm/kvm_host.h @@ -385,12 +385,12 @@ struct kvm_mmu { void (*set_cr3)(struct kvm_vcpu *vcpu, unsigned long root); unsigned long (*get_cr3)(struct kvm_vcpu *vcpu); u64 (*get_pdptr)(struct kvm_vcpu *vcpu, int index); - int (*page_fault)(struct kvm_vcpu *vcpu, gva_t gva, u32 err, + int (*page_fault)(struct kvm_vcpu *vcpu, gpa_t cr2_or_gpa, u32 err, bool prefault); void (*inject_page_fault)(struct kvm_vcpu *vcpu, struct x86_exception *fault); - gpa_t (*gva_to_gpa)(struct kvm_vcpu *vcpu, gva_t gva, u32 access, - struct x86_exception *exception); + gpa_t (*gva_to_gpa)(struct kvm_vcpu *vcpu, gpa_t gva_or_gpa, + u32 access, struct x86_exception *exception); gpa_t (*translate_gpa)(struct kvm_vcpu *vcpu, gpa_t gpa, u32 access, struct x86_exception *exception); int (*sync_page)(struct kvm_vcpu *vcpu, @@ -555,6 +555,7 @@ struct kvm_vcpu_arch { unsigned long cr4; unsigned long cr4_guest_owned_bits; unsigned long cr8; + u32 host_pkru; u32 pkru; u32 hflags; u64 efer; @@ -570,6 +571,7 @@ struct kvm_vcpu_arch { u64 smbase; u64 smi_count; bool tpr_access_reporting; + bool xsaves_enabled; u64 ia32_xss; u64 microcode_version; u64 arch_capabilities; @@ -620,7 +622,7 @@ struct kvm_vcpu_arch { * "guest_fpu" state here contains the guest FPU context, with the * host PRKU bits. */ - struct fpu user_fpu; + struct fpu *user_fpu; struct fpu *guest_fpu; u64 xcr0; @@ -672,10 +674,10 @@ struct kvm_vcpu_arch { bool pvclock_set_guest_stopped_request; struct { + u8 preempted; u64 msr_val; u64 last_steal; - struct gfn_to_hva_cache stime; - struct kvm_steal_time steal; + struct gfn_to_pfn_cache cache; } st; u64 tsc_offset; @@ -1094,7 +1096,7 @@ struct kvm_x86_ops { void (*load_eoi_exitmap)(struct kvm_vcpu *vcpu, u64 *eoi_exit_bitmap); void (*set_virtual_apic_mode)(struct kvm_vcpu *vcpu); void (*set_apic_access_page_addr)(struct kvm_vcpu *vcpu, hpa_t hpa); - void (*deliver_posted_interrupt)(struct kvm_vcpu *vcpu, int vector); + int (*deliver_posted_interrupt)(struct kvm_vcpu *vcpu, int vector); int (*sync_pir_to_irr)(struct kvm_vcpu *vcpu); int (*set_tss_addr)(struct kvm *kvm, unsigned int addr); int (*set_identity_map_addr)(struct kvm *kvm, u64 ident_addr); @@ -1124,8 +1126,9 @@ struct kvm_x86_ops { bool (*xsaves_supported)(void); bool (*umip_emulated)(void); bool (*pt_supported)(void); + bool (*pku_supported)(void); - int (*check_nested_events)(struct kvm_vcpu *vcpu, bool external_intr); + int (*check_nested_events)(struct kvm_vcpu *vcpu); void (*request_immediate_exit)(struct kvm_vcpu *vcpu); void (*sched_in)(struct kvm_vcpu *kvm, int cpu); @@ -1154,7 +1157,7 @@ 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 (*write_log_dirty)(struct kvm_vcpu *vcpu); + int (*write_log_dirty)(struct kvm_vcpu *vcpu, gpa_t l2_gpa); /* pmu operations of sub-arch */ const struct kvm_pmu_ops *pmu_ops; @@ -1417,7 +1420,7 @@ void kvm_vcpu_deactivate_apicv(struct kvm_vcpu *vcpu); int kvm_emulate_hypercall(struct kvm_vcpu *vcpu); -int kvm_mmu_page_fault(struct kvm_vcpu *vcpu, gva_t gva, u64 error_code, +int kvm_mmu_page_fault(struct kvm_vcpu *vcpu, gpa_t cr2_or_gpa, u64 error_code, void *insn, int insn_len); void kvm_mmu_invlpg(struct kvm_vcpu *vcpu, gva_t gva); void kvm_mmu_invpcid_gva(struct kvm_vcpu *vcpu, gva_t gva, unsigned long pcid); @@ -1585,8 +1588,8 @@ void kvm_set_msi_irq(struct kvm *kvm, struct kvm_kernel_irq_routing_entry *e, static inline bool kvm_irq_is_postable(struct kvm_lapic_irq *irq) { /* We can only post Fixed and LowPrio IRQs */ - return (irq->delivery_mode == dest_Fixed || - irq->delivery_mode == dest_LowestPrio); + return (irq->delivery_mode == APIC_DM_FIXED || + irq->delivery_mode == APIC_DM_LOWEST); } static inline void kvm_arch_vcpu_blocking(struct kvm_vcpu *vcpu) diff --git a/arch/x86/include/asm/microcode_amd.h b/arch/x86/include/asm/microcode_amd.h index 209492849566..5c524d4f71cd 100644 --- a/arch/x86/include/asm/microcode_amd.h +++ b/arch/x86/include/asm/microcode_amd.h @@ -41,7 +41,7 @@ struct microcode_amd { unsigned int mpb[0]; }; -#define PATCH_MAX_SIZE PAGE_SIZE +#define PATCH_MAX_SIZE (3 * PAGE_SIZE) #ifdef CONFIG_MICROCODE_AMD extern void __init load_ucode_amd_bsp(unsigned int family); diff --git a/arch/x86/include/asm/mshyperv.h b/arch/x86/include/asm/mshyperv.h index cc60e617931c..ae44aa1f8a80 100644 --- a/arch/x86/include/asm/mshyperv.h +++ b/arch/x86/include/asm/mshyperv.h @@ -343,7 +343,7 @@ static inline int cpumask_to_vpset(struct hv_vpset *vpset, void __init hyperv_init(void); void hyperv_setup_mmu_ops(void); -void hyperv_report_panic(struct pt_regs *regs, long err); +void hyperv_report_panic(struct pt_regs *regs, long err, bool in_die); void hyperv_report_panic_msg(phys_addr_t pa, size_t size); bool hv_is_hyperv_initialized(void); void hyperv_cleanup(void); diff --git a/arch/x86/include/asm/msr-index.h b/arch/x86/include/asm/msr-index.h index bae74871c017..e1c4bf0fa66c 100644 --- a/arch/x86/include/asm/msr-index.h +++ b/arch/x86/include/asm/msr-index.h @@ -110,6 +110,10 @@ #define TSX_CTRL_RTM_DISABLE BIT(0) /* Disable RTM feature */ #define TSX_CTRL_CPUID_CLEAR BIT(1) /* Disable TSX enumeration */ +/* SRBDS support */ +#define MSR_IA32_MCU_OPT_CTRL 0x00000123 +#define RNGDS_MITG_DIS BIT(0) + #define MSR_IA32_SYSENTER_CS 0x00000174 #define MSR_IA32_SYSENTER_ESP 0x00000175 #define MSR_IA32_SYSENTER_EIP 0x00000176 @@ -493,6 +497,8 @@ #define MSR_K7_HWCR 0xc0010015 #define MSR_K7_HWCR_SMMLOCK_BIT 0 #define MSR_K7_HWCR_SMMLOCK BIT_ULL(MSR_K7_HWCR_SMMLOCK_BIT) +#define MSR_K7_HWCR_IRPERF_EN_BIT 30 +#define MSR_K7_HWCR_IRPERF_EN BIT_ULL(MSR_K7_HWCR_IRPERF_EN_BIT) #define MSR_K7_FID_VID_CTL 0xc0010041 #define MSR_K7_FID_VID_STATUS 0xc0010042 diff --git a/arch/x86/include/asm/nmi.h b/arch/x86/include/asm/nmi.h index 75ded1d13d98..9d5d949e662e 100644 --- a/arch/x86/include/asm/nmi.h +++ b/arch/x86/include/asm/nmi.h @@ -41,7 +41,6 @@ struct nmiaction { struct list_head list; nmi_handler_t handler; u64 max_duration; - struct irq_work irq_work; unsigned long flags; const char *name; }; diff --git a/arch/x86/include/asm/pgtable.h b/arch/x86/include/asm/pgtable.h index 5e0509b41986..c8e859cdead7 100644 --- a/arch/x86/include/asm/pgtable.h +++ b/arch/x86/include/asm/pgtable.h @@ -253,6 +253,7 @@ static inline int pmd_large(pmd_t pte) } #ifdef CONFIG_TRANSPARENT_HUGEPAGE +/* NOTE: when predicate huge page, consider also pmd_devmap, or use pmd_large */ static inline int pmd_trans_huge(pmd_t pmd) { return (pmd_val(pmd) & (_PAGE_PSE|_PAGE_DEVMAP)) == _PAGE_PSE; @@ -624,12 +625,15 @@ static inline pmd_t pmd_modify(pmd_t pmd, pgprot_t newprot) return __pmd(val); } -/* mprotect needs to preserve PAT bits when updating vm_page_prot */ +/* + * mprotect needs to preserve PAT and encryption bits when updating + * vm_page_prot + */ #define pgprot_modify pgprot_modify static inline pgprot_t pgprot_modify(pgprot_t oldprot, pgprot_t newprot) { pgprotval_t preservebits = pgprot_val(oldprot) & _PAGE_CHG_MASK; - pgprotval_t addbits = pgprot_val(newprot); + pgprotval_t addbits = pgprot_val(newprot) & ~_PAGE_CHG_MASK; return __pgprot(preservebits | addbits); } diff --git a/arch/x86/include/asm/pgtable_types.h b/arch/x86/include/asm/pgtable_types.h index d6ff0bbdb394..9484b06291ec 100644 --- a/arch/x86/include/asm/pgtable_types.h +++ b/arch/x86/include/asm/pgtable_types.h @@ -124,7 +124,7 @@ */ #define _PAGE_CHG_MASK (PTE_PFN_MASK | _PAGE_PCD | _PAGE_PWT | \ _PAGE_SPECIAL | _PAGE_ACCESSED | _PAGE_DIRTY | \ - _PAGE_SOFT_DIRTY | _PAGE_DEVMAP) + _PAGE_SOFT_DIRTY | _PAGE_DEVMAP | _PAGE_ENC) #define _HPAGE_CHG_MASK (_PAGE_CHG_MASK | _PAGE_PSE) /* diff --git a/arch/x86/include/asm/processor.h b/arch/x86/include/asm/processor.h index 5024aa0f82a7..f9300c86d95d 100644 --- a/arch/x86/include/asm/processor.h +++ b/arch/x86/include/asm/processor.h @@ -331,7 +331,7 @@ struct x86_hw_tss { #define INVALID_IO_BITMAP_OFFSET 0x8000 struct entry_stack { - unsigned long words[64]; + char stack[PAGE_SIZE]; }; struct entry_stack_page { diff --git a/arch/x86/include/asm/set_memory.h b/arch/x86/include/asm/set_memory.h index ae7b909dc242..75d298cbc780 100644 --- a/arch/x86/include/asm/set_memory.h +++ b/arch/x86/include/asm/set_memory.h @@ -93,28 +93,35 @@ void set_kernel_text_rw(void); void set_kernel_text_ro(void); #ifdef CONFIG_X86_64 -static inline int set_mce_nospec(unsigned long pfn) +/* + * Prevent speculative access to the page by either unmapping + * it (if we do not require access to any part of the page) or + * marking it uncacheable (if we want to try to retrieve data + * from non-poisoned lines in the page). + */ +static inline int set_mce_nospec(unsigned long pfn, bool unmap) { unsigned long decoy_addr; int rc; /* - * Mark the linear address as UC to make sure we don't log more - * errors because of speculative access to the page. * We would like to just call: - * set_memory_uc((unsigned long)pfn_to_kaddr(pfn), 1); + * set_memory_XX((unsigned long)pfn_to_kaddr(pfn), 1); * but doing that would radically increase the odds of a * speculative access to the poison page because we'd have * the virtual address of the kernel 1:1 mapping sitting * around in registers. * Instead we get tricky. We create a non-canonical address * that looks just like the one we want, but has bit 63 flipped. - * This relies on set_memory_uc() properly sanitizing any __pa() + * This relies on set_memory_XX() properly sanitizing any __pa() * results with __PHYSICAL_MASK or PTE_PFN_MASK. */ decoy_addr = (pfn << PAGE_SHIFT) + (PAGE_OFFSET ^ BIT(63)); - rc = set_memory_uc(decoy_addr, 1); + if (unmap) + rc = set_memory_np(decoy_addr, 1); + else + rc = set_memory_uc(decoy_addr, 1); if (rc) pr_warn("Could not invalidate pfn=0x%lx from 1:1 map\n", pfn); return rc; diff --git a/arch/x86/include/asm/smap.h b/arch/x86/include/asm/smap.h index 27c47d183f4b..8b58d6975d5d 100644 --- a/arch/x86/include/asm/smap.h +++ b/arch/x86/include/asm/smap.h @@ -57,8 +57,10 @@ static __always_inline unsigned long smap_save(void) { unsigned long flags; - asm volatile (ALTERNATIVE("", "pushf; pop %0; " __ASM_CLAC, - X86_FEATURE_SMAP) + asm volatile ("# smap_save\n\t" + ALTERNATIVE("jmp 1f", "", X86_FEATURE_SMAP) + "pushf; pop %0; " __ASM_CLAC "\n\t" + "1:" : "=rm" (flags) : : "memory", "cc"); return flags; @@ -66,7 +68,10 @@ static __always_inline unsigned long smap_save(void) static __always_inline void smap_restore(unsigned long flags) { - asm volatile (ALTERNATIVE("", "push %0; popf", X86_FEATURE_SMAP) + asm volatile ("# smap_restore\n\t" + ALTERNATIVE("jmp 1f", "", X86_FEATURE_SMAP) + "push %0; popf\n\t" + "1:" : : "g" (flags) : "memory", "cc"); } diff --git a/arch/x86/include/asm/stackprotector.h b/arch/x86/include/asm/stackprotector.h index 91e29b6a86a5..9804a7957f4e 100644 --- a/arch/x86/include/asm/stackprotector.h +++ b/arch/x86/include/asm/stackprotector.h @@ -55,8 +55,13 @@ /* * Initialize the stackprotector canary value. * - * NOTE: this must only be called from functions that never return, + * NOTE: this must only be called from functions that never return * and it must always be inlined. + * + * In addition, it should be called from a compilation unit for which + * stack protector is disabled. Alternatively, the caller should not end + * with a function call which gets tail-call optimized as that would + * lead to checking a modified canary value. */ static __always_inline void boot_init_stack_canary(void) { diff --git a/arch/x86/include/asm/syscall.h b/arch/x86/include/asm/syscall.h index 2dc4a021beea..8db3fdb6102e 100644 --- a/arch/x86/include/asm/syscall.h +++ b/arch/x86/include/asm/syscall.h @@ -36,6 +36,10 @@ extern const sys_call_ptr_t sys_call_table[]; extern const sys_call_ptr_t ia32_sys_call_table[]; #endif +#ifdef CONFIG_X86_X32_ABI +extern const sys_call_ptr_t x32_sys_call_table[]; +#endif + /* * Only the low 32 bits of orig_ax are meaningful, so we return int. * This importantly ignores the high bits on 64-bit, so comparisons diff --git a/arch/x86/include/asm/syscall_wrapper.h b/arch/x86/include/asm/syscall_wrapper.h index e046a405743d..e2389ce9bf58 100644 --- a/arch/x86/include/asm/syscall_wrapper.h +++ b/arch/x86/include/asm/syscall_wrapper.h @@ -6,6 +6,8 @@ #ifndef _ASM_X86_SYSCALL_WRAPPER_H #define _ASM_X86_SYSCALL_WRAPPER_H +struct pt_regs; + /* Mapping of registers to parameters for syscalls on x86-64 and x32 */ #define SC_X86_64_REGS_TO_ARGS(x, ...) \ __MAP(x,__SC_ARGS \ @@ -28,13 +30,21 @@ * kernel/sys_ni.c and SYS_NI in kernel/time/posix-stubs.c to cover this * case as well. */ +#define __IA32_COMPAT_SYS_STUB0(x, name) \ + asmlinkage long __ia32_compat_sys_##name(const struct pt_regs *regs);\ + ALLOW_ERROR_INJECTION(__ia32_compat_sys_##name, ERRNO); \ + asmlinkage long __ia32_compat_sys_##name(const struct pt_regs *regs)\ + { \ + return __se_compat_sys_##name(); \ + } + #define __IA32_COMPAT_SYS_STUBx(x, name, ...) \ asmlinkage long __ia32_compat_sys##name(const struct pt_regs *regs);\ ALLOW_ERROR_INJECTION(__ia32_compat_sys##name, ERRNO); \ asmlinkage long __ia32_compat_sys##name(const struct pt_regs *regs)\ { \ return __se_compat_sys##name(SC_IA32_REGS_TO_ARGS(x,__VA_ARGS__));\ - } \ + } #define __IA32_SYS_STUBx(x, name, ...) \ asmlinkage long __ia32_sys##name(const struct pt_regs *regs); \ @@ -48,16 +58,23 @@ * To keep the naming coherent, re-define SYSCALL_DEFINE0 to create an alias * named __ia32_sys_*() */ -#define SYSCALL_DEFINE0(sname) \ - SYSCALL_METADATA(_##sname, 0); \ - asmlinkage long __x64_sys_##sname(void); \ - ALLOW_ERROR_INJECTION(__x64_sys_##sname, ERRNO); \ - SYSCALL_ALIAS(__ia32_sys_##sname, __x64_sys_##sname); \ - asmlinkage long __x64_sys_##sname(void) -#define COND_SYSCALL(name) \ - cond_syscall(__x64_sys_##name); \ - cond_syscall(__ia32_sys_##name) +#define SYSCALL_DEFINE0(sname) \ + SYSCALL_METADATA(_##sname, 0); \ + asmlinkage long __x64_sys_##sname(const struct pt_regs *__unused);\ + ALLOW_ERROR_INJECTION(__x64_sys_##sname, ERRNO); \ + SYSCALL_ALIAS(__ia32_sys_##sname, __x64_sys_##sname); \ + asmlinkage long __x64_sys_##sname(const struct pt_regs *__unused) + +#define COND_SYSCALL(name) \ + asmlinkage __weak long __x64_sys_##name(const struct pt_regs *__unused) \ + { \ + return sys_ni_syscall(); \ + } \ + asmlinkage __weak long __ia32_sys_##name(const struct pt_regs *__unused)\ + { \ + return sys_ni_syscall(); \ + } #define SYS_NI(name) \ SYSCALL_ALIAS(__x64_sys_##name, sys_ni_posix_timers); \ @@ -75,15 +92,24 @@ * of the x86-64-style parameter ordering of x32 syscalls. The syscalls common * with x86_64 obviously do not need such care. */ +#define __X32_COMPAT_SYS_STUB0(x, name, ...) \ + asmlinkage long __x32_compat_sys_##name(const struct pt_regs *regs);\ + ALLOW_ERROR_INJECTION(__x32_compat_sys_##name, ERRNO); \ + asmlinkage long __x32_compat_sys_##name(const struct pt_regs *regs)\ + { \ + return __se_compat_sys_##name();\ + } + #define __X32_COMPAT_SYS_STUBx(x, name, ...) \ asmlinkage long __x32_compat_sys##name(const struct pt_regs *regs);\ ALLOW_ERROR_INJECTION(__x32_compat_sys##name, ERRNO); \ asmlinkage long __x32_compat_sys##name(const struct pt_regs *regs)\ { \ return __se_compat_sys##name(SC_X86_64_REGS_TO_ARGS(x,__VA_ARGS__));\ - } \ + } #else /* CONFIG_X86_X32 */ +#define __X32_COMPAT_SYS_STUB0(x, name) #define __X32_COMPAT_SYS_STUBx(x, name, ...) #endif /* CONFIG_X86_X32 */ @@ -94,6 +120,17 @@ * mapping of registers to parameters, we need to generate stubs for each * of them. */ +#define COMPAT_SYSCALL_DEFINE0(name) \ + static long __se_compat_sys_##name(void); \ + static inline long __do_compat_sys_##name(void); \ + __IA32_COMPAT_SYS_STUB0(x, name) \ + __X32_COMPAT_SYS_STUB0(x, name) \ + static long __se_compat_sys_##name(void) \ + { \ + return __do_compat_sys_##name(); \ + } \ + static inline long __do_compat_sys_##name(void) + #define COMPAT_SYSCALL_DEFINEx(x, name, ...) \ static long __se_compat_sys##name(__MAP(x,__SC_LONG,__VA_ARGS__)); \ static inline long __do_compat_sys##name(__MAP(x,__SC_DECL,__VA_ARGS__));\ @@ -181,15 +218,19 @@ * macros to work correctly. */ #ifndef SYSCALL_DEFINE0 -#define SYSCALL_DEFINE0(sname) \ - SYSCALL_METADATA(_##sname, 0); \ - asmlinkage long __x64_sys_##sname(void); \ - ALLOW_ERROR_INJECTION(__x64_sys_##sname, ERRNO); \ - asmlinkage long __x64_sys_##sname(void) +#define SYSCALL_DEFINE0(sname) \ + SYSCALL_METADATA(_##sname, 0); \ + asmlinkage long __x64_sys_##sname(const struct pt_regs *__unused);\ + ALLOW_ERROR_INJECTION(__x64_sys_##sname, ERRNO); \ + asmlinkage long __x64_sys_##sname(const struct pt_regs *__unused) #endif #ifndef COND_SYSCALL -#define COND_SYSCALL(name) cond_syscall(__x64_sys_##name) +#define COND_SYSCALL(name) \ + asmlinkage __weak long __x64_sys_##name(const struct pt_regs *__unused) \ + { \ + return sys_ni_syscall(); \ + } #endif #ifndef SYS_NI @@ -201,7 +242,6 @@ * For VSYSCALLS, we need to declare these three syscalls with the new * pt_regs-based calling convention for in-kernel use. */ -struct pt_regs; asmlinkage long __x64_sys_getcpu(const struct pt_regs *regs); asmlinkage long __x64_sys_gettimeofday(const struct pt_regs *regs); asmlinkage long __x64_sys_time(const struct pt_regs *regs); diff --git a/arch/x86/include/asm/unistd.h b/arch/x86/include/asm/unistd.h index 146859efd83c..b923b8d333d4 100644 --- a/arch/x86/include/asm/unistd.h +++ b/arch/x86/include/asm/unistd.h @@ -5,12 +5,6 @@ #include <uapi/asm/unistd.h> -# ifdef CONFIG_X86_X32_ABI -# define __SYSCALL_MASK (~(__X32_SYSCALL_BIT)) -# else -# define __SYSCALL_MASK (~0) -# endif - # ifdef CONFIG_X86_32 # include <asm/unistd_32.h> diff --git a/arch/x86/include/asm/unwind.h b/arch/x86/include/asm/unwind.h index 499578f7e6d7..70fc159ebe69 100644 --- a/arch/x86/include/asm/unwind.h +++ b/arch/x86/include/asm/unwind.h @@ -19,7 +19,7 @@ struct unwind_state { #if defined(CONFIG_UNWINDER_ORC) bool signal, full_regs; unsigned long sp, bp, ip; - struct pt_regs *regs; + struct pt_regs *regs, *prev_regs; #elif defined(CONFIG_UNWINDER_FRAME_POINTER) bool got_irq; unsigned long *bp, *orig_sp, ip; diff --git a/arch/x86/include/uapi/asm/unistd.h b/arch/x86/include/uapi/asm/unistd.h index 30d7d04d72d6..be5e2e747f50 100644 --- a/arch/x86/include/uapi/asm/unistd.h +++ b/arch/x86/include/uapi/asm/unistd.h @@ -2,7 +2,14 @@ #ifndef _UAPI_ASM_X86_UNISTD_H #define _UAPI_ASM_X86_UNISTD_H -/* x32 syscall flag bit */ +/* + * x32 syscall flag bit. Some user programs expect syscall NR macros + * and __X32_SYSCALL_BIT to have type int, even though syscall numbers + * are, for practical purposes, unsigned long. + * + * Fortunately, expressions like (nr & ~__X32_SYSCALL_BIT) do the right + * thing regardless. + */ #define __X32_SYSCALL_BIT 0x40000000 #ifndef __KERNEL__ diff --git a/arch/x86/kernel/acpi/boot.c b/arch/x86/kernel/acpi/boot.c index 17b33ef604f3..ea019ba02942 100644 --- a/arch/x86/kernel/acpi/boot.c +++ b/arch/x86/kernel/acpi/boot.c @@ -1740,7 +1740,7 @@ int __acpi_acquire_global_lock(unsigned int *lock) new = (((old & ~0x3) + 2) + ((old >> 1) & 0x1)); val = cmpxchg(lock, old, new); } while (unlikely (val != old)); - return (new < 3) ? -1 : 0; + return ((new & 0x3) < 3) ? -1 : 0; } int __acpi_release_global_lock(unsigned int *lock) diff --git a/arch/x86/kernel/acpi/cstate.c b/arch/x86/kernel/acpi/cstate.c index a5e5484988fd..a5d650a15d55 100644 --- a/arch/x86/kernel/acpi/cstate.c +++ b/arch/x86/kernel/acpi/cstate.c @@ -146,7 +146,8 @@ int acpi_processor_ffh_cstate_probe(unsigned int cpu, /* Make sure we are running on right CPU */ - retval = work_on_cpu(cpu, acpi_processor_ffh_cstate_probe_cpu, cx); + retval = call_on_cpu(cpu, acpi_processor_ffh_cstate_probe_cpu, cx, + false); if (retval == 0) { /* Use the hint in CST */ percpu_entry->states[cx->index].eax = cx->address; diff --git a/arch/x86/kernel/amd_nb.c b/arch/x86/kernel/amd_nb.c index 8c26b696d893..8e283685f471 100644 --- a/arch/x86/kernel/amd_nb.c +++ b/arch/x86/kernel/amd_nb.c @@ -18,10 +18,13 @@ #define PCI_DEVICE_ID_AMD_17H_ROOT 0x1450 #define PCI_DEVICE_ID_AMD_17H_M10H_ROOT 0x15d0 #define PCI_DEVICE_ID_AMD_17H_M30H_ROOT 0x1480 +#define PCI_DEVICE_ID_AMD_17H_M60H_ROOT 0x1630 #define PCI_DEVICE_ID_AMD_17H_DF_F4 0x1464 #define PCI_DEVICE_ID_AMD_17H_M10H_DF_F4 0x15ec #define PCI_DEVICE_ID_AMD_17H_M30H_DF_F4 0x1494 +#define PCI_DEVICE_ID_AMD_17H_M60H_DF_F4 0x144c #define PCI_DEVICE_ID_AMD_17H_M70H_DF_F4 0x1444 +#define PCI_DEVICE_ID_AMD_19H_DF_F4 0x1654 /* Protect the PCI config register pairs used for SMN and DF indirect access. */ static DEFINE_MUTEX(smn_mutex); @@ -32,6 +35,7 @@ static const struct pci_device_id amd_root_ids[] = { { PCI_DEVICE(PCI_VENDOR_ID_AMD, PCI_DEVICE_ID_AMD_17H_ROOT) }, { PCI_DEVICE(PCI_VENDOR_ID_AMD, PCI_DEVICE_ID_AMD_17H_M10H_ROOT) }, { PCI_DEVICE(PCI_VENDOR_ID_AMD, PCI_DEVICE_ID_AMD_17H_M30H_ROOT) }, + { PCI_DEVICE(PCI_VENDOR_ID_AMD, PCI_DEVICE_ID_AMD_17H_M60H_ROOT) }, {} }; @@ -50,8 +54,10 @@ const struct pci_device_id amd_nb_misc_ids[] = { { PCI_DEVICE(PCI_VENDOR_ID_AMD, PCI_DEVICE_ID_AMD_17H_DF_F3) }, { PCI_DEVICE(PCI_VENDOR_ID_AMD, PCI_DEVICE_ID_AMD_17H_M10H_DF_F3) }, { PCI_DEVICE(PCI_VENDOR_ID_AMD, PCI_DEVICE_ID_AMD_17H_M30H_DF_F3) }, + { PCI_DEVICE(PCI_VENDOR_ID_AMD, PCI_DEVICE_ID_AMD_17H_M60H_DF_F3) }, { PCI_DEVICE(PCI_VENDOR_ID_AMD, PCI_DEVICE_ID_AMD_CNB17H_F3) }, { PCI_DEVICE(PCI_VENDOR_ID_AMD, PCI_DEVICE_ID_AMD_17H_M70H_DF_F3) }, + { PCI_DEVICE(PCI_VENDOR_ID_AMD, PCI_DEVICE_ID_AMD_19H_DF_F3) }, {} }; EXPORT_SYMBOL_GPL(amd_nb_misc_ids); @@ -65,7 +71,9 @@ static const struct pci_device_id amd_nb_link_ids[] = { { PCI_DEVICE(PCI_VENDOR_ID_AMD, PCI_DEVICE_ID_AMD_17H_DF_F4) }, { PCI_DEVICE(PCI_VENDOR_ID_AMD, PCI_DEVICE_ID_AMD_17H_M10H_DF_F4) }, { PCI_DEVICE(PCI_VENDOR_ID_AMD, PCI_DEVICE_ID_AMD_17H_M30H_DF_F4) }, + { PCI_DEVICE(PCI_VENDOR_ID_AMD, PCI_DEVICE_ID_AMD_17H_M60H_DF_F4) }, { PCI_DEVICE(PCI_VENDOR_ID_AMD, PCI_DEVICE_ID_AMD_17H_M70H_DF_F4) }, + { PCI_DEVICE(PCI_VENDOR_ID_AMD, PCI_DEVICE_ID_AMD_19H_DF_F4) }, { PCI_DEVICE(PCI_VENDOR_ID_AMD, PCI_DEVICE_ID_AMD_CNB17H_F4) }, {} }; diff --git a/arch/x86/kernel/apic/apic.c b/arch/x86/kernel/apic/apic.c index 142e7cfa8a3c..8dadfd73c5ad 100644 --- a/arch/x86/kernel/apic/apic.c +++ b/arch/x86/kernel/apic/apic.c @@ -195,7 +195,7 @@ static struct resource lapic_resource = { .flags = IORESOURCE_MEM | IORESOURCE_BUSY, }; -unsigned int lapic_timer_frequency = 0; +unsigned int lapic_timer_period = 0; static void apic_pm_activate(void); @@ -352,8 +352,6 @@ static void __setup_APIC_LVTT(unsigned int clocks, int oneshot, int irqen) * According to Intel, MFENCE can do the serialization here. */ asm volatile("mfence" : : : "memory"); - - printk_once(KERN_DEBUG "TSC deadline timer enabled\n"); return; } @@ -501,7 +499,7 @@ lapic_timer_set_periodic_oneshot(struct clock_event_device *evt, bool oneshot) if (evt->features & CLOCK_EVT_FEAT_DUMMY) return 0; - __setup_APIC_LVTT(lapic_timer_frequency, oneshot, 1); + __setup_APIC_LVTT(lapic_timer_period, oneshot, 1); return 0; } @@ -552,7 +550,7 @@ static DEFINE_PER_CPU(struct clock_event_device, lapic_events); #define DEADLINE_MODEL_MATCH_REV(model, rev) \ { X86_VENDOR_INTEL, 6, model, X86_FEATURE_ANY, (unsigned long)rev } -static u32 hsx_deadline_rev(void) +static __init u32 hsx_deadline_rev(void) { switch (boot_cpu_data.x86_stepping) { case 0x02: return 0x3a; /* EP */ @@ -562,7 +560,7 @@ static u32 hsx_deadline_rev(void) return ~0U; } -static u32 bdx_deadline_rev(void) +static __init u32 bdx_deadline_rev(void) { switch (boot_cpu_data.x86_stepping) { case 0x02: return 0x00000011; @@ -574,7 +572,7 @@ static u32 bdx_deadline_rev(void) return ~0U; } -static u32 skx_deadline_rev(void) +static __init u32 skx_deadline_rev(void) { switch (boot_cpu_data.x86_stepping) { case 0x03: return 0x01000136; @@ -587,7 +585,7 @@ static u32 skx_deadline_rev(void) return ~0U; } -static const struct x86_cpu_id deadline_match[] = { +static const struct x86_cpu_id deadline_match[] __initconst = { DEADLINE_MODEL_MATCH_FUNC( INTEL_FAM6_HASWELL_X, hsx_deadline_rev), DEADLINE_MODEL_MATCH_REV ( INTEL_FAM6_BROADWELL_X, 0x0b000020), DEADLINE_MODEL_MATCH_FUNC( INTEL_FAM6_BROADWELL_XEON_D, bdx_deadline_rev), @@ -609,18 +607,19 @@ static const struct x86_cpu_id deadline_match[] = { {}, }; -static void apic_check_deadline_errata(void) +static __init bool apic_validate_deadline_timer(void) { const struct x86_cpu_id *m; u32 rev; - if (!boot_cpu_has(X86_FEATURE_TSC_DEADLINE_TIMER) || - boot_cpu_has(X86_FEATURE_HYPERVISOR)) - return; + if (!boot_cpu_has(X86_FEATURE_TSC_DEADLINE_TIMER)) + return false; + if (boot_cpu_has(X86_FEATURE_HYPERVISOR)) + return true; m = x86_match_cpu(deadline_match); if (!m) - return; + return true; /* * Function pointers will have the MSB set due to address layout, @@ -632,11 +631,12 @@ static void apic_check_deadline_errata(void) rev = (u32)m->driver_data; if (boot_cpu_data.microcode >= rev) - return; + return true; setup_clear_cpu_cap(X86_FEATURE_TSC_DEADLINE_TIMER); pr_err(FW_BUG "TSC_DEADLINE disabled due to Errata; " "please update microcode to version: 0x%x (or later)\n", rev); + return false; } /* @@ -805,11 +805,11 @@ calibrate_by_pmtimer(long deltapm, long *delta, long *deltatsc) static int __init lapic_init_clockevent(void) { - if (!lapic_timer_frequency) + if (!lapic_timer_period) return -1; /* Calculate the scaled math multiplication factor */ - lapic_clockevent.mult = div_sc(lapic_timer_frequency/APIC_DIVISOR, + lapic_clockevent.mult = div_sc(lapic_timer_period/APIC_DIVISOR, TICK_NSEC, lapic_clockevent.shift); lapic_clockevent.max_delta_ns = clockevent_delta2ns(0x7FFFFFFF, &lapic_clockevent); @@ -840,7 +840,7 @@ static int __init calibrate_APIC_clock(void) */ if (!lapic_init_clockevent()) { apic_printk(APIC_VERBOSE, "lapic timer already calibrated %d\n", - lapic_timer_frequency); + lapic_timer_period); /* * Direct calibration methods must have an always running * local APIC timer, no need for broadcast timer. @@ -921,13 +921,13 @@ static int __init calibrate_APIC_clock(void) pm_referenced = !calibrate_by_pmtimer(lapic_cal_pm2 - lapic_cal_pm1, &delta, &deltatsc); - lapic_timer_frequency = (delta * APIC_DIVISOR) / LAPIC_CAL_LOOPS; + lapic_timer_period = (delta * APIC_DIVISOR) / LAPIC_CAL_LOOPS; lapic_init_clockevent(); apic_printk(APIC_VERBOSE, "..... delta %ld\n", delta); apic_printk(APIC_VERBOSE, "..... mult: %u\n", lapic_clockevent.mult); apic_printk(APIC_VERBOSE, "..... calibration result: %u\n", - lapic_timer_frequency); + lapic_timer_period); if (boot_cpu_has(X86_FEATURE_TSC)) { apic_printk(APIC_VERBOSE, "..... CPU clock speed is " @@ -938,13 +938,13 @@ static int __init calibrate_APIC_clock(void) apic_printk(APIC_VERBOSE, "..... host bus clock speed is " "%u.%04u MHz.