diff options
Diffstat (limited to 'arch/x86')
65 files changed, 1353 insertions, 331 deletions
diff --git a/arch/x86/Kconfig b/arch/x86/Kconfig index d4fc98c50378..20da391b5f32 100644 --- a/arch/x86/Kconfig +++ b/arch/x86/Kconfig @@ -55,7 +55,6 @@ config X86 select ARCH_HAS_GCOV_PROFILE_ALL select ARCH_HAS_KCOV if X86_64 select ARCH_HAS_PMEM_API if X86_64 - # Causing hangs/crashes, see the commit that added this change for details. select ARCH_HAS_REFCOUNT select ARCH_HAS_UACCESS_FLUSHCACHE if X86_64 select ARCH_HAS_SET_MEMORY @@ -89,6 +88,7 @@ config X86 select GENERIC_CLOCKEVENTS_MIN_ADJUST select GENERIC_CMOS_UPDATE select GENERIC_CPU_AUTOPROBE + select GENERIC_CPU_VULNERABILITIES select GENERIC_EARLY_IOREMAP select GENERIC_FIND_FIRST_BIT select GENERIC_IOMAP @@ -429,6 +429,19 @@ config GOLDFISH def_bool y depends on X86_GOLDFISH +config RETPOLINE + bool "Avoid speculative indirect branches in kernel" + default y + help + Compile kernel with the retpoline compiler options to guard against + kernel-to-user data leaks by avoiding speculative indirect + branches. Requires a compiler with -mindirect-branch=thunk-extern + support for full protection. The kernel may run slower. + + Without compiler support, at least indirect branches in assembler + code are eliminated. Since this includes the syscall entry path, + it is not entirely pointless. + config INTEL_RDT bool "Intel Resource Director Technology support" default n diff --git a/arch/x86/Makefile b/arch/x86/Makefile index 3e73bc255e4e..fad55160dcb9 100644 --- a/arch/x86/Makefile +++ b/arch/x86/Makefile @@ -230,6 +230,14 @@ KBUILD_CFLAGS += -Wno-sign-compare # KBUILD_CFLAGS += -fno-asynchronous-unwind-tables +# Avoid indirect branches in kernel to deal with Spectre +ifdef CONFIG_RETPOLINE + RETPOLINE_CFLAGS += $(call cc-option,-mindirect-branch=thunk-extern -mindirect-branch-register) + ifneq ($(RETPOLINE_CFLAGS),) + KBUILD_CFLAGS += $(RETPOLINE_CFLAGS) -DRETPOLINE + endif +endif + archscripts: scripts_basic $(Q)$(MAKE) $(build)=arch/x86/tools relocs diff --git a/arch/x86/crypto/aesni-intel_asm.S b/arch/x86/crypto/aesni-intel_asm.S index 16627fec80b2..3d09e3aca18d 100644 --- a/arch/x86/crypto/aesni-intel_asm.S +++ b/arch/x86/crypto/aesni-intel_asm.S @@ -32,6 +32,7 @@ #include <linux/linkage.h> #include <asm/inst.h> #include <asm/frame.h> +#include <asm/nospec-branch.h> /* * The following macros are used to move an (un)aligned 16 byte value to/from @@ -2884,7 +2885,7 @@ ENTRY(aesni_xts_crypt8) pxor INC, STATE4 movdqu IV, 0x30(OUTP) - call *%r11 + CALL_NOSPEC %r11 movdqu 0x00(OUTP), INC pxor INC, STATE1 @@ -2929,7 +2930,7 @@ ENTRY(aesni_xts_crypt8) _aesni_gf128mul_x_ble() movups IV, (IVP) - call *%r11 + CALL_NOSPEC %r11 movdqu 0x40(OUTP), INC pxor INC, STATE1 diff --git a/arch/x86/crypto/camellia-aesni-avx-asm_64.S b/arch/x86/crypto/camellia-aesni-avx-asm_64.S index f7c495e2863c..a14af6eb09cb 100644 --- a/arch/x86/crypto/camellia-aesni-avx-asm_64.S +++ b/arch/x86/crypto/camellia-aesni-avx-asm_64.S @@ -17,6 +17,7 @@ #include <linux/linkage.h> #include <asm/frame.h> +#include <asm/nospec-branch.h> #define CAMELLIA_TABLE_BYTE_LEN 272 @@ -1227,7 +1228,7 @@ camellia_xts_crypt_16way: vpxor 14 * 16(%rax), %xmm15, %xmm14; vpxor 15 * 16(%rax), %xmm15, %xmm15; - call *%r9; + CALL_NOSPEC %r9; addq $(16 * 16), %rsp; diff --git a/arch/x86/crypto/camellia-aesni-avx2-asm_64.S b/arch/x86/crypto/camellia-aesni-avx2-asm_64.S index eee5b3982cfd..b66bbfa62f50 100644 --- a/arch/x86/crypto/camellia-aesni-avx2-asm_64.S +++ b/arch/x86/crypto/camellia-aesni-avx2-asm_64.S @@ -12,6 +12,7 @@ #include <linux/linkage.h> #include <asm/frame.h> +#include <asm/nospec-branch.h> #define CAMELLIA_TABLE_BYTE_LEN 272 @@ -1343,7 +1344,7 @@ camellia_xts_crypt_32way: vpxor 14 * 32(%rax), %ymm15, %ymm14; vpxor 15 * 32(%rax), %ymm15, %ymm15; - call *%r9; + CALL_NOSPEC %r9; addq $(16 * 32), %rsp; diff --git a/arch/x86/crypto/crc32c-pcl-intel-asm_64.S b/arch/x86/crypto/crc32c-pcl-intel-asm_64.S index 7a7de27c6f41..d9b734d0c8cc 100644 --- a/arch/x86/crypto/crc32c-pcl-intel-asm_64.S +++ b/arch/x86/crypto/crc32c-pcl-intel-asm_64.S @@ -45,6 +45,7 @@ #include <asm/inst.h> #include <linux/linkage.h> +#include <asm/nospec-branch.h> ## ISCSI CRC 32 Implementation with crc32 and pclmulqdq Instruction @@ -172,7 +173,7 @@ continue_block: movzxw (bufp, %rax, 2), len lea crc_array(%rip), bufp lea (bufp, len, 1), bufp - jmp *bufp + JMP_NOSPEC bufp ################################################################ ## 2a) PROCESS FULL BLOCKS: diff --git a/arch/x86/entry/calling.h b/arch/x86/entry/calling.h index 45a63e00a6af..3f48f695d5e6 100644 --- a/arch/x86/entry/calling.h +++ b/arch/x86/entry/calling.h @@ -198,8 +198,11 @@ For 32-bit we have the following conventions - kernel is built with * PAGE_TABLE_ISOLATION PGDs are 8k. Flip bit 12 to switch between the two * halves: */ -#define PTI_SWITCH_PGTABLES_MASK (1<<PAGE_SHIFT) -#define PTI_SWITCH_MASK (PTI_SWITCH_PGTABLES_MASK|(1<<X86_CR3_PTI_SWITCH_BIT)) +#define PTI_USER_PGTABLE_BIT PAGE_SHIFT +#define PTI_USER_PGTABLE_MASK (1 << PTI_USER_PGTABLE_BIT) +#define PTI_USER_PCID_BIT X86_CR3_PTI_PCID_USER_BIT +#define PTI_USER_PCID_MASK (1 << PTI_USER_PCID_BIT) +#define PTI_USER_PGTABLE_AND_PCID_MASK (PTI_USER_PCID_MASK | PTI_USER_PGTABLE_MASK) .macro SET_NOFLUSH_BIT reg:req bts $X86_CR3_PCID_NOFLUSH_BIT, \reg @@ -208,7 +211,7 @@ For 32-bit we have the following conventions - kernel is built with .macro ADJUST_KERNEL_CR3 reg:req ALTERNATIVE "", "SET_NOFLUSH_BIT \reg", X86_FEATURE_PCID /* Clear PCID and "PAGE_TABLE_ISOLATION bit", point CR3 at kernel pagetables: */ - andq $(~PTI_SWITCH_MASK), \reg + andq $(~PTI_USER_PGTABLE_AND_PCID_MASK), \reg .endm .macro SWITCH_TO_KERNEL_CR3 scratch_reg:req @@ -239,15 +242,19 @@ For 32-bit we have the following conventions - kernel is built with /* Flush needed, clear the bit */ btr \scratch_reg, THIS_CPU_user_pcid_flush_mask movq \scratch_reg2, \scratch_reg - jmp .Lwrcr3_\@ + jmp .Lwrcr3_pcid_\@ .Lnoflush_\@: movq \scratch_reg2, \scratch_reg SET_NOFLUSH_BIT \scratch_reg +.Lwrcr3_pcid_\@: + /* Flip the ASID to the user version */ + orq $(PTI_USER_PCID_MASK), \scratch_reg + .Lwrcr3_\@: - /* Flip the PGD and ASID to the user version */ - orq $(PTI_SWITCH_MASK), \scratch_reg + /* Flip the PGD to the user version */ + orq $(PTI_USER_PGTABLE_MASK), \scratch_reg mov \scratch_reg, %cr3 .Lend_\@: .endm @@ -263,17 +270,12 @@ For 32-bit we have the following conventions - kernel is built with movq %cr3, \scratch_reg movq \scratch_reg, \save_reg /* - * Is the "switch mask" all zero? That means that both of - * these are zero: - * - * 1. The user/kernel PCID bit, and - * 2. The user/kernel "bit" that points CR3 to the - * bottom half of the 8k PGD - * - * That indicates a kernel CR3 value, not a user CR3. + * Test the user pagetable bit. If set, then the user page tables + * are active. If clear CR3 already has the kernel page table + * active. */ - testq $(PTI_SWITCH_MASK), \scratch_reg - jz .Ldone_\@ + bt $PTI_USER_PGTABLE_BIT, \scratch_reg + jnc .Ldone_\@ ADJUST_KERNEL_CR3 \scratch_reg movq \scratch_reg, %cr3 @@ -290,7 +292,7 @@ For 32-bit we have the following conventions - kernel is built with * KERNEL pages can always resume with NOFLUSH as we do * explicit flushes. */ - bt $X86_CR3_PTI_SWITCH_BIT, \save_reg + bt $PTI_USER_PGTABLE_BIT, \save_reg jnc .Lnoflush_\@ /* diff --git a/arch/x86/entry/entry_32.S b/arch/x86/entry/entry_32.S index ace8f321a5a1..60c4c342316c 100644 --- a/arch/x86/entry/entry_32.S +++ b/arch/x86/entry/entry_32.S @@ -44,6 +44,7 @@ #include <asm/asm.h> #include <asm/smap.h> #include <asm/frame.h> +#include <asm/nospec-branch.h> .section .entry.text, "ax" @@ -243,6 +244,17 @@ ENTRY(__switch_to_asm) movl %ebx, PER_CPU_VAR(stack_canary)+stack_canary_offset #endif +#ifdef CONFIG_RETPOLINE + /* + * When switching from a shallower to a deeper call stack + * the RSB may either underflow or use entries populated + * with userspace addresses. On CPUs where those concerns + * exist, overwrite the RSB with entries which capture + * speculative execution to prevent attack. + */ + FILL_RETURN_BUFFER %ebx, RSB_CLEAR_LOOPS, X86_FEATURE_RSB_CTXSW +#endif + /* restore callee-saved registers */ popl %esi popl %edi @@ -290,7 +302,7 @@ ENTRY(ret_from_fork) /* kernel thread */ 1: movl %edi, %eax - call *%ebx + CALL_NOSPEC %ebx /* * A kernel thread is allowed to return here after successfully * calling do_execve(). Exit to