\n", - lapic_timer_frequency / (1000000 / HZ), - lapic_timer_frequency % (1000000 / HZ)); + lapic_timer_period / (1000000 / HZ), + lapic_timer_period % (1000000 / HZ)); /* * Do a sanity check on the APIC calibration result */ - if (lapic_timer_frequency < (1000000 / HZ)) { + if (lapic_timer_period < (1000000 / HZ)) { local_irq_enable(); pr_warning("APIC frequency too slow, disabling apic timer\n"); return -1; @@ -2037,7 +2037,8 @@ void __init init_apic_mappings(void) { unsigned int new_apicid; - apic_check_deadline_errata(); + if (apic_validate_deadline_timer()) + pr_info("TSC deadline timer available\n"); if (x2apic_mode) { boot_cpu_physical_apicid = read_apic_id(); diff --git a/arch/x86/kernel/apic/io_apic.c b/arch/x86/kernel/apic/io_apic.c index e8c6466ef65e..70718977ce7a 100644 --- a/arch/x86/kernel/apic/io_apic.c +++ b/arch/x86/kernel/apic/io_apic.c @@ -1726,9 +1726,10 @@ static bool io_apic_level_ack_pending(struct mp_chip_data *data) static inline bool ioapic_irqd_mask(struct irq_data *data) { - /* If we are moving the irq we need to mask it */ + /* If we are moving the IRQ we need to mask it */ if (unlikely(irqd_is_setaffinity_pending(data))) { - mask_ioapic_irq(data); + if (!irqd_irq_masked(data)) + mask_ioapic_irq(data); return true; } return false; @@ -1765,7 +1766,9 @@ static inline void ioapic_irqd_unmask(struct irq_data *data, bool masked) */ if (!io_apic_level_ack_pending(data->chip_data)) irq_move_masked_irq(data); - unmask_ioapic_irq(data); + /* If the IRQ is masked in the core, leave it: */ + if (!irqd_irq_masked(data)) + unmask_ioapic_irq(data); } } #else diff --git a/arch/x86/kernel/apic/msi.c b/arch/x86/kernel/apic/msi.c index dad0dd759de2..e0c3c57ed7c0 100644 --- a/arch/x86/kernel/apic/msi.c +++ b/arch/x86/kernel/apic/msi.c @@ -23,10 +23,8 @@ static struct irq_domain *msi_default_domain; -static void irq_msi_compose_msg(struct irq_data *data, struct msi_msg *msg) +static void __irq_msi_compose_msg(struct irq_cfg *cfg, struct msi_msg *msg) { - struct irq_cfg *cfg = irqd_cfg(data); - msg->address_hi = MSI_ADDR_BASE_HI; if (x2apic_enabled()) @@ -47,6 +45,127 @@ static void irq_msi_compose_msg(struct irq_data *data, struct msi_msg *msg) MSI_DATA_VECTOR(cfg->vector); } +static void irq_msi_compose_msg(struct irq_data *data, struct msi_msg *msg) +{ + __irq_msi_compose_msg(irqd_cfg(data), msg); +} + +static void irq_msi_update_msg(struct irq_data *irqd, struct irq_cfg *cfg) +{ + struct msi_msg msg[2] = { [1] = { }, }; + + __irq_msi_compose_msg(cfg, msg); + irq_data_get_irq_chip(irqd)->irq_write_msi_msg(irqd, msg); +} + +static int +msi_set_affinity(struct irq_data *irqd, const struct cpumask *mask, bool force) +{ + struct irq_cfg old_cfg, *cfg = irqd_cfg(irqd); + struct irq_data *parent = irqd->parent_data; + unsigned int cpu; + int ret; + + /* Save the current configuration */ + cpu = cpumask_first(irq_data_get_effective_affinity_mask(irqd)); + old_cfg = *cfg; + + /* Allocate a new target vector */ + ret = parent->chip->irq_set_affinity(parent, mask, force); + if (ret < 0 || ret == IRQ_SET_MASK_OK_DONE) + return ret; + + /* + * For non-maskable and non-remapped MSI interrupts the migration + * to a different destination CPU and a different vector has to be + * done careful to handle the possible stray interrupt which can be + * caused by the non-atomic update of the address/data pair. + * + * Direct update is possible when: + * - The MSI is maskable (remapped MSI does not use this code path)). + * The quirk bit is not set in this case. + * - The new vector is the same as the old vector + * - The old vector is MANAGED_IRQ_SHUTDOWN_VECTOR (interrupt starts up) + * - The new destination CPU is the same as the old destination CPU + */ + if (!irqd_msi_nomask_quirk(irqd) || + cfg->vector == old_cfg.vector || + old_cfg.vector == MANAGED_IRQ_SHUTDOWN_VECTOR || + cfg->dest_apicid == old_cfg.dest_apicid) { + irq_msi_update_msg(irqd, cfg); + return ret; + } + + /* + * Paranoia: Validate that the interrupt target is the local + * CPU. + */ + if (WARN_ON_ONCE(cpu != smp_processor_id())) { + irq_msi_update_msg(irqd, cfg); + return ret; + } + + /* + * Redirect the interrupt to the new vector on the current CPU + * first. This might cause a spurious interrupt on this vector if + * the device raises an interrupt right between this update and the + * update to the final destination CPU. + * + * If the vector is in use then the installed device handler will + * denote it as spurious which is no harm as this is a rare event + * and interrupt handlers have to cope with spurious interrupts + * anyway. If the vector is unused, then it is marked so it won't + * trigger the 'No irq handler for vector' warning in do_IRQ(). + * + * This requires to hold vector lock to prevent concurrent updates to + * the affected vector. + */ + lock_vector_lock(); + + /* + * Mark the new target vector on the local CPU if it is currently + * unused. Reuse the VECTOR_RETRIGGERED state which is also used in + * the CPU hotplug path for a similar purpose. This cannot be + * undone here as the current CPU has interrupts disabled and + * cannot handle the interrupt before the whole set_affinity() + * section is done. In the CPU unplug case, the current CPU is + * about to vanish and will not handle any interrupts anymore. The + * vector is cleaned up when the CPU comes online again. + */ + if (IS_ERR_OR_NULL(this_cpu_read(vector_irq[cfg->vector]))) + this_cpu_write(vector_irq[cfg->vector], VECTOR_RETRIGGERED); + + /* Redirect it to the new vector on the local CPU temporarily */ + old_cfg.vector = cfg->vector; + irq_msi_update_msg(irqd, &old_cfg); + + /* Now transition it to the target CPU */ + irq_msi_update_msg(irqd, cfg); + + /* + * All interrupts after this point are now targeted at the new + * vector/CPU. + * + * Drop vector lock before testing whether the temporary assignment + * to the local CPU was hit by an interrupt raised in the device, + * because the retrigger function acquires vector lock again. + */ + unlock_vector_lock(); + + /* + * Check whether the transition raced with a device interrupt and + * is pending in the local APICs IRR. It is safe to do this outside + * of vector lock as the irq_desc::lock of this interrupt is still + * held and interrupts are disabled: The check is not accessing the + * underlying vector store. It's just checking the local APIC's + * IRR. + */ + if (lapic_vector_set_in_irr(cfg->vector)) + irq_data_get_irq_chip(irqd)->irq_retrigger(irqd); + + return ret; +} + /* * IRQ Chip for MSI PCI/PCI-X/PCI-Express Devices, * which implement the MSI or MSI-X Capability Structure. @@ -58,6 +177,7 @@ static struct irq_chip pci_msi_controller = { .irq_ack = irq_chip_ack_parent, .irq_retrigger = irq_chip_retrigger_hierarchy, .irq_compose_msi_msg = irq_msi_compose_msg, + .irq_set_affinity = msi_set_affinity, .flags = IRQCHIP_SKIP_SET_WAKE, }; @@ -146,6 +266,8 @@ void __init arch_init_msi_domain(struct irq_domain *parent) } if (!msi_default_domain) pr_warn("failed to initialize irqdomain for MSI/MSI-x.\n"); + else + msi_default_domain->flags |= IRQ_DOMAIN_MSI_NOMASK_QUIRK; } #ifdef CONFIG_IRQ_REMAP diff --git a/arch/x86/kernel/apic/vector.c b/arch/x86/kernel/apic/vector.c index 2c5676b0a6e7..259d17d08983 100644 --- a/arch/x86/kernel/apic/vector.c +++ b/arch/x86/kernel/apic/vector.c @@ -446,12 +446,10 @@ static int x86_vector_activate(struct irq_domain *dom, struct irq_data *irqd, trace_vector_activate(irqd->irq, apicd->is_managed, apicd->can_reserve, reserve); - /* Nothing to do for fixed assigned vectors */ - if (!apicd->can_reserve && !apicd->is_managed) - return 0; - raw_spin_lock_irqsave(&vector_lock, flags); - if (reserve || irqd_is_managed_and_shutdown(irqd)) + if (!apicd->can_reserve && !apicd->is_managed) + assign_irq_vector_any_locked(irqd); + else if (reserve || irqd_is_managed_and_shutdown(irqd)) vector_assign_managed_shutdown(irqd); else if (apicd->is_managed) ret = activate_managed(irqd); @@ -557,6 +555,16 @@ static int x86_vector_alloc_irqs(struct irq_domain *domain, unsigned int virq, irqd->hwirq = virq + i; irqd_set_single_target(irqd); /* + * Prevent that any of these interrupts is invoked in + * non interrupt context via e.g. generic_handle_irq() + * as that can corrupt the affinity move state. + */ + irqd_set_handle_enforce_irqctx(irqd); + + /* Don't invoke affinity setter on deactivated interrupts */ + irqd_set_affinity_on_activate(irqd); + + /* * Legacy vectors are already assigned when the IOAPIC * takes them over. They stay on the same vector. This is * required for check_timer() to work correctly as it might @@ -769,20 +777,10 @@ void lapic_offline(void) static int apic_set_affinity(struct irq_data *irqd, const struct cpumask *dest, bool force) { - struct apic_chip_data *apicd = apic_chip_data(irqd); int err; - /* - * Core code can call here for inactive interrupts. For inactive - * interrupts which use managed or reservation mode there is no - * point in going through the vector assignment right now as the - * activation will assign a vector which fits the destination - * cpumask. Let the core code store the destination mask and be - * done with it. - */ - if (!irqd_is_activated(irqd) && - (apicd->is_managed || apicd->can_reserve)) - return IRQ_SET_MASK_OK; + if (WARN_ON_ONCE(!irqd_is_activated(irqd))) + return -EIO; raw_spin_lock(&vector_lock); cpumask_and(vector_searchmask, dest, cpu_online_mask); diff --git a/arch/x86/kernel/asm-offsets_64.c b/arch/x86/kernel/asm-offsets_64.c index d3d075226c0a..70e97727a26a 100644 --- a/arch/x86/kernel/asm-offsets_64.c +++ b/arch/x86/kernel/asm-offsets_64.c @@ -6,13 +6,28 @@ #include <asm/ia32.h> #define __SYSCALL_64(nr, sym, qual) [nr] = 1, +#define __SYSCALL_X32(nr, sym, qual) static char syscalls_64[] = { #include <asm/syscalls_64.h> }; +#undef __SYSCALL_64 +#undef __SYSCALL_X32 + +#ifdef CONFIG_X86_X32_ABI +#define __SYSCALL_64(nr, sym, qual) +#define __SYSCALL_X32(nr, sym, qual) [nr] = 1, +static char syscalls_x32[] = { +#include <asm/syscalls_64.h> +}; +#undef __SYSCALL_64 +#undef __SYSCALL_X32 +#endif + #define __SYSCALL_I386(nr, sym, qual) [nr] = 1, static char syscalls_ia32[] = { #include <asm/syscalls_32.h> }; +#undef __SYSCALL_I386 #if defined(CONFIG_KVM_GUEST) && defined(CONFIG_PARAVIRT_SPINLOCKS) #include <asm/kvm_para.h> @@ -80,6 +95,11 @@ int main(void) DEFINE(__NR_syscall_max, sizeof(syscalls_64) - 1); DEFINE(NR_syscalls, sizeof(syscalls_64)); +#ifdef CONFIG_X86_X32_ABI + DEFINE(__NR_syscall_x32_max, sizeof(syscalls_x32) - 1); + DEFINE(X32_NR_syscalls, sizeof(syscalls_x32)); +#endif + DEFINE(__NR_syscall_compat_max, sizeof(syscalls_ia32) - 1); DEFINE(IA32_NR_syscalls, sizeof(syscalls_ia32)); diff --git a/arch/x86/kernel/cpu/amd.c b/arch/x86/kernel/cpu/amd.c index 68c363c341bf..fe3649f725dc 100644 --- a/arch/x86/kernel/cpu/amd.c +++ b/arch/x86/kernel/cpu/amd.c @@ -27,6 +27,7 @@ static const int amd_erratum_383[]; static const int amd_erratum_400[]; +static const int amd_erratum_1054[]; static bool cpu_has_amd_erratum(struct cpuinfo_x86 *cpu, const int *erratum); /* @@ -614,9 +615,9 @@ static void early_detect_mem_encrypt(struct cpuinfo_x86 *c) return; clear_all: - clear_cpu_cap(c, X86_FEATURE_SME); + setup_clear_cpu_cap(X86_FEATURE_SME); clear_sev: - clear_cpu_cap(c, X86_FEATURE_SEV); + setup_clear_cpu_cap(X86_FEATURE_SEV); } } @@ -988,6 +989,15 @@ static void init_amd(struct cpuinfo_x86 *c) /* AMD CPUs don't reset SS attributes on SYSRET, Xen does. */ if (!cpu_has(c, X86_FEATURE_XENPV)) set_cpu_bug(c, X86_BUG_SYSRET_SS_ATTRS); + + /* + * Turn on the Instructions Retired free counter on machines not + * susceptible to erratum #1054 "Instructions Retired Performance + * Counter May Be Inaccurate". + */ + if (cpu_has(c, X86_FEATURE_IRPERF) && + !cpu_has_amd_erratum(c, amd_erratum_1054)) + msr_set_bit(MSR_K7_HWCR, MSR_K7_HWCR_IRPERF_EN_BIT); } #ifdef CONFIG_X86_32 @@ -1115,6 +1125,9 @@ static const int amd_erratum_400[] = static const int amd_erratum_383[] = AMD_OSVW_ERRATUM(3, AMD_MODEL_RANGE(0x10, 0, 0, 0xff, 0xf)); +/* #1054: Instructions Retired Performance Counter May Be Inaccurate */ +static const int amd_erratum_1054[] = + AMD_LEGACY_ERRATUM(AMD_MODEL_RANGE(0x17, 0, 0, 0x2f, 0xf)); static bool cpu_has_amd_erratum(struct cpuinfo_x86 *cpu, const int *erratum) { diff --git a/arch/x86/kernel/cpu/bugs.c b/arch/x86/kernel/cpu/bugs.c index 08bbc67adf13..a277fa17c4ee 100644 --- a/arch/x86/kernel/cpu/bugs.c +++ b/arch/x86/kernel/cpu/bugs.c @@ -41,6 +41,7 @@ static void __init l1tf_select_mitigation(void); static void __init mds_select_mitigation(void); static void __init mds_print_mitigation(void); static void __init taa_select_mitigation(void); +static void __init srbds_select_mitigation(void); /* The base value of the SPEC_CTRL MSR that always has to be preserved. */ u64 x86_spec_ctrl_base; @@ -108,6 +109,7 @@ void __init check_bugs(void) l1tf_select_mitigation(); mds_select_mitigation(); taa_select_mitigation(); + srbds_select_mitigation(); /* * As MDS and TAA mitigations are inter-related, print MDS @@ -391,6 +393,97 @@ static int __init tsx_async_abort_parse_cmdline(char *str) early_param("tsx_async_abort", tsx_async_abort_parse_cmdline); #undef pr_fmt +#define pr_fmt(fmt) "SRBDS: " fmt + +enum srbds_mitigations { + SRBDS_MITIGATION_OFF, + SRBDS_MITIGATION_UCODE_NEEDED, + SRBDS_MITIGATION_FULL, + SRBDS_MITIGATION_TSX_OFF, + SRBDS_MITIGATION_HYPERVISOR, +}; + +static enum srbds_mitigations srbds_mitigation __ro_after_init = SRBDS_MITIGATION_FULL; + +static const char * const srbds_strings[] = { + [SRBDS_MITIGATION_OFF] = "Vulnerable", + [SRBDS_MITIGATION_UCODE_NEEDED] = "Vulnerable: No microcode", + [SRBDS_MITIGATION_FULL] = "Mitigation: Microcode", + [SRBDS_MITIGATION_TSX_OFF] = "Mitigation: TSX disabled", + [SRBDS_MITIGATION_HYPERVISOR] = "Unknown: Dependent on hypervisor status", +}; + +static bool srbds_off; + +void update_srbds_msr(void) +{ + u64 mcu_ctrl; + + if (!boot_cpu_has_bug(X86_BUG_SRBDS)) + return; + + if (boot_cpu_has(X86_FEATURE_HYPERVISOR)) + return; + + if (srbds_mitigation == SRBDS_MITIGATION_UCODE_NEEDED) + return; + + rdmsrl(MSR_IA32_MCU_OPT_CTRL, mcu_ctrl); + + switch (srbds_mitigation) { + case SRBDS_MITIGATION_OFF: + case SRBDS_MITIGATION_TSX_OFF: + mcu_ctrl |= RNGDS_MITG_DIS; + break; + case SRBDS_MITIGATION_FULL: + mcu_ctrl &= ~RNGDS_MITG_DIS; + break; + default: + break; + } + + wrmsrl(MSR_IA32_MCU_OPT_CTRL, mcu_ctrl); +} + +static void __init srbds_select_mitigation(void) +{ + u64 ia32_cap; + + if (!boot_cpu_has_bug(X86_BUG_SRBDS)) + return; + + /* + * Check to see if this is one of the MDS_NO systems supporting + * TSX that are only exposed to SRBDS when TSX is enabled. + */ + ia32_cap = x86_read_arch_cap_msr(); + if ((ia32_cap & ARCH_CAP_MDS_NO) && !boot_cpu_has(X86_FEATURE_RTM)) + srbds_mitigation = SRBDS_MITIGATION_TSX_OFF; + else if (boot_cpu_has(X86_FEATURE_HYPERVISOR)) + srbds_mitigation = SRBDS_MITIGATION_HYPERVISOR; + else if (!boot_cpu_has(X86_FEATURE_SRBDS_CTRL)) + srbds_mitigation = SRBDS_MITIGATION_UCODE_NEEDED; + else if (cpu_mitigations_off() || srbds_off) + srbds_mitigation = SRBDS_MITIGATION_OFF; + + update_srbds_msr(); + pr_info("%s\n", srbds_strings[srbds_mitigation]); +} + +static int __init srbds_parse_cmdline(char *str) +{ + if (!str) + return -EINVAL; + + if (!boot_cpu_has_bug(X86_BUG_SRBDS)) + return 0; + + srbds_off = !strcmp(str, "off"); + return 0; +} +early_param("srbds", srbds_parse_cmdline); + +#undef pr_fmt #define pr_fmt(fmt) "Spectre V1 : " fmt enum spectre_v1_mitigation { @@ -488,7 +581,9 @@ early_param("nospectre_v1", nospectre_v1_cmdline); static enum spectre_v2_mitigation spectre_v2_enabled __ro_after_init = SPECTRE_V2_NONE; -static enum spectre_v2_user_mitigation spectre_v2_user __ro_after_init = +static enum spectre_v2_user_mitigation spectre_v2_user_stibp __ro_after_init = + SPECTRE_V2_USER_NONE; +static enum spectre_v2_user_mitigation spectre_v2_user_ibpb __ro_after_init = SPECTRE_V2_USER_NONE; #ifdef CONFIG_RETPOLINE @@ -634,15 +729,6 @@ spectre_v2_user_select_mitigation(enum spectre_v2_mitigation_cmd v2_cmd) break; } - /* - * At this point, an STIBP mode other than "off" has been set. - * If STIBP support is not being forced, check if STIBP always-on - * is preferred. - */ - if (mode != SPECTRE_V2_USER_STRICT && - boot_cpu_has(X86_FEATURE_AMD_STIBP_ALWAYS_ON)) - mode = SPECTRE_V2_USER_STRICT_PREFERRED; - /* Initialize Indirect Branch Prediction Barrier */ if (boot_cpu_has(X86_FEATURE_IBPB)) { setup_force_cpu_cap(X86_FEATURE_USE_IBPB); @@ -665,23 +751,36 @@ spectre_v2_user_select_mitigation(enum spectre_v2_mitigation_cmd v2_cmd) pr_info("mitigation: Enabling %s Indirect Branch Prediction Barrier\n", static_key_enabled(&switch_mm_always_ibpb) ? "always-on" : "conditional"); + + spectre_v2_user_ibpb = mode; } - /* If enhanced IBRS is enabled no STIBP required */ - if (spectre_v2_enabled == SPECTRE_V2_IBRS_ENHANCED) + /* + * If enhanced IBRS is enabled or SMT impossible, STIBP is not + * required. + */ + if (!smt_possible || spectre_v2_enabled == SPECTRE_V2_IBRS_ENHANCED) return; /* - * If SMT is not possible or STIBP is not available clear the STIBP - * mode. + * At this point, an STIBP mode other than "off" has been set. + * If STIBP support is not being forced, check if STIBP always-on + * is preferred. + */ + if (mode != SPECTRE_V2_USER_STRICT && + boot_cpu_has(X86_FEATURE_AMD_STIBP_ALWAYS_ON)) + mode = SPECTRE_V2_USER_STRICT_PREFERRED; + + /* + * If STIBP is not available, clear the STIBP mode. */ - if (!smt_possible || !boot_cpu_has(X86_FEATURE_STIBP)) + if (!boot_cpu_has(X86_FEATURE_STIBP)) mode = SPECTRE_V2_USER_NONE; + + spectre_v2_user_stibp = mode; + set_mode: - spectre_v2_user = mode; - /* Only print the STIBP mode when SMT possible */ - if (smt_possible) - pr_info("%s\n", spectre_v2_user_strings[mode]); + pr_info("%s\n", spectre_v2_user_strings[mode]); } static const char * const spectre_v2_strings[] = { @@ -914,7 +1013,7 @@ void cpu_bugs_smt_update(void) { mutex_lock(&spec_ctrl_mutex); - switch (spectre_v2_user) { + switch (spectre_v2_user_stibp) { case SPECTRE_V2_USER_NONE: break; case SPECTRE_V2_USER_STRICT: @@ -1157,14 +1256,19 @@ static int ib_prctl_set(struct task_struct *task, unsigned long ctrl) { switch (ctrl) { case PR_SPEC_ENABLE: - if (spectre_v2_user == SPECTRE_V2_USER_NONE) + if (spectre_v2_user_ibpb == SPECTRE_V2_USER_NONE && + spectre_v2_user_stibp == SPECTRE_V2_USER_NONE) return 0; /* * Indirect branch speculation is always disabled in strict - * mode. + * mode. It can neither be enabled if it was force-disabled + * by a previous prctl call. + */ - if (spectre_v2_user == SPECTRE_V2_USER_STRICT || - spectre_v2_user == SPECTRE_V2_USER_STRICT_PREFERRED) + if (spectre_v2_user_ibpb == SPECTRE_V2_USER_STRICT || + spectre_v2_user_stibp == SPECTRE_V2_USER_STRICT || + spectre_v2_user_stibp == SPECTRE_V2_USER_STRICT_PREFERRED || + task_spec_ib_force_disable(task)) return -EPERM; task_clear_spec_ib_disable(task); task_update_spec_tif(task); @@ -1175,10 +1279,12 @@ static int ib_prctl_set(struct task_struct *task, unsigned long ctrl) * Indirect branch speculation is always allowed when * mitigation is force disabled. */ - if (spectre_v2_user == SPECTRE_V2_USER_NONE) + if (spectre_v2_user_ibpb == SPECTRE_V2_USER_NONE && + spectre_v2_user_stibp == SPECTRE_V2_USER_NONE) return -EPERM; - if (spectre_v2_user == SPECTRE_V2_USER_STRICT || - spectre_v2_user == SPECTRE_V2_USER_STRICT_PREFERRED) + if (spectre_v2_user_ibpb == SPECTRE_V2_USER_STRICT || + spectre_v2_user_stibp == SPECTRE_V2_USER_STRICT || + spectre_v2_user_stibp == SPECTRE_V2_USER_STRICT_PREFERRED) return 0; task_set_spec_ib_disable(task); if (ctrl == PR_SPEC_FORCE_DISABLE) @@ -1209,7 +1315,8 @@ void arch_seccomp_spec_mitigate(struct task_struct *task) { if (ssb_mode == SPEC_STORE_BYPASS_SECCOMP) ssb_prctl_set(task, PR_SPEC_FORCE_DISABLE); - if (spectre_v2_user == SPECTRE_V2_USER_SECCOMP) + if (spectre_v2_user_ibpb == SPECTRE_V2_USER_SECCOMP || + spectre_v2_user_stibp == SPECTRE_V2_USER_SECCOMP) ib_prctl_set(task, PR_SPEC_FORCE_DISABLE); } #endif @@ -1240,22 +1347,24 @@ static int ib_prctl_get(struct task_struct *task) if (!boot_cpu_has_bug(X86_BUG_SPECTRE_V2)) return PR_SPEC_NOT_AFFECTED; - switch (spectre_v2_user) { - case SPECTRE_V2_USER_NONE: + if (spectre_v2_user_ibpb == SPECTRE_V2_USER_NONE && + spectre_v2_user_stibp == SPECTRE_V2_USER_NONE) return PR_SPEC_ENABLE; - case SPECTRE_V2_USER_PRCTL: - case SPECTRE_V2_USER_SECCOMP: + else if (spectre_v2_user_ibpb == SPECTRE_V2_USER_STRICT || + spectre_v2_user_stibp == SPECTRE_V2_USER_STRICT || + spectre_v2_user_stibp == SPECTRE_V2_USER_STRICT_PREFERRED) + return PR_SPEC_DISABLE; + else if (spectre_v2_user_ibpb == SPECTRE_V2_USER_PRCTL || + spectre_v2_user_ibpb == SPECTRE_V2_USER_SECCOMP || + spectre_v2_user_stibp == SPECTRE_V2_USER_PRCTL || + spectre_v2_user_stibp == SPECTRE_V2_USER_SECCOMP) { if (task_spec_ib_force_disable(task)) return PR_SPEC_PRCTL | PR_SPEC_FORCE_DISABLE; if (task_spec_ib_disable(task)) return PR_SPEC_PRCTL | PR_SPEC_DISABLE; return PR_SPEC_PRCTL | PR_SPEC_ENABLE; - case SPECTRE_V2_USER_STRICT: - case SPECTRE_V2_USER_STRICT_PREFERRED: - return PR_SPEC_DISABLE; - default: + } else return PR_SPEC_NOT_AFFECTED; - } } int arch_prctl_spec_ctrl_get(struct task_struct *task, unsigned long which) @@ -1494,7 +1603,7 @@ static char *stibp_state(void) if (spectre_v2_enabled == SPECTRE_V2_IBRS_ENHANCED) return ""; - switch (spectre_v2_user) { + switch (spectre_v2_user_stibp) { case SPECTRE_V2_USER_NONE: return ", STIBP: disabled"; case SPECTRE_V2_USER_STRICT: @@ -1521,6 +1630,11 @@ static char *ibpb_state(void) return ""; } +static ssize_t srbds_show_state(char *buf) +{ + return sprintf(buf, "%s\n", srbds_strings[srbds_mitigation]); +} + static ssize_t cpu_show_common(struct device *dev, struct device_attribute *attr, char *buf, unsigned int bug) { @@ -1565,6 +1679,9 @@ static ssize_t cpu_show_common(struct device *dev, struct device_attribute *attr case X86_BUG_ITLB_MULTIHIT: return itlb_multihit_show_state(buf); + case X86_BUG_SRBDS: + return srbds_show_state(buf); + default: break; } @@ -1611,4 +1728,9 @@ ssize_t cpu_show_itlb_multihit(struct device *dev, struct device_attribute *attr { return cpu_show_common(dev, attr, buf, X86_BUG_ITLB_MULTIHIT); } + +ssize_t cpu_show_srbds(struct device *dev, struct device_attribute *attr, char *buf) +{ + return cpu_show_common(dev, attr, buf, X86_BUG_SRBDS); +} #endif diff --git a/arch/x86/kernel/cpu/common.c b/arch/x86/kernel/cpu/common.c index f6bc5b879e51..1c44715818e6 100644 --- a/arch/x86/kernel/cpu/common.c +++ b/arch/x86/kernel/cpu/common.c @@ -366,6 +366,9 @@ out: cr4_clear_bits(X86_CR4_UMIP); } +/* These bits should not change their value after CPU init is finished. */ +static const unsigned long cr4_pinned_mask = + X86_CR4_SMEP | X86_CR4_SMAP | X86_CR4_UMIP | X86_CR4_FSGSBASE; static DEFINE_STATIC_KEY_FALSE_RO(cr_pinning); static unsigned long cr4_pinned_bits __ro_after_init; @@ -390,20 +393,20 @@ EXPORT_SYMBOL(native_write_cr0); void native_write_cr4(unsigned long val) { - unsigned long bits_missing = 0; + unsigned long bits_changed = 0; set_register: asm volatile("mov %0,%%cr4": "+r" (val), "+m" (cr4_pinned_bits)); if (static_branch_likely(&cr_pinning)) { - if (unlikely((val & cr4_pinned_bits) != cr4_pinned_bits)) { - bits_missing = ~val & cr4_pinned_bits; - val |= bits_missing; + if (unlikely((val & cr4_pinned_mask) != cr4_pinned_bits)) { + bits_changed = (val & cr4_pinned_mask) ^ cr4_pinned_bits; + val = (val & ~cr4_pinned_mask) | cr4_pinned_bits; goto set_register; } - /* Warn after we've set the missing bits. */ - WARN_ONCE(bits_missing, "CR4 bits went missing: %lx!?\n", - bits_missing); + /* Warn after we've corrected the changed bits. */ + WARN_ONCE(bits_changed, "pinned CR4 bits changed: 0x%lx!?\n", + bits_changed); } } EXPORT_SYMBOL(native_write_cr4); @@ -415,7 +418,7 @@ void cr4_init(void) if (boot_cpu_has(X86_FEATURE_PCID)) cr4 |= X86_CR4_PCIDE; if (static_branch_likely(&cr_pinning)) - cr4 |= cr4_pinned_bits; + cr4 = (cr4 & ~cr4_pinned_mask) | cr4_pinned_bits; __write_cr4(cr4); @@ -430,10 +433,7 @@ void cr4_init(void) */ static void __init setup_cr_pinning(void) { - unsigned long mask; - - mask = (X86_CR4_SMEP | X86_CR4_SMAP | X86_CR4_UMIP); - cr4_pinned_bits = this_cpu_read(cpu_tlbstate.cr4) & mask; + cr4_pinned_bits = this_cpu_read(cpu_tlbstate.cr4) & cr4_pinned_mask; static_key_enable(&cr_pinning.key); } @@ -464,7 +464,7 @@ static __always_inline void setup_pku(struct cpuinfo_x86 *c) * cpuid bit to be set. We need to ensure that we * update that bit in this CPU's "cpu_info". */ - get_cpu_cap(c); + set_cpu_cap(c, X86_FEATURE_OSPKE); } #ifdef CONFIG_X86_INTEL_MEMORY_PROTECTION_KEYS @@ -1081,9 +1081,30 @@ static const __initconst struct x86_cpu_id cpu_vuln_whitelist[] = { {} }; -static bool __init cpu_matches(unsigned long which) +#define VULNBL_INTEL_STEPPINGS(model, steppings, issues) \ + X86_MATCH_VENDOR_FAM_MODEL_STEPPINGS_FEATURE(INTEL, 6, \ + INTEL_FAM6_##model, steppings, \ + X86_FEATURE_ANY, issues) + +#define SRBDS BIT(0) + +static const struct x86_cpu_id cpu_vuln_blacklist[] __initconst = { + VULNBL_INTEL_STEPPINGS(IVYBRIDGE, X86_STEPPING_ANY, SRBDS), + VULNBL_INTEL_STEPPINGS(HASWELL_CORE, X86_STEPPING_ANY, SRBDS), + VULNBL_INTEL_STEPPINGS(HASWELL_ULT, X86_STEPPING_ANY, SRBDS), + VULNBL_INTEL_STEPPINGS(HASWELL_GT3E, X86_STEPPING_ANY, SRBDS), + VULNBL_INTEL_STEPPINGS(BROADWELL_GT3E, X86_STEPPING_ANY, SRBDS), + VULNBL_INTEL_STEPPINGS(BROADWELL_CORE, X86_STEPPING_ANY, SRBDS), + VULNBL_INTEL_STEPPINGS(SKYLAKE_MOBILE, X86_STEPPING_ANY, SRBDS), + VULNBL_INTEL_STEPPINGS(SKYLAKE_DESKTOP, X86_STEPPING_ANY, SRBDS), + VULNBL_INTEL_STEPPINGS(KABYLAKE_MOBILE, X86_STEPPINGS(0x0, 0xC), SRBDS), + VULNBL_INTEL_STEPPINGS(KABYLAKE_DESKTOP,X86_STEPPINGS(0x0, 0xD), SRBDS), + {} +}; + +static bool __init cpu_matches(const struct x86_cpu_id *table, unsigned long which) { - const struct x86_cpu_id *m = x86_match_cpu(cpu_vuln_whitelist); + const struct x86_cpu_id *m = x86_match_cpu(table); return m && !!(m->driver_data & which); } @@ -1103,29 +1124,32 @@ static void __init cpu_set_bug_bits(struct cpuinfo_x86 *c) u64 ia32_cap = x86_read_arch_cap_msr(); /* Set ITLB_MULTIHIT bug if cpu is not in the whitelist and not mitigated */ - if (!cpu_matches(NO_ITLB_MULTIHIT) && !(ia32_cap & ARCH_CAP_PSCHANGE_MC_NO)) + if (!cpu_matches(cpu_vuln_whitelist, NO_ITLB_MULTIHIT) && + !(ia32_cap & ARCH_CAP_PSCHANGE_MC_NO)) setup_force_cpu_bug(X86_BUG_ITLB_MULTIHIT); - if (cpu_matches(NO_SPECULATION)) + if (cpu_matches(cpu_vuln_whitelist, NO_SPECULATION)) return; setup_force_cpu_bug(X86_BUG_SPECTRE_V1); setup_force_cpu_bug(X86_BUG_SPECTRE_V2); - if (!cpu_matches(NO_SSB) && !(ia32_cap & ARCH_CAP_SSB_NO) && + if (!cpu_matches(cpu_vuln_whitelist, NO_SSB) && + !(ia32_cap & ARCH_CAP_SSB_NO) && !cpu_has(c, X86_FEATURE_AMD_SSB_NO)) setup_force_cpu_bug(X86_BUG_SPEC_STORE_BYPASS); if (ia32_cap & ARCH_CAP_IBRS_ALL) setup_force_cpu_cap(X86_FEATURE_IBRS_ENHANCED); - if (!cpu_matches(NO_MDS) && !(ia32_cap & ARCH_CAP_MDS_NO)) { + if (!cpu_matches(cpu_vuln_whitelist, NO_MDS) && + !(ia32_cap & ARCH_CAP_MDS_NO)) { setup_force_cpu_bug(X86_BUG_MDS); - if (cpu_matches(MSBDS_ONLY)) + if (cpu_matches(cpu_vuln_whitelist, MSBDS_ONLY)) setup_force_cpu_bug(X86_BUG_MSBDS_ONLY); } - if (!cpu_matches(NO_SWAPGS)) + if (!cpu_matches(cpu_vuln_whitelist, NO_SWAPGS)) setup_force_cpu_bug(X86_BUG_SWAPGS); /* @@ -1143,7 +1167,16 @@ static void __init cpu_set_bug_bits(struct cpuinfo_x86 *c) (ia32_cap & ARCH_CAP_TSX_CTRL_MSR))) setup_force_cpu_bug(X86_BUG_TAA); - if (cpu_matches(NO_MELTDOWN)) + /* + * SRBDS affects CPUs which support RDRAND or RDSEED and are listed + * in the vulnerability blacklist. + */ + if ((cpu_has(c, X86_FEATURE_RDRAND) || + cpu_has(c, X86_FEATURE_RDSEED)) && + cpu_matches(cpu_vuln_blacklist, SRBDS)) + setup_force_cpu_bug(X86_BUG_SRBDS); + + if (cpu_matches(cpu_vuln_whitelist, NO_MELTDOWN)) return; /* Rogue Data Cache Load? No! */ @@ -1152,7 +1185,7 @@ static void __init cpu_set_bug_bits(struct cpuinfo_x86 *c) setup_force_cpu_bug(X86_BUG_CPU_MELTDOWN); - if (cpu_matches(NO_L1TF)) + if (cpu_matches(cpu_vuln_whitelist, NO_L1TF)) return; setup_force_cpu_bug(X86_BUG_L1TF); @@ -1589,6 +1622,7 @@ void identify_secondary_cpu(struct cpuinfo_x86 *c) mtrr_ap_init(); validate_apic_and_package_id(c); x86_spec_ctrl_setup_ap(); + update_srbds_msr(); } static __init int setup_noclflush(char *arg) diff --git a/arch/x86/kernel/cpu/cpu.h b/arch/x86/kernel/cpu/cpu.h index 38ab6e115eac..9d033693519a 100644 --- a/arch/x86/kernel/cpu/cpu.h +++ b/arch/x86/kernel/cpu/cpu.h @@ -77,6 +77,7 @@ extern void detect_ht(struct cpuinfo_x86 *c); unsigned int aperfmperf_get_khz(int cpu); extern void x86_spec_ctrl_setup_ap(void); +extern void update_srbds_msr(void); extern u64 x86_read_arch_cap_msr(void); diff --git a/arch/x86/kernel/cpu/intel.c b/arch/x86/kernel/cpu/intel.c index 92b107ab283f..c979a056a46f 100644 --- a/arch/x86/kernel/cpu/intel.c +++ b/arch/x86/kernel/cpu/intel.c @@ -66,6 +66,32 @@ void check_mpx_erratum(struct cpuinfo_x86 *c) } } +/* + * Processors which have self-snooping capability can handle conflicting + * memory type across CPUs by snooping its own cache. However, there exists + * CPU models in which having conflicting memory types still leads to + * unpredictable behavior, machine check errors, or hangs. Clear this + * feature to prevent its use on machines with known erratas. + */ +static void check_memory_type_self_snoop_errata(struct cpuinfo_x86 *c) +{ + switch (c->x86_model) { + case INTEL_FAM6_CORE_YONAH: + case INTEL_FAM6_CORE2_MEROM: + case INTEL_FAM6_CORE2_MEROM_L: + case INTEL_FAM6_CORE2_PENRYN: + case INTEL_FAM6_CORE2_DUNNINGTON: + case INTEL_FAM6_NEHALEM: + case INTEL_FAM6_NEHALEM_G: + case INTEL_FAM6_NEHALEM_EP: + case INTEL_FAM6_NEHALEM_EX: + case INTEL_FAM6_WESTMERE: + case INTEL_FAM6_WESTMERE_EP: + case INTEL_FAM6_SANDYBRIDGE: + setup_clear_cpu_cap(X86_FEATURE_SELFSNOOP); + } +} + static bool ring3mwait_disabled __read_mostly; static int __init ring3mwait_disable(char *__unused) @@ -239,9 +265,9 @@ static void early_init_intel(struct cpuinfo_x86 *c) /* Penwell and Cloverview have the TSC which doesn't sleep on S3 */ if (c->x86 == 6) { switch (c->x86_model) { - case 0x27: /* Penwell */ - case 0x35: /* Cloverview */ - case 0x4a: /* Merrifield */ + case INTEL_FAM6_ATOM_SALTWELL_MID: + case INTEL_FAM6_ATOM_SALTWELL_TABLET: + case INTEL_FAM6_ATOM_SILVERMONT_MID: set_cpu_cap(c, X86_FEATURE_NONSTOP_TSC_S3); break; default: @@ -304,6 +330,7 @@ static void early_init_intel(struct cpuinfo_x86 *c) } check_mpx_erratum(c); + check_memory_type_self_snoop_errata(c); /* * Get the number of SMT siblings early from the extended topology diff --git a/arch/x86/kernel/cpu/match.c b/arch/x86/kernel/cpu/match.c index 6dd78d8235e4..2f163e6646b6 100644 --- a/arch/x86/kernel/cpu/match.c +++ b/arch/x86/kernel/cpu/match.c @@ -34,13 +34,18 @@ const struct x86_cpu_id *x86_match_cpu(const struct x86_cpu_id *match) const struct x86_cpu_id *m; struct cpuinfo_x86 *c = &boot_cpu_data; - for (m = match; m->vendor | m->family | m->model | m->feature; m++) { + for (m = match; + m->vendor | m->family | m->model | m->steppings | m->feature; + m++) { if (m->vendor != X86_VENDOR_ANY && c->x86_vendor != m->vendor) continue; if (m->family != X86_FAMILY_ANY && c->x86 != m->family) continue; if (m->model != X86_MODEL_ANY && c->x86_model != m->model) continue; + if (m->steppings != X86_STEPPING_ANY && + !(BIT(c->x86_stepping) & m->steppings)) + continue; if (m->feature != X86_FEATURE_ANY && !cpu_has(c, m->feature)) continue; return m; diff --git a/arch/x86/kernel/cpu/mce/amd.c b/arch/x86/kernel/cpu/mce/amd.c index 785050af85e5..f1c845416790 100644 --- a/arch/x86/kernel/cpu/mce/amd.c +++ b/arch/x86/kernel/cpu/mce/amd.c @@ -244,10 +244,10 @@ static void smca_configure(unsigned int bank, unsigned int cpu) } /* Return early if this bank was already initialized. */ - if (smca_banks[bank].hwid) + if (smca_banks[bank].hwid && smca_banks[bank].hwid->hwid_mcatype != 0) return; - if (rdmsr_safe_on_cpu(cpu, MSR_AMD64_SMCA_MCx_IPID(bank), &low, &high)) { + if (rdmsr_safe(MSR_AMD64_SMCA_MCx_IPID(bank), &low, &high)) { pr_warn("Failed to read MCA_IPID for bank %d\n", bank); return; } @@ -1159,9 +1159,12 @@ static const struct sysfs_ops threshold_ops = { .store = store, }; +static void threshold_block_release(struct kobject *kobj); + static struct kobj_type threshold_ktype = { .sysfs_ops = &threshold_ops, .default_attrs = default_attrs, + .release = threshold_block_release, }; static const char *get_name(unsigned int bank, struct threshold_block *b) @@ -1194,8 +1197,9 @@ static const char *get_name(unsigned int bank, struct threshold_block *b) return buf_mcatype; } -static int allocate_threshold_blocks(unsigned int cpu, unsigned int bank, - unsigned int block, u32 address) +static int allocate_threshold_blocks(unsigned int cpu, struct threshold_bank *tb, + unsigned int bank, unsigned int block, + u32 address) { struct threshold_block *b = NULL; u32 low, high; @@ -1239,16 +1243,12 @@ static int allocate_threshold_blocks(unsigned int cpu, unsigned int bank, INIT_LIST_HEAD(&b->miscj); - if (per_cpu(threshold_banks, cpu)[bank]->blocks) { - list_add(&b->miscj, - &per_cpu(threshold_banks, cpu)[bank]->blocks->miscj); - } else { - per_cpu(threshold_banks, cpu)[bank]->blocks = b; - } + if (tb->blocks) + list_add(&b->miscj, &tb->blocks->miscj); + else + tb->blocks = b; - err = kobject_init_and_add(&b->kobj, &threshold_ktype, - per_cpu(threshold_banks, cpu)[bank]->kobj, - get_name(bank, b)); + err = kobject_init_and_add(&b->kobj, &threshold_ktype, tb->kobj, get_name(bank, b)); if (err) goto out_free; recurse: @@ -1256,7 +1256,7 @@ recurse: if (!address) return 0; - err = allocate_threshold_blocks(cpu, bank, block, address); + err = allocate_threshold_blocks(cpu, tb, bank, block, address); if (err) goto out_free; @@ -1341,8 +1341,6 @@ static int threshold_create_bank(unsigned int cpu, unsigned int bank) goto out_free; } - per_cpu(threshold_banks, cpu)[bank] = b; - if (is_shared_bank(bank)) { refcount_set(&b->cpus, 1); @@ -1353,9 +1351,13 @@ static int threshold_create_bank(unsigned int cpu, unsigned int bank) } } - err = allocate_threshold_blocks(cpu, bank, 0, msr_ops.misc(bank)); - if (!err) - goto out; + err = allocate_threshold_blocks(cpu, b, bank, 0, msr_ops.misc(bank)); + if (err) + goto out_free; + + per_cpu(threshold_banks, cpu)[bank] = b; + + return 0; out_free: kfree(b); @@ -1364,8 +1366,12 @@ static int threshold_create_bank(unsigned int cpu, unsigned int bank) return err; } -static void deallocate_threshold_block(unsigned int cpu, - unsigned int bank) +static void threshold_block_release(struct kobject *kobj) +{ + kfree(to_block(kobj)); +} + +static void deallocate_threshold_block(unsigned int cpu, unsigned int bank) { struct threshold_block *pos = NULL; struct threshold_block *tmp = NULL; @@ -1375,13 +1381,11 @@ static void deallocate_threshold_block(unsigned int cpu, return; list_for_each_entry_safe(pos, tmp, &head->blocks->miscj, miscj) { - kobject_put(&pos->kobj); list_del(&pos->miscj); - kfree(pos); + kobject_put(&pos->kobj); } - kfree(per_cpu(threshold_banks, cpu)[bank]->blocks); - per_cpu(threshold_banks, cpu)[bank]->blocks = NULL; + kobject_put(&head->blocks->kobj); } static void __threshold_remove_blocks(struct threshold_bank *b) diff --git a/arch/x86/kernel/cpu/mce/core.c b/arch/x86/kernel/cpu/mce/core.c index 282916f3b8d8..db1a8a1612f9 100644 --- a/arch/x86/kernel/cpu/mce/core.c +++ b/arch/x86/kernel/cpu/mce/core.c @@ -517,6 +517,13 @@ bool mce_is_memory_error(struct mce *m) } EXPORT_SYMBOL_GPL(mce_is_memory_error); +static bool whole_page(struct mce *m) +{ + if (!mca_cfg.ser || !(m->status & MCI_STATUS_MISCV)) + return true; + return MCI_MISC_ADDR_LSB(m->misc) >= PAGE_SHIFT; +} + bool mce_is_correctable(struct mce *m) { if (m->cpuvendor == X86_VENDOR_AMD && m->status & MCI_STATUS_DEFERRED) @@ -585,7 +592,7 @@ static int srao_decode_notifier(struct notifier_block *nb, unsigned long val, if (mce_usable_address(mce) && (mce->severity == MCE_AO_SEVERITY)) { pfn = mce->addr >> PAGE_SHIFT; if (!memory_failure(pfn, 0)) - set_mce_nospec(pfn); + set_mce_nospec(pfn, whole_page(mce)); } return NOTIFY_OK; @@ -797,8 +804,8 @@ static int mce_no_way_out(struct mce *m, char **msg, unsigned long *validp, if (quirk_no_way_out) quirk_no_way_out(i, m, regs); + m->bank = i; if (mce_severity(m, mca_cfg.tolerant, &tmp, true) >= MCE_PANIC_SEVERITY) { - m->bank = i; mce_read_aux(m, i); *msg = tmp; return 1; @@ -1086,7 +1093,7 @@ static int do_memory_failure(struct mce *m) if (ret) pr_err("Memory error not recovered"); else - set_mce_nospec(m->addr >> PAGE_SHIFT); + set_mce_nospec(m->addr >> PAGE_SHIFT, whole_page(m)); return ret; } diff --git a/arch/x86/kernel/cpu/mce/dev-mcelog.c b/arch/x86/kernel/cpu/mce/dev-mcelog.c index 7c8958dee103..6c9b91b773ef 100644 --- a/arch/x86/kernel/cpu/mce/dev-mcelog.c +++ b/arch/x86/kernel/cpu/mce/dev-mcelog.c @@ -328,6 +328,7 @@ static const struct file_operations mce_chrdev_ops = { .write = mce_chrdev_write, .poll = mce_chrdev_poll, .unlocked_ioctl = mce_chrdev_ioctl, + .compat_ioctl = compat_ptr_ioctl, .llseek = no_llseek, }; diff --git a/arch/x86/kernel/cpu/mce/inject.c b/arch/x86/kernel/cpu/mce/inject.c index 5d108f70f315..799b74b1582c 100644 --- a/arch/x86/kernel/cpu/mce/inject.c +++ b/arch/x86/kernel/cpu/mce/inject.c @@ -511,7 +511,7 @@ static void do_inject(void) */ if (inj_type == DFR_INT_INJ) { i_mce.status |= MCI_STATUS_DEFERRED; - i_mce.status |= (i_mce.status & ~MCI_STATUS_UC); + i_mce.status &= ~MCI_STATUS_UC; } /* diff --git a/arch/x86/kernel/cpu/mce/intel.c b/arch/x86/kernel/cpu/mce/intel.c index e43eb6732630..693c8cfac75d 100644 --- a/arch/x86/kernel/cpu/mce/intel.c +++ b/arch/x86/kernel/cpu/mce/intel.c @@ -489,17 +489,18 @@ static void intel_ppin_init(struct cpuinfo_x86 *c) return; if ((val & 3UL) == 1UL) { - /* PPIN available but disabled: */ + /* PPIN locked in disabled mode */ return; } - /* If PPIN is disabled, but not locked, try to enable: */ - if (!(val & 3UL)) { + /* If PPIN is disabled, try to enable */ + if (!(val & 2UL)) { wrmsrl_safe(MSR_PPIN_CTL, val | 2UL); rdmsrl_safe(MSR_PPIN_CTL, &val); } - if ((val & 3UL) == 2UL) + /* Is the enable bit set? */ + if (val & 2UL) set_cpu_cap(c, X86_FEATURE_INTEL_PPIN); } } diff --git a/arch/x86/kernel/cpu/mce/therm_throt.c b/arch/x86/kernel/cpu/mce/therm_throt.c index 6e2becf547c5..bc441d68d060 100644 --- a/arch/x86/kernel/cpu/mce/therm_throt.c +++ b/arch/x86/kernel/cpu/mce/therm_throt.c @@ -188,7 +188,7 @@ static void therm_throt_process(bool new_event, int event, int level) /* if we just entered the thermal event */ if (new_event) { if (event == THERMAL_THROTTLING_EVENT) - pr_crit("CPU%d: %s temperature above threshold, cpu clock throttled (total events = %lu)\n", + pr_warn("CPU%d: %s temperature above threshold, cpu clock throttled (total events = %lu)\n", this_cpu, level == CORE_LEVEL ? "Core" : "Package", state->count); diff --git a/arch/x86/kernel/cpu/mshyperv.c b/arch/x86/kernel/cpu/mshyperv.c index 7df29f08871b..920aa2f0b52b 100644 --- a/arch/x86/kernel/cpu/mshyperv.c +++ b/arch/x86/kernel/cpu/mshyperv.c @@ -220,8 +220,8 @@ static void __init ms_hyperv_init_platform(void) ms_hyperv.misc_features = cpuid_edx(HYPERV_CPUID_FEATURES); ms_hyperv.hints = cpuid_eax(HYPERV_CPUID_ENLIGHTMENT_INFO); - pr_info("Hyper-V: features 0x%x, hints 0x%x\n", - ms_hyperv.features, ms_hyperv.hints); + pr_info("Hyper-V: features 0x%x, hints 0x%x, misc 0x%x\n", + ms_hyperv.features, ms_hyperv.hints, ms_hyperv.misc_features); ms_hyperv.max_vp_index = cpuid_eax(HYPERV_CPUID_IMPLEMENT_LIMITS); ms_hyperv.max_lp_index = cpuid_ebx(HYPERV_CPUID_IMPLEMENT_LIMITS); @@ -256,6 +256,16 @@ static void __init ms_hyperv_init_platform(void) cpuid_eax(HYPERV_CPUID_NESTED_FEATURES); } + /* + * Hyper-V expects to get crash register data or kmsg when + * crash enlightment is available and system crashes. Set + * crash_kexec_post_notifiers to be true to make sure that + * calling crash enlightment interface before running kdump + * kernel. + */ + if (ms_hyperv.misc_features & HV_FEATURE_GUEST_CRASH_MSR_AVAILABLE) + crash_kexec_post_notifiers = true; + #ifdef CONFIG_X86_LOCAL_APIC if (ms_hyperv.features & HV_X64_ACCESS_FREQUENCY_MSRS && ms_hyperv.misc_features & HV_FEATURE_FREQUENCY_MSRS_AVAILABLE) { @@ -266,9 +276,9 @@ static void __init ms_hyperv_init_platform(void) rdmsrl(HV_X64_MSR_APIC_FREQUENCY, hv_lapic_frequency); hv_lapic_frequency = div_u64(hv_lapic_frequency, HZ); - lapic_timer_frequency = hv_lapic_frequency; + lapic_timer_period = hv_lapic_frequency; pr_info("Hyper-V: LAPIC Timer Frequency: %#x\n", - lapic_timer_frequency); + lapic_timer_period); } register_nmi_handler(NMI_UNKNOWN, hv_nmi_unknown, NMI_FLAG_FIRST, diff --git a/arch/x86/kernel/cpu/resctrl/core.c b/arch/x86/kernel/cpu/resctrl/core.c index 03eb90d00af0..d8cc5223b7ce 100644 --- a/arch/x86/kernel/cpu/resctrl/core.c +++ b/arch/x86/kernel/cpu/resctrl/core.c @@ -578,6 +578,8 @@ static void domain_add_cpu(int cpu, struct rdt_resource *r) d->id = id; cpumask_set_cpu(cpu, &d->cpu_mask); + rdt_domain_reconfigure_cdp(r); + if (r->alloc_capable && domain_setup_ctrlval(r, d)) { kfree(d); return; @@ -618,7 +620,7 @@ static void domain_remove_cpu(int cpu, struct rdt_resource *r) if (static_branch_unlikely(&rdt_mon_enable_key)) rmdir_mondata_subdir_allrdtgrp(r, d->id); list_del(&d->list); - if (is_mbm_enabled()) + if (r->mon_capable && is_mbm_enabled()) cancel_delayed_work(&d->mbm_over); if (is_llc_occupancy_enabled() && has_busy_rmid(r, d)) { /* diff --git a/arch/x86/kernel/cpu/resctrl/ctrlmondata.c b/arch/x86/kernel/cpu/resctrl/ctrlmondata.c index efbd54cc4e69..055c8613b531 100644 --- a/arch/x86/kernel/cpu/resctrl/ctrlmondata.c +++ b/arch/x86/kernel/cpu/resctrl/ctrlmondata.c @@ -522,6 +522,10 @@ int rdtgroup_mondata_show(struct seq_file *m, void *arg) int ret = 0; rdtgrp = rdtgroup_kn_lock_live(of->kn); + if (!rdtgrp) { + ret = -ENOENT; + goto out; + } md.priv = of->kn->priv; resid = md.u.rid; diff --git a/arch/x86/kernel/cpu/resctrl/internal.h b/arch/x86/kernel/cpu/resctrl/internal.h index e49b77283924..3dd13f3a8b23 100644 --- a/arch/x86/kernel/cpu/resctrl/internal.h +++ b/arch/x86/kernel/cpu/resctrl/internal.h @@ -57,6 +57,7 @@ static inline struct rdt_fs_context *rdt_fc2context(struct fs_context *fc) } DECLARE_STATIC_KEY_FALSE(rdt_enable_key); +DECLARE_STATIC_KEY_FALSE(rdt_mon_enable_key); /** * struct mon_evt - Entry in the event list of a resource @@ -600,5 +601,6 @@ bool has_busy_rmid(struct rdt_resource *r, struct rdt_domain *d); void __check_limbo(struct rdt_domain *d, bool force_free); bool cbm_validate_intel(char *buf, u32 *data, struct rdt_resource *r); bool cbm_validate_amd(char *buf, u32 *data, struct rdt_resource *r); +void rdt_domain_reconfigure_cdp(struct rdt_resource *r); #endif /* _ASM_X86_RESCTRL_INTERNAL_H */ diff --git a/arch/x86/kernel/cpu/resctrl/monitor.c b/arch/x86/kernel/cpu/resctrl/monitor.c index 397206f23d14..773124b0e18a 100644 --- a/arch/x86/kernel/cpu/resctrl/monitor.c +++ b/arch/x86/kernel/cpu/resctrl/monitor.c @@ -514,7 +514,7 @@ void mbm_handle_overflow(struct work_struct *work) mutex_lock(&rdtgroup_mutex); - if (!static_branch_likely(&rdt_enable_key)) + if (!static_branch_likely(&rdt_mon_enable_key)) goto out_unlock; d = get_domain_from_cpu(cpu, &rdt_resources_all[RDT_RESOURCE_L3]); @@ -543,7 +543,7 @@ void mbm_setup_overflow_handler(struct rdt_domain *dom, unsigned long delay_ms) unsigned long delay = msecs_to_jiffies(delay_ms); int cpu; - if (!static_branch_likely(&rdt_enable_key)) + if (!static_branch_likely(&rdt_mon_enable_key)) return; cpu = cpumask_any(&dom->cpu_mask); dom->mbm_work_cpu = cpu; diff --git a/arch/x86/kernel/cpu/resctrl/rdtgroup.c b/arch/x86/kernel/cpu/resctrl/rdtgroup.c index 2f4824793798..81200c253002 100644 --- a/arch/x86/kernel/cpu/resctrl/rdtgroup.c +++ b/arch/x86/kernel/cpu/resctrl/rdtgroup.c @@ -461,10 +461,8 @@ static ssize_t rdtgroup_cpus_write(struct kernfs_open_file *of, } rdtgrp = rdtgroup_kn_lock_live(of->kn); - rdt_last_cmd_clear(); if (!rdtgrp) { ret = -ENOENT; - rdt_last_cmd_puts("Directory was removed\n"); goto unlock; } @@ -1029,6 +1027,7 @@ static int rdt_cdp_peer_get(struct rdt_resource *r, struct rdt_domain *d, _d_cdp = rdt_find_domain(_r_cdp, d->id, NULL); if (WARN_ON(IS_ERR_OR_NULL(_d_cdp))) { _r_cdp = NULL; + _d_cdp = NULL; ret = -EINVAL; } @@ -1743,9 +1742,6 @@ static int set_cache_qos_cfg(int level, bool enable) struct rdt_domain *d; int cpu; - if (!zalloc_cpumask_var(&cpu_mask, GFP_KERNEL)) - return -ENOMEM; - if (level == RDT_RESOURCE_L3) update = l3_qos_cfg_update; else if (level == RDT_RESOURCE_L2) @@ -1753,6 +1749,9 @@ static int set_cache_qos_cfg(int level, bool enable) else return -EINVAL; + if (!zalloc_cpumask_var(&cpu_mask, GFP_KERNEL)) + return -ENOMEM; + r_l = &rdt_resources_all[level]; list_for_each_entry(d, &r_l->domains, list) { /* Pick one CPU from each domain instance to update MSR */ @@ -1771,6 +1770,19 @@ static int set_cache_qos_cfg(int level, bool enable) return 0; } +/* Restore the qos cfg state when a domain comes online */ +void rdt_domain_reconfigure_cdp(struct rdt_resource *r) +{ + if (!r->alloc_capable) + return; + + if (r == &rdt_resources_all[RDT_RESOURCE_L2DATA]) + l2_qos_cfg_update(&r->alloc_enabled); + + if (r == &rdt_resources_all[RDT_RESOURCE_L3DATA]) + l3_qos_cfg_update(&r->alloc_enabled); +} + /* * Enable or disable the MBA software controller * which helps user specify bandwidth in MBps. @@ -1972,7 +1984,7 @@ static int rdt_get_tree(struct fs_context *fc) if (rdt_mon_capable) { ret = mongroup_create_dir(rdtgroup_default.kn, - NULL, "mon_groups", + &rdtgroup_default, "mon_groups", &kn_mongrp); if (ret < 0) goto out_info; @@ -2208,7 +2220,11 @@ static void free_all_child_rdtgrp(struct rdtgroup *rdtgrp) list_for_each_entry_safe(sentry, stmp, head, mon.crdtgrp_list) { free_rmid(sentry->mon.rmid); list_del(&sentry->mon.crdtgrp_list); - kfree(sentry); + + if (atomic_read(&sentry->waitcount) != 0) + sentry->flags = RDT_DELETED; + else + kfree(sentry); } } @@ -2246,7 +2262,11 @@ static void rmdir_all_sub(void) kernfs_remove(rdtgrp->kn); list_del(&rdtgrp->rdtgroup_list); - kfree(rdtgrp); + + if (atomic_read(&rdtgrp->waitcount) != 0) + rdtgrp->flags = RDT_DELETED; + else + kfree(rdtgrp); } /* Notify online CPUs to update per cpu storage and PQR_ASSOC MSR */ update_closid_rmid(cpu_online_mask, &rdtgroup_default); @@ -2449,7 +2469,7 @@ static int mkdir_mondata_all(struct kernfs_node *parent_kn, /* * Create the mon_data directory first. */ - ret = mongroup_create_dir(parent_kn, NULL, "mon_data", &kn); + ret = mongroup_create_dir(parent_kn, prgrp, "mon_data", &kn); if (ret) return ret; @@ -2648,11 +2668,9 @@ static int mkdir_rdt_prepare(struct kernfs_node *parent_kn, uint files = 0; int ret; - prdtgrp = rdtgroup_kn_lock_live(prgrp_kn); - rdt_last_cmd_clear(); + prdtgrp = rdtgroup_kn_lock_live(parent_kn); if (!prdtgrp) { ret = -ENODEV; - rdt_last_cmd_puts("Directory was removed\n"); goto out_unlock; } @@ -2723,7 +2741,7 @@ static int mkdir_rdt_prepare(struct kernfs_node *parent_kn, kernfs_activate(kn); /* - * The caller unlocks the prgrp_kn upon success. + * The caller unlocks the parent_kn upon success. */ return 0; @@ -2734,7 +2752,7 @@ out_destroy: out_free_rgrp: kfree(rdtgrp); out_unlock: - rdtgroup_kn_unlock(prgrp_kn); + rdtgroup_kn_unlock(parent_kn); return ret; } @@ -2772,7 +2790,7 @@ static int rdtgroup_mkdir_mon(struct kernfs_node *parent_kn, */ list_add_tail(&rdtgrp->mon.crdtgrp_list, &prgrp->mon.crdtgrp_list); - rdtgroup_kn_unlock(prgrp_kn); + rdtgroup_kn_unlock(parent_kn); return ret; } @@ -2815,7 +2833,7 @@ static int rdtgroup_mkdir_ctrl_mon(struct kernfs_node *parent_kn, * Create an empty mon_groups directory to hold the subset * of tasks and cpus to monitor. */ - ret = mongroup_create_dir(kn, NULL, "mon_groups", NULL); + ret = mongroup_create_dir(kn, rdtgrp, "mon_groups", NULL); if (ret) { rdt_last_cmd_puts("kernfs subdir error\n"); goto out_del_list; @@ -2831,7 +2849,7 @@ out_id_free: out_common_fail: mkdir_rdt_prepare_clean(rdtgrp); out_unlock: - rdtgroup_kn_unlock(prgrp_kn); + rdtgroup_kn_unlock(parent_kn); return ret; } @@ -2957,13 +2975,13 @@ static int rdtgroup_rmdir_ctrl(struct kernfs_node *kn, struct rdtgroup *rdtgrp, closid_free(rdtgrp->closid); free_rmid(rdtgrp->mon.rmid); + rdtgroup_ctrl_remove(kn, rdtgrp); + /* * Free all the child monitor group rmids. */ free_all_child_rdtgrp(rdtgrp); - rdtgroup_ctrl_remove(kn, rdtgrp); - return 0; } @@ -2990,7 +3008,8 @@ static int rdtgroup_rmdir(struct kernfs_node *kn) * If the rdtgroup is a mon group and parent directory * is a valid "mon_groups" directory, remove the mon group. */ - if (rdtgrp->type == RDTCTRL_GROUP && parent_kn == rdtgroup_default.kn) { + if (rdtgrp->type == RDTCTRL_GROUP && parent_kn == rdtgroup_default.kn && + rdtgrp != &rdtgroup_default) { if (rdtgrp->mode == RDT_MODE_PSEUDO_LOCKSETUP || rdtgrp->mode == RDT_MODE_PSEUDO_LOCKED) { ret = rdtgroup_ctrl_remove(kn, rdtgrp); diff --git a/arch/x86/kernel/cpu/tsx.c b/arch/x86/kernel/cpu/tsx.c index 3e20d322bc98..032509adf9de 100644 --- a/arch/x86/kernel/cpu/tsx.c +++ b/arch/x86/kernel/cpu/tsx.c @@ -115,11 +115,12 @@ void __init tsx_init(void) tsx_disable(); /* - * tsx_disable() will change the state of the - * RTM CPUID bit. Clear it here since it is now - * expected to be not set. + * tsx_disable() will change the state of the RTM and HLE CPUID + * bits. Clear them here since they are now expected to be not + * set. */ setup_clear_cpu_cap(X86_FEATURE_RTM); + setup_clear_cpu_cap(X86_FEATURE_HLE); } else if (tsx_ctrl_state == TSX_CTRL_ENABLE) { /* @@ -131,10 +132,10 @@ void __init tsx_init(void) tsx_enable(); /* - * tsx_enable() will change the state of the - * RTM CPUID bit. Force it here since it is now - * expected to be set. + * tsx_enable() will change the state of the RTM and HLE CPUID + * bits. Force them here since they are now expected to be set. */ setup_force_cpu_cap(X86_FEATURE_RTM); + setup_force_cpu_cap(X86_FEATURE_HLE); } } diff --git a/arch/x86/kernel/cpu/vmware.c b/arch/x86/kernel/cpu/vmware.c index 34ab4161fc39..88569536d529 100644 --- a/arch/x86/kernel/cpu/vmware.c +++ b/arch/x86/kernel/cpu/vmware.c @@ -158,7 +158,7 @@ static void __init vmware_platform_setup(void) #ifdef CONFIG_X86_LOCAL_APIC /* Skip lapic calibration since we know the bus frequency. */ - lapic_timer_frequency = ecx / HZ; + lapic_timer_period = ecx / HZ; pr_info("Host bus clock speed read from hypervisor : %u Hz\n", ecx); #endif diff --git a/arch/x86/kernel/early-quirks.c b/arch/x86/kernel/early-quirks.c index 43abebc2fc77..7c9259306d74 100644 --- a/arch/x86/kernel/early-quirks.c +++ b/arch/x86/kernel/early-quirks.c @@ -709,8 +709,12 @@ static struct chipset early_qrk[] __initdata = { */ { PCI_VENDOR_ID_INTEL, 0x0f00, PCI_CLASS_BRIDGE_HOST, PCI_ANY_ID, 0, force_disable_hpet}, + { PCI_VENDOR_ID_INTEL, 0x3e20, + PCI_CLASS_BRIDGE_HOST, PCI_ANY_ID, 0, force_disable_hpet}, { PCI_VENDOR_ID_INTEL, 0x3ec4, PCI_CLASS_BRIDGE_HOST, PCI_ANY_ID, 0, force_disable_hpet}, + { PCI_VENDOR_ID_INTEL, 0x8a12, + PCI_CLASS_BRIDGE_HOST, PCI_ANY_ID, 0, force_disable_hpet}, { PCI_VENDOR_ID_BROADCOM, 0x4331, PCI_CLASS_NETWORK_OTHER, PCI_ANY_ID, 0, apple_airport_reset}, {} diff --git a/arch/x86/kernel/fpu/core.c b/arch/x86/kernel/fpu/core.c index 649fbc3fcf9f..8ba0e53dec75 100644 --- a/arch/x86/kernel/fpu/core.c +++ b/arch/x86/kernel/fpu/core.c @@ -113,6 +113,12 @@ static void __kernel_fpu_begin(void) } } __cpu_invalidate_fpregs_state(); + + if (boot_cpu_has(X86_FEATURE_XMM)) + ldmxcsr(MXCSR_DEFAULT); + + if (boot_cpu_has(X86_FEATURE_FPU)) + asm volatile ("fninit"); } static void __kernel_fpu_end(void) diff --git a/arch/x86/kernel/fpu/signal.c b/arch/x86/kernel/fpu/signal.c index 0071b794ed19..400a05e1c1c5 100644 --- a/arch/x86/kernel/fpu/signal.c +++ b/arch/x86/kernel/fpu/signal.c @@ -352,6 +352,7 @@ static int __fpu__restore_sig(void __user *buf, void __user *buf_fx, int size) fpregs_unlock(); return 0; } + fpregs_deactivate(fpu); fpregs_unlock(); } @@ -403,6 +404,8 @@ static int __fpu__restore_sig(void __user *buf, void __user *buf_fx, int size) } if (!ret) fpregs_mark_activate(); + else + fpregs_deactivate(fpu); fpregs_unlock(); err_out: diff --git a/arch/x86/kernel/fpu/xstate.c b/arch/x86/kernel/fpu/xstate.c index 3c36dd1784db..085afecd878c 100644 --- a/arch/x86/kernel/fpu/xstate.c +++ b/arch/x86/kernel/fpu/xstate.c @@ -959,18 +959,31 @@ static inline bool xfeatures_mxcsr_quirk(u64 xfeatures) return true; } -/* - * This is similar to user_regset_copyout(), but will not add offset to - * the source data pointer or increment pos, count, kbuf, and ubuf. - */ -static inline void -__copy_xstate_to_kernel(void *kbuf, const void *data, - unsigned int offset, unsigned int size, unsigned int size_total) +static void fill_gap(unsigned to, void **kbuf, unsigned *pos, unsigned *count) { - if (offset < size_total) { - unsigned int copy = min(size, size_total - offset); + if (*pos < to) { + unsigned size = to - *pos; + + if (size > *count) + size = *count; + memcpy(*kbuf, (void *)&init_fpstate.xsave + *pos, size); + *kbuf += size; + *pos += size; + *count -= size; + } +} - memcpy(kbuf + offset, data, copy); +static void copy_part(unsigned offset, unsigned size, void *from, + void **kbuf, unsigned *pos, unsigned *count) +{ + fill_gap(offset, kbuf, pos, count); + if (size > *count) + size = *count; + if (size) { + memcpy(*kbuf, from, size); + *kbuf += size; + *pos += size; + *count -= size; } } @@ -983,8 +996,9 @@ __copy_xstate_to_kernel(void *kbuf, const void *data, */ int copy_xstate_to_kernel(void *kbuf, struct xregs_state *xsave, unsigned int offset_start, unsigned int size_total) { - unsigned int offset, size; struct xstate_header header; + const unsigned off_mxcsr = offsetof(struct fxregs_state, mxcsr); + unsigned count = size_total; int i; /* @@ -1000,46 +1014,42 @@ int copy_xstate_to_kernel(void *kbuf, struct xregs_state *xsave, unsigned int of header.xfeatures = xsave->header.xfeatures; header.xfeatures &= ~XFEATURE_MASK_SUPERVISOR; + if (header.xfeatures & XFEATURE_MASK_FP) + copy_part(0, off_mxcsr, + &xsave->i387, &kbuf, &offset_start, &count); + if (header.xfeatures & (XFEATURE_MASK_SSE | XFEATURE_MASK_YMM)) + copy_part(off_mxcsr, MXCSR_AND_FLAGS_SIZE, + &xsave->i387.mxcsr, &kbuf, &offset_start, &count); + if (header.xfeatures & XFEATURE_MASK_FP) + copy_part(offsetof(struct fxregs_state, st_space), 128, + &xsave->i387.st_space, &kbuf, &offset_start, &count); + if (header.xfeatures & XFEATURE_MASK_SSE) + copy_part(xstate_offsets[XFEATURE_SSE], 256, + &xsave->i387.xmm_space, &kbuf, &offset_start, &count); + /* + * Fill xsave->i387.sw_reserved value for ptrace frame: + */ + copy_part(offsetof(struct fxregs_state, sw_reserved), 48, + xstate_fx_sw_bytes, &kbuf, &offset_start, &count); /* * Copy xregs_state->header: */ - offset = offsetof(struct xregs_state, header); - size = sizeof(header); - - __copy_xstate_to_kernel(kbuf, &header, offset, size, size_total); + copy_part(offsetof(struct xregs_state, header), sizeof(header), + &header, &kbuf, &offset_start, &count); - for (i = 0; i < XFEATURE_MAX; i++) { + for (i = FIRST_EXTENDED_XFEATURE; i < XFEATURE_MAX; i++) { /* * Copy only in-use xstates: */ if ((header.xfeatures >> i) & 1) { void *src = __raw_xsave_addr(xsave, i); - offset = xstate_offsets[i]; - size = xstate_sizes[i]; - - /* The next component has to fit fully into the output buffer: */ - if (offset + size > size_total) - break; - - __copy_xstate_to_kernel(kbuf, src, offset, size, size_total); + copy_part(xstate_offsets[i], xstate_sizes[i], + src, &kbuf, &offset_start, &count); } } - - if (xfeatures_mxcsr_quirk(header.xfeatures)) { - offset = offsetof(struct fxregs_state, mxcsr); - size = MXCSR_AND_FLAGS_SIZE; - __copy_xstate_to_kernel(kbuf, &xsave->i387.mxcsr, offset, size, size_total); - } - - /* - * Fill xsave->i387.sw_reserved value for ptrace frame: - */ - offset = offsetof(struct fxregs_state, sw_reserved); - size = sizeof(xstate_fx_sw_bytes); - - __copy_xstate_to_kernel(kbuf, xstate_fx_sw_bytes, offset, size, size_total); + fill_gap(size_total, &kbuf, &offset_start, &count); return 0; } diff --git a/arch/x86/kernel/i8259.c b/arch/x86/kernel/i8259.c index 519649ddf100..fe522691ac71 100644 --- a/arch/x86/kernel/i8259.c +++ b/arch/x86/kernel/i8259.c @@ -207,7 +207,7 @@ spurious_8259A_irq: * lets ACK and report it. [once per IRQ] */ if (!(spurious_irq_mask & irqmask)) { - printk(KERN_DEBUG + printk_deferred(KERN_DEBUG "spurious 8259A interrupt: IRQ%d.\n", irq); spurious_irq_mask |= irqmask; } diff --git a/arch/x86/kernel/idt.c b/arch/x86/kernel/idt.c index 87ef69a72c52..7bb4c3cbf4dc 100644 --- a/arch/x86/kernel/idt.c +++ b/arch/x86/kernel/idt.c @@ -318,7 +318,11 @@ void __init idt_setup_apic_and_irq_gates(void) #ifdef CONFIG_X86_LOCAL_APIC for_each_clear_bit_from(i, system_vectors, NR_VECTORS) { - set_bit(i, system_vectors); + /* + * Don't set the non assigned system vectors in the + * system_vectors bitmap. Otherwise they show up in + * /proc/interrupts. + */ entry = spurious_entries_start + 8 * (i - FIRST_SYSTEM_VECTOR); set_intr_gate(i, entry); } diff --git a/arch/x86/kernel/ima_arch.c b/arch/x86/kernel/ima_arch.c index 4c407833faca..fa188de3f424 100644 --- a/arch/x86/kernel/ima_arch.c +++ b/arch/x86/kernel/ima_arch.c @@ -10,8 +10,6 @@ extern struct boot_params boot_params; static enum efi_secureboot_mode get_sb_mode(void) { - efi_char16_t efi_SecureBoot_name[] = L"SecureBoot"; - efi_char16_t efi_SetupMode_name[] = L"SecureBoot"; efi_guid_t efi_variable_guid = EFI_GLOBAL_VARIABLE_GUID; efi_status_t status; unsigned long size; @@ -25,7 +23,7 @@ static enum efi_secureboot_mode get_sb_mode(void) } /* Get variable contents into buffer */ - status = efi.get_variable(efi_SecureBoot_name, &efi_variable_guid, + status = efi.get_variable(L"SecureBoot", &efi_variable_guid, NULL, &size, &secboot); if (status == EFI_NOT_FOUND) { pr_info("ima: secureboot mode disabled\n"); @@ -38,7 +36,7 @@ static enum efi_secureboot_mode get_sb_mode(void) } size = sizeof(setupmode); - status = efi.get_variable(efi_SetupMode_name, &efi_variable_guid, + status = efi.get_variable(L"SetupMode", &efi_variable_guid, NULL, &size, &setupmode); if (status != EFI_SUCCESS) /* ignore unknown SetupMode */ diff --git a/arch/x86/kernel/irq_64.c b/arch/x86/kernel/irq_64.c index 6bf6517a05bb..5bfa35f3dbac 100644 --- a/arch/x86/kernel/irq_64.c +++ b/arch/x86/kernel/irq_64.c @@ -52,7 +52,7 @@ static int map_irq_stack(unsigned int cpu) pages[i] = pfn_to_page(pa >> PAGE_SHIFT); } - va = vmap(pages, IRQ_STACK_SIZE / PAGE_SIZE, GFP_KERNEL, PAGE_KERNEL); + va = vmap(pages, IRQ_STACK_SIZE / PAGE_SIZE, VM_MAP, PAGE_KERNEL); if (!va) return -ENOMEM; diff --git a/arch/x86/kernel/jailhouse.c b/arch/x86/kernel/jailhouse.c index 1b2ee55a2dfb..ba95bc70460d 100644 --- a/arch/x86/kernel/jailhouse.c +++ b/arch/x86/kernel/jailhouse.c @@ -45,7 +45,7 @@ static void jailhouse_get_wallclock(struct timespec64 *now) static void __init jailhouse_timer_init(void) { - lapic_timer_frequency = setup_data.apic_khz * (1000 / HZ); + lapic_timer_period = setup_data.apic_khz * (1000 / HZ); } static unsigned long jailhouse_get_tsc(void) diff --git a/arch/x86/kernel/kprobes/core.c b/arch/x86/kernel/kprobes/core.c index bd17dbb15d6a..27159a40dc93 100644 --- a/arch/x86/kernel/kprobes/core.c +++ b/arch/x86/kernel/kprobes/core.c @@ -746,16 +746,11 @@ asm( NOKPROBE_SYMBOL(kretprobe_trampoline); STACK_FRAME_NON_STANDARD(kretprobe_trampoline); -static struct kprobe kretprobe_kprobe = { - .addr = (void *)kretprobe_trampoline, -}; - /* * Called from kretprobe_trampoline */ __used __visible void *trampoline_handler(struct pt_regs *regs) { - struct kprobe_ctlblk *kcb; struct kretprobe_instance *ri = NULL; struct hlist_head *head, empty_rp; struct hlist_node *tmp; @@ -765,16 +760,12 @@ __used __visible void *trampoline_handler(struct pt_regs *regs) void *frame_pointer; bool skipped = false; - preempt_disable(); - /* * Set a dummy kprobe for avoiding kretprobe recursion. * Since kretprobe never run in kprobe handler, kprobe must not * be running at this point. */ - kcb = get_kprobe_ctlblk(); - __this_cpu_write(current_kprobe, &kretprobe_kprobe); - kcb->kprobe_status = KPROBE_HIT_ACTIVE; + kprobe_busy_begin(); INIT_HLIST_HEAD(&empty_rp); kretprobe_hash_lock(current, &head, &flags); @@ -850,7 +841,7 @@ __used __visible void *trampoline_handler(struct pt_regs *regs) __this_cpu_write(current_kprobe, &ri->rp->kp); ri->ret_addr = correct_ret_addr; ri->rp->handler(ri, regs); - __this_cpu_write(current_kprobe, &kretprobe_kprobe); + __this_cpu_write(current_kprobe, &kprobe_busy); } recycle_rp_inst(ri, &empty_rp); @@ -866,8 +857,7 @@ __used __visible void *trampoline_handler(struct pt_regs *regs) kretprobe_hash_unlock(current, &flags); - __this_cpu_write(current_kprobe, NULL); - preempt_enable(); + kprobe_busy_end(); hlist_for_each_entry_safe(ri, tmp, &empty_rp, hlist) { hlist_del(&ri->hlist); diff --git a/arch/x86/kernel/nmi.c b/arch/x86/kernel/nmi.c index 4df7705022b9..d7f40ad34432 100644 --- a/arch/x86/kernel/nmi.c +++ b/arch/x86/kernel/nmi.c @@ -104,18 +104,22 @@ static int __init nmi_warning_debugfs(void) } fs_initcall(nmi_warning_debugfs); -static void nmi_max_handler(struct irq_work *w) +static void nmi_check_duration(struct nmiaction *action, u64 duration) { - struct nmiaction *a = container_of(w, struct nmiaction, irq_work); + u64 whole_msecs = READ_ONCE(action->max_duration); int remainder_ns, decimal_msecs; - u64 whole_msecs = READ_ONCE(a->max_duration); + + if (duration < nmi_longest_ns || duration < action->max_duration) + return; + + action->max_duration = duration; remainder_ns = do_div(whole_msecs, (1000 * 1000)); decimal_msecs = remainder_ns / 1000; printk_ratelimited(KERN_INFO "INFO: NMI handler (%ps) took too long to run: %lld.%03d msecs\n", - a->handler, whole_msecs, decimal_msecs); + action->handler, whole_msecs, decimal_msecs); } static int nmi_handle(unsigned int type, struct pt_regs *regs) @@ -142,11 +146,7 @@ static int nmi_handle(unsigned int type, struct pt_regs *regs) delta = sched_clock() - delta; trace_nmi_handler(a->handler, (int)delta, thishandled); - if (delta < nmi_longest_ns || delta < a->max_duration) - continue; - - a->max_duration = delta; - irq_work_queue(&a->irq_work); + nmi_check_duration(a, delta); } rcu_read_unlock(); @@ -164,8 +164,6 @@ int __register_nmi_handler(unsigned int type, struct nmiaction *action) if (!action->handler) return -EINVAL; - init_irq_work(&action->irq_work, nmi_max_handler); - raw_spin_lock_irqsave(&desc->lock, flags); /* diff --git a/arch/x86/kernel/process.c b/arch/x86/kernel/process.c index 75fea0d48c0e..a04e43ff4b5e 100644 --- a/arch/x86/kernel/process.c +++ b/arch/x86/kernel/process.c @@ -428,28 +428,20 @@ static __always_inline void __speculation_ctrl_update(unsigned long tifp, lockdep_assert_irqs_disabled(); - /* - * If TIF_SSBD is different, select the proper mitigation - * method. Note that if SSBD mitigation is disabled or permanentely - * enabled this branch can't be taken because nothing can set - * TIF_SSBD. - */ - if (tif_diff & _TIF_SSBD) { - if (static_cpu_has(X86_FEATURE_VIRT_SSBD)) { + /* Handle change of TIF_SSBD depending on the mitigation method. */ + if (static_cpu_has(X86_FEATURE_VIRT_SSBD)) { + if (tif_diff & _TIF_SSBD) amd_set_ssb_virt_state(tifn); - } else if (static_cpu_has(X86_FEATURE_LS_CFG_SSBD)) { + } else if (static_cpu_has(X86_FEATURE_LS_CFG_SSBD)) { + if (tif_diff & _TIF_SSBD) amd_set_core_ssb_state(tifn); - } else if (static_cpu_has(X86_FEATURE_SPEC_CTRL_SSBD) || - static_cpu_has(X86_FEATURE_AMD_SSBD)) { - msr |= ssbd_tif_to_spec_ctrl(tifn); - updmsr = true; - } + } else if (static_cpu_has(X86_FEATURE_SPEC_CTRL_SSBD) || + static_cpu_has(X86_FEATURE_AMD_SSBD)) { + updmsr |= !!(tif_diff & _TIF_SSBD); + msr |= ssbd_tif_to_spec_ctrl(tifn); } - /* - * Only evaluate TIF_SPEC_IB if conditional STIBP is enabled, - * otherwise avoid the MSR write. - */ + /* Only evaluate TIF_SPEC_IB if conditional STIBP is enabled. */ if (IS_ENABLED(CONFIG_SMP) && static_branch_unlikely(&switch_to_cond_stibp)) { updmsr |= !!(tif_diff & _TIF_SPEC_IB); diff --git a/arch/x86/kernel/process_64.c b/arch/x86/kernel/process_64.c index 250e4c4ac6d9..d02874cddda3 100644 --- a/arch/x86/kernel/process_64.c +++ b/arch/x86/kernel/process_64.c @@ -326,7 +326,7 @@ static unsigned long x86_fsgsbase_read_task(struct task_struct *task, */ mutex_lock(&task->mm->context.lock); ldt = task->mm->context.ldt; - if (unlikely(idx >= ldt->nr_entries)) + if (unlikely(!ldt || idx >= ldt->nr_entries)) base = 0; else base = get_desc_base(ldt->entries + idx); diff --git a/arch/x86/kernel/reboot.c b/arch/x86/kernel/reboot.c index 09d6bded3c1e..3f677832fc12 100644 --- a/arch/x86/kernel/reboot.c +++ b/arch/x86/kernel/reboot.c @@ -197,6 +197,14 @@ static const struct dmi_system_id reboot_dmi_table[] __initconst = { DMI_MATCH(DMI_PRODUCT_NAME, "MacBook5"), }, }, + { /* Handle problems with rebooting on Apple MacBook6,1 */ + .callback = set_pci_reboot, + .ident = "Apple MacBook6,1", + .matches = { + DMI_MATCH(DMI_SYS_VENDOR, "Apple Inc."), + DMI_MATCH(DMI_PRODUCT_NAME, "MacBook6,1"), + }, + }, { /* Handle problems with rebooting on Apple MacBookPro5 */ .callback = set_pci_reboot, .ident = "Apple MacBookPro5", diff --git a/arch/x86/kernel/smpboot.c b/arch/x86/kernel/smpboot.c index 0bacaeaeeac4..5fe11d5d29c1 100644 --- a/arch/x86/kernel/smpboot.c +++ b/arch/x86/kernel/smpboot.c @@ -257,6 +257,14 @@ static void notrace start_secondary(void *unused) wmb(); cpu_startup_entry(CPUHP_AP_ONLINE_IDLE); + + /* + * Prevent tail call to cpu_startup_entry() because the stack protector + * guard has been changed a couple of function calls up, in + * boot_init_stack_canary() and must not be checked before tail calling + * another function. + */ + prevent_tail_call_optimization(); } /** diff --git a/arch/x86/kernel/stacktrace.c b/arch/x86/kernel/stacktrace.c index 2d6898c2cb64..6d83b4b857e6 100644 --- a/arch/x86/kernel/stacktrace.c +++ b/arch/x86/kernel/stacktrace.c @@ -58,7 +58,6 @@ int arch_stack_walk_reliable(stack_trace_consume_fn consume_entry, * or a page fault), which can make frame pointers * unreliable. */ - if (IS_ENABLED(CONFIG_FRAME_POINTER)) return -EINVAL; } @@ -81,10 +80,6 @@ int arch_stack_walk_reliable(stack_trace_consume_fn consume_entry, if (unwind_error(&state)) return -EINVAL; - /* Success path for non-user tasks, i.e. kthreads and idle tasks */ - if (!(task->flags & (PF_KTHREAD | PF_IDLE))) - return -EINVAL; - return 0; } diff --git a/arch/x86/kernel/sysfb_simplefb.c b/arch/x86/kernel/sysfb_simplefb.c index 01f0e2263b86..298fc1edd9c9 100644 --- a/arch/x86/kernel/sysfb_simplefb.c +++ b/arch/x86/kernel/sysfb_simplefb.c @@ -90,11 +90,11 @@ __init int create_simplefb(const struct screen_info *si, if (si->orig_video_isVGA == VIDEO_TYPE_VLFB) size <<= 16; length = mode->height * mode->stride; - length = PAGE_ALIGN(length); if (length > size) { printk(KERN_WARNING "sysfb: VRAM smaller than advertised\n"); return -EINVAL; } + length = PAGE_ALIGN(length); /* setup IORESOURCE_MEM as framebuffer memory */ memset(&res, 0, sizeof(res)); diff --git a/arch/x86/kernel/time.c b/arch/x86/kernel/time.c index 2acbab329754..befb70359551 100644 --- a/arch/x86/kernel/time.c +++ b/arch/x86/kernel/time.c @@ -25,10 +25,6 @@ #include <asm/hpet.h> #include <asm/time.h> -#ifdef CONFIG_X86_64 -__visible volatile unsigned long jiffies __cacheline_aligned_in_smp = INITIAL_JIFFIES; -#endif - unsigned long profile_pc(struct pt_regs *regs) { unsigned long pc = instruction_pointer(regs); diff --git a/arch/x86/kernel/tsc.c b/arch/x86/kernel/tsc.c index 0b29e58f288e..f30730621c8a 100644 --- a/arch/x86/kernel/tsc.c +++ b/arch/x86/kernel/tsc.c @@ -665,6 +665,16 @@ unsigned long native_calibrate_tsc(void) if (boot_cpu_data.x86_model == INTEL_FAM6_ATOM_GOLDMONT) setup_force_cpu_cap(X86_FEATURE_TSC_RELIABLE); +#ifdef CONFIG_X86_LOCAL_APIC + /* + * The local APIC appears to be fed by the core crystal clock + * (which sounds entirely sensible). We can set the global + * lapic_timer_period here to avoid having to calibrate the APIC + * timer later. + */ + lapic_timer_period = crystal_khz * 1000 / HZ; +#endif + return crystal_khz * ebx_numerator / eax_denominator; } @@ -1488,6 +1498,9 @@ void __init tsc_init(void) return; } + if (tsc_clocksource_reliable || no_tsc_watchdog) + clocksource_tsc_early.flags &= ~CLOCK_SOURCE_MUST_VERIFY; + clocksource_register_khz(&clocksource_tsc_early, tsc_khz); detect_art(); } diff --git a/arch/x86/kernel/tsc_msr.c b/arch/x86/kernel/tsc_msr.c index 3d0e9aeea7c8..6f56071aa909 100644 --- a/arch/x86/kernel/tsc_msr.c +++ b/arch/x86/kernel/tsc_msr.c @@ -15,18 +15,46 @@ #include <asm/param.h> #include <asm/tsc.h> -#define MAX_NUM_FREQS 9 +#define MAX_NUM_FREQS 16 /* 4 bits to select the frequency */ + +/* + * The frequency numbers in the SDM are e.g. 83.3 MHz, which does not contain a + * lot of accuracy which leads to clock drift. As far as we know Bay Trail SoCs + * use a 25 MHz crystal and Cherry Trail uses a 19.2 MHz crystal, the crystal + * is the source clk for a root PLL which outputs 1600 and 100 MHz. It is + * unclear if the root PLL outputs are used directly by the CPU clock PLL or + * if there is another PLL in between. + * This does not matter though, we can model the chain of PLLs as a single PLL + * with a quotient equal to the quotients of all PLLs in the chain multiplied. + * So we can create a simplified model of the CPU clock setup using a reference + * clock of 100 MHz plus a quotient which gets us as close to the frequency + * from the SDM as possible. + * For the 83.3 MHz example from above this would give us 100 MHz * 5 / 6 = + * 83 and 1/3 MHz, which matches exactly what has been measured on actual hw. + */ +#define TSC_REFERENCE_KHZ 100000 + +struct muldiv { + u32 multiplier; + u32 divider; +}; /* * If MSR_PERF_STAT[31] is set, the maximum resolved bus ratio can be * read in MSR_PLATFORM_ID[12:8], otherwise in MSR_PERF_STAT[44:40]. * Unfortunately some Intel Atom SoCs aren't quite compliant to this, * so we need manually differentiate SoC families. This is what the - * field msr_plat does. + * field use_msr_plat does. */ struct freq_desc { - u8 msr_plat; /* 1: use MSR_PLATFORM_INFO, 0: MSR_IA32_PERF_STATUS */ + bool use_msr_plat; + struct muldiv muldiv[MAX_NUM_FREQS]; + /* + * Some CPU frequencies in the SDM do not map to known PLL freqs, in + * that case the muldiv array is empty and the freqs array is used. + */ u32 freqs[MAX_NUM_FREQS]; + u32 mask; }; /* @@ -35,27 +63,74 @@ struct freq_desc { * by MSR based on SDM. */ static const struct freq_desc freq_desc_pnw = { - 0, { 0, 0, 0, 0, 0, 99840, 0, 83200 } + .use_msr_plat = false, + .freqs = { 0, 0, 0, 0, 0, 99840, 0, 83200 }, + .mask = 0x07, }; static const struct freq_desc freq_desc_clv = { - 0, { 0, 133200, 0, 0, 0, 99840, 0, 83200 } + .use_msr_plat = false, + .freqs = { 0, 133200, 0, 0, 0, 99840, 0, 83200 }, + .mask = 0x07, }; +/* + * Bay Trail SDM MSR_FSB_FREQ frequencies simplified PLL model: + * 000: 100 * 5 / 6 = 83.3333 MHz + * 001: 100 * 1 / 1 = 100.0000 MHz + * 010: 100 * 4 / 3 = 133.3333 MHz + * 011: 100 * 7 / 6 = 116.6667 MHz + * 100: 100 * 4 / 5 = 80.0000 MHz + */ static const struct freq_desc freq_desc_byt = { - 1, { 83300, 100000, 133300, 116700, 80000, 0, 0, 0 } + .use_msr_plat = true, + .muldiv = { { 5, 6 }, { 1, 1 }, { 4, 3 }, { 7, 6 }, + { 4, 5 } }, + .mask = 0x07, }; +/* + * Cherry Trail SDM MSR_FSB_FREQ frequencies simplified PLL model: + * 0000: 100 * 5 / 6 = 83.3333 MHz + * 0001: 100 * 1 / 1 = 100.0000 MHz + * 0010: 100 * 4 / 3 = 133.3333 MHz + * 0011: 100 * 7 / 6 = 116.6667 MHz + * 0100: 100 * 4 / 5 = 80.0000 MHz + * 0101: 100 * 14 / 15 = 93.3333 MHz + * 0110: 100 * 9 / 10 = 90.0000 MHz + * 0111: 100 * 8 / 9 = 88.8889 MHz + * 1000: 100 * 7 / 8 = 87.5000 MHz + */ static const struct freq_desc freq_desc_cht = { - 1, { 83300, 100000, 133300, 116700, 80000, 93300, 90000, 88900, 87500 } + .use_msr_plat = true, + .muldiv = { { 5, 6 }, { 1, 1 }, { 4, 3 }, { 7, 6 }, + { 4, 5 }, { 14, 15 }, { 9, 10 }, { 8, 9 }, + { 7, 8 } }, + .mask = 0x0f, }; +/* + * Merriefield SDM MSR_FSB_FREQ frequencies simplified PLL model: + * 0001: 100 * 1 / 1 = 100.0000 MHz + * 0010: 100 * 4 / 3 = 133.3333 MHz + */ static const struct freq_desc freq_desc_tng = { - 1, { 0, 100000, 133300, 0, 0, 0, 0, 0 } + .use_msr_plat = true, + .muldiv = { { 0, 0 }, { 1, 1 }, { 4, 3 } }, + .mask = 0x07, }; +/* + * Moorefield SDM MSR_FSB_FREQ frequencies simplified PLL model: + * 0000: 100 * 5 / 6 = 83.3333 MHz + * 0001: 100 * 1 / 1 = 100.0000 MHz + * 0010: 100 * 4 / 3 = 133.3333 MHz + * 0011: 100 * 1 / 1 = 100.0000 MHz + */ static const struct freq_desc freq_desc_ann = { - 1, { 83300, 100000, 133300, 100000, 0, 0, 0, 0 } + .use_msr_plat = true, + .muldiv = { { 5, 6 }, { 1, 1 }, { 4, 3 }, { 1, 1 } }, + .mask = 0x0f, }; static const struct x86_cpu_id tsc_msr_cpu_ids[] = { @@ -71,22 +146,24 @@ static const struct x86_cpu_id tsc_msr_cpu_ids[] = { /* * MSR-based CPU/TSC frequency discovery for certain CPUs. * - * Set global "lapic_timer_frequency" to bus_clock_cycles/jiffy + * Set global "lapic_timer_period" to bus_clock_cycles/jiffy * Return processor base frequency in KHz, or 0 on failure. */ unsigned long cpu_khz_from_msr(void) { - u32 lo, hi, ratio, freq; + u32 lo, hi, ratio, freq, tscref; const struct freq_desc *freq_desc; const struct x86_cpu_id *id; + const struct muldiv *md; unsigned long res; + int index; id = x86_match_cpu(tsc_msr_cpu_ids); if (!id) return 0; freq_desc = (struct freq_desc *)id->driver_data; - if (freq_desc->msr_plat) { + if (freq_desc->use_msr_plat) { rdmsr(MSR_PLATFORM_INFO, lo, hi); ratio = (lo >> 8) & 0xff; } else { @@ -96,15 +173,31 @@ unsigned long cpu_khz_from_msr(void) /* Get FSB FREQ ID */ rdmsr(MSR_FSB_FREQ, lo, hi); + index = lo & freq_desc->mask; + md = &freq_desc->muldiv[index]; - /* Map CPU reference clock freq ID(0-7) to CPU reference clock freq(KHz) */ - freq = freq_desc->freqs[lo & 0x7]; + /* + * Note this also catches cases where the index points to an unpopulated + * part of muldiv, in that case the else will set freq and res to 0. + */ + if (md->divider) { + tscref = TSC_REFERENCE_KHZ * md->multiplier; + freq = DIV_ROUND_CLOSEST(tscref, md->divider); + /* + * Multiplying by ratio before the division has better + * accuracy than just calculating freq * ratio. + */ + res = DIV_ROUND_CLOSEST(tscref * ratio, md->divider); + } else { + freq = freq_desc->freqs[index]; + res = freq * ratio; + } - /* TSC frequency = maximum resolved freq * maximum resolved bus ratio */ - res = freq * ratio; + if (freq == 0) + pr_err("Error MSR_FSB_FREQ index %d is unknown\n", index); #ifdef CONFIG_X86_LOCAL_APIC - lapic_timer_frequency = (freq * 1000) / HZ; + lapic_timer_period = (freq * 1000) / HZ; #endif /* diff --git a/arch/x86/kernel/unwind_orc.c b/arch/x86/kernel/unwind_orc.c index 332ae6530fa8..187a86e0e753 100644 --- a/arch/x86/kernel/unwind_orc.c +++ b/arch/x86/kernel/unwind_orc.c @@ -142,9 +142,6 @@ static struct orc_entry *orc_find(unsigned long ip) { static struct orc_entry *orc; - if (!orc_init) - return NULL; - if (ip == 0) return &null_orc_entry; @@ -314,12 +311,19 @@ EXPORT_SYMBOL_GPL(unwind_get_return_address); unsigned long *unwind_get_return_address_ptr(struct unwind_state *state) { + struct task_struct *task = state->task; + if (unwind_done(state)) return NULL; if (state->regs) return &state->regs->ip; + if (task != current && state->sp == task->thread.sp) { + struct inactive_task_frame *frame = (void *)task->thread.sp; + return &frame->ret_addr; + } + if (state->sp) return (unsigned long *)state->sp - 1; @@ -378,9 +382,38 @@ static bool deref_stack_iret_regs(struct unwind_state *state, unsigned long addr return true; } +/* + * If state->regs is non-NULL, and points to a full pt_regs, just get the reg + * value from state->regs. + * + * Otherwise, if state->regs just points to IRET regs, and the previous frame + * had full regs, it's safe to get the value from the previous regs. This can + * happen when early/late IRQ entry code gets interrupted by an NMI. + */ +static bool get_reg(struct unwind_state *state, unsigned int reg_off, + unsigned long *val) +{ + unsigned int reg = reg_off/8; + + if (!state->regs) + return false; + + if (state->full_regs) { + *val = ((unsigned long *)state->regs)[reg]; + return true; + } + + if (state->prev_regs) { + *val = ((unsigned long *)state->prev_regs)[reg]; + return true; + } + + return false; +} + bool unwind_next_frame(struct unwind_state *state) { - unsigned long ip_p, sp, orig_ip = state->ip, prev_sp = state->sp; + unsigned long ip_p, sp, tmp, orig_ip = state->ip, prev_sp = state->sp; enum stack_type prev_type = state->stack_info.type; struct orc_entry *orc; bool indirect = false; @@ -398,8 +431,11 @@ bool unwind_next_frame(struct unwind_state *state) /* * Find the orc_entry associated with the text address. * - * Decrement call return addresses by one so they work for sibling - * calls and calls to noreturn functions. + * For a call frame (as opposed to a signal frame), state->ip points to + * the instruction after the call. That instruction's stack layout + * could be different from the call instruction's layout, for example + * if the call was to a noreturn function. So get the ORC data for the + * call instruction itself. */ orc = orc_find(state->signal ? state->ip : state->ip - 1); if (!orc) { @@ -442,39 +478,35 @@ bool unwind_next_frame(struct unwind_state *state) break; case ORC_REG_R10: - if (!state->regs || !state->full_regs) { + if (!get_reg(state, offsetof(struct pt_regs, r10), &sp)) { orc_warn("missing regs for base reg R10 at ip %pB\n", (void *)state->ip); goto err; } - sp = state->regs->r10; break; case ORC_REG_R13: - if (!state->regs || !state->full_regs) { + if (!get_reg(state, offsetof(struct pt_regs, r13), &sp)) { orc_warn("missing regs for base reg R13 at ip %pB\n", (void *)state->ip); goto err; } - sp = state->regs->r13; break; case ORC_REG_DI: - if (!state->regs || !state->full_regs) { + if (!get_reg(state, offsetof(struct pt_regs, di), &sp)) { orc_warn("missing regs for base reg DI at ip %pB\n", (void *)state->ip); goto err; } - sp = state->regs->di; break; case ORC_REG_DX: - if (!state->regs || !state->full_regs) { + if (!get_reg(state, offsetof(struct pt_regs, dx), &sp)) { orc_warn("missing regs for base reg DX at ip %pB\n", (void *)state->ip); goto err; } - sp = state->regs->dx; break; default: @@ -501,6 +533,7 @@ bool unwind_next_frame(struct unwind_state *state) state->sp = sp; state->regs = NULL; + state->prev_regs = NULL; state->signal = false; break; @@ -512,6 +545,7 @@ bool unwind_next_frame(struct unwind_state *state) } state->regs = (struct pt_regs *)sp; + state->prev_regs = NULL; state->full_regs = true; state->signal = true; break; @@ -523,6 +557,8 @@ bool unwind_next_frame(struct unwind_state *state) goto err; } + if (state->full_regs) + state->prev_regs = state->regs; state->regs = (void *)sp - IRET_FRAME_OFFSET; state->full_regs = false; state->signal = true; @@ -531,14 +567,14 @@ bool unwind_next_frame(struct unwind_state *state) default: orc_warn("unknown .orc_unwind entry type %d for ip %pB\n", orc->type, (void *)orig_ip); - break; + goto err; } /* Find BP: */ switch (orc->bp_reg) { case ORC_REG_UNDEFINED: - if (state->regs && state->full_regs) - state->bp = state->regs->bp; + if (get_reg(state, offsetof(struct pt_regs, bp), &tmp)) + state->bp = tmp; break; case ORC_REG_PREV_SP: @@ -585,17 +621,20 @@ void __unwind_start(struct unwind_state *state, struct task_struct *task, memset(state, 0, sizeof(*state)); state->task = task; + if (!orc_init) + goto err; + /* * Refuse to unwind the stack of a task while it's executing on another * CPU. This check is racy, but that's ok: the unwinder has other * checks to prevent it from going off the rails. */ if (task_on_another_cpu(task)) - goto done; + goto err; if (regs) { if (user_mode(regs)) - goto done; + goto the_end; state->ip = regs->ip; state->sp = regs->sp; @@ -617,6 +656,7 @@ void __unwind_start(struct unwind_state *state, struct task_struct *task, state->sp = task->thread.sp; state->bp = READ_ONCE_NOCHECK(frame->bp); state->ip = READ_ONCE_NOCHECK(frame->ret_addr); + state->signal = (void *)state->ip == ret_from_fork; } if (get_stack_info((unsigned long *)state->sp, state->task, @@ -628,6 +668,7 @@ void __unwind_start(struct unwind_state *state, struct task_struct *task, * generate some kind of backtrace if this happens. */ void *next_page = (void *)PAGE_ALIGN((unsigned long)state->sp); + state->error = true; if (get_stack_info(next_page, state->task, &state->stack_info, &state->stack_mask)) return; @@ -648,13 +689,14 @@ void __unwind_start(struct unwind_state *state, struct task_struct *task, /* Otherwise, skip ahead to the user-specified starting frame: */ while (!unwind_done(state) && (!on_stack(&state->stack_info, first_frame, sizeof(long)) || - state->sp <= (unsigned long)first_frame)) + state->sp < (unsigned long)first_frame)) unwind_next_frame(state); return; -done: +err: + state->error = true; +the_end: state->stack_info.type = STACK_TYPE_UNKNOWN; - return; } EXPORT_SYMBOL_GPL(__unwind_start); diff --git a/arch/x86/kernel/vmlinux.lds.S b/arch/x86/kernel/vmlinux.lds.S index 4d1517022a14..96d8025ea1b0 100644 --- a/arch/x86/kernel/vmlinux.lds.S +++ b/arch/x86/kernel/vmlinux.lds.S @@ -36,13 +36,13 @@ OUTPUT_FORMAT(CONFIG_OUTPUT_FORMAT) #ifdef CONFIG_X86_32 OUTPUT_ARCH(i386) ENTRY(phys_startup_32) -jiffies = jiffies_64; #else OUTPUT_ARCH(i386:x86-64) ENTRY(phys_startup_64) -jiffies_64 = jiffies; #endif +jiffies = jiffies_64; + #if defined(CONFIG_X86_64) /* * On 64-bit, align RODATA to 2MB so we retain large page mappings for @@ -362,6 +362,7 @@ SECTIONS .bss : AT(ADDR(.bss) - LOAD_OFFSET) { __bss_start = .; *(.bss..page_aligned) + . = ALIGN(PAGE_SIZE); *(BSS_MAIN) BSS_DECRYPTED . = ALIGN(PAGE_SIZE); diff --git a/arch/x86/kvm/cpuid.c b/arch/x86/kvm/cpuid.c index 4992e7c99588..e8e7d053c7b4 100644 --- a/arch/x86/kvm/cpuid.c +++ b/arch/x86/kvm/cpuid.c @@ -333,6 +333,7 @@ static inline int __do_cpuid_ent(struct kvm_cpuid_entry2 *entry, u32 function, unsigned f_umip = kvm_x86_ops->umip_emulated() ? F(UMIP) : 0; unsigned f_intel_pt = kvm_x86_ops->pt_supported() ? F(INTEL_PT) : 0; unsigned f_la57 = 0; + unsigned f_pku = kvm_x86_ops->pku_supported() ? F(PKU) : 0; /* cpuid 1.edx */ const u32 kvm_cpuid_1_edx_x86_features = @@ -399,7 +400,7 @@ static inline int __do_cpuid_ent(struct kvm_cpuid_entry2 *entry, u32 function, /* cpuid 7.0.ecx*/ const u32 kvm_cpuid_7_0_ecx_x86_features = - F(AVX512VBMI) | F(LA57) | F(PKU) | 0 /*OSPKE*/ | + F(AVX512VBMI) | F(LA57) | 0 /*PKU*/ | 0 /*OSPKE*/ | F(AVX512_VPOPCNTDQ) | F(UMIP) | F(AVX512_VBMI2) | F(GFNI) | F(VAES) | F(VPCLMULQDQ) | F(AVX512_VNNI) | F(AVX512_BITALG) | F(CLDEMOTE) | F(MOVDIRI) | F(MOVDIR64B); @@ -415,7 +416,7 @@ static inline int __do_cpuid_ent(struct kvm_cpuid_entry2 *entry, u32 function, r = -E2BIG; - if (*nent >= maxnent) + if (WARN_ON(*nent >= maxnent)) goto out; do_cpuid_1_ent(entry, function, index); @@ -494,6 +495,7 @@ static inline int __do_cpuid_ent(struct kvm_cpuid_entry2 *entry, u32 function, /* Set LA57 based on hardware capability. */ entry->ecx |= f_la57; entry->ecx |= f_umip; + entry->ecx |= f_pku; /* PKU is not yet implemented for shadow paging. */ if (!tdp_enabled || !boot_cpu_has(X86_FEATURE_OSPKE)) entry->ecx &= ~F(PKU); @@ -733,6 +735,9 @@ out: static int do_cpuid_ent(struct kvm_cpuid_entry2 *entry, u32 func, u32 idx, int *nent, int maxnent, unsigned int type) { + if (*nent >= maxnent) + return -E2BIG; + if (type == KVM_GET_EMULATED_CPUID) return __do_cpuid_ent_emulated(entry, func, idx, nent, maxnent); diff --git a/arch/x86/kvm/emulate.c b/arch/x86/kvm/emulate.c index 2fe9912aeed7..5560ac478135 100644 --- a/arch/x86/kvm/emulate.c +++ b/arch/x86/kvm/emulate.c @@ -22,6 +22,7 @@ #include "kvm_cache_regs.h" #include <asm/kvm_emulate.h> #include <linux/stringify.h> +#include <asm/fpu/api.h> #include <asm/debugreg.h> #include <asm/nospec-branch.h> @@ -1057,8 +1058,23 @@ static void fetch_register_operand(struct operand *op) } } +static void emulator_get_fpu(void) +{ + fpregs_lock(); + + fpregs_assert_state_consistent(); + if (test_thread_flag(TIF_NEED_FPU_LOAD)) + switch_fpu_return(); +} + +static void emulator_put_fpu(void) +{ + fpregs_unlock(); +} + static void read_sse_reg(struct x86_emulate_ctxt *ctxt, sse128_t *data, int reg) { + emulator_get_fpu(); switch (reg) { case 0: asm("movdqa %%xmm0, %0" : "=m"(*data)); break; case 1: asm("movdqa %%xmm1, %0" : "=m"(*data)); break; @@ -1080,11 +1096,13 @@ static void read_sse_reg(struct x86_emulate_ctxt *ctxt, sse128_t *data, int reg) #endif default: BUG(); } + emulator_put_fpu(); } static void write_sse_reg(struct x86_emulate_ctxt *ctxt, sse128_t *data, int reg) { + emulator_get_fpu(); switch (reg) { case 0: asm("movdqa %0, %%xmm0" : : "m"(*data)); break; case 1: asm("movdqa %0, %%xmm1" : : "m"(*data)); break; @@ -1106,10 +1124,12 @@ static void write_sse_reg(struct x86_emulate_ctxt *ctxt, sse128_t *data, #endif default: BUG(); } + emulator_put_fpu(); } static void read_mmx_reg(struct x86_emulate_ctxt *ctxt, u64 *data, int reg) { + emulator_get_fpu(); switch (reg) { case 0: asm("movq %%mm0, %0" : "=m"(*data)); break; case 1: asm("movq %%mm1, %0" : "=m"(*data)); break; @@ -1121,10 +1141,12 @@ static void read_mmx_reg(struct x86_emulate_ctxt *ctxt, u64 *data, int reg) case 7: asm("movq %%mm7, %0" : "=m"(*data)); break; default: BUG(); } + emulator_put_fpu(); } static void write_mmx_reg(struct x86_emulate_ctxt *ctxt, u64 *data, int reg) { + emulator_get_fpu(); switch (reg) { case 0: asm("movq %0, %%mm0" : : "m"(*data)); break; case 1: asm("movq %0, %%mm1" : : "m"(*data)); break; @@ -1136,6 +1158,7 @@ static void write_mmx_reg(struct x86_emulate_ctxt *ctxt, u64 *data, int reg) case 7: asm("movq %0, %%mm7" : : "m"(*data)); break; default: BUG(); } + emulator_put_fpu(); } static int em_fninit(struct x86_emulate_ctxt *ctxt) @@ -1143,7 +1166,9 @@ static int em_fninit(struct x86_emulate_ctxt *ctxt) if (ctxt->ops->get_cr(ctxt, 0) & (X86_CR0_TS | X86_CR0_EM)) return emulate_nm(ctxt); + emulator_get_fpu(); asm volatile("fninit"); + emulator_put_fpu(); return X86EMUL_CONTINUE; } @@ -1154,7 +1179,9 @@ static int em_fnstcw(struct x86_emulate_ctxt *ctxt) if (ctxt->ops->get_cr(ctxt, 0) & (X86_CR0_TS | X86_CR0_EM)) return emulate_nm(ctxt); + emulator_get_fpu(); asm volatile("fnstcw %0": "+m"(fcw)); + emulator_put_fpu(); ctxt->dst.val = fcw; @@ -1168,7 +1195,9 @@ static int em_fnstsw(struct x86_emulate_ctxt *ctxt) if (ctxt->ops->get_cr(ctxt, 0) & (X86_CR0_TS | X86_CR0_EM)) return emulate_nm(ctxt); + emulator_get_fpu(); asm volatile("fnstsw %0": "+m"(fsw)); + emulator_put_fpu(); ctxt->dst.val = fsw; @@ -4076,8 +4105,12 @@ static int em_fxsave(struct x86_emulate_ctxt *ctxt) if (rc != X86EMUL_CONTINUE) return rc; + emulator_get_fpu(); + rc = asm_safe("fxsave %[fx]", , [fx] "+m"(fx_state)); + emulator_put_fpu(); + if (rc != X86EMUL_CONTINUE) return rc; @@ -4120,6 +4153,8 @@ static int em_fxrstor(struct x86_emulate_ctxt *ctxt) if (rc != X86EMUL_CONTINUE) return rc; + emulator_get_fpu(); + if (size < __fxstate_size(16)) { rc = fxregs_fixup(&fx_state, size); if (rc != X86EMUL_CONTINUE) @@ -4135,6 +4170,8 @@ static int em_fxrstor(struct x86_emulate_ctxt *ctxt) rc = asm_safe("fxrstor %[fx]", : [fx] "m"(fx_state)); out: + emulator_put_fpu(); + return rc; } @@ -5121,6 +5158,7 @@ int x86_decode_insn(struct x86_emulate_ctxt *ctxt, void *insn, int insn_len) ctxt->fetch.ptr = ctxt->fetch.data; ctxt->fetch.end = ctxt->fetch.data + insn_len; ctxt->opcode_len = 1; + ctxt->intercept = x86_intercept_none; if (insn_len > 0) memcpy(ctxt->fetch.data, insn, insn_len); else { @@ -5173,16 +5211,28 @@ int x86_decode_insn(struct x86_emulate_ctxt *ctxt, void *insn, int insn_len) ctxt->ad_bytes = def_ad_bytes ^ 6; break; case 0x26: /* ES override */ + has_seg_override = true; + ctxt->seg_override = VCPU_SREG_ES; + break; case 0x2e: /* CS override */ + has_seg_override = true; + ctxt->seg_override = VCPU_SREG_CS; + break; case 0x36: /* SS override */ + has_seg_override = true; + ctxt->seg_override = VCPU_SREG_SS; + break; case 0x3e: /* DS override */ has_seg_override = true; - ctxt->seg_override = (ctxt->b >> 3) & 3; + ctxt->seg_override = VCPU_SREG_DS; break; case 0x64: /* FS override */ + has_seg_override = true; + ctxt->seg_override = VCPU_SREG_FS; + break; case 0x65: /* GS override */ has_seg_override = true; - ctxt->seg_override = ctxt->b & 7; + ctxt->seg_override = VCPU_SREG_GS; break; case 0x40 ... 0x4f: /* REX */ if (mode != X86EMUL_MODE_PROT64) @@ -5266,10 +5316,15 @@ done_prefixes: } break; case Escape: - if (ctxt->modrm > 0xbf) - opcode = opcode.u.esc->high[ctxt->modrm - 0xc0]; - else + if (ctxt->modrm > 0xbf) { + size_t size = ARRAY_SIZE(opcode.u.esc->high); + u32 index = array_index_nospec( + ctxt->modrm - 0xc0, size); + + opcode = opcode.u.esc->high[index]; + } else { opcode = opcode.u.esc->op[(ctxt->modrm >> 3) & 7]; + } break; case InstrDual: if ((ctxt->modrm >> 6) == 3) @@ -5411,7 +5466,9 @@ static int flush_pending_x87_faults(struct x86_emulate_ctxt *ctxt) { int rc; + emulator_get_fpu(); rc = asm_safe("fwait"); + emulator_put_fpu(); if (unlikely(rc != X86EMUL_CONTINUE)) return emulate_exception(ctxt, MF_VECTOR, 0, false); diff --git a/arch/x86/kvm/hyperv.c b/arch/x86/kvm/hyperv.c index 72200998687c..2d4c1fe5f380 100644 --- a/arch/x86/kvm/hyperv.c +++ b/arch/x86/kvm/hyperv.c @@ -808,11 +808,12 @@ static int kvm_hv_msr_get_crash_data(struct kvm_vcpu *vcpu, u32 index, u64 *pdata) { struct kvm_hv *hv = &vcpu->kvm->arch.hyperv; + size_t size = ARRAY_SIZE(hv->hv_crash_param); - if (WARN_ON_ONCE(index >= ARRAY_SIZE(hv->hv_crash_param))) + if (WARN_ON_ONCE(index >= size)) return -EINVAL; - *pdata = hv->hv_crash_param[index]; + *pdata = hv->hv_crash_param[array_index_nospec(index, size)]; return 0; } @@ -851,11 +852,12 @@ static int kvm_hv_msr_set_crash_data(struct kvm_vcpu *vcpu, u32 index, u64 data) { struct kvm_hv *hv = &vcpu->kvm->arch.hyperv; + size_t size = ARRAY_SIZE(hv->hv_crash_param); - if (WARN_ON_ONCE(index >= ARRAY_SIZE(hv->hv_crash_param))) + if (WARN_ON_ONCE(index >= size)) return -EINVAL; - hv->hv_crash_param[index] = data; + hv->hv_crash_param[array_index_nospec(index, size)] = data; return 0; } diff --git a/arch/x86/kvm/i8259.c b/arch/x86/kvm/i8259.c index 8b38bb4868a6..629a09ca9860 100644 --- a/arch/x86/kvm/i8259.c +++ b/arch/x86/kvm/i8259.c @@ -460,10 +460,14 @@ static int picdev_write(struct kvm_pic *s, switch (addr) { case 0x20: case 0x21: + pic_lock(s); + pic_ioport_write(&s->pics[0], addr, data); + pic_unlock(s); + break; case 0xa0: case 0xa1: pic_lock(s); - pic_ioport_write(&s->pics[addr >> 7], addr, data); + pic_ioport_write(&s->pics[1], addr, data); pic_unlock(s); break; case 0x4d0: diff --git a/arch/x86/kvm/ioapic.c b/arch/x86/kvm/ioapic.c index 1add1bc881e2..9446613625e1 100644 --- a/arch/x86/kvm/ioapic.c +++ b/arch/x86/kvm/ioapic.c @@ -36,6 +36,7 @@ #include <linux/io.h> #include <linux/slab.h> #include <linux/export.h> +#include <linux/nospec.h> #include <asm/processor.h> #include <asm/page.h> #include <asm/current.h> @@ -73,13 +74,14 @@ static unsigned long ioapic_read_indirect(struct kvm_ioapic *ioapic, default: { u32 redir_index = (ioapic->ioregsel - 0x10) >> 1; - u64 redir_content; + u64 redir_content = ~0ULL; - if (redir_index < IOAPIC_NUM_PINS) - redir_content = - ioapic->redirtbl[redir_index].bits; - else - redir_content = ~0ULL; + if (redir_index < IOAPIC_NUM_PINS) { + u32 index = array_index_nospec( + redir_index, IOAPIC_NUM_PINS); + + redir_content = ioapic->redirtbl[index].bits; + } result = (ioapic->ioregsel & 0x1) ? (redir_content >> 32) & 0xffffffff : @@ -297,6 +299,7 @@ static void ioapic_write_indirect(struct kvm_ioapic *ioapic, u32 val) ioapic_debug("change redir index %x val %x\n", index, val); if (index >= IOAPIC_NUM_PINS) return; + index = array_index_nospec(index, IOAPIC_NUM_PINS); e = &ioapic->redirtbl[index]; mask_before = e->fields.mask; /* Preserve read-only fields */ diff --git a/arch/x86/kvm/irq_comm.c b/arch/x86/kvm/irq_comm.c index 924b3bd5a7b7..e3ab10d6b12e 100644 --- a/arch/x86/kvm/irq_comm.c +++ b/arch/x86/kvm/irq_comm.c @@ -416,7 +416,7 @@ void kvm_scan_ioapic_routes(struct kvm_vcpu *vcpu, kvm_set_msi_irq(vcpu->kvm, entry, &irq); - if (irq.level && kvm_apic_match_dest(vcpu, NULL, 0, + if (irq.trig_mode && kvm_apic_match_dest(vcpu, NULL, 0, irq.dest_id, irq.dest_mode)) __set_bit(irq.vector, ioapic_handled_vectors); } diff --git a/arch/x86/kvm/kvm_cache_regs.h b/arch/x86/kvm/kvm_cache_regs.h index 1cc6c47dc77e..341f58a01de0 100644 --- a/arch/x86/kvm/kvm_cache_regs.h +++ b/arch/x86/kvm/kvm_cache_regs.h @@ -7,7 +7,7 @@ #define KVM_POSSIBLE_CR0_GUEST_BITS X86_CR0_TS #define KVM_POSSIBLE_CR4_GUEST_BITS \ (X86_CR4_PVI | X86_CR4_DE | X86_CR4_PCE | X86_CR4_OSFXSR \ - | X86_CR4_OSXMMEXCPT | X86_CR4_LA57 | X86_CR4_PGE) + | X86_CR4_OSXMMEXCPT | X86_CR4_LA57 | X86_CR4_PGE | X86_CR4_TSD) #define BUILD_KVM_GPR_ACCESSORS(lname, uname) \ static __always_inline unsigned long kvm_##lname##_read(struct kvm_vcpu *vcpu)\ diff --git a/arch/x86/kvm/lapic.c b/arch/x86/kvm/lapic.c index 8d22c79f5333..9483b9da8864 100644 --- a/arch/x86/kvm/lapic.c +++ b/arch/x86/kvm/lapic.c @@ -59,9 +59,6 @@ #define APIC_VERSION (0x14UL | ((KVM_APIC_LVT_NUM - 1) << 16)) #define LAPIC_MMIO_LENGTH (1 << 12) /* followed define is not in apicdef.h */ -#define APIC_SHORT_MASK 0xc0000 -#define APIC_DEST_NOSHORT 0x0 -#define APIC_DEST_MASK 0x800 #define MAX_APIC_VECTOR 256 #define APIC_VECTORS_PER_REG 32 @@ -635,9 +632,11 @@ static inline bool pv_eoi_enabled(struct kvm_vcpu *vcpu) static bool pv_eoi_get_pending(struct kvm_vcpu *vcpu) { u8 val; - if (pv_eoi_get_user(vcpu, &val) < 0) + if (pv_eoi_get_user(vcpu, &val) < 0) { apic_debug("Can't read EOI MSR value: 0x%llx\n", (unsigned long long)vcpu->arch.pv_eoi.msr_val); + return false; + } return val & 0x1; } @@ -1063,11 +1062,8 @@ static int __apic_accept_irq(struct kvm_lapic *apic, int delivery_mode, apic_clear_vector(vector, apic->regs + APIC_TMR); } - if (vcpu->arch.apicv_active) - kvm_x86_ops->deliver_posted_interrupt(vcpu, vector); - else { + if (kvm_x86_ops->deliver_posted_interrupt(vcpu, vector)) { kvm_lapic_set_irr(vector, apic); - kvm_make_request(KVM_REQ_EVENT, vcpu); kvm_vcpu_kick(vcpu); } @@ -1918,15 +1914,20 @@ int kvm_lapic_reg_write(struct kvm_lapic *apic, u32 reg, u32 val) case APIC_LVTTHMR: case APIC_LVTPC: case APIC_LVT1: - case APIC_LVTERR: + case APIC_LVTERR: { /* TODO: Check vector */ + size_t size; + u32 index; + if (!kvm_apic_sw_enabled(apic)) val |= APIC_LVT_MASKED; - - val &= apic_lvt_mask[(reg - APIC_LVTT) >> 4]; + size = ARRAY_SIZE(apic_lvt_mask); + index = array_index_nospec( + (reg - APIC_LVTT) >> 4, size); + val &= apic_lvt_mask[index]; kvm_lapic_set_reg(apic, reg, val); - break; + } case APIC_LVTT: if (!kvm_apic_sw_enabled(apic)) @@ -2086,7 +2087,7 @@ void kvm_set_lapic_tscdeadline_msr(struct kvm_vcpu *vcpu, u64 data) { struct kvm_lapic *apic = vcpu->arch.apic; - if (!lapic_in_kernel(vcpu) || apic_lvtt_oneshot(apic) || + if (!kvm_apic_present(vcpu) || apic_lvtt_oneshot(apic) || apic_lvtt_period(apic)) return; diff --git a/arch/x86/kvm/lapic.h b/arch/x86/kvm/lapic.h index d6d049ba3045..29980b4cc57b 100644 --- a/arch/x86/kvm/lapic.h +++ b/arch/x86/kvm/lapic.h @@ -10,8 +10,9 @@ #define KVM_APIC_SIPI 1 #define KVM_APIC_LVT_NUM 6 -#define KVM_APIC_SHORT_MASK 0xc0000 -#define KVM_APIC_DEST_MASK 0x800 +#define APIC_SHORT_MASK 0xc0000 +#define APIC_DEST_NOSHORT 0x0 +#define APIC_DEST_MASK 0x800 #define APIC_BUS_CYCLE_NS 1 #define APIC_BUS_FREQUENCY (1000000000ULL / APIC_BUS_CYCLE_NS) diff --git a/arch/x86/kvm/mmu.c b/arch/x86/kvm/mmu.c index 35348302a6e0..bc5154c57b4e 100644 --- a/arch/x86/kvm/mmu.c +++ b/arch/x86/kvm/mmu.c @@ -154,11 +154,6 @@ module_param(dbg, bool, 0644); #define PT64_PERM_MASK (PT_PRESENT_MASK | PT_WRITABLE_MASK | shadow_user_mask \ | shadow_x_mask | shadow_nx_mask | shadow_me_mask) -#define ACC_EXEC_MASK 1 -#define ACC_WRITE_MASK PT_WRITABLE_MASK -#define ACC_USER_MASK PT_USER_MASK -#define ACC_ALL (ACC_EXEC_MASK | ACC_WRITE_MASK | ACC_USER_MASK) - /* The mask for the R/X bits in EPT PTEs */ #define PT64_EPT_READABLE_MASK 0x1ull #define PT64_EPT_EXECUTABLE_MASK 0x4ull @@ -242,6 +237,7 @@ static u64 __read_mostly shadow_accessed_mask; static u64 __read_mostly shadow_dirty_mask; static u64 __read_mostly shadow_mmio_mask; static u64 __read_mostly shadow_mmio_value; +static u64 __read_mostly shadow_mmio_access_mask; static u64 __read_mostly shadow_present_mask; static u64 __read_mostly shadow_me_mask; @@ -284,6 +280,11 @@ static const u64 shadow_nonpresent_or_rsvd_mask_len = 5; */ static u64 __read_mostly shadow_nonpresent_or_rsvd_lower_gfn_mask; +/* + * The number of non-reserved physical address bits irrespective of features + * that repurpose legal bits, e.g. MKTME. + */ +u8 __read_mostly shadow_phys_bits; static void mmu_spte_set(u64 *sptep, u64 spte); static union kvm_mmu_page_role @@ -318,11 +319,15 @@ static void kvm_flush_remote_tlbs_with_address(struct kvm *kvm, kvm_flush_remote_tlbs_with_range(kvm, &range); } -void kvm_mmu_set_mmio_spte_mask(u64 mmio_mask, u64 mmio_value) +void kvm_mmu_set_mmio_spte_mask(u64 mmio_mask, u64 mmio_value, u64 access_mask) { + BUG_ON((u64)(unsigned)access_mask != access_mask); BUG_ON((mmio_mask & mmio_value) != mmio_value); + WARN_ON(mmio_value & (shadow_nonpresent_or_rsvd_mask << shadow_nonpresent_or_rsvd_mask_len)); + WARN_ON(mmio_value & shadow_nonpresent_or_rsvd_lower_gfn_mask); shadow_mmio_value = mmio_value | SPTE_SPECIAL_MASK; shadow_mmio_mask = mmio_mask | SPTE_SPECIAL_MASK; + shadow_mmio_access_mask = access_mask; } EXPORT_SYMBOL_GPL(kvm_mmu_set_mmio_spte_mask); @@ -413,7 +418,7 @@ static void mark_mmio_spte(struct kvm_vcpu *vcpu, u64 *sptep, u64 gfn, u64 mask = generation_mmio_spte_mask(gen); u64 gpa = gfn << PAGE_SHIFT; - access &= ACC_WRITE_MASK | ACC_USER_MASK; + access &= shadow_mmio_access_mask; mask |= shadow_mmio_value | access; mask |= gpa | shadow_nonpresent_or_rsvd_mask; mask |= (gpa & shadow_nonpresent_or_rsvd_mask) @@ -440,8 +445,7 @@ static gfn_t get_mmio_spte_gfn(u64 spte) static unsigned get_mmio_spte_access(u64 spte) { - u64 mask = generation_mmio_spte_mask(MMIO_SPTE_GEN_MASK) | shadow_mmio_mask; - return (spte & ~mask) & ~PAGE_MASK; + return spte & shadow_mmio_access_mask; } static bool set_mmio_spte(struct kvm_vcpu *vcpu, u64 *sptep, gfn_t gfn, @@ -496,6 +500,25 @@ void kvm_mmu_set_mask_ptes(u64 user_mask, u64 accessed_mask, } EXPORT_SYMBOL_GPL(kvm_mmu_set_mask_ptes); +static u8 kvm_get_shadow_phys_bits(void) +{ + /* + * boot_cpu_data.x86_phys_bits is reduced when MKTME or SME are detected + * in CPU detection code, but the processor treats those reduced bits as + * 'keyID' thus they are not reserved bits. Therefore KVM needs to look at + * the physical address bits reported by CPUID. + */ + if (likely(boot_cpu_data.extended_cpuid_level >= 0x80000008)) + return cpuid_eax(0x80000008) & 0xff; + + /* + * Quite weird to have VMX or SVM but not MAXPHYADDR; probably a VM with + * custom CPUID. Proceed with whatever the kernel found since these features + * aren't virtualizable (SME/SEV also require CPUIDs higher than 0x80000008). + */ + return boot_cpu_data.x86_phys_bits; +} + static void kvm_mmu_reset_all_pte_masks(void) { u8 low_phys_bits; @@ -509,6 +532,8 @@ static void kvm_mmu_reset_all_pte_masks(void) shadow_present_mask = 0; shadow_acc_track_mask = 0; + shadow_phys_bits = kvm_get_shadow_phys_bits(); + /* * If the CPU has 46 or less physical address bits, then set an * appropriate mask to guard against L1TF attacks. Otherwise, it is @@ -520,16 +545,15 @@ static void kvm_mmu_reset_all_pte_masks(void) * the most significant bits of legal physical address space. */ shadow_nonpresent_or_rsvd_mask = 0; - low_phys_bits = boot_cpu_data.x86_cache_bits; - if (boot_cpu_data.x86_cache_bits < - 52 - shadow_nonpresent_or_rsvd_mask_len) { + low_phys_bits = boot_cpu_data.x86_phys_bits; + if (boot_cpu_has_bug(X86_BUG_L1TF) && + !WARN_ON_ONCE(boot_cpu_data.x86_cache_bits >= + 52 - shadow_nonpresent_or_rsvd_mask_len)) { + low_phys_bits = boot_cpu_data.x86_cache_bits + - shadow_nonpresent_or_rsvd_mask_len; shadow_nonpresent_or_rsvd_mask = - rsvd_bits(boot_cpu_data.x86_cache_bits - - shadow_nonpresent_or_rsvd_mask_len, - boot_cpu_data.x86_cache_bits - 1); - low_phys_bits -= shadow_nonpresent_or_rsvd_mask_len; - } else - WARN_ON_ONCE(boot_cpu_has_bug(X86_BUG_L1TF)); + rsvd_bits(low_phys_bits, boot_cpu_data.x86_cache_bits - 1); + } shadow_nonpresent_or_rsvd_lower_gfn_mask = GENMASK_ULL(low_phys_bits - 1, PAGE_SHIFT); @@ -1220,12 +1244,12 @@ static bool mmu_gfn_lpage_is_disallowed(struct kvm_vcpu *vcpu, gfn_t gfn, return __mmu_gfn_lpage_is_disallowed(gfn, level, slot); } -static int host_mapping_level(struct kvm *kvm, gfn_t gfn) +static int host_mapping_level(struct kvm_vcpu *vcpu, gfn_t gfn) { unsigned long page_size; int i, ret = 0; - page_size = kvm_host_page_size(kvm, gfn); + page_size = kvm_host_page_size(vcpu, gfn); for (i = PT_PAGE_TABLE_LEVEL; i <= PT_MAX_HUGEPAGE_LEVEL; ++i) { if (page_size >= KVM_HPAGE_SIZE(i)) @@ -1275,7 +1299,7 @@ static int mapping_level(struct kvm_vcpu *vcpu, gfn_t large_gfn, if (unlikely(*force_pt_level)) return PT_PAGE_TABLE_LEVEL; - host_level = host_mapping_level(vcpu->kvm, large_gfn); + host_level = host_mapping_level(vcpu, large_gfn); if (host_level == PT_PAGE_TABLE_LEVEL) return host_level; @@ -1747,10 +1771,10 @@ void kvm_arch_mmu_enable_log_dirty_pt_masked(struct kvm *kvm, * Emulate arch specific page modification logging for the * nested hypervisor */ -int kvm_arch_write_log_dirty(struct kvm_vcpu *vcpu) +int kvm_arch_write_log_dirty(struct kvm_vcpu *vcpu, gpa_t l2_gpa) { if (kvm_x86_ops->write_log_dirty) - return kvm_x86_ops->write_log_dirty(vcpu); + return kvm_x86_ops->write_log_dirty(vcpu, l2_gpa); return 0; } @@ -3363,7 +3387,8 @@ static bool handle_abnormal_pfn(struct kvm_vcpu *vcpu, gva_t gva, gfn_t gfn, } if (unlikely(is_noslot_pfn(pfn))) - vcpu_cache_mmio_info(vcpu, gva, gfn, access); + vcpu_cache_mmio_info(vcpu, gva, gfn, + access & shadow_mmio_access_mask); return false; } @@ -3457,7 +3482,7 @@ static bool is_access_allowed(u32 fault_err_code, u64 spte) * - true: let the vcpu to access on the same address again. * - false: let the real page fault path to fix it. */ -static bool fast_page_fault(struct kvm_vcpu *vcpu, gva_t gva, int level, +static bool fast_page_fault(struct kvm_vcpu *vcpu, gpa_t cr2_or_gpa, int level, u32 error_code) { struct kvm_shadow_walk_iterator iterator; @@ -3477,7 +3502,7 @@ static bool fast_page_fault(struct kvm_vcpu *vcpu, gva_t gva, int level, do { u64 new_spte; - for_each_shadow_entry_lockless(vcpu, gva, iterator, spte) + for_each_shadow_entry_lockless(vcpu, cr2_or_gpa, iterator, spte) if (!is_shadow_present_pte(spte) || iterator.level < level) break; @@ -3555,7 +3580,7 @@ static bool fast_page_fault(struct kvm_vcpu *vcpu, gva_t gva, int level, } while (true); - trace_fast_page_fault(vcpu, gva, error_code, iterator.sptep, + trace_fast_page_fault(vcpu, cr2_or_gpa, error_code, iterator.sptep, spte, fault_handled); walk_shadow_page_lockless_end(vcpu); @@ -3563,10 +3588,11 @@ static bool fast_page_fault(struct kvm_vcpu *vcpu, gva_t gva, int level, } static bool try_async_pf(struct kvm_vcpu *vcpu, bool prefault, gfn_t gfn, - gva_t gva, kvm_pfn_t *pfn, bool write, bool *writable); + gpa_t cr2_or_gpa, kvm_pfn_t *pfn, bool write, + bool *writable); static int make_mmu_pages_available(struct kvm_vcpu *vcpu); -static int nonpaging_map(struct kvm_vcpu *vcpu, gva_t v, u32 error_code, +static int nonpaging_map(struct kvm_vcpu *vcpu, gpa_t gpa, u32 error_code, gfn_t gfn, bool prefault) { int r; @@ -3592,16 +3618,16 @@ static int nonpaging_map(struct kvm_vcpu *vcpu, gva_t v, u32 error_code, gfn &= ~(KVM_PAGES_PER_HPAGE(level) - 1); } - if (fast_page_fault(vcpu, v, level, error_code)) + if (fast_page_fault(vcpu, gpa, level, error_code)) return RET_PF_RETRY; mmu_seq = vcpu->kvm->mmu_notifier_seq; smp_rmb(); - if (try_async_pf(vcpu, prefault, gfn, v, &pfn, write, &map_writable)) + if (try_async_pf(vcpu, prefault, gfn, gpa, &pfn, write, &map_writable)) return RET_PF_RETRY; - if (handle_abnormal_pfn(vcpu, v, gfn, pfn, ACC_ALL, &r)) + if (handle_abnormal_pfn(vcpu, gpa, gfn, pfn, ACC_ALL, &r)) return r; spin_lock(&vcpu->kvm->mmu_lock); @@ -3611,7 +3637,7 @@ static int nonpaging_map(struct kvm_vcpu *vcpu, gva_t v, u32 error_code, goto out_unlock; if (likely(!force_pt_level)) transparent_hugepage_adjust(vcpu, &gfn, &pfn, &level); - r = __direct_map(vcpu, v, write, map_writable, level, pfn, + r = __direct_map(vcpu, gpa, write, map_writable, level, pfn, prefault, false); spin_unlock(&vcpu->kvm->mmu_lock); @@ -3912,7 +3938,7 @@ void kvm_mmu_sync_roots(struct kvm_vcpu *vcpu) } EXPORT_SYMBOL_GPL(kvm_mmu_sync_roots); -static gpa_t nonpaging_gva_to_gpa(struct kvm_vcpu *vcpu, gva_t vaddr, +static gpa_t nonpaging_gva_to_gpa(struct kvm_vcpu *vcpu, gpa_t vaddr, u32 access, struct x86_exception *exception) { if (exception) @@ -3920,7 +3946,7 @@ static gpa_t nonpaging_gva_to_gpa(struct kvm_vcpu *vcpu, gva_t vaddr, return vaddr; } -static gpa_t nonpaging_gva_to_gpa_nested(struct kvm_vcpu *vcpu, gva_t vaddr, +static gpa_t nonpaging_gva_to_gpa_nested(struct kvm_vcpu *vcpu, gpa_t vaddr, u32 access, struct x86_exception *exception) { @@ -4080,13 +4106,14 @@ static void shadow_page_table_clear_flood(struct kvm_vcpu *vcpu, gva_t addr) walk_shadow_page_lockless_end(vcpu); } -static int nonpaging_page_fault(struct kvm_vcpu *vcpu, gva_t gva, +static int nonpaging_page_fault(struct kvm_vcpu *vcpu, gpa_t gpa, u32 error_code, bool prefault) { - gfn_t gfn = gva >> PAGE_SHIFT; + gfn_t gfn = gpa >> PAGE_SHIFT; int r; - pgprintk("%s: gva %lx error %x\n", __func__, gva, error_code); + /* Note, paging is disabled, ergo gva == gpa. */ + pgprintk("%s: gva %lx error %x\n", __func__, gpa, error_code); if (page_fault_handle_page_track(vcpu, error_code, gfn)) return RET_PF_EMULATE; @@ -4098,11 +4125,12 @@ static int nonpaging_page_fault(struct kvm_vcpu *vcpu, gva_t gva, MMU_WARN_ON(!VALID_PAGE(vcpu->arch.mmu->root_hpa)); - return nonpaging_map(vcpu, gva & PAGE_MASK, + return nonpaging_map(vcpu, gpa & PAGE_MASK, error_code, gfn, prefault); } -static int kvm_arch_setup_async_pf(struct kvm_vcpu *vcpu, gva_t gva, gfn_t gfn) +static int kvm_arch_setup_async_pf(struct kvm_vcpu *vcpu, gpa_t cr2_or_gpa, + gfn_t gfn) { struct kvm_arch_async_pf arch; @@ -4111,7 +4139,8 @@ static int kvm_arch_setup_async_pf(struct kvm_vcpu *vcpu, gva_t gva, gfn_t gfn) arch.direct_map = vcpu->arch.mmu->direct_map; arch.cr3 = vcpu->arch.mmu->get_cr3(vcpu); - return kvm_setup_async_pf(vcpu, gva, kvm_vcpu_gfn_to_hva(vcpu, gfn), &arch); + return kvm_setup_async_pf(vcpu, cr2_or_gpa, + kvm_vcpu_gfn_to_hva(vcpu, gfn), &arch); } bool kvm_can_do_async_pf(struct kvm_vcpu *vcpu) @@ -4128,7 +4157,8 @@ bool kvm_can_do_async_pf(struct kvm_vcpu *vcpu) } static bool try_async_pf(struct kvm_vcpu *vcpu, bool prefault, gfn_t gfn, - gva_t gva, kvm_pfn_t *pfn, bool write, bool *writable) + gpa_t cr2_or_gpa, kvm_pfn_t *pfn, bool write, + bool *writable) { struct kvm_memory_slot *slot; bool async; @@ -4148,12 +4178,12 @@ static bool try_async_pf(struct kvm_vcpu *vcpu, bool prefault, gfn_t gfn, return false; /* *pfn has correct page already */ if (!prefault && kvm_can_do_async_pf(vcpu)) { - trace_kvm_try_async_get_page(gva, gfn); + trace_kvm_try_async_get_page(cr2_or_gpa, gfn); if (kvm_find_async_pf_gfn(vcpu, gfn)) { - trace_kvm_async_pf_doublefault(gva, gfn); + trace_kvm_async_pf_doublefault(cr2_or_gpa, gfn); kvm_make_request(KVM_REQ_APF_HALT, vcpu); return true; - } else if (kvm_arch_setup_async_pf(vcpu, gva, gfn)) + } else if (kvm_arch_setup_async_pf(vcpu, cr2_or_gpa, gfn)) return true; } @@ -4166,6 +4196,12 @@ int kvm_handle_page_fault(struct kvm_vcpu *vcpu, u64 error_code, { int r = 1; +#ifndef CONFIG_X86_64 + /* A 64-bit CR2 should be impossible on 32-bit KVM. */ + if (WARN_ON_ONCE(fault_address >> 32)) + return -EFAULT; +#endif + vcpu->arch.l1tf_flush_l1d = true; switch (vcpu->arch.apf.host_apf_reason) { default: @@ -4203,7 +4239,7 @@ check_hugepage_cache_consistency(struct kvm_vcpu *vcpu, gfn_t gfn, int level) return kvm_mtrr_check_gfn_range_consistency(vcpu, gfn, page_num); } -static int tdp_page_fault(struct kvm_vcpu *vcpu, gva_t gpa, u32 error_code, +static int tdp_page_fault(struct kvm_vcpu *vcpu, gpa_t gpa, u32 error_code, bool prefault) { kvm_pfn_t pfn; @@ -4510,7 +4546,7 @@ __reset_rsvds_bits_mask(struct kvm_vcpu *vcpu, nonleaf_bit8_rsvd | rsvd_bits(7, 7) | rsvd_bits(maxphyaddr, 51); rsvd_check->rsvd_bits_mask[0][2] = exb_bit_rsvd | - nonleaf_bit8_rsvd | gbpages_bit_rsvd | + gbpages_bit_rsvd | rsvd_bits(maxphyaddr, 51); rsvd_check->rsvd_bits_mask[0][1] = exb_bit_rsvd | rsvd_bits(maxphyaddr, 51); @@ -4603,7 +4639,7 @@ reset_shadow_zero_bits_mask(struct kvm_vcpu *vcpu, struct kvm_mmu *context) */ shadow_zero_check = &context->shadow_zero_check; __reset_rsvds_bits_mask(vcpu, shadow_zero_check, - boot_cpu_data.x86_phys_bits, + shadow_phys_bits, context->shadow_root_level, uses_nx, guest_cpuid_has(vcpu, X86_FEATURE_GBPAGES), is_pse(vcpu), true); @@ -4640,13 +4676,13 @@ reset_tdp_shadow_zero_bits_mask(struct kvm_vcpu *vcpu, if (boot_cpu_is_amd()) __reset_rsvds_bits_mask(vcpu, shadow_zero_check, - boot_cpu_data.x86_phys_bits, + shadow_phys_bits, context->shadow_root_level, false, boot_cpu_has(X86_FEATURE_GBPAGES), true, true); else __reset_rsvds_bits_mask_ept(shadow_zero_check, - boot_cpu_data.x86_phys_bits, + shadow_phys_bits, false); if (!shadow_me_mask) @@ -4667,7 +4703,7 @@ reset_ept_shadow_zero_bits_mask(struct kvm_vcpu *vcpu, struct kvm_mmu *context, bool execonly) { __reset_rsvds_bits_mask_ept(&context->shadow_zero_check, - boot_cpu_data.x86_phys_bits, execonly); + shadow_phys_bits, execonly); } #define BYTE_MASK(access) \ @@ -5462,7 +5498,7 @@ static int make_mmu_pages_available(struct kvm_vcpu *vcpu) return 0; } -int kvm_mmu_page_fault(struct kvm_vcpu *vcpu, gva_t cr2, u64 error_code, +int kvm_mmu_page_fault(struct kvm_vcpu *vcpu, gpa_t cr2_or_gpa, u64 error_code, void *insn, int insn_len) { int r, emulation_type = 0; @@ -5472,18 +5508,18 @@ int kvm_mmu_page_fault(struct kvm_vcpu *vcpu, gva_t cr2, u64 error_code, /* With shadow page tables, fault_address contains a GVA or nGPA. */ if (vcpu->arch.mmu->direct_map) { vcpu->arch.gpa_available = true; - vcpu->arch.gpa_val = cr2; + vcpu->arch.gpa_val = cr2_or_gpa; } r = RET_PF_INVALID; if (unlikely(error_code & PFERR_RSVD_MASK)) { - r = handle_mmio_page_fault(vcpu, cr2, direct); + r = handle_mmio_page_fault(vcpu, cr2_or_gpa, direct); if (r == RET_PF_EMULATE) goto emulate; } if (r == RET_PF_INVALID) { - r = vcpu->arch.mmu->page_fault(vcpu, cr2, + r = vcpu->arch.mmu->page_fault(vcpu, cr2_or_gpa, lower_32_bits(error_code), false); WARN_ON(r == RET_PF_INVALID); @@ -5503,7 +5539,7 @@ int kvm_mmu_page_fault(struct kvm_vcpu *vcpu, gva_t cr2, u64 error_code, */ if (vcpu->arch.mmu->direct_map && (error_code & PFERR_NESTED_GUEST_PAGE) == PFERR_NESTED_GUEST_PAGE) { - kvm_mmu_unprotect_page(vcpu->kvm, gpa_to_gfn(cr2)); + kvm_mmu_unprotect_page(vcpu->kvm, gpa_to_gfn(cr2_or_gpa)); return 1; } @@ -5518,7 +5554,7 @@ int kvm_mmu_page_fault(struct kvm_vcpu *vcpu, gva_t cr2, u64 error_code, * explicitly shadowing L1's page tables, i.e. unprotecting something * for L1 isn't going to magically fix whatever issue cause L2 to fail. */ - if (!mmio_info_in_cache(vcpu, cr2, direct) && !is_guest_mode(vcpu)) + if (!mmio_info_in_cache(vcpu, cr2_or_gpa, direct) && !is_guest_mode(vcpu)) emulation_type = EMULTYPE_ALLOW_RETRY; emulate: /* @@ -5533,7 +5569,7 @@ emulate: return 1; } - er = x86_emulate_instruction(vcpu, cr2, emulation_type, insn, insn_len); + er = x86_emulate_instruction(vcpu, cr2_or_gpa, emulation_type, insn, insn_len); switch (er) { case EMULATE_DONE: @@ -6189,14 +6225,13 @@ static int set_nx_huge_pages(const char *val, const struct kernel_param *kp) if (new_val != old_val) { struct kvm *kvm; - int idx; spin_lock(&kvm_lock); list_for_each_entry(kvm, &vm_list, vm_list) { - idx = srcu_read_lock(&kvm->srcu); + mutex_lock(&kvm->slots_lock); kvm_mmu_zap_all_fast(kvm); - srcu_read_unlock(&kvm->srcu, idx); + mutex_unlock(&kvm->slots_lock); wake_up_process(kvm->arch.nx_lpage_recovery_thread); } diff --git a/arch/x86/kvm/mmu.h b/arch/x86/kvm/mmu.h index 4610230ddaea..b0fefb3ccc87 100644 --- a/arch/x86/kvm/mmu.h +++ b/arch/x86/kvm/mmu.h @@ -43,6 +43,11 @@ #define PT32_ROOT_LEVEL 2 #define PT32E_ROOT_LEVEL 3 +#define ACC_EXEC_MASK 1 +#define ACC_WRITE_MASK PT_WRITABLE_MASK +#define ACC_USER_MASK PT_USER_MASK +#define ACC_ALL (ACC_EXEC_MASK | ACC_WRITE_MASK | ACC_USER_MASK) + static inline u64 rsvd_bits(int s, int e) { if (e < s) @@ -51,7 +56,7 @@ static inline u64 rsvd_bits(int s, int e) return ((1ULL << (e - s + 1)) - 1) << s; } -void kvm_mmu_set_mmio_spte_mask(u64 mmio_mask, u64 mmio_value); +void kvm_mmu_set_mmio_spte_mask(u64 mmio_mask, u64 mmio_value, u64 access_mask); void reset_shadow_zero_bits_mask(struct kvm_vcpu *vcpu, struct kvm_mmu *context); @@ -209,7 +214,7 @@ void kvm_mmu_gfn_disallow_lpage(struct kvm_memory_slot *slot, gfn_t gfn); void kvm_mmu_gfn_allow_lpage(struct kvm_memory_slot *slot, gfn_t gfn); bool kvm_mmu_slot_gfn_write_protect(struct kvm *kvm, struct kvm_memory_slot *slot, u64 gfn); -int kvm_arch_write_log_dirty(struct kvm_vcpu *vcpu); +int kvm_arch_write_log_dirty(struct kvm_vcpu *vcpu, gpa_t l2_gpa); int kvm_mmu_post_init_vm(struct kvm *kvm); void kvm_mmu_pre_destroy_vm(struct kvm *kvm); diff --git a/arch/x86/kvm/mmutrace.h b/arch/x86/kvm/mmutrace.h index dd30dccd2ad5..c2cabd4c6678 100644 --- a/arch/x86/kvm/mmutrace.h +++ b/arch/x86/kvm/mmutrace.h @@ -246,13 +246,13 @@ TRACE_EVENT( TRACE_EVENT( fast_page_fault, - TP_PROTO(struct kvm_vcpu *vcpu, gva_t gva, u32 error_code, + TP_PROTO(struct kvm_vcpu *vcpu, gpa_t cr2_or_gpa, u32 error_code, u64 *sptep, u64 old_spte, bool retry), - TP_ARGS(vcpu, gva, error_code, sptep, old_spte, retry), + TP_ARGS(vcpu, cr2_or_gpa, error_code, sptep, old_spte, retry), TP_STRUCT__entry( __field(int, vcpu_id) - __field(gva_t, gva) + __field(gpa_t, cr2_or_gpa) __field(u32, error_code) __field(u64 *, sptep) __field(u64, old_spte) @@ -262,7 +262,7 @@ TRACE_EVENT( TP_fast_assign( __entry->vcpu_id = vcpu->vcpu_id; - __entry->gva = gva; + __entry->cr2_or_gpa = cr2_or_gpa; __entry->error_code = error_code; __entry->sptep = sptep; __entry->old_spte = old_spte; @@ -270,9 +270,9 @@ TRACE_EVENT( __entry->retry = retry; ), - TP_printk("vcpu %d gva %lx error_code %s sptep %p old %#llx" + TP_printk("vcpu %d gva %llx error_code %s sptep %p old %#llx" " new %llx spurious %d fixed %d", __entry->vcpu_id, - __entry->gva, __print_flags(__entry->error_code, "|", + __entry->cr2_or_gpa, __print_flags(__entry->error_code, "|", kvm_mmu_trace_pferr_flags), __entry->sptep, __entry->old_spte, __entry->new_spte, __spte_satisfied(old_spte), __spte_satisfied(new_spte) diff --git a/arch/x86/kvm/mtrr.c b/arch/x86/kvm/mtrr.c index 25ce3edd1872..7f0059aa30e1 100644 --- a/arch/x86/kvm/mtrr.c +++ b/arch/x86/kvm/mtrr.c @@ -192,11 +192,15 @@ static bool fixed_msr_to_seg_unit(u32 msr, int *seg, int *unit) break; case MSR_MTRRfix16K_80000 ... MSR_MTRRfix16K_A0000: *seg = 1; - *unit = msr - MSR_MTRRfix16K_80000; + *unit = array_index_nospec( + msr - MSR_MTRRfix16K_80000, + MSR_MTRRfix16K_A0000 - MSR_MTRRfix16K_80000 + 1); break; case MSR_MTRRfix4K_C0000 ... MSR_MTRRfix4K_F8000: *seg = 2; - *unit = msr - MSR_MTRRfix4K_C0000; + *unit = array_index_nospec( + msr - MSR_MTRRfix4K_C0000, + MSR_MTRRfix4K_F8000 - MSR_MTRRfix4K_C0000 + 1); break; default: return false; diff --git a/arch/x86/kvm/paging_tmpl.h b/arch/x86/kvm/paging_tmpl.h index 4a906f7111ce..7f64d44735f9 100644 --- a/arch/x86/kvm/paging_tmpl.h +++ b/arch/x86/kvm/paging_tmpl.h @@ -33,7 +33,7 @@ #define PT_GUEST_ACCESSED_SHIFT PT_ACCESSED_SHIFT #define PT_HAVE_ACCESSED_DIRTY(mmu) true #ifdef CONFIG_X86_64 - #define PT_MAX_FULL_LEVELS 4 + #define PT_MAX_FULL_LEVELS PT64_ROOT_MAX_LEVEL #define CMPXCHG cmpxchg #else #define CMPXCHG cmpxchg64 @@ -220,7 +220,7 @@ static inline unsigned FNAME(gpte_access)(u64 gpte) static int FNAME(update_accessed_dirty_bits)(struct kvm_vcpu *vcpu, struct kvm_mmu *mmu, struct guest_walker *walker, - int write_fault) + gpa_t addr, int write_fault) { unsigned level, index; pt_element_t pte, orig_pte; @@ -245,7 +245,7 @@ static int FNAME(update_accessed_dirty_bits)(struct kvm_vcpu *vcpu, !(pte & PT_GUEST_DIRTY_MASK)) { trace_kvm_mmu_set_dirty_bit(table_gfn, index, sizeof(pte)); #if PTTYPE == PTTYPE_EPT - if (kvm_arch_write_log_dirty(vcpu)) + if (kvm_arch_write_log_dirty(vcpu, addr)) return -EINVAL; #endif pte |= PT_GUEST_DIRTY_MASK; @@ -291,11 +291,11 @@ static inline unsigned FNAME(gpte_pkeys)(struct kvm_vcpu *vcpu, u64 gpte) } /* - * Fetch a guest pte for a guest virtual address + * Fetch a guest pte for a guest virtual address, or for an L2's GPA. */ static int FNAME(walk_addr_generic)(struct guest_walker *walker, struct kvm_vcpu *vcpu, struct kvm_mmu *mmu, - gva_t addr, u32 access) + gpa_t addr, u32 access) { int ret; pt_element_t pte; @@ -442,7 +442,8 @@ retry_walk: (PT_GUEST_DIRTY_SHIFT - PT_GUEST_ACCESSED_SHIFT); if (unlikely(!accessed_dirty)) { - ret = FNAME(update_accessed_dirty_bits)(vcpu, mmu, walker, write_fault); + ret = FNAME(update_accessed_dirty_bits)(vcpu, mmu, walker, + addr, write_fault); if (unlikely(ret < 0)) goto error; else if (ret) @@ -496,7 +497,7 @@ error: } static int FNAME(walk_addr)(struct guest_walker *walker, - struct kvm_vcpu *vcpu, gva_t addr, u32 access) + struct kvm_vcpu *vcpu, gpa_t addr, u32 access) { return FNAME(walk_addr_generic)(walker, vcpu, vcpu->arch.mmu, addr, access); @@ -610,7 +611,7 @@ static void FNAME(pte_prefetch)(struct kvm_vcpu *vcpu, struct guest_walker *gw, * If the guest tries to write a write-protected page, we need to * emulate this operation, return 1 to indicate this case. */ -static int FNAME(fetch)(struct kvm_vcpu *vcpu, gva_t addr, +static int FNAME(fetch)(struct kvm_vcpu *vcpu, gpa_t addr, struct guest_walker *gw, int write_fault, int hlevel, kvm_pfn_t pfn, bool map_writable, bool prefault, @@ -763,7 +764,7 @@ FNAME(is_self_change_mapping)(struct kvm_vcpu *vcpu, * Returns: 1 if we need to emulate the instruction, 0 otherwise, or * a negative value on error. */ -static int FNAME(page_fault)(struct kvm_vcpu *vcpu, gva_t addr, u32 error_code, +static int FNAME(page_fault)(struct kvm_vcpu *vcpu, gpa_t addr, u32 error_code, bool prefault) { int write_fault = error_code & PFERR_WRITE_MASK; @@ -945,18 +946,19 @@ static void FNAME(invlpg)(struct kvm_vcpu *vcpu, gva_t gva, hpa_t root_hpa) spin_unlock(&vcpu->kvm->mmu_lock); } -static gpa_t FNAME(gva_to_gpa)(struct kvm_vcpu *vcpu, gva_t vaddr, u32 access, +/* Note, @addr is a GPA when gva_to_gpa() translates an L2 GPA to an L1 GPA. */ +static gpa_t FNAME(gva_to_gpa)(struct kvm_vcpu *vcpu, gpa_t addr, u32 access, struct x86_exception *exception) { struct guest_walker walker; gpa_t gpa = UNMAPPED_GVA; int r; - r = FNAME(walk_addr)(&walker, vcpu, vaddr, access); + r = FNAME(walk_addr)(&walker, vcpu, addr, access); if (r) { gpa = gfn_to_gpa(walker.gfn); - gpa |= vaddr & ~PAGE_MASK; + gpa |= addr & ~PAGE_MASK; } else if (exception) *exception = walker.fault; @@ -964,7 +966,8 @@ static gpa_t FNAME(gva_to_gpa)(struct kvm_vcpu *vcpu, gva_t vaddr, u32 access, } #if PTTYPE != PTTYPE_EPT -static gpa_t FNAME(gva_to_gpa_nested)(struct kvm_vcpu *vcpu, gva_t vaddr, +/* Note, gva_to_gpa_nested() is only used to translate L2 GVAs. */ +static gpa_t FNAME(gva_to_gpa_nested)(struct kvm_vcpu *vcpu, gpa_t vaddr, u32 access, struct x86_exception *exception) { @@ -972,6 +975,11 @@ static gpa_t FNAME(gva_to_gpa_nested)(struct kvm_vcpu *vcpu, gva_t vaddr, gpa_t gpa = UNMAPPED_GVA; int r; +#ifndef CONFIG_X86_64 + /* A 64-bit GVA should be impossible on 32-bit KVM. */ + WARN_ON_ONCE(vaddr >> 32); +#endif + r = FNAME(walk_addr_nested)(&walker, vcpu, vaddr, access); if (r) { diff --git a/arch/x86/kvm/pmu.h b/arch/x86/kvm/pmu.h index 22dff661145a..7b4828e50ab3 100644 --- a/arch/x86/kvm/pmu.h +++ b/arch/x86/kvm/pmu.h @@ -2,6 +2,8 @@ #ifndef __KVM_X86_PMU_H #define __KVM_X86_PMU_H +#include <linux/nospec.h> + #define vcpu_to_pmu(vcpu) (&(vcpu)->arch.pmu) #define pmu_to_vcpu(pmu) (container_of((pmu), struct kvm_vcpu, arch.pmu)) #define pmc_to_pmu(pmc) (&(pmc)->vcpu->arch.pmu) @@ -86,8 +88,12 @@ static inline bool pmc_is_enabled(struct kvm_pmc *pmc) static inline struct kvm_pmc *get_gp_pmc(struct kvm_pmu *pmu, u32 msr, u32 base) { - if (msr >= base && msr < base + pmu->nr_arch_gp_counters) - return &pmu->gp_counters[msr - base]; + if (msr >= base && msr < base + pmu->nr_arch_gp_counters) { + u32 index = array_index_nospec(msr - base, + pmu->nr_arch_gp_counters); + + return &pmu->gp_counters[index]; + } return NULL; } @@ -97,8 +103,12 @@ static inline struct kvm_pmc *get_fixed_pmc(struct kvm_pmu *pmu, u32 msr) { int base = MSR_CORE_PERF_FIXED_CTR0; - if (msr >= base && msr < base + pmu->nr_arch_fixed_counters) - return &pmu->fixed_counters[msr - base]; + if (msr >= base && msr < base + pmu->nr_arch_fixed_counters) { + u32 index = array_index_nospec(msr - base, + pmu->nr_arch_fixed_counters); + + return &pmu->fixed_counters[index]; + } return NULL; } diff --git a/arch/x86/kvm/svm.c b/arch/x86/kvm/svm.c index 68f63d9684a6..bf0d805e75c9 100644 --- a/arch/x86/kvm/svm.c +++ b/arch/x86/kvm/svm.c @@ -996,33 +996,32 @@ static void svm_cpu_uninit(int cpu) static int svm_cpu_init(int cpu) { struct svm_cpu_data *sd; - int r; sd = kzalloc(sizeof(struct svm_cpu_data), GFP_KERNEL); if (!sd) return -ENOMEM; sd->cpu = cpu; - r = -ENOMEM; sd->save_area = alloc_page(GFP_KERNEL); if (!sd->save_area) - goto err_1; + goto free_cpu_data; if (svm_sev_enabled()) { - r = -ENOMEM; sd->sev_vmcbs = kmalloc_array(max_sev_asid + 1, sizeof(void *), GFP_KERNEL); if (!sd->sev_vmcbs) - goto err_1; + goto free_save_area; } per_cpu(svm_data, cpu) = sd; return 0; -err_1: +free_save_area: + __free_page(sd->save_area); +free_cpu_data: kfree(sd); - return r; + return -ENOMEM; } @@ -1296,6 +1295,47 @@ static void shrink_ple_window(struct kvm_vcpu *vcpu) control->pause_filter_count, old); } +/* + * The default MMIO mask is a single bit (excluding the present bit), + * which could conflict with the memory encryption bit. Check for + * memory encryption support and override the default MMIO mask if + * memory encryption is enabled. + */ +static __init void svm_adjust_mmio_mask(void) +{ + unsigned int enc_bit, mask_bit; + u64 msr, mask; + + /* If there is no memory encryption support, use existing mask */ + if (cpuid_eax(0x80000000) < 0x8000001f) + return; + + /* If memory encryption is not enabled, use existing mask */ + rdmsrl(MSR_K8_SYSCFG, msr); + if (!(msr & MSR_K8_SYSCFG_MEM_ENCRYPT)) + return; + + enc_bit = cpuid_ebx(0x8000001f) & 0x3f; + mask_bit = boot_cpu_data.x86_phys_bits; + + /* Increment the mask bit if it is the same as the encryption bit */ + if (enc_bit == mask_bit) + mask_bit++; + + /* + * If the mask bit location is below 52, then some bits above the + * physical addressing limit will always be reserved, so use the + * rsvd_bits() function to generate the mask. This mask, along with + * the present bit, will be used to generate a page fault with + * PFER.RSV = 1. + * + * If the mask bit location is 52 (or above), then clear the mask. + */ + mask = (mask_bit < 52) ? rsvd_bits(mask_bit, 51) | PT_PRESENT_MASK : 0; + + kvm_mmu_set_mmio_spte_mask(mask, mask, PT_WRITABLE_MASK | PT_USER_MASK); +} + static __init int svm_hardware_setup(void) { int cpu; @@ -1350,6 +1390,8 @@ static __init int svm_hardware_setup(void) } } + svm_adjust_mmio_mask(); + for_each_possible_cpu(cpu) { r = svm_cpu_init(cpu); if (r) @@ -1811,7 +1853,7 @@ static struct page **sev_pin_memory(struct kvm *kvm, unsigned long uaddr, return NULL; /* Pin the user virtual address. */ - npinned = get_user_pages_fast(uaddr, npages, FOLL_WRITE, pages); + npinned = get_user_pages_fast(uaddr, npages, write ? FOLL_WRITE : 0, pages); if (npinned != npages) { pr_err("SEV: Failure locking %lu pages.\n", npages); goto err; @@ -1876,6 +1918,10 @@ static struct kvm *svm_vm_alloc(void) struct kvm_svm *kvm_svm = __vmalloc(sizeof(struct kvm_svm), GFP_KERNEL_ACCOUNT | __GFP_ZERO, PAGE_KERNEL); + + if (!kvm_svm) + return NULL; + return &kvm_svm->kvm; } @@ -2140,12 +2186,20 @@ static struct kvm_vcpu *svm_create_vcpu(struct kvm *kvm, unsigned int id) goto out; } + svm->vcpu.arch.user_fpu = kmem_cache_zalloc(x86_fpu_cache, + GFP_KERNEL_ACCOUNT); + if (!svm->vcpu.arch.user_fpu) { + printk(KERN_ERR "kvm: failed to allocate kvm userspace's fpu\n"); + err = -ENOMEM; + goto free_partial_svm; + } + svm->vcpu.arch.guest_fpu = kmem_cache_zalloc(x86_fpu_cache, GFP_KERNEL_ACCOUNT); if (!svm->vcpu.arch.guest_fpu) { printk(KERN_ERR "kvm: failed to allocate vcpu's fpu\n"); err = -ENOMEM; - goto free_partial_svm; + goto free_user_fpu; } err = kvm_vcpu_init(&svm->vcpu, kvm, id); @@ -2208,6 +2262,8 @@ uninit: kvm_vcpu_uninit(&svm->vcpu); free_svm: kmem_cache_free(x86_fpu_cache, svm->vcpu.arch.guest_fpu); +free_user_fpu: + kmem_cache_free(x86_fpu_cache, svm->vcpu.arch.user_fpu); free_partial_svm: kmem_cache_free(kvm_vcpu_cache, svm); out: @@ -2238,6 +2294,7 @@ static void svm_free_vcpu(struct kvm_vcpu *vcpu) __free_page(virt_to_page(svm->nested.hsave)); __free_pages(virt_to_page(svm->nested.msrpm), MSRPM_ALLOC_ORDER); kvm_vcpu_uninit(vcpu); + kmem_cache_free(x86_fpu_cache, svm->vcpu.arch.user_fpu); kmem_cache_free(x86_fpu_cache, svm->vcpu.arch.guest_fpu); kmem_cache_free(kvm_vcpu_cache, svm); } @@ -3171,8 +3228,8 @@ static int nested_svm_exit_special(struct vcpu_svm *svm) return NESTED_EXIT_HOST; break; case SVM_EXIT_EXCP_BASE + PF_VECTOR: - /* When we're shadowing, trap PFs, but not async PF */ - if (!npt_enabled && svm->vcpu.arch.apf.host_apf_reason == 0) + /* Trap async PF even if not shadowing */ + if (!npt_enabled || svm->vcpu.arch.apf.host_apf_reason) return NESTED_EXIT_HOST; break; default: @@ -3261,7 +3318,7 @@ static inline void copy_vmcb_control_area(struct vmcb *dst_vmcb, struct vmcb *fr dst->iopm_base_pa = from->iopm_base_pa; dst->msrpm_base_pa = from->msrpm_base_pa; dst->tsc_offset = from->tsc_offset; - dst->asid = from->asid; + /* asid not copied, it is handled manually for svm->vmcb. */ dst->tlb_ctl = from->tlb_ctl; dst->int_ctl = from->int_ctl; dst->int_vector = from->int_vector; @@ -4537,9 +4594,9 @@ static int avic_incomplete_ipi_interception(struct vcpu_svm *svm) */ kvm_for_each_vcpu(i, vcpu, kvm) { bool m = kvm_apic_match_dest(vcpu, apic, - icrl & KVM_APIC_SHORT_MASK, + icrl & APIC_SHORT_MASK, GET_APIC_DEST_FIELD(icrh), - icrl & KVM_APIC_DEST_MASK); + icrl & APIC_DEST_MASK); if (m && !avic_vcpu_is_running(vcpu)) kvm_vcpu_wake_up(vcpu); @@ -5161,8 +5218,11 @@ static void svm_load_eoi_exitmap(struct kvm_vcpu *vcpu, u64 *eoi_exit_bitmap) return; } -static void svm_deliver_avic_intr(struct kvm_vcpu *vcpu, int vec) +static int svm_deliver_avic_intr(struct kvm_vcpu *vcpu, int vec) { + if (!vcpu->arch.apicv_active) + return -1; + kvm_lapic_set_irr(vec, vcpu->arch.apic); smp_mb__after_atomic(); @@ -5171,6 +5231,8 @@ static void svm_deliver_avic_intr(struct kvm_vcpu *vcpu, int vec) kvm_cpu_get_apicid(vcpu->cpu)); else kvm_vcpu_wake_up(vcpu); + + return 0; } static bool svm_dy_apicv_has_pending_interrupt(struct kvm_vcpu *vcpu) @@ -5905,6 +5967,9 @@ static void svm_cpuid_update(struct kvm_vcpu *vcpu) { struct vcpu_svm *svm = to_svm(vcpu); + vcpu->arch.xsaves_enabled = guest_cpuid_has(vcpu, X86_FEATURE_XSAVE) && + boot_cpu_has(X86_FEATURE_XSAVES); + /* Update nrips enabled cache */ svm->nrips_enabled = !!guest_cpuid_has(&svm->vcpu, X86_FEATURE_NRIPS); @@ -5991,6 +6056,11 @@ static bool svm_has_wbinvd_exit(void) return true; } +static bool svm_pku_supported(void) +{ + return false; +} + #define PRE_EX(exit) { .exit_code = (exit), \ .stage = X86_ICPT_PRE_EXCEPT, } #define POST_EX(exit) { .exit_code = (exit), \ @@ -7280,6 +7350,7 @@ static struct kvm_x86_ops svm_x86_ops __ro_after_init = { .xsaves_supported = svm_xsaves_supported, .umip_emulated = svm_umip_emulated, .pt_supported = svm_pt_supported, + .pku_supported = svm_pku_supported, .set_supported_cpuid = svm_set_supported_cpuid, diff --git a/arch/x86/kvm/trace.h b/arch/x86/kvm/trace.h index 4d47a2631d1f..e11689b876d7 100644 --- a/arch/x86/kvm/trace.h +++ b/arch/x86/kvm/trace.h @@ -1462,6 +1462,25 @@ TRACE_EVENT(kvm_hv_send_ipi_ex, __entry->vector, __entry->format, __entry->valid_bank_mask) ); + +TRACE_EVENT(kvm_pv_tlb_flush, + TP_PROTO(unsigned int vcpu_id, bool need_flush_tlb), + TP_ARGS(vcpu_id, need_flush_tlb), + + TP_STRUCT__entry( + __field( unsigned int, vcpu_id ) + __field( bool, need_flush_tlb ) + ), + + TP_fast_assign( + __entry->vcpu_id = vcpu_id; + __entry->need_flush_tlb = need_flush_tlb; + ), + + TP_printk("vcpu %u need_flush_tlb %s", __entry->vcpu_id, + __entry->need_flush_tlb ? "true" : "false") +); + #endif /* _TRACE_KVM_H */ #undef TRACE_INCLUDE_PATH diff --git a/arch/x86/kvm/vmx/capabilities.h b/arch/x86/kvm/vmx/capabilities.h index d6664ee3d127..7cd3f8683b8c 100644 --- a/arch/x86/kvm/vmx/capabilities.h +++ b/arch/x86/kvm/vmx/capabilities.h @@ -12,6 +12,7 @@ extern bool __read_mostly enable_ept; extern bool __read_mostly enable_unrestricted_guest; extern bool __read_mostly enable_ept_ad_bits; extern bool __read_mostly enable_pml; +extern bool __read_mostly enable_apicv; extern int __read_mostly pt_mode; #define PT_MODE_SYSTEM 0 @@ -145,6 +146,11 @@ static inline bool vmx_umip_emulated(void) SECONDARY_EXEC_DESC; } +static inline bool vmx_pku_supported(void) +{ + return boot_cpu_has(X86_FEATURE_PKU); +} + static inline bool cpu_has_vmx_rdtscp(void) { return vmcs_config.cpu_based_2nd_exec_ctrl & diff --git a/arch/x86/kvm/vmx/nested.c b/arch/x86/kvm/vmx/nested.c index 22437ad335b0..c6deeed854f1 100644 --- a/arch/x86/kvm/vmx/nested.c +++ b/arch/x86/kvm/vmx/nested.c @@ -2384,6 +2384,16 @@ static int prepare_vmcs02(struct kvm_vcpu *vcpu, struct vmcs12 *vmcs12, entry_failure_code)) return -EINVAL; + /* + * Immediately write vmcs02.GUEST_CR3. It will be propagated to vmcs12 + * on nested VM-Exit, which can occur without actually running L2 and + * thus without hitting vmx_set_cr3(), e.g. if L1 is entering L2 with + * vmcs12.GUEST_ACTIVITYSTATE=HLT, in which case KVM will intercept the + * transition to HLT instead of running L2. + */ + if (enable_ept) + vmcs_writel(GUEST_CR3, vmcs12->guest_cr3); + if (!enable_ept) vcpu->arch.walk_mmu->inject_page_fault = vmx_inject_page_fault_nested; @@ -3357,7 +3367,7 @@ static void nested_vmx_inject_exception_vmexit(struct kvm_vcpu *vcpu, nested_vmx_vmexit(vcpu, EXIT_REASON_EXCEPTION_NMI, intr_info, exit_qual); } -static int vmx_check_nested_events(struct kvm_vcpu *vcpu, bool external_intr) +static int vmx_check_nested_events(struct kvm_vcpu *vcpu) { struct vcpu_vmx *vmx = to_vmx(vcpu); unsigned long exit_qual; @@ -3395,8 +3405,7 @@ static int vmx_check_nested_events(struct kvm_vcpu *vcpu, bool external_intr) return 0; } - if ((kvm_cpu_has_interrupt(vcpu) || external_intr) && - nested_exit_on_intr(vcpu)) { + if (kvm_cpu_has_interrupt(vcpu) && nested_exit_on_intr(vcpu)) { if (block_nested_events) return -EBUSY; nested_vmx_vmexit(vcpu, EXIT_REASON_EXTERNAL_INTERRUPT, 0, 0); @@ -3970,17 +3979,8 @@ void nested_vmx_vmexit(struct kvm_vcpu *vcpu, u32 exit_reason, vcpu->arch.mp_state = KVM_MP_STATE_RUNNABLE; if (likely(!vmx->fail)) { - /* - * TODO: SDM says that with acknowledge interrupt on - * exit, bit 31 of the VM-exit interrupt information - * (valid interrupt) is always set to 1 on - * EXIT_REASON_EXTERNAL_INTERRUPT, so we shouldn't - * need kvm_cpu_has_interrupt(). See the commit - * message for details. - */ - if (nested_exit_intr_ack_set(vcpu) && - exit_reason == EXIT_REASON_EXTERNAL_INTERRUPT && - kvm_cpu_has_interrupt(vcpu)) { + if (exit_reason == EXIT_REASON_EXTERNAL_INTERRUPT && + nested_exit_intr_ack_set(vcpu)) { int irq = kvm_cpu_get_interrupt(vcpu); WARN_ON(irq < 0); vmcs12->vm_exit_intr_info = irq | @@ -4452,8 +4452,10 @@ static int handle_vmread(struct kvm_vcpu *vcpu) vmx_instruction_info, true, len, &gva)) return 1; /* _system ok, nested_vmx_check_permission has verified cpl=0 */ - if (kvm_write_guest_virt_system(vcpu, gva, &field_value, len, &e)) + if (kvm_write_guest_virt_system(vcpu, gva, &field_value, len, &e)) { kvm_inject_page_fault(vcpu, &e); + return 1; + } } return nested_vmx_succeed(vcpu); @@ -4882,24 +4884,17 @@ fail: return 1; } - -static bool nested_vmx_exit_handled_io(struct kvm_vcpu *vcpu, - struct vmcs12 *vmcs12) +/* + * Return true if an IO instruction with the specified port and size should cause + * a VM-exit into L1. + */ +bool nested_vmx_check_io_bitmaps(struct kvm_vcpu *vcpu, unsigned int port, + int size) { - unsigned long exit_qualification; + struct vmcs12 *vmcs12 = get_vmcs12(vcpu); gpa_t bitmap, last_bitmap; - unsigned int port; - int size; u8 b; - if (!nested_cpu_has(vmcs12, CPU_BASED_USE_IO_BITMAPS)) - return nested_cpu_has(vmcs12, CPU_BASED_UNCOND_IO_EXITING); - - exit_qualification = vmcs_readl(EXIT_QUALIFICATION); - - port = exit_qualification >> 16; - size = (exit_qualification & 7) + 1; - last_bitmap = (gpa_t)-1; b = -1; @@ -4926,6 +4921,24 @@ static bool nested_vmx_exit_handled_io(struct kvm_vcpu *vcpu, return false; } +static bool nested_vmx_exit_handled_io(struct kvm_vcpu *vcpu, + struct vmcs12 *vmcs12) +{ + unsigned long exit_qualification; + unsigned short port; + int size; + + if (!nested_cpu_has(vmcs12, CPU_BASED_USE_IO_BITMAPS)) + return nested_cpu_has(vmcs12, CPU_BASED_UNCOND_IO_EXITING); + + exit_qualification = vmcs_readl(EXIT_QUALIFICATION); + + port = exit_qualification >> 16; + size = (exit_qualification & 7) + 1; + + return nested_vmx_check_io_bitmaps(vcpu, port, size); +} + /* * Return 1 if we should exit from L2 to L1 to handle an MSR access access, * rather than handle it ourselves in L0. I.e., check whether L1 expressed @@ -5112,7 +5125,7 @@ bool nested_vmx_exit_reflected(struct kvm_vcpu *vcpu, u32 exit_reason) vmcs_read32(VM_EXIT_INTR_ERROR_CODE), KVM_ISA_VMX); - switch (exit_reason) { + switch ((u16)exit_reason) { case EXIT_REASON_EXCEPTION_NMI: if (is_nmi(intr_info)) return false; @@ -5546,8 +5559,7 @@ void nested_vmx_vcpu_setup(void) * bit in the high half is on if the corresponding bit in the control field * may be on. See also vmx_control_verify(). */ -void nested_vmx_setup_ctls_msrs(struct nested_vmx_msrs *msrs, u32 ept_caps, - bool apicv) +void nested_vmx_setup_ctls_msrs(struct nested_vmx_msrs *msrs, u32 ept_caps) { /* * Note that as a general rule, the high half of the MSRs (bits in @@ -5574,7 +5586,7 @@ void nested_vmx_setup_ctls_msrs(struct nested_vmx_msrs *msrs, u32 ept_caps, PIN_BASED_EXT_INTR_MASK | PIN_BASED_NMI_EXITING | PIN_BASED_VIRTUAL_NMIS | - (apicv ? PIN_BASED_POSTED_INTR : 0); + (enable_apicv ? PIN_BASED_POSTED_INTR : 0); msrs->pinbased_ctls_high |= PIN_BASED_ALWAYSON_WITHOUT_TRUE_MSR | PIN_BASED_VMX_PREEMPTION_TIMER; diff --git a/arch/x86/kvm/vmx/nested.h b/arch/x86/kvm/vmx/nested.h index 29d205bb4e4f..161c305de3f3 100644 --- a/arch/x86/kvm/vmx/nested.h +++ b/arch/x86/kvm/vmx/nested.h @@ -7,8 +7,7 @@ #include "vmx.h" void vmx_leave_nested(struct kvm_vcpu *vcpu); -void nested_vmx_setup_ctls_msrs(struct nested_vmx_msrs *msrs, u32 ept_caps, - bool apicv); +void nested_vmx_setup_ctls_msrs(struct nested_vmx_msrs *msrs, u32 ept_caps); void nested_vmx_hardware_unsetup(void); __init int nested_vmx_hardware_setup(int (*exit_handlers[])(struct kvm_vcpu *)); void nested_vmx_vcpu_setup(void); @@ -22,6 +21,8 @@ int vmx_set_vmx_msr(struct kvm_vcpu *vcpu, u32 msr_index, u64 data); int vmx_get_vmx_msr(struct nested_vmx_msrs *msrs, u32 msr_index, u64 *pdata); int get_vmx_mem_address(struct kvm_vcpu *vcpu, unsigned long exit_qualification, u32 vmx_instruction_info, bool wr, int len, gva_t *ret); +bool nested_vmx_check_io_bitmaps(struct kvm_vcpu *vcpu, unsigned int port, + int size); static inline struct vmcs12 *get_vmcs12(struct kvm_vcpu *vcpu) { diff --git a/arch/x86/kvm/vmx/pmu_intel.c b/arch/x86/kvm/vmx/pmu_intel.c index 68d231d49c7a..cb3d9872a88d 100644 --- a/arch/x86/kvm/vmx/pmu_intel.c +++ b/arch/x86/kvm/vmx/pmu_intel.c @@ -84,10 +84,14 @@ static unsigned intel_find_arch_event(struct kvm_pmu *pmu, static unsigned intel_find_fixed_event(int idx) { - if (idx >= ARRAY_SIZE(fixed_pmc_events)) + u32 event; + size_t size = ARRAY_SIZE(fixed_pmc_events); + + if (idx >= size) return PERF_COUNT_HW_MAX; - return intel_arch_events[fixed_pmc_events[idx]].event_type; + event = fixed_pmc_events[array_index_nospec(idx, size)]; + return intel_arch_events[event].event_type; } /* check if a PMC is enabled by comparing it with globl_ctrl bits. */ @@ -128,16 +132,20 @@ static struct kvm_pmc *intel_msr_idx_to_pmc(struct kvm_vcpu *vcpu, struct kvm_pmu *pmu = vcpu_to_pmu(vcpu); bool fixed = idx & (1u << 30); struct kvm_pmc *counters; + unsigned int num_counters; idx &= ~(3u << 30); - if (!fixed && idx >= pmu->nr_arch_gp_counters) - return NULL; - if (fixed && idx >= pmu->nr_arch_fixed_counters) + if (fixed) { + counters = pmu->fixed_counters; + num_counters = pmu->nr_arch_fixed_counters; + } else { + counters = pmu->gp_counters; + num_counters = pmu->nr_arch_gp_counters; + } + if (idx >= num_counters) return NULL; - counters = fixed ? pmu->fixed_counters : pmu->gp_counters; *mask &= pmu->counter_bitmask[fixed ? KVM_PMC_FIXED : KVM_PMC_GP]; - - return &counters[idx]; + return &counters[array_index_nospec(idx, num_counters)]; } static bool intel_is_valid_msr(struct kvm_vcpu *vcpu, u32 msr) diff --git a/arch/x86/kvm/vmx/vmenter.S b/arch/x86/kvm/vmx/vmenter.S index d4cb1945b2e3..f83368b5af87 100644 --- a/arch/x86/kvm/vmx/vmenter.S +++ b/arch/x86/kvm/vmx/vmenter.S @@ -86,6 +86,9 @@ ENTRY(vmx_vmexit) /* IMPORTANT: Stuff the RSB immediately after VM-Exit, before RET! */ FILL_RETURN_BUFFER %_ASM_AX, RSB_CLEAR_LOOPS, X86_FEATURE_RETPOLINE + /* Clear RFLAGS.CF and RFLAGS.ZF to preserve VM-Exit, i.e. !VM-Fail. */ + or $1, %_ASM_AX + pop %_ASM_AX .Lvmexit_skip_rsb: #endif diff --git a/arch/x86/kvm/vmx/vmx.c b/arch/x86/kvm/vmx/vmx.c index ea5040117fbb..b177e25e3786 100644 --- a/arch/x86/kvm/vmx/vmx.c +++ b/arch/x86/kvm/vmx/vmx.c @@ -95,7 +95,7 @@ module_param(emulate_invalid_guest_state, bool, S_IRUGO); static bool __read_mostly fasteoi = 1; module_param(fasteoi, bool, S_IRUGO); -static bool __read_mostly enable_apicv = 1; +bool __read_mostly enable_apicv = 1; module_param(enable_apicv, bool, S_IRUGO); /* @@ -402,6 +402,7 @@ const u32 vmx_msr_index[] = { MSR_SYSCALL_MASK, MSR_LSTAR, MSR_CSTAR, #endif MSR_EFER, MSR_TSC_AUX, MSR_STAR, + MSR_IA32_TSX_CTRL, }; #if IS_ENABLED(CONFIG_HYPERV) @@ -565,6 +566,23 @@ struct shared_msr_entry *find_msr_entry(struct vcpu_vmx *vmx, u32 msr) return NULL; } +static int vmx_set_guest_msr(struct vcpu_vmx *vmx, struct shared_msr_entry *msr, u64 data) +{ + int ret = 0; + + u64 old_msr_data = msr->data; + msr->data = data; + if (msr - vmx->guest_msrs < vmx->save_nmsrs) { + preempt_disable(); + ret = kvm_set_shared_msr(msr->index, msr->data, + msr->mask); + preempt_enable(); + if (ret) + msr->data = old_msr_data; + } + return ret; +} + void loaded_vmcs_init(struct loaded_vmcs *loaded_vmcs) { vmcs_clear(loaded_vmcs->vmcs); @@ -575,43 +593,15 @@ void loaded_vmcs_init(struct loaded_vmcs *loaded_vmcs) } #ifdef CONFIG_KEXEC_CORE -/* - * This bitmap is used to indicate whether the vmclear - * operation is enabled on all cpus. All disabled by - * default. - */ -static cpumask_t crash_vmclear_enabled_bitmap = CPU_MASK_NONE; - -static inline void crash_enable_local_vmclear(int cpu) -{ - cpumask_set_cpu(cpu, &crash_vmclear_enabled_bitmap); -} - -static inline void crash_disable_local_vmclear(int cpu) -{ - cpumask_clear_cpu(cpu, &crash_vmclear_enabled_bitmap); -} - -static inline int crash_local_vmclear_enabled(int cpu) -{ - return cpumask_test_cpu(cpu, &crash_vmclear_enabled_bitmap); -} - static void crash_vmclear_local_loaded_vmcss(void) { int cpu = raw_smp_processor_id(); struct loaded_vmcs *v; - if (!crash_local_vmclear_enabled(cpu)) - return; - list_for_each_entry(v, &per_cpu(loaded_vmcss_on_cpu, cpu), loaded_vmcss_on_cpu_link) vmcs_clear(v->vmcs); } -#else -static inline void crash_enable_local_vmclear(int cpu) { } -static inline void crash_disable_local_vmclear(int cpu) { } #endif /* CONFIG_KEXEC_CORE */ static void __loaded_vmcs_clear(void *arg) @@ -623,19 +613,24 @@ static void __loaded_vmcs_clear(void *arg) return; /* vcpu migration can race with cpu offline */ if (per_cpu(current_vmcs, cpu) == loaded_vmcs->vmcs) per_cpu(current_vmcs, cpu) = NULL; - crash_disable_local_vmclear(cpu); + + vmcs_clear(loaded_vmcs->vmcs); + if (loaded_vmcs->shadow_vmcs && loaded_vmcs->launched) + vmcs_clear(loaded_vmcs->shadow_vmcs); + list_del(&loaded_vmcs->loaded_vmcss_on_cpu_link); /* - * we should ensure updating loaded_vmcs->loaded_vmcss_on_cpu_link - * is before setting loaded_vmcs->vcpu to -1 which is done in - * loaded_vmcs_init. Otherwise, other cpu can see vcpu = -1 fist - * then adds the vmcs into percpu list before it is deleted. + * Ensure all writes to loaded_vmcs, including deleting it from its + * current percpu list, complete before setting loaded_vmcs->vcpu to + * -1, otherwise a different cpu can see vcpu == -1 first and add + * loaded_vmcs to its percpu list before it's deleted from this cpu's + * list. Pairs with the smp_rmb() in vmx_vcpu_load_vmcs(). */ smp_wmb(); - loaded_vmcs_init(loaded_vmcs); - crash_enable_local_vmclear(cpu); + loaded_vmcs->cpu = -1; + loaded_vmcs->launched = 0; } void loaded_vmcs_clear(struct loaded_vmcs *loaded_vmcs) @@ -1229,18 +1224,17 @@ void vmx_vcpu_load(struct kvm_vcpu *vcpu, int cpu) if (!already_loaded) { loaded_vmcs_clear(vmx->loaded_vmcs); local_irq_disable(); - crash_disable_local_vmclear(cpu); /* - * Read loaded_vmcs->cpu should be before fetching - * loaded_vmcs->loaded_vmcss_on_cpu_link. - * See the comments in __loaded_vmcs_clear(). + * Ensure loaded_vmcs->cpu is read before adding loaded_vmcs to + * this cpu's percpu list, otherwise it may not yet be deleted + * from its previous cpu's percpu list. Pairs with the + * smb_wmb() in __loaded_vmcs_clear(). */ smp_rmb(); list_add(&vmx->loaded_vmcs->loaded_vmcss_on_cpu_link, &per_cpu(loaded_vmcss_on_cpu, cpu)); - crash_enable_local_vmclear(cpu); local_irq_enable(); } @@ -1284,7 +1278,6 @@ void vmx_vcpu_load(struct kvm_vcpu *vcpu, int cpu) decache_tsc_multiplier(vmx); vmx_vcpu_pi_load(vcpu, cpu); - vmx->host_pkru = read_pkru(); vmx->host_debugctlmsr = get_debugctlmsr(); } @@ -1569,6 +1562,9 @@ static void setup_msrs(struct vcpu_vmx *vmx) index = __find_msr_index(vmx, MSR_TSC_AUX); if (index >= 0 && guest_cpuid_has(&vmx->vcpu, X86_FEATURE_RDTSCP)) move_msr_up(vmx, index, save_nmsrs++); + index = __find_msr_index(vmx, MSR_IA32_TSX_CTRL); + if (index >= 0) + move_msr_up(vmx, index, save_nmsrs++); vmx->save_nmsrs = save_nmsrs; vmx->guest_msrs_dirty = true; @@ -1668,6 +1664,11 @@ static int vmx_get_msr(struct kvm_vcpu *vcpu, struct msr_data *msr_info) #endif case MSR_EFER: return kvm_get_msr_common(vcpu, msr_info); + case MSR_IA32_TSX_CTRL: + if (!msr_info->host_initiated && + !(vcpu->arch.arch_capabilities & ARCH_CAP_TSX_CTRL_MSR)) + return 1; + goto find_shared_msr; case MSR_IA32_SPEC_CTRL: if (!msr_info->host_initiated && !guest_cpuid_has(vcpu, X86_FEATURE_SPEC_CTRL)) @@ -1710,10 +1711,8 @@ static int vmx_get_msr(struct kvm_vcpu *vcpu, struct msr_data *msr_info) return vmx_get_vmx_msr(&vmx->nested.msrs, msr_info->index, &msr_info->data); case MSR_IA32_XSS: - if (!vmx_xsaves_supported() || - (!msr_info->host_initiated && - !(guest_cpuid_has(vcpu, X86_FEATURE_XSAVE) && - guest_cpuid_has(vcpu, X86_FEATURE_XSAVES)))) + if (!msr_info->host_initiated && + !guest_cpuid_has(vcpu, X86_FEATURE_XSAVES)) return 1; msr_info->data = vcpu->arch.ia32_xss; break; @@ -1767,8 +1766,9 @@ static int vmx_get_msr(struct kvm_vcpu *vcpu, struct msr_data *msr_info) if (!msr_info->host_initiated && !guest_cpuid_has(vcpu, X86_FEATURE_RDTSCP)) return 1; - /* Else, falls through */ + goto find_shared_msr; default: + find_shared_msr: msr = find_msr_entry(vmx, msr_info->index); if (msr) { msr_info->data = msr->data; @@ -1863,6 +1863,13 @@ static int vmx_set_msr(struct kvm_vcpu *vcpu, struct msr_data *msr_info) MSR_IA32_SPEC_CTRL, MSR_TYPE_RW); break; + case MSR_IA32_TSX_CTRL: + if (!msr_info->host_initiated && + !(vcpu->arch.arch_capabilities & ARCH_CAP_TSX_CTRL_MSR)) + return 1; + if (data & ~(TSX_CTRL_RTM_DISABLE | TSX_CTRL_CPUID_CLEAR)) + return 1; + goto find_shared_msr; case MSR_IA32_PRED_CMD: if (!msr_info->host_initiated && !guest_cpuid_has(vcpu, X86_FEATURE_SPEC_CTRL)) @@ -1928,10 +1935,8 @@ static int vmx_set_msr(struct kvm_vcpu *vcpu, struct msr_data *msr_info) return 1; return vmx_set_vmx_msr(vcpu, msr_index, data); case MSR_IA32_XSS: - if (!vmx_xsaves_supported() || - (!msr_info->host_initiated && - !(guest_cpuid_has(vcpu, X86_FEATURE_XSAVE) && - guest_cpuid_has(vcpu, X86_FEATURE_XSAVES)))) + if (!msr_info->host_initiated && + !guest_cpuid_has(vcpu, X86_FEATURE_XSAVES)) return 1; /* * The only supported bit as of Skylake is bit 8, but @@ -1940,11 +1945,13 @@ static int vmx_set_msr(struct kvm_vcpu *vcpu, struct msr_data *msr_info) if (data != 0) return 1; vcpu->arch.ia32_xss = data; - if (vcpu->arch.ia32_xss != host_xss) - add_atomic_switch_msr(vmx, MSR_IA32_XSS, - vcpu->arch.ia32_xss, host_xss, false); - else - clear_atomic_switch_msr(vmx, MSR_IA32_XSS); + if (vcpu->arch.xsaves_enabled) { + if (vcpu->arch.ia32_xss != host_xss) + add_atomic_switch_msr(vmx, MSR_IA32_XSS, + vcpu->arch.ia32_xss, host_xss, false); + else + clear_atomic_switch_msr(vmx, MSR_IA32_XSS); + } break; case MSR_IA32_RTIT_CTL: if ((pt_mode != PT_MODE_HOST_GUEST) || @@ -1998,6 +2005,8 @@ static int vmx_set_msr(struct kvm_vcpu *vcpu, struct msr_data *msr_info) (index >= 2 * intel_pt_validate_cap(vmx->pt_desc.caps, PT_CAP_num_address_ranges))) return 1; + if (is_noncanonical_address(data, vcpu)) + return 1; if (index % 2) vmx->pt_desc.guest.addr_b[index / 2] = data; else @@ -2010,23 +2019,15 @@ static int vmx_set_msr(struct kvm_vcpu *vcpu, struct msr_data *msr_info) /* Check reserved bit, higher 32 bits should be zero */ if ((data >> 32) != 0) return 1; - /* Else, falls through */ + goto find_shared_msr; + default: + find_shared_msr: msr = find_msr_entry(vmx, msr_index); - if (msr) { - u64 old_msr_data = msr->data; - msr->data = data; - if (msr - vmx->guest_msrs < vmx->save_nmsrs) { - preempt_disable(); - ret = kvm_set_shared_msr(msr->index, msr->data, - msr->mask); - preempt_enable(); - if (ret) - msr->data = old_msr_data; - } - break; - } - ret = kvm_set_msr_common(vcpu, msr_info); + if (msr) + ret = vmx_set_guest_msr(vmx, msr, data); + else + ret = kvm_set_msr_common(vcpu, msr_info); } return ret; @@ -2108,21 +2109,6 @@ static int hardware_enable(void) !hv_get_vp_assist_page(cpu)) return -EFAULT; - INIT_LIST_HEAD(&per_cpu(loaded_vmcss_on_cpu, cpu)); - INIT_LIST_HEAD(&per_cpu(blocked_vcpu_on_cpu, cpu)); - spin_lock_init(&per_cpu(blocked_vcpu_on_cpu_lock, cpu)); - - /* - * Now we can enable the vmclear operation in kdump - * since the loaded_vmcss_on_cpu list on this cpu - * has been initialized. - * - * Though the cpu is not in VMX operation now, there - * is no problem to enable the vmclear operation - * for the loaded_vmcss_on_cpu list is empty! - */ - crash_enable_local_vmclear(cpu); - rdmsrl(MSR_IA32_FEATURE_CONTROL, old); test_bits = FEATURE_CONTROL_LOCKED; @@ -2829,6 +2815,9 @@ void vmx_set_cr0(struct kvm_vcpu *vcpu, unsigned long cr0) static int get_ept_level(struct kvm_vcpu *vcpu) { + /* Nested EPT currently only supports 4-level walks. */ + if (is_guest_mode(vcpu) && nested_cpu_has_ept(get_vmcs12(vcpu))) + return 4; if (cpu_has_vmx_ept_5levels() && (cpuid_maxphyaddr(vcpu) > 48)) return 5; return 4; @@ -2851,6 +2840,7 @@ u64 construct_eptp(struct kvm_vcpu *vcpu, unsigned long root_hpa) void vmx_set_cr3(struct kvm_vcpu *vcpu, unsigned long cr3) { struct kvm *kvm = vcpu->kvm; + bool update_guest_cr3 = true; unsigned long guest_cr3; u64 eptp; @@ -2867,15 +2857,17 @@ void vmx_set_cr3(struct kvm_vcpu *vcpu, unsigned long cr3) spin_unlock(&to_kvm_vmx(kvm)->ept_pointer_lock); } - if (enable_unrestricted_guest || is_paging(vcpu) || - is_guest_mode(vcpu)) - guest_cr3 = kvm_read_cr3(vcpu); - else + if (!enable_unrestricted_guest && !is_paging(vcpu)) guest_cr3 = to_kvm_vmx(kvm)->ept_identity_map_addr; + else if (test_bit(VCPU_EXREG_CR3, (ulong *)&vcpu->arch.regs_avail)) + guest_cr3 = vcpu->arch.cr3; + else /* vmcs01.GUEST_CR3 is already up-to-date. */ + update_guest_cr3 = false; ept_load_pdptrs(vcpu); } - vmcs_writel(GUEST_CR3, guest_cr3); + if (update_guest_cr3) + vmcs_writel(GUEST_CR3, guest_cr3); } int vmx_set_cr4(struct kvm_vcpu *vcpu, unsigned long cr4) @@ -3700,24 +3692,29 @@ static int vmx_deliver_nested_posted_interrupt(struct kvm_vcpu *vcpu, * 2. If target vcpu isn't running(root mode), kick it to pick up the * interrupt from PIR in next vmentry. */ -static void vmx_deliver_posted_interrupt(struct kvm_vcpu *vcpu, int vector) +static int vmx_deliver_posted_interrupt(struct kvm_vcpu *vcpu, int vector) { struct vcpu_vmx *vmx = to_vmx(vcpu); int r; r = vmx_deliver_nested_posted_interrupt(vcpu, vector); if (!r) - return; + return 0; + + if (!vcpu->arch.apicv_active) + return -1; if (pi_test_and_set_pir(vector, &vmx->pi_desc)) - return; + return 0; /* If a previous notification has sent the IPI, nothing to do. */ if (pi_test_and_set_on(&vmx->pi_desc)) - return; + return 0; if (!kvm_vcpu_trigger_posted_interrupt(vcpu, false)) kvm_vcpu_kick(vcpu); + + return 0; } /* @@ -3788,6 +3785,8 @@ void vmx_set_constant_host_state(struct vcpu_vmx *vmx) void set_cr4_guest_host_mask(struct vcpu_vmx *vmx) { + BUILD_BUG_ON(KVM_CR4_GUEST_OWNED_BITS & ~KVM_POSSIBLE_CR4_GUEST_BITS); + vmx->vcpu.arch.cr4_guest_owned_bits = KVM_CR4_GUEST_OWNED_BITS; if (enable_ept) vmx->vcpu.arch.cr4_guest_owned_bits |= X86_CR4_PGE; @@ -3904,6 +3903,8 @@ static void vmx_compute_secondary_exec_control(struct vcpu_vmx *vmx) guest_cpuid_has(vcpu, X86_FEATURE_XSAVE) && guest_cpuid_has(vcpu, X86_FEATURE_XSAVES); + vcpu->arch.xsaves_enabled = xsaves_enabled; + if (!xsaves_enabled) exec_control &= ~SECONDARY_EXEC_XSAVES; @@ -3993,7 +3994,7 @@ static void ept_set_mmio_spte_mask(void) * of an EPT paging-structure entry is 110b (write/execute). */ kvm_mmu_set_mmio_spte_mask(VMX_EPT_RWX_MASK, - VMX_EPT_MISCONFIG_WX_VALUE); + VMX_EPT_MISCONFIG_WX_VALUE, 0); } #define VMX_XSS_EXIT_BITMAP 0 @@ -4076,7 +4077,20 @@ static void vmx_vcpu_setup(struct vcpu_vmx *vmx) continue; vmx->guest_msrs[j].index = i; vmx->guest_msrs[j].data = 0; - vmx->guest_msrs[j].mask = -1ull; + + switch (index) { + case MSR_IA32_TSX_CTRL: + /* + * No need to pass TSX_CTRL_CPUID_CLEAR through, so + * let's avoid changing CPUID bits under the host + * kernel's feet. + */ + vmx->guest_msrs[j].mask = ~(u64)TSX_CTRL_CPUID_CLEAR; + break; + default: + vmx->guest_msrs[j].mask = -1ull; + break; + } ++vmx->nmsrs; } @@ -4334,8 +4348,13 @@ static int vmx_nmi_allowed(struct kvm_vcpu *vcpu) static int vmx_interrupt_allowed(struct kvm_vcpu *vcpu) { - return (!to_vmx(vcpu)->nested.nested_run_pending && - vmcs_readl(GUEST_RFLAGS) & X86_EFLAGS_IF) && + if (to_vmx(vcpu)->nested.nested_run_pending) + return false; + + if (is_guest_mode(vcpu) && nested_exit_on_intr(vcpu)) + return true; + + return (vmcs_readl(GUEST_RFLAGS) & X86_EFLAGS_IF) && !(vmcs_read32(GUEST_INTERRUPTIBILITY_INFO) & (GUEST_INTR_STATE_STI | GUEST_INTR_STATE_MOV_SS)); } @@ -4429,7 +4448,7 @@ static int handle_rmode_exception(struct kvm_vcpu *vcpu, */ static void kvm_machine_check(void) { -#if defined(CONFIG_X86_MCE) && defined(CONFIG_X86_64) +#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, @@ -6090,7 +6109,11 @@ static int vmx_sync_pir_to_irr(struct kvm_vcpu *vcpu) static bool vmx_dy_apicv_has_pending_interrupt(struct kvm_vcpu *vcpu) { - return pi_test_on(vcpu_to_pi_desc(vcpu)); + struct pi_desc *pi_desc = vcpu_to_pi_desc(vcpu); + + return pi_test_on(pi_desc) || + (pi_test_sn(pi_desc) && + !bitmap_empty((unsigned long *)pi_desc->pir, NR_VECTORS)); } static void vmx_load_eoi_exitmap(struct kvm_vcpu *vcpu, u64 *eoi_exit_bitmap) @@ -6429,11 +6452,6 @@ static void vmx_vcpu_run(struct kvm_vcpu *vcpu) kvm_load_guest_xcr0(vcpu); - if (static_cpu_has(X86_FEATURE_PKU) && - kvm_read_cr4_bits(vcpu, X86_CR4_PKE) && - vcpu->arch.pkru != vmx->host_pkru) - __write_pkru(vcpu->arch.pkru); - pt_guest_enter(vmx); atomic_switch_perf_msrs(vmx); @@ -6513,18 +6531,6 @@ static void vmx_vcpu_run(struct kvm_vcpu *vcpu) pt_guest_exit(vmx); - /* - * eager fpu is enabled if PKEY is supported and CR4 is switched - * back on host, so it is safe to read guest PKRU from current - * XSAVE. - */ - if (static_cpu_has(X86_FEATURE_PKU) && - kvm_read_cr4_bits(vcpu, X86_CR4_PKE)) { - vcpu->arch.pkru = rdpkru(); - if (vcpu->arch.pkru != vmx->host_pkru) - __write_pkru(vmx->host_pkru); - } - kvm_put_guest_xcr0(vcpu); vmx->nested.nested_run_pending = 0; @@ -6550,6 +6556,10 @@ static struct kvm *vmx_vm_alloc(void) struct kvm_vmx *kvm_vmx = __vmalloc(sizeof(struct kvm_vmx), GFP_KERNEL_ACCOUNT | __GFP_ZERO, PAGE_KERNEL); + + if (!kvm_vmx) + return NULL; + return &kvm_vmx->kvm; } @@ -6569,6 +6579,7 @@ static void vmx_free_vcpu(struct kvm_vcpu *vcpu) free_loaded_vmcs(vmx->loaded_vmcs); kfree(vmx->guest_msrs); kvm_vcpu_uninit(vcpu); + kmem_cache_free(x86_fpu_cache, vmx->vcpu.arch.user_fpu); kmem_cache_free(x86_fpu_cache, vmx->vcpu.arch.guest_fpu); kmem_cache_free(kvm_vcpu_cache, vmx); } @@ -6584,12 +6595,20 @@ static struct kvm_vcpu *vmx_create_vcpu(struct kvm *kvm, unsigned int id) if (!vmx) return ERR_PTR(-ENOMEM); + vmx->vcpu.arch.user_fpu = kmem_cache_zalloc(x86_fpu_cache, + GFP_KERNEL_ACCOUNT); + if (!vmx->vcpu.arch.user_fpu) { + printk(KERN_ERR "kvm: failed to allocate kvm userspace's fpu\n"); + err = -ENOMEM; + goto free_partial_vcpu; + } + vmx->vcpu.arch.guest_fpu = kmem_cache_zalloc(x86_fpu_cache, GFP_KERNEL_ACCOUNT); if (!vmx->vcpu.arch.guest_fpu) { printk(KERN_ERR "kvm: failed to allocate vcpu's fpu\n"); err = -ENOMEM; - goto free_partial_vcpu; + goto free_user_fpu; } vmx->vpid = allocate_vpid(); @@ -6654,8 +6673,7 @@ static struct kvm_vcpu *vmx_create_vcpu(struct kvm *kvm, unsigned int id) if (nested) nested_vmx_setup_ctls_msrs(&vmx->nested.msrs, - vmx_capability.ept, - kvm_vcpu_apicv_active(&vmx->vcpu)); + vmx_capability.ept); else memset(&vmx->nested.msrs, 0, sizeof(vmx->nested.msrs)); @@ -6686,6 +6704,8 @@ uninit_vcpu: free_vcpu: free_vpid(vmx->vpid); kmem_cache_free(x86_fpu_cache, vmx->vcpu.arch.guest_fpu); +free_user_fpu: + kmem_cache_free(x86_fpu_cache, vmx->vcpu.arch.user_fpu); free_partial_vcpu: kmem_cache_free(kvm_vcpu_cache, vmx); return ERR_PTR(err); @@ -6736,8 +6756,7 @@ static void __init vmx_check_processor_compat(void *rtn) if (setup_vmcs_config(&vmcs_conf, &vmx_cap) < 0) *(int *)rtn = -EIO; if (nested) - nested_vmx_setup_ctls_msrs(&vmcs_conf.nested, vmx_cap.ept, - enable_apicv); + nested_vmx_setup_ctls_msrs(&vmcs_conf.nested, vmx_cap.ept); if (memcmp(&vmcs_config, &vmcs_conf, sizeof(struct vmcs_config)) != 0) { printk(KERN_ERR "kvm: CPU %d feature inconsistency!\n", smp_processor_id()); @@ -6949,6 +6968,9 @@ static void vmx_cpuid_update(struct kvm_vcpu *vcpu) { struct vcpu_vmx *vmx = to_vmx(vcpu); + /* xsaves_enabled is recomputed in vmx_compute_secondary_exec_control(). */ + vcpu->arch.xsaves_enabled = false; + if (cpu_has_secondary_exec_ctrls()) { vmx_compute_secondary_exec_control(vmx); vmcs_set_secondary_exec_control(vmx->secondary_exec_control); @@ -6969,6 +6991,15 @@ static void vmx_cpuid_update(struct kvm_vcpu *vcpu) if (boot_cpu_has(X86_FEATURE_INTEL_PT) && guest_cpuid_has(vcpu, X86_FEATURE_INTEL_PT)) update_intel_pt_cfg(vcpu); + + if (boot_cpu_has(X86_FEATURE_RTM)) { + struct shared_msr_entry *msr; + msr = find_msr_entry(vmx, MSR_IA32_TSX_CTRL); + if (msr) { + bool enabled = guest_cpuid_has(vcpu, X86_FEATURE_RTM); + vmx_set_guest_msr(vmx, msr, enabled ? 0 : TSX_CTRL_RTM_DISABLE); + } + } } static void vmx_set_supported_cpuid(u32 func, struct kvm_cpuid_entry2 *entry) @@ -6982,6 +7013,40 @@ static void vmx_request_immediate_exit(struct kvm_vcpu *vcpu) to_vmx(vcpu)->req_immediate_exit = true; } +static int vmx_check_intercept_io(struct kvm_vcpu *vcpu, + struct x86_instruction_info *info) +{ + struct vmcs12 *vmcs12 = get_vmcs12(vcpu); + unsigned short port; + bool intercept; + int size; + + if (info->intercept == x86_intercept_in || + info->intercept == x86_intercept_ins) { + port = info->src_val; + size = info->dst_bytes; + } else { + port = info->dst_val; + size = info->src_bytes; + } + + /* + * If the 'use IO bitmaps' VM-execution control is 0, IO instruction + * VM-exits depend on the 'unconditional IO exiting' VM-execution + * control. + * + * Otherwise, IO instruction VM-exits are controlled by the IO bitmaps. + */ + if (!nested_cpu_has(vmcs12, CPU_BASED_USE_IO_BITMAPS)) + intercept = nested_cpu_has(vmcs12, + CPU_BASED_UNCOND_IO_EXITING); + else + intercept = nested_vmx_check_io_bitmaps(vcpu, port, size); + + /* FIXME: produce nested vmexit and return X86EMUL_INTERCEPTED. */ + return intercept ? X86EMUL_UNHANDLEABLE : X86EMUL_CONTINUE; +} + static int vmx_check_intercept(struct kvm_vcpu *vcpu, struct x86_instruction_info *info, enum x86_intercept_stage stage) @@ -6989,19 +7054,45 @@ static int vmx_check_intercept(struct kvm_vcpu *vcpu, struct vmcs12 *vmcs12 = get_vmcs12(vcpu); struct x86_emulate_ctxt *ctxt = &vcpu->arch.emulate_ctxt; + switch (info->intercept) { /* * RDPID causes #UD if disabled through secondary execution controls. * Because it is marked as EmulateOnUD, we need to intercept it here. */ - if (info->intercept == x86_intercept_rdtscp && - !nested_cpu_has2(vmcs12, SECONDARY_EXEC_RDTSCP)) { - ctxt->exception.vector = UD_VECTOR; - ctxt->exception.error_code_valid = false; - return X86EMUL_PROPAGATE_FAULT; - } + case x86_intercept_rdtscp: + if (!nested_cpu_has2(vmcs12, SECONDARY_EXEC_RDTSCP)) { + ctxt->exception.vector = UD_VECTOR; + ctxt->exception.error_code_valid = false; + return X86EMUL_PROPAGATE_FAULT; + } + break; + + case x86_intercept_in: + case x86_intercept_ins: + case x86_intercept_out: + case x86_intercept_outs: + return vmx_check_intercept_io(vcpu, info); + + case x86_intercept_lgdt: + case x86_intercept_lidt: + case x86_intercept_lldt: + case x86_intercept_ltr: + case x86_intercept_sgdt: + case x86_intercept_sidt: + case x86_intercept_sldt: + case x86_intercept_str: + if (!nested_cpu_has2(vmcs12, SECONDARY_EXEC_DESC)) + return X86EMUL_CONTINUE; + + /* FIXME: produce nested vmexit and return X86EMUL_INTERCEPTED. */ + break; /* TODO: check more intercepts... */ - return X86EMUL_CONTINUE; + default: + break; + } + + return X86EMUL_UNHANDLEABLE; } #ifdef CONFIG_X86_64 @@ -7096,11 +7187,11 @@ static void vmx_flush_log_dirty(struct kvm *kvm) kvm_flush_pml_buffers(kvm); } -static int vmx_write_pml_buffer(struct kvm_vcpu *vcpu) +static int vmx_write_pml_buffer(struct kvm_vcpu *vcpu, gpa_t gpa) { struct vmcs12 *vmcs12; struct vcpu_vmx *vmx = to_vmx(vcpu); - gpa_t gpa, dst; + gpa_t dst; if (is_guest_mode(vcpu)) { WARN_ON_ONCE(vmx->nested.pml_full); @@ -7119,7 +7210,7 @@ static int vmx_write_pml_buffer(struct kvm_vcpu *vcpu) return 1; } - gpa = vmcs_read64(GUEST_PHYSICAL_ADDRESS) & ~0xFFFull; + gpa &= ~0xFFFull; dst = vmcs12->pml_address + sizeof(u64) * vmcs12->guest_pml_index; if (kvm_write_guest_page(vcpu->kvm, gpa_to_gfn(dst), &gpa, @@ -7560,7 +7651,7 @@ static __init int hardware_setup(void) if (nested) { nested_vmx_setup_ctls_msrs(&vmcs_config.nested, - vmx_capability.ept, enable_apicv); + vmx_capability.ept); r = nested_vmx_hardware_setup(kvm_vmx_exit_handlers); if (r) @@ -7694,6 +7785,7 @@ static struct kvm_x86_ops vmx_x86_ops __ro_after_init = { .xsaves_supported = vmx_xsaves_supported, .umip_emulated = vmx_umip_emulated, .pt_supported = vmx_pt_supported, + .pku_supported = vmx_pku_supported, .request_immediate_exit = vmx_request_immediate_exit, @@ -7780,7 +7872,7 @@ module_exit(vmx_exit); static int __init vmx_init(void) { - int r; + int r, cpu; #if IS_ENABLED(CONFIG_HYPERV) /* @@ -7831,6 +7923,12 @@ static int __init vmx_init(void) } } + for_each_possible_cpu(cpu) { + INIT_LIST_HEAD(&per_cpu(loaded_vmcss_on_cpu, cpu)); + INIT_LIST_HEAD(&per_cpu(blocked_vcpu_on_cpu, cpu)); + spin_lock_init(&per_cpu(blocked_vcpu_on_cpu_lock, cpu)); + } + #ifdef CONFIG_KEXEC_CORE rcu_assign_pointer(crash_vmclear_loaded_vmcss, crash_vmclear_local_loaded_vmcss); diff --git a/arch/x86/kvm/vmx/vmx.h b/arch/x86/kvm/vmx/vmx.h index 61128b48c503..6935eff28122 100644 --- a/arch/x86/kvm/vmx/vmx.h +++ b/arch/x86/kvm/vmx/vmx.h @@ -256,8 +256,6 @@ struct vcpu_vmx { u64 current_tsc_ratio; - u32 host_pkru; - unsigned long host_debugctlmsr; u64 msr_ia32_power_ctl; diff --git a/arch/x86/kvm/x86.c b/arch/x86/kvm/x86.c index cfd880ab841d..df6f6df902c6 100644 --- a/arch/x86/kvm/x86.c +++ b/arch/x86/kvm/x86.c @@ -90,6 +90,8 @@ u64 __read_mostly efer_reserved_bits = ~((u64)(EFER_SCE | EFER_LME | EFER_LMA)); static u64 __read_mostly efer_reserved_bits = ~((u64)EFER_SCE); #endif +static u64 __read_mostly cr4_reserved_bits = CR4_RESERVED_BITS; + #define VM_STAT(x, ...) offsetof(struct kvm, stat.x), KVM_STAT_VM, ## __VA_ARGS__ #define VCPU_STAT(x, ...) offsetof(struct kvm_vcpu, stat.x), KVM_STAT_VCPU, ## __VA_ARGS__ @@ -295,13 +297,14 @@ int kvm_set_shared_msr(unsigned slot, u64 value, u64 mask) struct kvm_shared_msrs *smsr = per_cpu_ptr(shared_msrs, cpu); int err; - if (((value ^ smsr->values[slot].curr) & mask) == 0) + value = (value & mask) | (smsr->values[slot].host & ~mask); + if (value == smsr->values[slot].curr) return 0; - smsr->values[slot].curr = value; err = wrmsrl_safe(shared_msrs_global.msrs[slot], value); if (err) return 1; + smsr->values[slot].curr = value; if (!smsr->registered) { smsr->urn.on_user_return = kvm_on_user_return; user_return_notifier_register(&smsr->urn); @@ -437,6 +440,14 @@ void kvm_deliver_exception_payload(struct kvm_vcpu *vcpu) * for #DB exceptions under VMX. */ vcpu->arch.dr6 ^= payload & DR6_RTM; + + /* + * The #DB payload is defined as compatible with the 'pending + * debug exceptions' field under VMX, not DR6. While bit 12 is + * defined in the 'pending debug exceptions' field (enabled + * breakpoint), it is reserved and must be zero in DR6. + */ + vcpu->arch.dr6 &= ~BIT(12); break; case PF_VECTOR: vcpu->arch.cr2 = payload; @@ -816,11 +827,25 @@ void kvm_load_guest_xcr0(struct kvm_vcpu *vcpu) xsetbv(XCR_XFEATURE_ENABLED_MASK, vcpu->arch.xcr0); vcpu->guest_xcr0_loaded = 1; } + + if (static_cpu_has(X86_FEATURE_PKU) && + (kvm_read_cr4_bits(vcpu, X86_CR4_PKE) || + (vcpu->arch.xcr0 & XFEATURE_MASK_PKRU)) && + vcpu->arch.pkru != vcpu->arch.host_pkru) + __write_pkru(vcpu->arch.pkru); } EXPORT_SYMBOL_GPL(kvm_load_guest_xcr0); void kvm_put_guest_xcr0(struct kvm_vcpu *vcpu) { + if (static_cpu_has(X86_FEATURE_PKU) && + (kvm_read_cr4_bits(vcpu, X86_CR4_PKE) || + (vcpu->arch.xcr0 & XFEATURE_MASK_PKRU))) { + vcpu->arch.pkru = rdpkru(); + if (vcpu->arch.pkru != vcpu->arch.host_pkru) + __write_pkru(vcpu->arch.host_pkru); + } + if (vcpu->guest_xcr0_loaded) { if (vcpu->arch.xcr0 != host_xcr0) xsetbv(XCR_XFEATURE_ENABLED_MASK, host_xcr0); @@ -880,9 +905,38 @@ int kvm_set_xcr(struct kvm_vcpu *vcpu, u32 index, u64 xcr) } EXPORT_SYMBOL_GPL(kvm_set_xcr); +static u64 kvm_host_cr4_reserved_bits(struct cpuinfo_x86 *c) +{ + u64 reserved_bits = CR4_RESERVED_BITS; + + if (!cpu_has(c, X86_FEATURE_XSAVE)) + reserved_bits |= X86_CR4_OSXSAVE; + + if (!cpu_has(c, X86_FEATURE_SMEP)) + reserved_bits |= X86_CR4_SMEP; + + if (!cpu_has(c, X86_FEATURE_SMAP)) + reserved_bits |= X86_CR4_SMAP; + + if (!cpu_has(c, X86_FEATURE_FSGSBASE)) + reserved_bits |= X86_CR4_FSGSBASE; + + if (!cpu_has(c, X86_FEATURE_PKU)) + reserved_bits |= X86_CR4_PKE; + + if (!cpu_has(c, X86_FEATURE_LA57) && + !(cpuid_ecx(0x7) & bit(X86_FEATURE_LA57))) + reserved_bits |= X86_CR4_LA57; + + if (!cpu_has(c, X86_FEATURE_UMIP) && !kvm_x86_ops->umip_emulated()) + reserved_bits |= X86_CR4_UMIP; + + return reserved_bits; +} + static int kvm_valid_cr4(struct kvm_vcpu *vcpu, unsigned long cr4) { - if (cr4 & CR4_RESERVED_BITS) + if (cr4 & cr4_reserved_bits) return -EINVAL; if (!guest_cpuid_has(vcpu, X86_FEATURE_XSAVE) && (cr4 & X86_CR4_OSXSAVE)) @@ -921,6 +975,8 @@ int kvm_set_cr4(struct kvm_vcpu *vcpu, unsigned long cr4) if (is_long_mode(vcpu)) { if (!(cr4 & X86_CR4_PAE)) return 1; + if ((cr4 ^ old_cr4) & X86_CR4_LA57) + return 1; } else if (is_paging(vcpu) && (cr4 & X86_CR4_PAE) && ((cr4 ^ old_cr4) & pdptr_bits) && !load_pdptrs(vcpu, vcpu->arch.walk_mmu, @@ -1048,9 +1104,11 @@ static u64 kvm_dr6_fixed(struct kvm_vcpu *vcpu) static int __kvm_set_dr(struct kvm_vcpu *vcpu, int dr, unsigned long val) { + size_t size = ARRAY_SIZE(vcpu->arch.db); + switch (dr) { case 0 ... 3: - vcpu->arch.db[dr] = val; + vcpu->arch.db[array_index_nospec(dr, size)] = val; if (!(vcpu->guest_debug & KVM_GUESTDBG_USE_HW_BP)) vcpu->arch.eff_db[dr] = val; break; @@ -1087,9 +1145,11 @@ EXPORT_SYMBOL_GPL(kvm_set_dr); int kvm_get_dr(struct kvm_vcpu *vcpu, int dr, unsigned long *val) { + size_t size = ARRAY_SIZE(vcpu->arch.db); + switch (dr) { case 0 ... 3: - *val = vcpu->arch.db[dr]; + *val = vcpu->arch.db[array_index_nospec(dr, size)]; break; case 4: /* fall through */ @@ -1250,27 +1310,18 @@ u64 kvm_get_arch_capabilities(void) data |= ARCH_CAP_SKIP_VMENTRY_L1DFLUSH; /* - * On TAA affected systems, export MDS_NO=0 when: - * - TSX is enabled on the host, i.e. X86_FEATURE_RTM=1. - * - Updated microcode is present. This is detected by - * the presence of ARCH_CAP_TSX_CTRL_MSR and ensures - * that VERW clears CPU buffers. - * - * When MDS_NO=0 is exported, guests deploy clear CPU buffer - * mitigation and don't complain: - * - * "Vulnerable: Clear CPU buffers attempted, no microcode" - * - * If TSX is disabled on the system, guests are also mitigated against - * TAA and clear CPU buffer mitigation is not required for guests. + * On TAA affected systems: + * - nothing to do if TSX is disabled on the host. + * - we emulate TSX_CTRL if present on the host. + * This lets the guest use VERW to clear CPU buffers. */ - if (boot_cpu_has_bug(X86_BUG_TAA) && boot_cpu_has(X86_FEATURE_RTM) && - (data & ARCH_CAP_TSX_CTRL_MSR)) - data &= ~ARCH_CAP_MDS_NO; + if (!boot_cpu_has(X86_FEATURE_RTM)) + data &= ~(ARCH_CAP_TAA_NO | ARCH_CAP_TSX_CTRL_MSR); + else if (!boot_cpu_has_bug(X86_BUG_TAA)) + data |= ARCH_CAP_TAA_NO; return data; } -EXPORT_SYMBOL_GPL(kvm_get_arch_capabilities); static int kvm_get_msr_feature(struct kvm_msr_entry *msr) { @@ -2372,7 +2423,10 @@ static int set_msr_mce(struct kvm_vcpu *vcpu, struct msr_data *msr_info) default: if (msr >= MSR_IA32_MC0_CTL && msr < MSR_IA32_MCx_CTL(bank_num)) { - u32 offset = msr - MSR_IA32_MC0_CTL; + u32 offset = array_index_nospec( + msr - MSR_IA32_MC0_CTL, + MSR_IA32_MCx_CTL(bank_num) - MSR_IA32_MC0_CTL); + /* only 0 or all 1s can be written to IA32_MCi_CTL * some Linux kernels though clear bit 10 in bank 4 to * workaround a BIOS/GART TBL issue on AMD K8s, ignore @@ -2467,43 +2521,47 @@ static void kvm_vcpu_flush_tlb(struct kvm_vcpu *vcpu, bool invalidate_gpa) static void record_steal_time(struct kvm_vcpu *vcpu) { + struct kvm_host_map map; + struct kvm_steal_time *st; + if (!(vcpu->arch.st.msr_val & KVM_MSR_ENABLED)) return; - if (unlikely(kvm_read_guest_cached(vcpu->kvm, &vcpu->arch.st.stime, - &vcpu->arch.st.steal, sizeof(struct kvm_steal_time)))) + /* -EAGAIN is returned in atomic context so we can just return. */ + if (kvm_map_gfn(vcpu, vcpu->arch.st.msr_val >> PAGE_SHIFT, + &map, &vcpu->arch.st.cache, false)) return; + st = map.hva + + offset_in_page(vcpu->arch.st.msr_val & KVM_STEAL_VALID_BITS); + /* * Doing a TLB flush here, on the guest's behalf, can avoid * expensive IPIs. */ - if (xchg(&vcpu->arch.st.steal.preempted, 0) & KVM_VCPU_FLUSH_TLB) + trace_kvm_pv_tlb_flush(vcpu->vcpu_id, + st->preempted & KVM_VCPU_FLUSH_TLB); + if (xchg(&st->preempted, 0) & KVM_VCPU_FLUSH_TLB) kvm_vcpu_flush_tlb(vcpu, false); - if (vcpu->arch.st.steal.version & 1) - vcpu->arch.st.steal.version += 1; /* first time write, random junk */ + vcpu->arch.st.preempted = 0; - vcpu->arch.st.steal.version += 1; + if (st->version & 1) + st->version += 1; /* first time write, random junk */ - kvm_write_guest_cached(vcpu->kvm, &vcpu->arch.st.stime, - &vcpu->arch.st.steal, sizeof(struct kvm_steal_time)); + st->version += 1; smp_wmb(); - vcpu->arch.st.steal.steal += current->sched_info.run_delay - + st->steal += current->sched_info.run_delay - vcpu->arch.st.last_steal; vcpu->arch.st.last_steal = current->sched_info.run_delay; - kvm_write_guest_cached(vcpu->kvm, &vcpu->arch.st.stime, - &vcpu->arch.st.steal, sizeof(struct kvm_steal_time)); - smp_wmb(); - vcpu->arch.st.steal.version += 1; + st->version += 1; - kvm_write_guest_cached(vcpu->kvm, &vcpu->arch.st.stime, - &vcpu->arch.st.steal, sizeof(struct kvm_steal_time)); + kvm_unmap_gfn(vcpu, &map, &vcpu->arch.st.cache, true, false); } int kvm_set_msr_common(struct kvm_vcpu *vcpu, struct msr_data *msr_info) @@ -2570,7 +2628,7 @@ int kvm_set_msr_common(struct kvm_vcpu *vcpu, struct msr_data *msr_info) return kvm_mtrr_set_msr(vcpu, msr, data); case MSR_IA32_APICBASE: return kvm_set_apic_base(vcpu, msr_info); - case APIC_BASE_MSR ... APIC_BASE_MSR + 0x3ff: + case APIC_BASE_MSR ... APIC_BASE_MSR + 0xff: return kvm_x2apic_msr_write(vcpu, msr, data); case MSR_IA32_TSCDEADLINE: kvm_set_lapic_tscdeadline_msr(vcpu, data); @@ -2648,11 +2706,6 @@ int kvm_set_msr_common(struct kvm_vcpu *vcpu, struct msr_data *msr_info) if (data & KVM_STEAL_RESERVED_MASK) return 1; - if (kvm_gfn_to_hva_cache_init(vcpu->kvm, &vcpu->arch.st.stime, - data & KVM_STEAL_VALID_BITS, - sizeof(struct kvm_steal_time))) - return 1; - vcpu->arch.st.msr_val = data; if (!(data & KVM_MSR_ENABLED)) @@ -2792,7 +2845,10 @@ static int get_msr_mce(struct kvm_vcpu *vcpu, u32 msr, u64 *pdata, bool host) default: if (msr >= MSR_IA32_MC0_CTL && msr < MSR_IA32_MCx_CTL(bank_num)) { - u32 offset = msr - MSR_IA32_MC0_CTL; + u32 offset = array_index_nospec( + msr - MSR_IA32_MC0_CTL, + MSR_IA32_MCx_CTL(bank_num) - MSR_IA32_MC0_CTL); + data = vcpu->arch.mce_banks[offset]; break; } @@ -2869,7 +2925,7 @@ int kvm_get_msr_common(struct kvm_vcpu *vcpu, struct msr_data *msr_info) case MSR_IA32_APICBASE: msr_info->data = kvm_get_apic_base(vcpu); break; - case APIC_BASE_MSR ... APIC_BASE_MSR + 0x3ff: + case APIC_BASE_MSR ... APIC_BASE_MSR + 0xff: return kvm_x2apic_msr_read(vcpu, msr_info->index, &msr_info->data); break; case MSR_IA32_TSCDEADLINE: @@ -3305,9 +3361,8 @@ void kvm_arch_vcpu_load(struct kvm_vcpu *vcpu, int cpu) kvm_x86_ops->vcpu_load(vcpu, cpu); - fpregs_assert_state_consistent(); - if (test_thread_flag(TIF_NEED_FPU_LOAD)) - switch_fpu_return(); + /* Save host pkru register if supported */ + vcpu->arch.host_pkru = read_pkru(); /* Apply any externally detected TSC adjustments (due to suspend) */ if (unlikely(vcpu->arch.tsc_offset_adjustment)) { @@ -3348,15 +3403,25 @@ void kvm_arch_vcpu_load(struct kvm_vcpu *vcpu, int cpu) static void kvm_steal_time_set_preempted(struct kvm_vcpu *vcpu) { + struct kvm_host_map map; + struct kvm_steal_time *st; + if (!(vcpu->arch.st.msr_val & KVM_MSR_ENABLED)) return; - vcpu->arch.st.steal.preempted = KVM_VCPU_PREEMPTED; + if (vcpu->arch.st.preempted) + return; - kvm_write_guest_offset_cached(vcpu->kvm, &vcpu->arch.st.stime, - &vcpu->arch.st.steal.preempted, - offsetof(struct kvm_steal_time, preempted), - sizeof(vcpu->arch.st.steal.preempted)); + if (kvm_map_gfn(vcpu, vcpu->arch.st.msr_val >> PAGE_SHIFT, &map, + &vcpu->arch.st.cache, true)) + return; + + st = map.hva + + offset_in_page(vcpu->arch.st.msr_val & KVM_STEAL_VALID_BITS); + + st->preempted = vcpu->arch.st.preempted = KVM_VCPU_PREEMPTED; + + kvm_unmap_gfn(vcpu, &map, &vcpu->arch.st.cache, true, true); } void kvm_arch_vcpu_put(struct kvm_vcpu *vcpu) @@ -3492,7 +3557,7 @@ static int kvm_vcpu_ioctl_x86_setup_mce(struct kvm_vcpu *vcpu, unsigned bank_num = mcg_cap & 0xff, bank; r = -EINVAL; - if (!bank_num || bank_num >= KVM_MAX_MCE_BANKS) + if (!bank_num || bank_num > KVM_MAX_MCE_BANKS) goto out; if (mcg_cap & ~(kvm_mce_cap_supported | 0xff | 0xff0000)) goto out; @@ -4285,6 +4350,7 @@ long kvm_arch_vcpu_ioctl(struct file *filp, case KVM_SET_NESTED_STATE: { struct kvm_nested_state __user *user_kvm_nested_state = argp; struct kvm_nested_state kvm_state; + int idx; r = -EINVAL; if (!kvm_x86_ops->set_nested_state) @@ -4308,7 +4374,9 @@ long kvm_arch_vcpu_ioctl(struct file *filp, && !(kvm_state.flags & KVM_STATE_NESTED_GUEST_MODE)) break; + idx = srcu_read_lock(&vcpu->kvm->srcu); r = kvm_x86_ops->set_nested_state(vcpu, user_kvm_nested_state, &kvm_state); + srcu_read_unlock(&vcpu->kvm->srcu, idx); break; } case KVM_GET_SUPPORTED_HV_CPUID: { @@ -6214,11 +6282,11 @@ static int handle_emulation_failure(struct kvm_vcpu *vcpu, int emulation_type) return r; } -static bool reexecute_instruction(struct kvm_vcpu *vcpu, gva_t cr2, +static bool reexecute_instruction(struct kvm_vcpu *vcpu, gpa_t cr2_or_gpa, bool write_fault_to_shadow_pgtable, int emulation_type) { - gpa_t gpa = cr2; + gpa_t gpa = cr2_or_gpa; kvm_pfn_t pfn; if (!(emulation_type & EMULTYPE_ALLOW_RETRY)) @@ -6232,7 +6300,7 @@ static bool reexecute_instruction(struct kvm_vcpu *vcpu, gva_t cr2, * Write permission should be allowed since only * write access need to be emulated. */ - gpa = kvm_mmu_gva_to_gpa_write(vcpu, cr2, NULL); + gpa = kvm_mmu_gva_to_gpa_write(vcpu, cr2_or_gpa, NULL); /* * If the mapping is invalid in guest, let cpu retry @@ -6289,10 +6357,10 @@ static bool reexecute_instruction(struct kvm_vcpu *vcpu, gva_t cr2, } static bool retry_instruction(struct x86_emulate_ctxt *ctxt, - unsigned long cr2, int emulation_type) + gpa_t cr2_or_gpa, int emulation_type) { struct kvm_vcpu *vcpu = emul_to_vcpu(ctxt); - unsigned long last_retry_eip, last_retry_addr, gpa = cr2; + unsigned long last_retry_eip, last_retry_addr, gpa = cr2_or_gpa; last_retry_eip = vcpu->arch.last_retry_eip; last_retry_addr = vcpu->arch.last_retry_addr; @@ -6321,14 +6389,14 @@ static bool retry_instruction(struct x86_emulate_ctxt *ctxt, if (x86_page_table_writing_insn(ctxt)) return false; - if (ctxt->eip == last_retry_eip && last_retry_addr == cr2) + if (ctxt->eip == last_retry_eip && last_retry_addr == cr2_or_gpa) return false; vcpu->arch.last_retry_eip = ctxt->eip; - vcpu->arch.last_retry_addr = cr2; + vcpu->arch.last_retry_addr = cr2_or_gpa; if (!vcpu->arch.mmu->direct_map) - gpa = kvm_mmu_gva_to_gpa_write(vcpu, cr2, NULL); + gpa = kvm_mmu_gva_to_gpa_write(vcpu, cr2_or_gpa, NULL); kvm_mmu_unprotect_page(vcpu->kvm, gpa_to_gfn(gpa)); @@ -6472,11 +6540,8 @@ static bool is_vmware_backdoor_opcode(struct x86_emulate_ctxt *ctxt) return false; } -int x86_emulate_instruction(struct kvm_vcpu *vcpu, - unsigned long cr2, - int emulation_type, - void *insn, - int insn_len) +int x86_emulate_instruction(struct kvm_vcpu *vcpu, gpa_t cr2_or_gpa, + int emulation_type, void *insn, int insn_len) { int r; struct x86_emulate_ctxt *ctxt = &vcpu->arch.emulate_ctxt; @@ -6519,8 +6584,9 @@ int x86_emulate_instruction(struct kvm_vcpu *vcpu, if (r != EMULATION_OK) { if (emulation_type & EMULTYPE_TRAP_UD) return EMULATE_FAIL; - if (reexecute_instruction(vcpu, cr2, write_fault_to_spt, - emulation_type)) + if (reexecute_instruction(vcpu, cr2_or_gpa, + write_fault_to_spt, + emulation_type)) return EMULATE_DONE; if (ctxt->have_exception) { /* @@ -6549,7 +6615,7 @@ int x86_emulate_instruction(struct kvm_vcpu *vcpu, return EMULATE_DONE; } - if (retry_instruction(ctxt, cr2, emulation_type)) + if (retry_instruction(ctxt, cr2_or_gpa, emulation_type)) return EMULATE_DONE; /* this is needed for vmware backdoor interface to work since it @@ -6561,7 +6627,7 @@ int x86_emulate_instruction(struct kvm_vcpu *vcpu, restart: /* Save the faulting GPA (cr2) in the address field */ - ctxt->exception.address = cr2; + ctxt->exception.address = cr2_or_gpa; r = x86_emulate_insn(ctxt); @@ -6569,7 +6635,7 @@ restart: return EMULATE_DONE; if (r == EMULATION_FAILED) { - if (reexecute_instruction(vcpu, cr2, write_fault_to_spt, + if (reexecute_instruction(vcpu, cr2_or_gpa, write_fault_to_spt, emulation_type)) return EMULATE_DONE; @@ -6606,7 +6672,7 @@ restart: if (!ctxt->have_exception || exception_type(ctxt->exception.vector) == EXCPT_TRAP) { kvm_rip_write(vcpu, ctxt->eip); - if (r == EMULATE_DONE && ctxt->tf) + if (r == EMULATE_DONE && (ctxt->tf || (vcpu->guest_debug & KVM_GUESTDBG_SINGLESTEP))) kvm_vcpu_do_singlestep(vcpu, &r); __kvm_set_rflags(vcpu, ctxt->eflags); } @@ -6968,33 +7034,25 @@ static struct perf_guest_info_callbacks kvm_guest_cbs = { .handle_intel_pt_intr = kvm_handle_intel_pt_intr, }; +extern u8 __read_mostly shadow_phys_bits; + static void kvm_set_mmio_spte_mask(void) { u64 mask; - int maxphyaddr = boot_cpu_data.x86_phys_bits; - - /* - * Set the reserved bits and the present bit of an paging-structure - * entry to generate page fault with PFER.RSV = 1. - */ /* - * Mask the uppermost physical address bit, which would be reserved as - * long as the supported physical address width is less than 52. + * Set a reserved PA bit in MMIO SPTEs to generate page faults with + * PFEC.RSVD=1 on MMIO accesses. 64-bit PTEs (PAE, x86-64, and EPT + * paging) support a maximum of 52 bits of PA, i.e. if the CPU supports + * 52-bit physical addresses then there are no reserved PA bits in the + * PTEs and so the reserved PA approach must be disabled. */ - mask = 1ull << 51; - - /* Set the present bit. */ - mask |= 1ull; - - /* - * If reserved bit is not supported, clear the present bit to disable - * mmio page fault. - */ - if (IS_ENABLED(CONFIG_X86_64) && maxphyaddr == 52) - mask &= ~1ull; + if (shadow_phys_bits < 52) + mask = BIT_ULL(51) | PT_PRESENT_MASK; + else + mask = 0; - kvm_mmu_set_mmio_spte_mask(mask, mask); + kvm_mmu_set_mmio_spte_mask(mask, mask, ACC_WRITE_MASK | ACC_USER_MASK); } #ifdef CONFIG_X86_64 @@ -7350,7 +7408,7 @@ static void update_cr8_intercept(struct kvm_vcpu *vcpu) kvm_x86_ops->update_cr8_intercept(vcpu, tpr, max_irr); } -static int inject_pending_event(struct kvm_vcpu *vcpu, bool req_int_win) +static int inject_pending_event(struct kvm_vcpu *vcpu) { int r; @@ -7386,7 +7444,7 @@ static int inject_pending_event(struct kvm_vcpu *vcpu, bool req_int_win) * from L2 to L1. */ if (is_guest_mode(vcpu) && kvm_x86_ops->check_nested_events) { - r = kvm_x86_ops->check_nested_events(vcpu, req_int_win); + r = kvm_x86_ops->check_nested_events(vcpu); if (r != 0) return r; } @@ -7448,7 +7506,7 @@ static int inject_pending_event(struct kvm_vcpu *vcpu, bool req_int_win) * KVM_REQ_EVENT only on certain events and not unconditionally? */ if (is_guest_mode(vcpu) && kvm_x86_ops->check_nested_events) { - r = kvm_x86_ops->check_nested_events(vcpu, req_int_win); + r = kvm_x86_ops->check_nested_events(vcpu); if (r != 0) return r; } @@ -7759,9 +7817,8 @@ static void vcpu_load_eoi_exitmap(struct kvm_vcpu *vcpu) kvm_x86_ops->load_eoi_exitmap(vcpu, eoi_exit_bitmap); } -int kvm_arch_mmu_notifier_invalidate_range(struct kvm *kvm, - unsigned long start, unsigned long end, - bool blockable) +void kvm_arch_mmu_notifier_invalidate_range(struct kvm *kvm, + unsigned long start, unsigned long end) { unsigned long apic_address; @@ -7772,8 +7829,6 @@ int kvm_arch_mmu_notifier_invalidate_range(struct kvm *kvm, apic_address = gfn_to_hva(kvm, APIC_DEFAULT_PHYS_BASE >> PAGE_SHIFT); if (start <= apic_address && apic_address < end) kvm_make_all_cpus_request(kvm, KVM_REQ_APIC_PAGE_RELOAD); - - return 0; } void kvm_vcpu_reload_apic_access_page(struct kvm_vcpu *vcpu) @@ -7921,7 +7976,7 @@ static int vcpu_enter_guest(struct kvm_vcpu *vcpu) goto out; } - if (inject_pending_event(vcpu, req_int_win) != 0) + if (inject_pending_event(vcpu) != 0) req_immediate_exit = true; else { /* Enable SMI/NMI/IRQ window open exits if needed. @@ -8016,8 +8071,9 @@ static int vcpu_enter_guest(struct kvm_vcpu *vcpu) wait_lapic_expire(vcpu); guest_enter_irqoff(); - /* The preempt notifier should have taken care of the FPU already. */ - WARN_ON_ONCE(test_thread_flag(TIF_NEED_FPU_LOAD)); + fpregs_assert_state_consistent(); + if (test_thread_flag(TIF_NEED_FPU_LOAD)) + switch_fpu_return(); if (unlikely(vcpu->arch.switch_db_regs)) { set_debugreg(0, 7); @@ -8137,7 +8193,7 @@ static inline int vcpu_block(struct kvm *kvm, struct kvm_vcpu *vcpu) static inline bool kvm_vcpu_running(struct kvm_vcpu *vcpu) { if (is_guest_mode(vcpu) && kvm_x86_ops->check_nested_events) - kvm_x86_ops->check_nested_events(vcpu, false); + kvm_x86_ops->check_nested_events(vcpu); return (vcpu->arch.mp_state == KVM_MP_STATE_RUNNABLE && !vcpu->arch.apf.halted); @@ -8274,12 +8330,26 @@ static int complete_emulated_mmio(struct kvm_vcpu *vcpu) return 0; } +static void kvm_save_current_fpu(struct fpu *fpu) +{ + /* + * If the target FPU state is not resident in the CPU registers, just + * memcpy() from current, else save CPU state directly to the target. + */ + if (test_thread_flag(TIF_NEED_FPU_LOAD)) + memcpy(&fpu->state, ¤t->thread.fpu.state, + fpu_kernel_xstate_size); + else + copy_fpregs_to_fpstate(fpu); +} + /* Swap (qemu) user FPU context for the guest FPU context. */ static void kvm_load_guest_fpu(struct kvm_vcpu *vcpu) { fpregs_lock(); - copy_fpregs_to_fpstate(&vcpu->arch.user_fpu); + 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); @@ -8295,8 +8365,9 @@ static void kvm_put_guest_fpu(struct kvm_vcpu *vcpu) { fpregs_lock(); - copy_fpregs_to_fpstate(vcpu->arch.guest_fpu); - copy_kernel_to_fpregs(&vcpu->arch.user_fpu.state); + kvm_save_current_fpu(vcpu->arch.guest_fpu); + + copy_kernel_to_fpregs(&vcpu->arch.user_fpu->state); fpregs_mark_activate(); fpregs_unlock(); @@ -8517,6 +8588,8 @@ int kvm_arch_vcpu_ioctl_get_mpstate(struct kvm_vcpu *vcpu, struct kvm_mp_state *mp_state) { vcpu_load(vcpu); + if (kvm_mpx_supported()) + kvm_load_guest_fpu(vcpu); kvm_apic_accept_events(vcpu); if (vcpu->arch.mp_state == KVM_MP_STATE_HALTED && @@ -8525,6 +8598,8 @@ int kvm_arch_vcpu_ioctl_get_mpstate(struct kvm_vcpu *vcpu, else mp_state->mp_state = vcpu->arch.mp_state; + if (kvm_mpx_supported()) + kvm_put_guest_fpu(vcpu); vcpu_put(vcpu); return 0; } @@ -8881,6 +8956,9 @@ static void fx_init(struct kvm_vcpu *vcpu) void kvm_arch_vcpu_free(struct kvm_vcpu *vcpu) { void *wbinvd_dirty_mask = vcpu->arch.wbinvd_dirty_mask; + struct gfn_to_pfn_cache *cache = &vcpu->arch.st.cache; + + kvm_release_pfn(cache->pfn, cache->dirty, cache); kvmclock_reset(vcpu); @@ -8941,13 +9019,7 @@ void kvm_arch_vcpu_postcreate(struct kvm_vcpu *vcpu) void kvm_arch_vcpu_destroy(struct kvm_vcpu *vcpu) { - vcpu->arch.apf.msr_val = 0; - - vcpu_load(vcpu); - kvm_mmu_unload(vcpu); - vcpu_put(vcpu); - - kvm_x86_ops->vcpu_free(vcpu); + kvm_arch_vcpu_free(vcpu); } void kvm_vcpu_reset(struct kvm_vcpu *vcpu, bool init_event) @@ -9139,6 +9211,8 @@ int kvm_arch_hardware_setup(void) if (r != 0) return r; + cr4_reserved_bits = kvm_host_cr4_reserved_bits(&boot_cpu_data); + if (kvm_has_tsc_control) { /* * Make sure the user can only configure tsc_khz values that @@ -9480,6 +9554,13 @@ int kvm_arch_create_memslot(struct kvm *kvm, struct kvm_memory_slot *slot, { int i; + /* + * Clear out the previous array pointers for the KVM_MR_MOVE case. The + * old arrays will be freed by __kvm_set_memory_region() if installing + * the new memslot is successful. + */ + memset(&slot->arch, 0, sizeof(slot->arch)); + for (i = 0; i < KVM_NR_PAGE_SIZES; ++i) { struct kvm_lpage_info *linfo; unsigned long ugfn; @@ -9542,11 +9623,18 @@ out_free: void kvm_arch_memslots_updated(struct kvm *kvm, u64 gen) { + struct kvm_vcpu *vcpu; + int i; + /* * memslots->generation has been incremented. * mmio generation may have reached its maximum value. */ kvm_mmu_invalidate_mmio_sptes(kvm, gen); + + /* Force re-initialization of steal_time cache */ + kvm_for_each_vcpu(i, vcpu, kvm) + kvm_vcpu_kick(vcpu); } int kvm_arch_prepare_memory_region(struct kvm *kvm, @@ -9554,6 +9642,10 @@ int kvm_arch_prepare_memory_region(struct kvm *kvm, const struct kvm_userspace_memory_region *mem, enum kvm_mr_change change) { + if (change == KVM_MR_MOVE) + return kvm_arch_create_memslot(kvm, memslot, + mem->memory_size >> PAGE_SHIFT); + return 0; } @@ -9793,7 +9885,7 @@ void kvm_arch_async_page_ready(struct kvm_vcpu *vcpu, struct kvm_async_pf *work) work->arch.cr3 != vcpu->arch.mmu->get_cr3(vcpu)) return; - vcpu->arch.mmu->page_fault(vcpu, work->gva, 0, true); + vcpu->arch.mmu->page_fault(vcpu, work->cr2_or_gpa, 0, true); } static inline u32 kvm_async_pf_hash_fn(gfn_t gfn) @@ -9876,7 +9968,7 @@ void kvm_arch_async_page_not_present(struct kvm_vcpu *vcpu, { struct x86_exception fault; - trace_kvm_async_pf_not_present(work->arch.token, work->gva); + trace_kvm_async_pf_not_present(work->arch.token, work->cr2_or_gpa); kvm_add_async_pf_gfn(vcpu, work->arch.gfn); if (!(vcpu->arch.apf.msr_val & KVM_ASYNC_PF_ENABLED) || @@ -9904,7 +9996,7 @@ void kvm_arch_async_page_present(struct kvm_vcpu *vcpu, work->arch.token = ~0; /* broadcast wakeup */ else kvm_del_async_pf_gfn(vcpu, work->arch.gfn); - trace_kvm_async_pf_ready(work->arch.token, work->gva); + trace_kvm_async_pf_ready(work->arch.token, work->cr2_or_gpa); if (vcpu->arch.apf.msr_val & KVM_ASYNC_PF_ENABLED && !apf_get_user(vcpu, &val)) { diff --git a/arch/x86/kvm/x86.h b/arch/x86/kvm/x86.h index a470ff0868c5..8c0b13cc3c6a 100644 --- a/arch/x86/kvm/x86.h +++ b/arch/x86/kvm/x86.h @@ -281,7 +281,7 @@ int kvm_mtrr_get_msr(struct kvm_vcpu *vcpu, u32 msr, u64 *pdata); bool kvm_mtrr_check_gfn_range_consistency(struct kvm_vcpu *vcpu, gfn_t gfn, int page_num); bool kvm_vector_hashing_enabled(void); -int x86_emulate_instruction(struct kvm_vcpu *vcpu, unsigned long cr2, +int x86_emulate_instruction(struct kvm_vcpu *vcpu, gpa_t cr2_or_gpa, int emulation_type, void *insn, int insn_len); #define KVM_SUPPORTED_XCR0 (XFEATURE_MASK_FP | XFEATURE_MASK_SSE \ diff --git a/arch/x86/lib/usercopy_64.c b/arch/x86/lib/usercopy_64.c index e0e006f1624e..67a91fd38eef 100644 --- a/arch/x86/lib/usercopy_64.c +++ b/arch/x86/lib/usercopy_64.c @@ -24,6 +24,7 @@ unsigned long __clear_user(void __user *addr, unsigned long size) asm volatile( " testq %[size8],%[size8]\n" " jz 4f\n" + " .align 16\n" "0: movq $0,(%[dst])\n" " addq $8,%[dst]\n" " decl %%ecx ; jnz 0b\n" diff --git a/arch/x86/lib/x86-opcode-map.txt b/arch/x86/lib/x86-opcode-map.txt index e0b85930dd77..5cb9f009f2be 100644 --- a/arch/x86/lib/x86-opcode-map.txt +++ b/arch/x86/lib/x86-opcode-map.txt @@ -333,7 +333,7 @@ AVXcode: 1 06: CLTS 07: SYSRET (o64) 08: INVD -09: WBINVD +09: WBINVD | WBNOINVD (F3) 0a: 0b: UD2 (1B) 0c: @@ -364,7 +364,7 @@ AVXcode: 1 # a ModR/M byte. 1a: BNDCL Gv,Ev (F3) | BNDCU Gv,Ev (F2) | BNDMOV Gv,Ev (66) | BNDLDX Gv,Ev 1b: BNDCN Gv,Ev (F2) | BNDMOV Ev,Gv (66) | BNDMK Gv,Ev (F3) | BNDSTX Ev,Gv -1c: +1c: Grp20 (1A),(1C) 1d: 1e: 1f: NOP Ev @@ -792,6 +792,8 @@ f3: Grp17 (1A) f5: BZHI Gy,Ey,By (v) | PEXT Gy,By,Ey (F3),(v) | PDEP Gy,By,Ey (F2),(v) f6: ADCX Gy,Ey (66) | ADOX Gy,Ey (F3) | MULX By,Gy,rDX,Ey (F2),(v) f7: BEXTR Gy,Ey,By (v) | SHLX Gy,Ey,By (66),(v) | SARX Gy,Ey,By (F3),(v) | SHRX Gy,Ey,By (F2),(v) +f8: MOVDIR64B Gv,Mdqq (66) | ENQCMD Gv,Mdqq (F2) | ENQCMDS Gv,Mdqq (F3) +f9: MOVDIRI My,Gy EndTable Table: 3-byte opcode 2 (0x0f 0x3a) @@ -907,7 +909,7 @@ EndTable GrpTable: Grp3_2 0: TEST Ev,Iz -1: +1: TEST Ev,Iz 2: NOT Ev 3: NEG Ev 4: MUL rAX,Ev @@ -943,9 +945,9 @@ GrpTable: Grp6 EndTable GrpTable: Grp7 -0: SGDT Ms | VMCALL (001),(11B) | VMLAUNCH (010),(11B) | VMRESUME (011),(11B) | VMXOFF (100),(11B) -1: SIDT Ms | MONITOR (000),(11B) | MWAIT (001),(11B) | CLAC (010),(11B) | STAC (011),(11B) -2: LGDT Ms | XGETBV (000),(11B) | XSETBV (001),(11B) | VMFUNC (100),(11B) | XEND (101)(11B) | XTEST (110)(11B) +0: SGDT Ms | VMCALL (001),(11B) | VMLAUNCH (010),(11B) | VMRESUME (011),(11B) | VMXOFF (100),(11B) | PCONFIG (101),(11B) | ENCLV (000),(11B) +1: SIDT Ms | MONITOR (000),(11B) | MWAIT (001),(11B) | CLAC (010),(11B) | STAC (011),(11B) | ENCLS (111),(11B) +2: LGDT Ms | XGETBV (000),(11B) | XSETBV (001),(11B) | VMFUNC (100),(11B) | XEND (101)(11B) | XTEST (110)(11B) | ENCLU (111),(11B) 3: LIDT Ms 4: SMSW Mw/Rv 5: rdpkru (110),(11B) | wrpkru (111),(11B) @@ -1020,7 +1022,7 @@ GrpTable: Grp15 3: vstmxcsr Md (v1) | WRGSBASE Ry (F3),(11B) 4: XSAVE | ptwrite Ey (F3),(11B) 5: XRSTOR | lfence (11B) -6: XSAVEOPT | clwb (66) | mfence (11B) +6: XSAVEOPT | clwb (66) | mfence (11B) | TPAUSE Rd (66),(11B) | UMONITOR Rv (F3),(11B) | UMWAIT Rd (F2),(11B) 7: clflush | clflushopt (66) | sfence (11B) EndTable @@ -1051,6 +1053,10 @@ GrpTable: Grp19 6: vscatterpf1qps/d Wx (66),(ev) EndTable +GrpTable: Grp20 +0: cldemote Mb +EndTable + # AMD's Prefetch Group GrpTable: GrpP 0: PREFETCH diff --git a/arch/x86/math-emu/fpu_system.h b/arch/x86/math-emu/fpu_system.h index f98a0c956764..9b41391867dc 100644 --- a/arch/x86/math-emu/fpu_system.h +++ b/arch/x86/math-emu/fpu_system.h @@ -107,6 +107,8 @@ static inline bool seg_writable(struct desc_struct *d) #define FPU_access_ok(y,z) if ( !access_ok(y,z) ) \ math_abort(FPU_info,SIGSEGV) #define FPU_abort math_abort(FPU_info, SIGSEGV) +#define FPU_copy_from_user(to, from, n) \ + do { if (copy_from_user(to, from, n)) FPU_abort; } while (0) #undef FPU_IGNORE_CODE_SEGV #ifdef FPU_IGNORE_CODE_SEGV @@ -122,7 +124,7 @@ static inline bool seg_writable(struct desc_struct *d) #define FPU_code_access_ok(z) FPU_access_ok((void __user *)FPU_EIP,z) #endif -#define FPU_get_user(x,y) get_user((x),(y)) -#define FPU_put_user(x,y) put_user((x),(y)) +#define FPU_get_user(x,y) do { if (get_user((x),(y))) FPU_abort; } while (0) +#define FPU_put_user(x,y) do { if (put_user((x),(y))) FPU_abort; } while (0) #endif diff --git a/arch/x86/math-emu/reg_ld_str.c b/arch/x86/math-emu/reg_ld_str.c index f3779743d15e..fe6246ff9887 100644 --- a/arch/x86/math-emu/reg_ld_str.c +++ b/arch/x86/math-emu/reg_ld_str.c @@ -85,7 +85,7 @@ int FPU_load_extended(long double __user *s, int stnr) RE_ENTRANT_CHECK_OFF; FPU_access_ok(s, 10); - __copy_from_user(sti_ptr, s, 10); + FPU_copy_from_user(sti_ptr, s, 10); RE_ENTRANT_CHECK_ON; return FPU_tagof(sti_ptr); @@ -1126,9 +1126,9 @@ void frstor(fpu_addr_modes addr_modes, u_char __user *data_address) /* Copy all registers in stack order. */ RE_ENTRANT_CHECK_OFF; FPU_access_ok(s, 80); - __copy_from_user(register_base + offset, s, other); + FPU_copy_from_user(register_base + offset, s, other); if (offset) - __copy_from_user(register_base, s + other, offset); + FPU_copy_from_user(register_base, s + other, offset); RE_ENTRANT_CHECK_ON; for (i = 0; i < 8; i++) { diff --git a/arch/x86/math-emu/wm_sqrt.S b/arch/x86/math-emu/wm_sqrt.S index f031c0e19356..515cdee90df7 100644 --- a/arch/x86/math-emu/wm_sqrt.S +++ b/arch/x86/math-emu/wm_sqrt.S @@ -209,7 +209,7 @@ sqrt_stage_2_finish: #ifdef PARANOID /* It should be possible to get here only if the arg is ffff....ffff */ - cmp $0xffffffff,FPU_fsqrt_arg_1 + cmpl $0xffffffff,FPU_fsqrt_arg_1 jnz sqrt_stage_2_error #endif /* PARANOID */ diff --git a/arch/x86/mm/fault.c b/arch/x86/mm/fault.c index da9684e95595..7aa188950d42 100644 --- a/arch/x86/mm/fault.c +++ b/arch/x86/mm/fault.c @@ -206,7 +206,7 @@ static inline pmd_t *vmalloc_sync_one(pgd_t *pgd, unsigned long address) return pmd_k; } -void vmalloc_sync_all(void) +static void vmalloc_sync(void) { unsigned long address; @@ -214,7 +214,7 @@ void vmalloc_sync_all(void) return; for (address = VMALLOC_START & PMD_MASK; - address >= TASK_SIZE_MAX && address < FIXADDR_TOP; + address >= TASK_SIZE_MAX && address < VMALLOC_END; address += PMD_SIZE) { struct page *page; @@ -233,6 +233,16 @@ void vmalloc_sync_all(void) } } +void vmalloc_sync_mappings(void) +{ + vmalloc_sync(); +} + +void vmalloc_sync_unmappings(void) +{ + vmalloc_sync(); +} + /* * 32-bit: * @@ -335,11 +345,23 @@ out: #else /* CONFIG_X86_64: */ -void vmalloc_sync_all(void) +void vmalloc_sync_mappings(void) { + /* + * 64-bit mappings might allocate new p4d/pud pages + * that need to be propagated to all tasks' PGDs. + */ sync_global_pgds(VMALLOC_START & PGDIR_MASK, VMALLOC_END); } +void vmalloc_sync_unmappings(void) +{ + /* + * Unmappings never allocate or free p4d/pud pages. + * No work is required here. + */ +} + /* * 64-bit: * diff --git a/arch/x86/mm/init.c b/arch/x86/mm/init.c index fd10d91a6115..af352e228fa2 100644 --- a/arch/x86/mm/init.c +++ b/arch/x86/mm/init.c @@ -121,8 +121,6 @@ __ref void *alloc_low_pages(unsigned int num) } else { pfn = pgt_buf_end; pgt_buf_end += num; - printk(KERN_DEBUG "BRK [%#010lx, %#010lx] PGTABLE\n", - pfn << PAGE_SHIFT, (pgt_buf_end << PAGE_SHIFT) - 1); } for (i = 0; i < num; i++) { diff --git a/arch/x86/mm/mmio-mod.c b/arch/x86/mm/mmio-mod.c index b8ef8557d4b3..2a36902d418c 100644 --- a/arch/x86/mm/mmio-mod.c +++ b/arch/x86/mm/mmio-mod.c @@ -372,7 +372,7 @@ static void enter_uniprocessor(void) int cpu; int err; - if (downed_cpus == NULL && + if (!cpumask_available(downed_cpus) && !alloc_cpumask_var(&downed_cpus, GFP_KERNEL)) { pr_notice("Failed to allocate mask\n"); goto out; @@ -402,7 +402,7 @@ static void leave_uniprocessor(void) int cpu; int err; - if (downed_cpus == NULL || cpumask_weight(downed_cpus) == 0) + if (!cpumask_available(downed_cpus) || cpumask_weight(downed_cpus) == 0) return; pr_notice("Re-enabling CPUs...\n"); for_each_cpu(cpu, downed_cpus) { diff --git a/arch/x86/mm/pageattr.c b/arch/x86/mm/pageattr.c index e14e95ea7338..7155b7e0899e 100644 --- a/arch/x86/mm/pageattr.c +++ b/arch/x86/mm/pageattr.c @@ -42,7 +42,8 @@ struct cpa_data { unsigned long pfn; unsigned int flags; unsigned int force_split : 1, - force_static_prot : 1; + force_static_prot : 1, + force_flush_all : 1; struct page **pages; }; @@ -352,10 +353,10 @@ static void cpa_flush(struct cpa_data *data, int cache) return; } - if (cpa->numpages <= tlb_single_page_flush_ceiling) - on_each_cpu(__cpa_flush_tlb, cpa, 1); - else + if (cpa->force_flush_all || cpa->numpages > tlb_single_page_flush_ceiling) flush_tlb_all(); + else + on_each_cpu(__cpa_flush_tlb, cpa, 1); if (!cache) return; @@ -1584,6 +1585,8 @@ static int cpa_process_alias(struct cpa_data *cpa) alias_cpa.flags &= ~(CPA_PAGES_ARRAY | CPA_ARRAY); alias_cpa.curpage = 0; + cpa->force_flush_all = 1; + ret = __change_page_attr_set_clr(&alias_cpa, 0); if (ret) return ret; @@ -1604,6 +1607,7 @@ static int cpa_process_alias(struct cpa_data *cpa) alias_cpa.flags &= ~(CPA_PAGES_ARRAY | CPA_ARRAY); alias_cpa.curpage = 0; + cpa->force_flush_all = 1; /* * The high mapping range is imprecise, so ignore the * return value. @@ -2325,7 +2329,7 @@ int __init kernel_map_pages_in_pgd(pgd_t *pgd, u64 pfn, unsigned long address, .pgd = pgd, .numpages = numpages, .mask_set = __pgprot(0), - .mask_clr = __pgprot(0), + .mask_clr = __pgprot(~page_flags & (_PAGE_NX|_PAGE_RW)), .flags = 0, }; @@ -2334,12 +2338,6 @@ int __init kernel_map_pages_in_pgd(pgd_t *pgd, u64 pfn, unsigned long address, if (!(__supported_pte_mask & _PAGE_NX)) goto out; - if (!(page_flags & _PAGE_NX)) - cpa.mask_clr = __pgprot(_PAGE_NX); - - if (!(page_flags & _PAGE_RW)) - cpa.mask_clr = __pgprot(_PAGE_RW); - if (!(page_flags & _PAGE_ENC)) cpa.mask_clr = pgprot_encrypted(cpa.mask_clr); diff --git a/arch/x86/mm/pgtable.c b/arch/x86/mm/pgtable.c index 1f67b1e15bf6..eed797e8735a 100644 --- a/arch/x86/mm/pgtable.c +++ b/arch/x86/mm/pgtable.c @@ -662,8 +662,8 @@ void __native_set_fixmap(enum fixed_addresses idx, pte_t pte) fixmaps_set++; } -void native_set_fixmap(enum fixed_addresses idx, phys_addr_t phys, - pgprot_t flags) +void native_set_fixmap(unsigned /* enum fixed_addresses */ idx, + phys_addr_t phys, pgprot_t flags) { /* Sanitize 'prot' against any unsupported bits: */ pgprot_val(flags) &= __default_kernel_pte_mask; diff --git a/arch/x86/net/bpf_jit_comp.c b/arch/x86/net/bpf_jit_comp.c index eaaed5bfc4a4..bd318043b259 100644 --- a/arch/x86/net/bpf_jit_comp.c +++ b/arch/x86/net/bpf_jit_comp.c @@ -138,6 +138,19 @@ static bool is_ereg(u32 reg) BIT(BPF_REG_AX)); } +/* + * is_ereg_8l() == true if BPF register 'reg' is mapped to access x86-64 + * lower 8-bit registers dil,sil,bpl,spl,r8b..r15b, which need extra byte + * of encoding. al,cl,dl,bl have simpler encoding. + */ +static bool is_ereg_8l(u32 reg) +{ + return is_ereg(reg) || + (1 << reg) & (BIT(BPF_REG_1) | + BIT(BPF_REG_2) | + BIT(BPF_REG_FP)); +} + static bool is_axreg(u32 reg) { return reg == BPF_REG_0; @@ -747,9 +760,8 @@ st: if (is_imm8(insn->off)) /* STX: *(u8*)(dst_reg + off) = src_reg */ case BPF_STX | BPF_MEM | BPF_B: /* Emit 'mov byte ptr [rax + off], al' */ - if (is_ereg(dst_reg) || is_ereg(src_reg) || - /* We have to add extra byte for x86 SIL, DIL regs */ - src_reg == BPF_REG_1 || src_reg == BPF_REG_2) + if (is_ereg(dst_reg) || is_ereg_8l(src_reg)) + /* Add extra byte for eregs or SIL,DIL,BPL in src_reg */ EMIT2(add_2mod(0x40, dst_reg, src_reg), 0x88); else EMIT1(0x88); diff --git a/arch/x86/net/bpf_jit_comp32.c b/arch/x86/net/bpf_jit_comp32.c index b29e82f190c7..4c9f10b73eb6 100644 --- a/arch/x86/net/bpf_jit_comp32.c +++ b/arch/x86/net/bpf_jit_comp32.c @@ -2056,7 +2056,9 @@ static int do_jit(struct bpf_prog *bpf_prog, int *addrs, u8 *image, STACK_VAR(dst_hi)); EMIT(0x0, 4); } else { - EMIT3(0xC7, add_1reg(0xC0, dst_hi), 0); + /* xor dst_hi,dst_hi */ + EMIT2(0x33, + add_2reg(0xC0, dst_hi, dst_hi)); } break; case BPF_DW: @@ -2157,6 +2159,13 @@ static int do_jit(struct bpf_prog *bpf_prog, int *addrs, u8 *image, add_2reg(0x40, IA32_EBP, IA32_EDX), STACK_VAR(dst_hi)); + } else { + /* mov dreg_lo,dst_lo */ + EMIT2(0x89, add_2reg(0xC0, dreg_lo, dst_lo)); + if (is_jmp64) + /* mov dreg_hi,dst_hi */ + EMIT2(0x89, + add_2reg(0xC0, dreg_hi, dst_hi)); } if (sstk) { @@ -2215,8 +2224,8 @@ static int do_jit(struct bpf_prog *bpf_prog, int *addrs, u8 *image, case BPF_JMP | BPF_JSET | BPF_X: case BPF_JMP32 | BPF_JSET | BPF_X: { bool is_jmp64 = BPF_CLASS(insn->code) == BPF_JMP; - u8 dreg_lo = dstk ? IA32_EAX : dst_lo; - u8 dreg_hi = dstk ? IA32_EDX : dst_hi; + u8 dreg_lo = IA32_EAX; + u8 dreg_hi = IA32_EDX; u8 sreg_lo = sstk ? IA32_ECX : src_lo; u8 sreg_hi = sstk ? IA32_EBX : src_hi; @@ -2241,17 +2250,19 @@ static int do_jit(struct bpf_prog *bpf_prog, int *addrs, u8 *image, } /* and dreg_lo,sreg_lo */ EMIT2(0x23, add_2reg(0xC0, sreg_lo, dreg_lo)); - /* and dreg_hi,sreg_hi */ - EMIT2(0x23, add_2reg(0xC0, sreg_hi, dreg_hi)); - /* or dreg_lo,dreg_hi */ - EMIT2(0x09, add_2reg(0xC0, dreg_lo, dreg_hi)); + if (is_jmp64) { + /* and dreg_hi,sreg_hi */ + EMIT2(0x23, add_2reg(0xC0, sreg_hi, dreg_hi)); + /* or dreg_lo,dreg_hi */ + EMIT2(0x09, add_2reg(0xC0, dreg_lo, dreg_hi)); + } goto emit_cond_jmp; } case BPF_JMP | BPF_JSET | BPF_K: case BPF_JMP32 | BPF_JSET | BPF_K: { bool is_jmp64 = BPF_CLASS(insn->code) == BPF_JMP; - u8 dreg_lo = dstk ? IA32_EAX : dst_lo; - u8 dreg_hi = dstk ? IA32_EDX : dst_hi; + u8 dreg_lo = IA32_EAX; + u8 dreg_hi = IA32_EDX; u8 sreg_lo = IA32_ECX; u8 sreg_hi = IA32_EBX; u32 hi; @@ -2264,6 +2275,13 @@ static int do_jit(struct bpf_prog *bpf_prog, int *addrs, u8 *image, add_2reg(0x40, IA32_EBP, IA32_EDX), STACK_VAR(dst_hi)); + } else { + /* mov dreg_lo,dst_lo */ + EMIT2(0x89, add_2reg(0xC0, dreg_lo, dst_lo)); + if (is_jmp64) + /* mov dreg_hi,dst_hi */ + EMIT2(0x89, + add_2reg(0xC0, dreg_hi, dst_hi)); } /* mov ecx,imm32 */ diff --git a/arch/x86/pci/fixup.c b/arch/x86/pci/fixup.c index 527e69b12002..0c67a5a94de3 100644 --- a/arch/x86/pci/fixup.c +++ b/arch/x86/pci/fixup.c @@ -572,6 +572,10 @@ DECLARE_PCI_FIXUP_EARLY(PCI_VENDOR_ID_INTEL, 0x2fc0, pci_invalid_bar); DECLARE_PCI_FIXUP_EARLY(PCI_VENDOR_ID_INTEL, 0x6f60, pci_invalid_bar); DECLARE_PCI_FIXUP_EARLY(PCI_VENDOR_ID_INTEL, 0x6fa0, pci_invalid_bar); DECLARE_PCI_FIXUP_EARLY(PCI_VENDOR_ID_INTEL, 0x6fc0, pci_invalid_bar); +DECLARE_PCI_FIXUP_EARLY(PCI_VENDOR_ID_INTEL, 0xa1ec, pci_invalid_bar); +DECLARE_PCI_FIXUP_EARLY(PCI_VENDOR_ID_INTEL, 0xa1ed, pci_invalid_bar); +DECLARE_PCI_FIXUP_EARLY(PCI_VENDOR_ID_INTEL, 0xa26c, pci_invalid_bar); +DECLARE_PCI_FIXUP_EARLY(PCI_VENDOR_ID_INTEL, 0xa26d, pci_invalid_bar); /* * Device [1022:7808] @@ -589,6 +593,17 @@ static void pci_fixup_amd_ehci_pme(struct pci_dev *dev) DECLARE_PCI_FIXUP_FINAL(PCI_VENDOR_ID_AMD, 0x7808, pci_fixup_amd_ehci_pme); /* + * Device [1022:7914] + * When in D0, PME# doesn't get asserted when plugging USB 2.0 device. + */ +static void pci_fixup_amd_fch_xhci_pme(struct pci_dev *dev) +{ + dev_info(&dev->dev, "PME# does not work under D0, disabling it\n"); + dev->pme_support &= ~(PCI_PM_CAP_PME_D0 >> PCI_PM_CAP_PME_SHIFT); +} +DECLARE_PCI_FIXUP_FINAL(PCI_VENDOR_ID_AMD, 0x7914, pci_fixup_amd_fch_xhci_pme); + +/* * Apple MacBook Pro: Avoid [mem 0x7fa00000-0x7fbfffff] * * Using the [mem 0x7fa00000-0x7fbfffff] region, e.g., by assigning it to diff --git a/arch/x86/platform/efi/efi.c b/arch/x86/platform/efi/efi.c index 3304f61538a2..9b1b133c860a 100644 --- a/arch/x86/platform/efi/efi.c +++ b/arch/x86/platform/efi/efi.c @@ -481,7 +481,6 @@ void __init efi_init(void) efi_char16_t *c16; char vendor[100] = "unknown"; int i = 0; - void *tmp; #ifdef CONFIG_X86_32 if (boot_params.efi_info.efi_systab_hi || @@ -506,14 +505,16 @@ void __init efi_init(void) /* * Show what we know for posterity */ - c16 = tmp = early_memremap(efi.systab->fw_vendor, 2); + c16 = early_memremap_ro(efi.systab->fw_vendor, + sizeof(vendor) * sizeof(efi_char16_t)); if (c16) { - for (i = 0; i < sizeof(vendor) - 1 && *c16; ++i) - vendor[i] = *c16++; + for (i = 0; i < sizeof(vendor) - 1 && c16[i]; ++i) + vendor[i] = c16[i]; vendor[i] = '\0'; - } else + early_memunmap(c16, sizeof(vendor) * sizeof(efi_char16_t)); + } else { pr_err("Could not map the firmware vendor!\n"); - early_memunmap(tmp, 2); + } pr_info("EFI v%u.%.02u by %s\n", efi.systab->hdr.revision >> 16, @@ -930,16 +931,14 @@ static void __init __efi_enter_virtual_mode(void) if (efi_alloc_page_tables()) { pr_err("Failed to allocate EFI page tables\n"); - clear_bit(EFI_RUNTIME_SERVICES, &efi.flags); - return; + goto err; } efi_merge_regions(); new_memmap = efi_map_regions(&count, &pg_shift); if (!new_memmap) { pr_err("Error reallocating memory, EFI runtime non-functional!\n"); - clear_bit(EFI_RUNTIME_SERVICES, &efi.flags); - return; + goto err; } pa = __pa(new_memmap); @@ -953,8 +952,7 @@ static void __init __efi_enter_virtual_mode(void) if (efi_memmap_init_late(pa, efi.memmap.desc_size * count)) { pr_err("Failed to remap late EFI memory map\n"); - clear_bit(EFI_RUNTIME_SERVICES, &efi.flags); - return; + goto err; } if (efi_enabled(EFI_DBG)) { @@ -962,12 +960,11 @@ static void __init __efi_enter_virtual_mode(void) efi_print_memmap(); } - BUG_ON(!efi.systab); + if (WARN_ON(!efi.systab)) + goto err; - if (efi_setup_page_tables(pa, 1 << pg_shift)) { - clear_bit(EFI_RUNTIME_SERVICES, &efi.flags); - return; - } + if (efi_setup_page_tables(pa, 1 << pg_shift)) + goto err; efi_sync_low_kernel_mappings(); @@ -987,9 +984,9 @@ static void __init __efi_enter_virtual_mode(void) } if (status != EFI_SUCCESS) { - pr_alert("Unable to switch EFI into virtual mode (status=%lx)!\n", - status); - panic("EFI call to SetVirtualAddressMap() failed!"); + pr_err("Unable to switch EFI into virtual mode (status=%lx)!\n", + status); + goto err; } efi_free_boot_services(); @@ -1018,6 +1015,10 @@ static void __init __efi_enter_virtual_mode(void) /* clean DUMMY object */ efi_delete_dummy_variable(); + return; + +err: + clear_bit(EFI_RUNTIME_SERVICES, &efi.flags); } void __init efi_enter_virtual_mode(void) diff --git a/arch/x86/platform/efi/efi_64.c b/arch/x86/platform/efi/efi_64.c index 08ce8177c3af..e39c930cfbd1 100644 --- a/arch/x86/platform/efi/efi_64.c +++ b/arch/x86/platform/efi/efi_64.c @@ -316,7 +316,7 @@ void efi_sync_low_kernel_mappings(void) static inline phys_addr_t virt_to_phys_or_null_size(void *va, unsigned long size) { - bool bad_size; + phys_addr_t pa; if (!va) return 0; @@ -324,16 +324,13 @@ virt_to_phys_or_null_size(void *va, unsigned long size) if (virt_addr_valid(va)) return virt_to_phys(va); - /* - * A fully aligned variable on the stack is guaranteed not to - * cross a page bounary. Try to catch strings on the stack by - * checking that 'size' is a power of two. - */ - bad_size = size > PAGE_SIZE || !is_power_of_2(size); + pa = slow_virt_to_phys(va); - WARN_ON(!IS_ALIGNED((unsigned long)va, size) || bad_size); + /* check if the object crosses a page boundary */ + if (WARN_ON((pa ^ (pa + size - 1)) & PAGE_MASK)) + return 0; - return slow_virt_to_phys(va); + return pa; } #define virt_to_phys_or_null(addr) \ @@ -392,11 +389,12 @@ int __init efi_setup_page_tables(unsigned long pa_memmap, unsigned num_pages) return 0; page = alloc_page(GFP_KERNEL|__GFP_DMA32); - if (!page) - panic("Unable to allocate EFI runtime stack < 4GB\n"); + if (!page) { + pr_err("Unable to allocate EFI runtime stack < 4GB\n"); + return 1; + } - efi_scratch.phys_stack = virt_to_phys(page_address(page)); - efi_scratch.phys_stack += PAGE_SIZE; /* stack grows down */ + efi_scratch.phys_stack = page_to_phys(page + 1); /* stack grows down */ npages = (_etext - _text) >> PAGE_SHIFT; text = __pa(_text); @@ -790,6 +788,8 @@ static efi_status_t efi_thunk_get_variable(efi_char16_t *name, efi_guid_t *vendor, u32 *attr, unsigned long *data_size, void *data) { + u8 buf[24] __aligned(8); + efi_guid_t *vnd = PTR_ALIGN((efi_guid_t *)buf, sizeof(*vnd)); efi_status_t status; u32 phys_name, phys_vendor, phys_attr; u32 phys_data_size, phys_data; @@ -797,14 +797,19 @@ efi_thunk_get_variable(efi_char16_t *name, efi_guid_t *vendor, spin_lock_irqsave(&efi_runtime_lock, flags); + *vnd = *vendor; + phys_data_size = virt_to_phys_or_null(data_size); - phys_vendor = virt_to_phys_or_null(vendor); + phys_vendor = virt_to_phys_or_null(vnd); phys_name = virt_to_phys_or_null_size(name, efi_name_size(name)); phys_attr = virt_to_phys_or_null(attr); phys_data = virt_to_phys_or_null_size(data, *data_size); - status = efi_thunk(get_variable, phys_name, phys_vendor, - phys_attr, phys_data_size, phys_data); + if (!phys_name || (data && !phys_data)) + status = EFI_INVALID_PARAMETER; + else + status = efi_thunk(get_variable, phys_name, phys_vendor, + phys_attr, phys_data_size, phys_data); spin_unlock_irqrestore(&efi_runtime_lock, flags); @@ -815,19 +820,25 @@ static efi_status_t efi_thunk_set_variable(efi_char16_t *name, efi_guid_t *vendor, u32 attr, unsigned long data_size, void *data) { + u8 buf[24] __aligned(8); + efi_guid_t *vnd = PTR_ALIGN((efi_guid_t *)buf, sizeof(*vnd)); u32 phys_name, phys_vendor, phys_data; efi_status_t status; unsigned long flags; spin_lock_irqsave(&efi_runtime_lock, flags); + *vnd = *vendor; + phys_name = virt_to_phys_or_null_size(name, efi_name_size(name)); - phys_vendor = virt_to_phys_or_null(vendor); + phys_vendor = virt_to_phys_or_null(vnd); phys_data = virt_to_phys_or_null_size(data, data_size); - /* If data_size is > sizeof(u32) we've got problems */ - status = efi_thunk(set_variable, phys_name, phys_vendor, - attr, data_size, phys_data); + if (!phys_name || (data && !phys_data)) + status = EFI_INVALID_PARAMETER; + else + status = efi_thunk(set_variable, phys_name, phys_vendor, + attr, data_size, phys_data); spin_unlock_irqrestore(&efi_runtime_lock, flags); @@ -839,6 +850,8 @@ efi_thunk_set_variable_nonblocking(efi_char16_t *name, efi_guid_t *vendor, u32 attr, unsigned long data_size, void *data) { + u8 buf[24] __aligned(8); + efi_guid_t *vnd = PTR_ALIGN((efi_guid_t *)buf, sizeof(*vnd)); u32 phys_name, phys_vendor, phys_data; efi_status_t status; unsigned long flags; @@ -846,13 +859,17 @@ efi_thunk_set_variable_nonblocking(efi_char16_t *name, efi_guid_t *vendor, if (!spin_trylock_irqsave(&efi_runtime_lock, flags)) return EFI_NOT_READY; + *vnd = *vendor; + phys_name = virt_to_phys_or_null_size(name, efi_name_size(name)); - phys_vendor = virt_to_phys_or_null(vendor); + phys_vendor = virt_to_phys_or_null(vnd); phys_data = virt_to_phys_or_null_size(data, data_size); - /* If data_size is > sizeof(u32) we've got problems */ - status = efi_thunk(set_variable, phys_name, phys_vendor, - attr, data_size, phys_data); + if (!phys_name || (data && !phys_data)) + status = EFI_INVALID_PARAMETER; + else + status = efi_thunk(set_variable, phys_name, phys_vendor, + attr, data_size, phys_data); spin_unlock_irqrestore(&efi_runtime_lock, flags); @@ -864,21 +881,29 @@ efi_thunk_get_next_variable(unsigned long *name_size, efi_char16_t *name, efi_guid_t *vendor) { + u8 buf[24] __aligned(8); + efi_guid_t *vnd = PTR_ALIGN((efi_guid_t *)buf, sizeof(*vnd)); efi_status_t status; u32 phys_name_size, phys_name, phys_vendor; unsigned long flags; spin_lock_irqsave(&efi_runtime_lock, flags); + *vnd = *vendor; + phys_name_size = virt_to_phys_or_null(name_size); - phys_vendor = virt_to_phys_or_null(vendor); + phys_vendor = virt_to_phys_or_null(vnd); phys_name = virt_to_phys_or_null_size(name, *name_size); - status = efi_thunk(get_next_variable, phys_name_size, - phys_name, phys_vendor); + if (!phys_name) + status = EFI_INVALID_PARAMETER; + else + status = efi_thunk(get_next_variable, phys_name_size, + phys_name, phys_vendor); spin_unlock_irqrestore(&efi_runtime_lock, flags); + *vendor = *vnd; return status; } diff --git a/arch/x86/platform/efi/quirks.c b/arch/x86/platform/efi/quirks.c index 3b9fd679cea9..aefe845dff59 100644 --- a/arch/x86/platform/efi/quirks.c +++ b/arch/x86/platform/efi/quirks.c @@ -260,10 +260,6 @@ void __init efi_arch_mem_reserve(phys_addr_t addr, u64 size) return; } - /* No need to reserve regions that will never be freed. */ - if (md.attribute & EFI_MEMORY_RUNTIME) - return; - size += addr % EFI_PAGE_SIZE; size = round_up(size, EFI_PAGE_SIZE); addr = round_down(addr, EFI_PAGE_SIZE); @@ -293,6 +289,8 @@ void __init efi_arch_mem_reserve(phys_addr_t addr, u64 size) early_memunmap(new, new_size); efi_memmap_install(new_phys, num_entries); + e820__range_update(addr, size, E820_TYPE_RAM, E820_TYPE_RESERVED); + e820__update_table(e820_table); } /* diff --git a/arch/x86/platform/olpc/olpc_dt.c b/arch/x86/platform/olpc/olpc_dt.c index c78bfc16a3ca..26d1f6693789 100644 --- a/arch/x86/platform/olpc/olpc_dt.c +++ b/arch/x86/platform/olpc/olpc_dt.c @@ -216,7 +216,7 @@ static u32 __init olpc_dt_get_board_revision(void) return be32_to_cpu(rev); } -int olpc_dt_compatible_match(phandle node, const char *compat) +static int __init olpc_dt_compatible_match(phandle node, const char *compat) { char buf[64], *p; int plen, len; diff --git a/arch/x86/purgatory/Makefile b/arch/x86/purgatory/Makefile index b81b5172cf99..2cfa0caef133 100644 --- a/arch/x86/purgatory/Makefile +++ b/arch/x86/purgatory/Makefile @@ -15,7 +15,10 @@ $(obj)/sha256.o: $(srctree)/lib/sha256.c FORCE LDFLAGS_purgatory.ro := -e purgatory_start -r --no-undefined -nostdlib -z nodefaultlib targets += purgatory.ro +# Sanitizer, etc. runtimes are unavailable and cannot be linked here. +GCOV_PROFILE := n KASAN_SANITIZE := n +UBSAN_SANITIZE := n KCOV_INSTRUMENT := n # These are adjustments to the compiler flags used for objects that @@ -23,7 +26,7 @@ KCOV_INSTRUMENT := n PURGATORY_CFLAGS_REMOVE := -mcmodel=kernel PURGATORY_CFLAGS := -mcmodel=large -ffreestanding -fno-zero-initialized-in-bss -PURGATORY_CFLAGS += $(DISABLE_STACKLEAK_PLUGIN) +PURGATORY_CFLAGS += $(DISABLE_STACKLEAK_PLUGIN) -DDISABLE_BRANCH_PROFILING # Default KBUILD_CFLAGS can have -pg option set when FTRACE is enabled. That # in turn leaves some undefined symbols like __fentry__ in purgatory and not diff --git a/arch/x86/xen/enlighten_pv.c b/arch/x86/xen/enlighten_pv.c index 896cfd22cfda..c9b51e1a0c53 100644 --- a/arch/x86/xen/enlighten_pv.c +++ b/arch/x86/xen/enlighten_pv.c @@ -907,14 +907,15 @@ static u64 xen_read_msr_safe(unsigned int msr, int *err) static int xen_write_msr_safe(unsigned int msr, unsigned low, unsigned high) { int ret; +#ifdef CONFIG_X86_64 + unsigned int which; + u64 base; +#endif ret = 0; switch (msr) { #ifdef CONFIG_X86_64 - unsigned which; - u64 base; - case MSR_FS_BASE: which = SEGBASE_FS; goto set; case MSR_KERNEL_GS_BASE: which = SEGBASE_GS_USER; goto set; case MSR_GS_BASE: which = SEGBASE_GS_KERNEL; goto set; diff --git a/arch/x86/xen/smp_pv.c b/arch/x86/xen/smp_pv.c index 72e658c0c7c6..0d2f07d23f72 100644 --- a/arch/x86/xen/smp_pv.c +++ b/arch/x86/xen/smp_pv.c @@ -92,6 +92,7 @@ asmlinkage __visible void cpu_bringup_and_idle(void) cpu_bringup(); boot_init_stack_canary(); cpu_startup_entry(CPUHP_AP_ONLINE_IDLE); + prevent_tail_call_optimization(); } void xen_smp_intr_free_pv(unsigned int cpu) |