userspace to complete the execve() @@ -919,7 +931,7 @@ common_exception: movl %ecx, %es TRACE_IRQS_OFF movl %esp, %eax # pt_regs pointer - call *%edi + CALL_NOSPEC %edi jmp ret_from_exception END(common_exception) diff --git a/arch/x86/entry/entry_64.S b/arch/x86/entry/entry_64.S index f048e384ff54..ff6f8022612c 100644 --- a/arch/x86/entry/entry_64.S +++ b/arch/x86/entry/entry_64.S @@ -37,6 +37,7 @@ #include <asm/pgtable_types.h> #include <asm/export.h> #include <asm/frame.h> +#include <asm/nospec-branch.h> #include <linux/err.h> #include "calling.h" @@ -191,7 +192,7 @@ ENTRY(entry_SYSCALL_64_trampoline) */ pushq %rdi movq $entry_SYSCALL_64_stage2, %rdi - jmp *%rdi + JMP_NOSPEC %rdi END(entry_SYSCALL_64_trampoline) .popsection @@ -270,7 +271,12 @@ entry_SYSCALL_64_fastpath: * It might end up jumping to the slow path. If it jumps, RAX * and all argument registers are clobbered. */ +#ifdef CONFIG_RETPOLINE + movq sys_call_table(, %rax, 8), %rax + call __x86_indirect_thunk_rax +#else call *sys_call_table(, %rax, 8) +#endif .Lentry_SYSCALL_64_after_fastpath_call: movq %rax, RAX(%rsp) @@ -442,7 +448,7 @@ ENTRY(stub_ptregs_64) jmp entry_SYSCALL64_slow_path 1: - jmp *%rax /* Called from C */ + JMP_NOSPEC %rax /* Called from C */ END(stub_ptregs_64) .macro ptregs_stub func @@ -485,6 +491,17 @@ ENTRY(__switch_to_asm) movq %rbx, PER_CPU_VAR(irq_stack_union)+stack_canary_offset #endif +#ifdef CONFIG_RETPOLINE + /* + * When switching from a shallower to a deeper call stack + * the RSB may either underflow or use entries populated + * with userspace addresses. On CPUs where those concerns + * exist, overwrite the RSB with entries which capture + * speculative execution to prevent attack. + */ + FILL_RETURN_BUFFER %r12, RSB_CLEAR_LOOPS, X86_FEATURE_RSB_CTXSW +#endif + /* restore callee-saved registers */ popq %r15 popq %r14 @@ -521,7 +538,7 @@ ENTRY(ret_from_fork) 1: /* kernel thread */ movq %r12, %rdi - call *%rbx + CALL_NOSPEC %rbx /* * A kernel thread is allowed to return here after successfully * calling do_execve(). Exit to userspace to complete the execve() @@ -1247,7 +1264,7 @@ idtentry async_page_fault do_async_page_fault has_error_code=1 #endif #ifdef CONFIG_X86_MCE -idtentry machine_check has_error_code=0 paranoid=1 do_sym=*machine_check_vector(%rip) +idtentry machine_check do_mce has_error_code=0 paranoid=1 #endif /* diff --git a/arch/x86/events/intel/bts.c b/arch/x86/events/intel/bts.c index 141e07b06216..24ffa1e88cf9 100644 --- a/arch/x86/events/intel/bts.c +++ b/arch/x86/events/intel/bts.c @@ -582,6 +582,24 @@ static __init int bts_init(void) if (!boot_cpu_has(X86_FEATURE_DTES64) || !x86_pmu.bts) return -ENODEV; + if (boot_cpu_has(X86_FEATURE_PTI)) { + /* + * BTS hardware writes through a virtual memory map we must + * either use the kernel physical map, or the user mapping of + * the AUX buffer. + * + * However, since this driver supports per-CPU and per-task inherit + * we cannot use the user mapping since it will not be availble + * if we're not running the owning process. + * + * With PTI we can't use the kernal map either, because its not + * there when we run userspace. + * + * For now, disable this driver when using PTI. + */ + return -ENODEV; + } + bts_pmu.capabilities = PERF_PMU_CAP_AUX_NO_SG | PERF_PMU_CAP_ITRACE | PERF_PMU_CAP_EXCLUSIVE; bts_pmu.task_ctx_nr = perf_sw_context; diff --git a/arch/x86/events/intel/rapl.c b/arch/x86/events/intel/rapl.c index 005908ee9333..a2efb490f743 100644 --- a/arch/x86/events/intel/rapl.c +++ b/arch/x86/events/intel/rapl.c @@ -755,14 +755,14 @@ static const struct x86_cpu_id rapl_cpu_match[] __initconst = { X86_RAPL_MODEL_MATCH(INTEL_FAM6_IVYBRIDGE_X, snbep_rapl_init), X86_RAPL_MODEL_MATCH(INTEL_FAM6_HASWELL_CORE, hsw_rapl_init), - X86_RAPL_MODEL_MATCH(INTEL_FAM6_HASWELL_X, hsw_rapl_init), + X86_RAPL_MODEL_MATCH(INTEL_FAM6_HASWELL_X, hsx_rapl_init), X86_RAPL_MODEL_MATCH(INTEL_FAM6_HASWELL_ULT, hsw_rapl_init), X86_RAPL_MODEL_MATCH(INTEL_FAM6_HASWELL_GT3E, hsw_rapl_init), X86_RAPL_MODEL_MATCH(INTEL_FAM6_BROADWELL_CORE, hsw_rapl_init), X86_RAPL_MODEL_MATCH(INTEL_FAM6_BROADWELL_GT3E, hsw_rapl_init), X86_RAPL_MODEL_MATCH(INTEL_FAM6_BROADWELL_X, hsx_rapl_init), - X86_RAPL_MODEL_MATCH(INTEL_FAM6_BROADWELL_XEON_D, hsw_rapl_init), + X86_RAPL_MODEL_MATCH(INTEL_FAM6_BROADWELL_XEON_D, hsx_rapl_init), X86_RAPL_MODEL_MATCH(INTEL_FAM6_XEON_PHI_KNL, knl_rapl_init), X86_RAPL_MODEL_MATCH(INTEL_FAM6_XEON_PHI_KNM, knl_rapl_init), diff --git a/arch/x86/include/asm/apic.h b/arch/x86/include/asm/apic.h index a9e57f08bfa6..98722773391d 100644 --- a/arch/x86/include/asm/apic.h +++ b/arch/x86/include/asm/apic.h @@ -136,6 +136,7 @@ extern void disconnect_bsp_APIC(int virt_wire_setup); extern void disable_local_APIC(void); extern void lapic_shutdown(void); extern void sync_Arb_IDs(void); +extern void init_bsp_APIC(void); extern void apic_intr_mode_init(void); extern void setup_local_APIC(void); extern void init_apic_mappings(void); diff --git a/arch/x86/include/asm/asm-prototypes.h b/arch/x86/include/asm/asm-prototypes.h index ff700d81e91e..0927cdc4f946 100644 --- a/arch/x86/include/asm/asm-prototypes.h +++ b/arch/x86/include/asm/asm-prototypes.h @@ -11,7 +11,32 @@ #include <asm/pgtable.h> #include <asm/special_insns.h> #include <asm/preempt.h> +#include <asm/asm.h> #ifndef CONFIG_X86_CMPXCHG64 extern void cmpxchg8b_emu(void); #endif + +#ifdef CONFIG_RETPOLINE +#ifdef CONFIG_X86_32 +#define INDIRECT_THUNK(reg) extern asmlinkage void __x86_indirect_thunk_e ## reg(void); +#else +#define INDIRECT_THUNK(reg) extern asmlinkage void __x86_indirect_thunk_r ## reg(void); +INDIRECT_THUNK(8) +INDIRECT_THUNK(9) +INDIRECT_THUNK(10) +INDIRECT_THUNK(11) +INDIRECT_THUNK(12) +INDIRECT_THUNK(13) +INDIRECT_THUNK(14) +INDIRECT_THUNK(15) +#endif +INDIRECT_THUNK(ax) +INDIRECT_THUNK(bx) +INDIRECT_THUNK(cx) +INDIRECT_THUNK(dx) +INDIRECT_THUNK(si) +INDIRECT_THUNK(di) +INDIRECT_THUNK(bp) +INDIRECT_THUNK(sp) +#endif /* CONFIG_RETPOLINE */ diff --git a/arch/x86/include/asm/cpufeatures.h b/arch/x86/include/asm/cpufeatures.h index 21ac898df2d8..25b9375c1484 100644 --- a/arch/x86/include/asm/cpufeatures.h +++ b/arch/x86/include/asm/cpufeatures.h @@ -203,12 +203,14 @@ #define X86_FEATURE_PROC_FEEDBACK ( 7*32+ 9) /* AMD ProcFeedbackInterface */ #define X86_FEATURE_SME ( 7*32+10) /* AMD Secure Memory Encryption */ #define X86_FEATURE_PTI ( 7*32+11) /* Kernel Page Table Isolation enabled */ +#define X86_FEATURE_RETPOLINE ( 7*32+12) /* Generic Retpoline mitigation for Spectre variant 2 */ +#define X86_FEATURE_RETPOLINE_AMD ( 7*32+13) /* AMD Retpoline mitigation for Spectre variant 2 */ #define X86_FEATURE_INTEL_PPIN ( 7*32+14) /* Intel Processor Inventory Number */ -#define X86_FEATURE_INTEL_PT ( 7*32+15) /* Intel Processor Trace */ #define X86_FEATURE_AVX512_4VNNIW ( 7*32+16) /* AVX-512 Neural Network Instructions */ #define X86_FEATURE_AVX512_4FMAPS ( 7*32+17) /* AVX-512 Multiply Accumulation Single precision */ #define X86_FEATURE_MBA ( 7*32+18) /* Memory Bandwidth Allocation */ +#define X86_FEATURE_RSB_CTXSW ( 7*32+19) /* Fill RSB on context switches */ /* Virtualization flags: Linux defined, word 8 */ #define X86_FEATURE_TPR_SHADOW ( 8*32+ 0) /* Intel TPR Shadow */ @@ -243,6 +245,7 @@ #define X86_FEATURE_AVX512IFMA ( 9*32+21) /* AVX-512 Integer Fused Multiply-Add instructions */ #define X86_FEATURE_CLFLUSHOPT ( 9*32+23) /* CLFLUSHOPT instruction */ #define X86_FEATURE_CLWB ( 9*32+24) /* CLWB instruction */ +#define X86_FEATURE_INTEL_PT ( 9*32+25) /* Intel Processor Trace */ #define X86_FEATURE_AVX512PF ( 9*32+26) /* AVX-512 Prefetch */ #define X86_FEATURE_AVX512ER ( 9*32+27) /* AVX-512 Exponential and Reciprocal */ #define X86_FEATURE_AVX512CD ( 9*32+28) /* AVX-512 Conflict Detection */ @@ -342,5 +345,7 @@ #define X86_BUG_MONITOR X86_BUG(12) /* IPI required to wake up remote CPU */ #define X86_BUG_AMD_E400 X86_BUG(13) /* CPU is among the affected by Erratum 400 */ #define X86_BUG_CPU_MELTDOWN X86_BUG(14) /* CPU is affected by meltdown attack and needs kernel page table isolation */ +#define X86_BUG_SPECTRE_V1 X86_BUG(15) /* CPU is affected by Spectre variant 1 attack with conditional branches */ +#define X86_BUG_SPECTRE_V2 X86_BUG(16) /* CPU is affected by Spectre variant 2 attack with indirect branches */ #endif /* _ASM_X86_CPUFEATURES_H */ diff --git a/arch/x86/include/asm/mem_encrypt.h b/arch/x86/include/asm/mem_encrypt.h index c9459a4c3c68..22c5f3e6f820 100644 --- a/arch/x86/include/asm/mem_encrypt.h +++ b/arch/x86/include/asm/mem_encrypt.h @@ -39,7 +39,7 @@ void __init sme_unmap_bootdata(char *real_mode_data); void __init sme_early_init(void); -void __init sme_encrypt_kernel(void); +void __init sme_encrypt_kernel(struct boot_params *bp); void __init sme_enable(struct boot_params *bp); int __init early_set_memory_decrypted(unsigned long vaddr, unsigned long size); @@ -67,7 +67,7 @@ static inline void __init sme_unmap_bootdata(char *real_mode_data) { } static inline void __init sme_early_init(void) { } -static inline void __init sme_encrypt_kernel(void) { } +static inline void __init sme_encrypt_kernel(struct boot_params *bp) { } static inline void __init sme_enable(struct boot_params *bp) { } static inline bool sme_active(void) { return false; } diff --git a/arch/x86/include/asm/mshyperv.h b/arch/x86/include/asm/mshyperv.h index 5400add2885b..8bf450b13d9f 100644 --- a/arch/x86/include/asm/mshyperv.h +++ b/arch/x86/include/asm/mshyperv.h @@ -7,6 +7,7 @@ #include <linux/nmi.h> #include <asm/io.h> #include <asm/hyperv.h> +#include <asm/nospec-branch.h> /* * The below CPUID leaves are present if VersionAndFeatures.HypervisorPresent @@ -186,10 +187,11 @@ static inline u64 hv_do_hypercall(u64 control, void *input, void *output) return U64_MAX; __asm__ __volatile__("mov %4, %%r8\n" - "call *%5" + CALL_NOSPEC : "=a" (hv_status), ASM_CALL_CONSTRAINT, "+c" (control), "+d" (input_address) - : "r" (output_address), "m" (hv_hypercall_pg) + : "r" (output_address), + THUNK_TARGET(hv_hypercall_pg) : "cc", "memory", "r8", "r9", "r10", "r11"); #else u32 input_address_hi = upper_32_bits(input_address); @@ -200,13 +202,13 @@ static inline u64 hv_do_hypercall(u64 control, void *input, void *output) if (!hv_hypercall_pg) return U64_MAX; - __asm__ __volatile__("call *%7" + __asm__ __volatile__(CALL_NOSPEC : "=A" (hv_status), "+c" (input_address_lo), ASM_CALL_CONSTRAINT : "A" (control), "b" (input_address_hi), "D"(output_address_hi), "S"(output_address_lo), - "m" (hv_hypercall_pg) + THUNK_TARGET(hv_hypercall_pg) : "cc", "memory"); #endif /* !x86_64 */ return hv_status; @@ -227,10 +229,10 @@ static inline u64 hv_do_fast_hypercall8(u16 code, u64 input1) #ifdef CONFIG_X86_64 { - __asm__ __volatile__("call *%4" + __asm__ __volatile__(CALL_NOSPEC : "=a" (hv_status), ASM_CALL_CONSTRAINT, "+c" (control), "+d" (input1) - : "m" (hv_hypercall_pg) + : THUNK_TARGET(hv_hypercall_pg) : "cc", "r8", "r9", "r10", "r11"); } #else @@ -238,13 +240,13 @@ static inline u64 hv_do_fast_hypercall8(u16 code, u64 input1) u32 input1_hi = upper_32_bits(input1); u32 input1_lo = lower_32_bits(input1); - __asm__ __volatile__ ("call *%5" + __asm__ __volatile__ (CALL_NOSPEC : "=A"(hv_status), "+c"(input1_lo), ASM_CALL_CONSTRAINT : "A" (control), "b" (input1_hi), - "m" (hv_hypercall_pg) + THUNK_TARGET(hv_hypercall_pg) : "cc", "edi", "esi"); } #endif diff --git a/arch/x86/include/asm/msr-index.h b/arch/x86/include/asm/msr-index.h index 34c4922bbc3f..e7b983a35506 100644 --- a/arch/x86/include/asm/msr-index.h +++ b/arch/x86/include/asm/msr-index.h @@ -355,6 +355,9 @@ #define FAM10H_MMIO_CONF_BASE_MASK 0xfffffffULL #define FAM10H_MMIO_CONF_BASE_SHIFT 20 #define MSR_FAM10H_NODE_ID 0xc001100c +#define MSR_F10H_DECFG 0xc0011029 +#define MSR_F10H_DECFG_LFENCE_SERIALIZE_BIT 1 +#define MSR_F10H_DECFG_LFENCE_SERIALIZE BIT_ULL(MSR_F10H_DECFG_LFENCE_SERIALIZE_BIT) /* K8 MSRs */ #define MSR_K8_TOP_MEM1 0xc001001a diff --git a/arch/x86/include/asm/nospec-branch.h b/arch/x86/include/asm/nospec-branch.h new file mode 100644 index 000000000000..4ad41087ce0e --- /dev/null +++ b/arch/x86/include/asm/nospec-branch.h @@ -0,0 +1,222 @@ +/* SPDX-License-Identifier: GPL-2.0 */ + +#ifndef __NOSPEC_BRANCH_H__ +#define __NOSPEC_BRANCH_H__ + +#include <asm/alternative.h> +#include <asm/alternative-asm.h> +#include <asm/cpufeatures.h> + +/* + * Fill the CPU return stack buffer. + * + * Each entry in the RSB, if used for a speculative 'ret', contains an + * infinite 'pause; lfence; jmp' loop to capture speculative execution. + * + * This is required in various cases for retpoline and IBRS-based + * mitigations for the Spectre variant 2 vulnerability. Sometimes to + * eliminate potentially bogus entries from the RSB, and sometimes + * purely to ensure that it doesn't get empty, which on some CPUs would + * allow predictions from other (unwanted!) sources to be used. + * + * We define a CPP macro such that it can be used from both .S files and + * inline assembly. It's possible to do a .macro and then include that + * from C via asm(".include <asm/nospec-branch.h>") but let's not go there. + */ + +#define RSB_CLEAR_LOOPS 32 /* To forcibly overwrite all entries */ +#define RSB_FILL_LOOPS 16 /* To avoid underflow */ + +/* + * Google experimented with loop-unrolling and this turned out to be + * the optimal version — two calls, each with their own speculation + * trap should their return address end up getting used, in a loop. + */ +#define __FILL_RETURN_BUFFER(reg, nr, sp) \ + mov $(nr/2), reg; \ +771: \ + call 772f; \ +773: /* speculation trap */ \ + pause; \ + lfence; \ + jmp 773b; \ +772: \ + call 774f; \ +775: /* speculation trap */ \ + pause; \ + lfence; \ + jmp 775b; \ +774: \ + dec reg; \ + jnz 771b; \ + add $(BITS_PER_LONG/8) * nr, sp; + +#ifdef __ASSEMBLY__ + +/* + * This should be used immediately before a retpoline alternative. It tells + * objtool where the retpolines are so that it can make sense of the control + * flow by just reading the original instruction(s) and ignoring the + * alternatives. + */ +.macro ANNOTATE_NOSPEC_ALTERNATIVE + .Lannotate_\@: + .pushsection .discard.nospec + .long .Lannotate_\@ - . + .popsection +.endm + +/* + * These are the bare retpoline primitives for indirect jmp and call. + * Do not use these directly; they only exist to make the ALTERNATIVE + * invocation below less ugly. + */ +.macro RETPOLINE_JMP reg:req + call .Ldo_rop_\@ +.Lspec_trap_\@: + pause + lfence + jmp .Lspec_trap_\@ +.Ldo_rop_\@: + mov \reg, (%_ASM_SP) + ret +.endm + +/* + * This is a wrapper around RETPOLINE_JMP so the called function in reg + * returns to the instruction after the macro. + */ +.macro RETPOLINE_CALL reg:req + jmp .Ldo_call_\@ +.Ldo_retpoline_jmp_\@: + RETPOLINE_JMP \reg +.Ldo_call_\@: + call .Ldo_retpoline_jmp_\@ +.endm + +/* + * JMP_NOSPEC and CALL_NOSPEC macros can be used instead of a simple + * indirect jmp/call which may be susceptible to the Spectre variant 2 + * attack. + */ +.macro JMP_NOSPEC reg:req +#ifdef CONFIG_RETPOLINE + ANNOTATE_NOSPEC_ALTERNATIVE + ALTERNATIVE_2 __stringify(jmp *\reg), \ + __stringify(RETPOLINE_JMP \reg), X86_FEATURE_RETPOLINE, \ + __stringify(lfence; jmp *\reg), X86_FEATURE_RETPOLINE_AMD +#else + jmp *\reg +#endif +.endm + +.macro CALL_NOSPEC reg:req +#ifdef CONFIG_RETPOLINE + ANNOTATE_NOSPEC_ALTERNATIVE + ALTERNATIVE_2 __stringify(call *\reg), \ + __stringify(RETPOLINE_CALL \reg), X86_FEATURE_RETPOLINE,\ + __stringify(lfence; call *\reg), X86_FEATURE_RETPOLINE_AMD +#else + call *\reg +#endif +.endm + + /* + * A simpler FILL_RETURN_BUFFER macro. Don't make people use the CPP + * monstrosity above, manually. + */ +.macro FILL_RETURN_BUFFER reg:req nr:req ftr:req +#ifdef CONFIG_RETPOLINE + ANNOTATE_NOSPEC_ALTERNATIVE + ALTERNATIVE "jmp .Lskip_rsb_\@", \ + __stringify(__FILL_RETURN_BUFFER(\reg,\nr,%_ASM_SP)) \ + \ftr +.Lskip_rsb_\@: +#endif +.endm + +#else /* __ASSEMBLY__ */ + +#define ANNOTATE_NOSPEC_ALTERNATIVE \ + "999:\n\t" \ + ".pushsection .discard.nospec\n\t" \ + ".long 999b - .\n\t" \ + ".popsection\n\t" + +#if defined(CONFIG_X86_64) && defined(RETPOLINE) + +/* + * Since the inline asm uses the %V modifier which is only in newer GCC, + * the 64-bit one is dependent on RETPOLINE not CONFIG_RETPOLINE. + */ +# define CALL_NOSPEC \ + ANNOTATE_NOSPEC_ALTERNATIVE \ + ALTERNATIVE( \ + "call *%[thunk_target]\n", \ + "call __x86_indirect_thunk_%V[thunk_target]\n", \ + X86_FEATURE_RETPOLINE) +# define THUNK_TARGET(addr) [thunk_target] "r" (addr) + +#elif defined(CONFIG_X86_32) && defined(CONFIG_RETPOLINE) +/* + * For i386 we use the original ret-equivalent retpoline, because + * otherwise we'll run out of registers. We don't care about CET + * here, anyway. + */ +# define CALL_NOSPEC ALTERNATIVE("call *%[thunk_target]\n", \ + " jmp 904f;\n" \ + " .align 16\n" \ + "901: call 903f;\n" \ + "902: pause;\n" \ + " lfence;\n" \ + " jmp 902b;\n" \ + " .align 16\n" \ + "903: addl $4, %%esp;\n" \ + " pushl %[thunk_target];\n" \ + " ret;\n" \ + " .align 16\n" \ + "904: call 901b;\n", \ + X86_FEATURE_RETPOLINE) + +# define THUNK_TARGET(addr) [thunk_target] "rm" (addr) +#else /* No retpoline for C / inline asm */ +# define CALL_NOSPEC "call *%[thunk_target]\n" +# define THUNK_TARGET(addr) [thunk_target] "rm" (addr) +#endif + +/* The Spectre V2 mitigation variants */ +enum spectre_v2_mitigation { + SPECTRE_V2_NONE, + SPECTRE_V2_RETPOLINE_MINIMAL, + SPECTRE_V2_RETPOLINE_MINIMAL_AMD, + SPECTRE_V2_RETPOLINE_GENERIC, + SPECTRE_V2_RETPOLINE_AMD, + SPECTRE_V2_IBRS, +}; + +extern char __indirect_thunk_start[]; +extern char __indirect_thunk_end[]; + +/* + * On VMEXIT we must ensure that no RSB predictions learned in the guest + * can be followed in the host, by overwriting the RSB completely. Both + * retpoline and IBRS mitigations for Spectre v2 need this; only on future + * CPUs with IBRS_ATT *might* it be avoided. + */ +static inline void vmexit_fill_RSB(void) +{ +#ifdef CONFIG_RETPOLINE + unsigned long loops; + + asm volatile (ANNOTATE_NOSPEC_ALTERNATIVE + ALTERNATIVE("jmp 910f", + __stringify(__FILL_RETURN_BUFFER(%0, RSB_CLEAR_LOOPS, %1)), + X86_FEATURE_RETPOLINE) + "910:" + : "=r" (loops), ASM_CALL_CONSTRAINT + : : "memory" ); +#endif +} + +#endif /* __ASSEMBLY__ */ +#endif /* __NOSPEC_BRANCH_H__ */ diff --git a/arch/x86/include/asm/pci_x86.h b/arch/x86/include/asm/pci_x86.h index 7a5d6695abd3..eb66fa9cd0fc 100644 --- a/arch/x86/include/asm/pci_x86.h +++ b/arch/x86/include/asm/pci_x86.h @@ -38,6 +38,7 @@ do { \ #define PCI_NOASSIGN_ROMS 0x80000 #define PCI_ROOT_NO_CRS 0x100000 #define PCI_NOASSIGN_BARS 0x200000 +#define PCI_BIG_ROOT_WINDOW 0x400000 extern unsigned int pci_probe; extern unsigned long pirq_table_addr; diff --git a/arch/x86/include/asm/processor-flags.h b/arch/x86/include/asm/processor-flags.h index 6a60fea90b9d..625a52a5594f 100644 --- a/arch/x86/include/asm/processor-flags.h +++ b/arch/x86/include/asm/processor-flags.h @@ -40,7 +40,7 @@ #define CR3_NOFLUSH BIT_ULL(63) #ifdef CONFIG_PAGE_TABLE_ISOLATION -# define X86_CR3_PTI_SWITCH_BIT 11 +# define X86_CR3_PTI_PCID_USER_BIT 11 #endif #else diff --git a/arch/x86/include/asm/tlbflush.h b/arch/x86/include/asm/tlbflush.h index 4a08dd2ab32a..d33e4a26dc7e 100644 --- a/arch/x86/include/asm/tlbflush.h +++ b/arch/x86/include/asm/tlbflush.h @@ -81,13 +81,13 @@ static inline u16 kern_pcid(u16 asid) * Make sure that the dynamic ASID space does not confict with the * bit we are using to switch between user and kernel ASIDs. */ - BUILD_BUG_ON(TLB_NR_DYN_ASIDS >= (1 << X86_CR3_PTI_SWITCH_BIT)); + BUILD_BUG_ON(TLB_NR_DYN_ASIDS >= (1 << X86_CR3_PTI_PCID_USER_BIT)); /* * The ASID being passed in here should have respected the * MAX_ASID_AVAILABLE and thus never have the switch bit set. */ - VM_WARN_ON_ONCE(asid & (1 << X86_CR3_PTI_SWITCH_BIT)); + VM_WARN_ON_ONCE(asid & (1 << X86_CR3_PTI_PCID_USER_BIT)); #endif /* * The dynamically-assigned ASIDs that get passed in are small @@ -112,7 +112,7 @@ static inline u16 user_pcid(u16 asid) { u16 ret = kern_pcid(asid); #ifdef CONFIG_PAGE_TABLE_ISOLATION - ret |= 1 << X86_CR3_PTI_SWITCH_BIT; + ret |= 1 << X86_CR3_PTI_PCID_USER_BIT; #endif return ret; } diff --git a/arch/x86/include/asm/traps.h b/arch/x86/include/asm/traps.h index 31051f35cbb7..3de69330e6c5 100644 --- a/arch/x86/include/asm/traps.h +++ b/arch/x86/include/asm/traps.h @@ -88,6 +88,7 @@ dotraplinkage void do_simd_coprocessor_error(struct pt_regs *, long); #ifdef CONFIG_X86_32 dotraplinkage void do_iret_error(struct pt_regs *, long); #endif +dotraplinkage void do_mce(struct pt_regs *, long); static inline int get_si_code(unsigned long condition) { diff --git a/arch/x86/include/asm/xen/hypercall.h b/arch/x86/include/asm/xen/hypercall.h index 7cb282e9e587..bfd882617613 100644 --- a/arch/x86/include/asm/xen/hypercall.h +++ b/arch/x86/include/asm/xen/hypercall.h @@ -44,6 +44,7 @@ #include <asm/page.h> #include <asm/pgtable.h> #include <asm/smap.h> +#include <asm/nospec-branch.h> #include <xen/interface/xen.h> #include <xen/interface/sched.h> @@ -217,9 +218,9 @@ privcmd_call(unsigned call, __HYPERCALL_5ARG(a1, a2, a3, a4, a5); stac(); - asm volatile("call *%[call]" + asm volatile(CALL_NOSPEC : __HYPERCALL_5PARAM - : [call] "a" (&hypercall_page[call]) + : [thunk_target] "a" (&hypercall_page[call]) : __HYPERCALL_CLOBBER5); clac(); diff --git a/arch/x86/kernel/Makefile b/arch/x86/kernel/Makefile index 81bb565f4497..7e2baf7304ae 100644 --- a/arch/x86/kernel/Makefile +++ b/arch/x86/kernel/Makefile @@ -29,10 +29,13 @@ KASAN_SANITIZE_stacktrace.o := n KASAN_SANITIZE_paravirt.o := n OBJECT_FILES_NON_STANDARD_relocate_kernel_$(BITS).o := y -OBJECT_FILES_NON_STANDARD_ftrace_$(BITS).o := y OBJECT_FILES_NON_STANDARD_test_nx.o := y OBJECT_FILES_NON_STANDARD_paravirt_patch_$(BITS).o := y +ifdef CONFIG_FRAME_POINTER +OBJECT_FILES_NON_STANDARD_ftrace_$(BITS).o := y +endif + # If instrumentation of this dir is enabled, boot hangs during first second. # Probably could be more selective here, but note that files related to irqs, # boot, dumpstack/stacktrace, etc are either non-interesting or can lead to diff --git a/arch/x86/kernel/alternative.c b/arch/x86/kernel/alternative.c index dbaf14d69ebd..4817d743c263 100644 --- a/arch/x86/kernel/alternative.c +++ b/arch/x86/kernel/alternative.c @@ -344,9 +344,12 @@ done: static void __init_or_module noinline optimize_nops(struct alt_instr *a, u8 *instr) { unsigned long flags; + int i; - if (instr[0] != 0x90) - return; + for (i = 0; i < a->padlen; i++) { + if (instr[i] != 0x90) + return; + } local_irq_save(flags); add_nops(instr + (a->instrlen - a->padlen), a->padlen); diff --git a/arch/x86/kernel/apic/apic.c b/arch/x86/kernel/apic/apic.c index 880441f24146..25ddf02598d2 100644 --- a/arch/x86/kernel/apic/apic.c +++ b/arch/x86/kernel/apic/apic.c @@ -1286,6 +1286,55 @@ static int __init apic_intr_mode_select(void) return APIC_SYMMETRIC_IO; } +/* + * An initial setup of the virtual wire mode. + */ +void __init init_bsp_APIC(void) +{ + unsigned int value; + + /* + * Don't do the setup now if we have a SMP BIOS as the + * through-I/O-APIC virtual wire mode might be active. + */ + if (smp_found_config || !boot_cpu_has(X86_FEATURE_APIC)) + return; + + /* + * Do not trust the local APIC being empty at bootup. + */ + clear_local_APIC(); + + /* + * Enable APIC. + */ + value = apic_read(APIC_SPIV); + value &= ~APIC_VECTOR_MASK; + value |= APIC_SPIV_APIC_ENABLED; + +#ifdef CONFIG_X86_32 + /* This bit is reserved on P4/Xeon and should be cleared */ + if ((boot_cpu_data.x86_vendor == X86_VENDOR_INTEL) && + (boot_cpu_data.x86 == 15)) + value &= ~APIC_SPIV_FOCUS_DISABLED; + else +#endif + value |= APIC_SPIV_FOCUS_DISABLED; + value |= SPURIOUS_APIC_VECTOR; + apic_write(APIC_SPIV, value); + + /* + * Set up the virtual wire mode. + */ + apic_write(APIC_LVT0, APIC_DM_EXTINT); + value = APIC_DM_NMI; + if (!lapic_is_integrated()) /* 82489DX */ + value |= APIC_LVT_LEVEL_TRIGGER; + if (apic_extnmi == APIC_EXTNMI_NONE) + value |= APIC_LVT_MASKED; + apic_write(APIC_LVT1, value); +} + /* Init the interrupt delivery mode for the BSP */ void __init apic_intr_mode_init(void) { diff --git a/arch/x86/kernel/apic/vector.c b/arch/x86/kernel/apic/vector.c index f8b03bb8e725..3cc471beb50b 100644 --- a/arch/x86/kernel/apic/vector.c +++ b/arch/x86/kernel/apic/vector.c @@ -542,14 +542,17 @@ static int x86_vector_alloc_irqs(struct irq_domain *domain, unsigned int virq, err = assign_irq_vector_policy(irqd, info); trace_vector_setup(virq + i, false, err); - if (err) + if (err) { + irqd->chip_data = NULL; + free_apic_chip_data(apicd); goto error; + } } return 0; error: - x86_vector_free_irqs(domain, virq, i + 1); + x86_vector_free_irqs(domain, virq, i); return err; } diff --git a/arch/x86/kernel/cpu/amd.c b/arch/x86/kernel/cpu/amd.c index bcb75dc97d44..ea831c858195 100644 --- a/arch/x86/kernel/cpu/amd.c +++ b/arch/x86/kernel/cpu/amd.c @@ -829,8 +829,32 @@ static void init_amd(struct cpuinfo_x86 *c) set_cpu_cap(c, X86_FEATURE_K8); if (cpu_has(c, X86_FEATURE_XMM2)) { - /* MFENCE stops RDTSC speculation */ - set_cpu_cap(c, X86_FEATURE_MFENCE_RDTSC); + unsigned long long val; + int ret; + + /* + * A serializing LFENCE has less overhead than MFENCE, so + * use it for execution serialization. On families which + * don't have that MSR, LFENCE is already serializing. + * msr_set_bit() uses the safe accessors, too, even if the MSR + * is not present. + */ + msr_set_bit(MSR_F10H_DECFG, + MSR_F10H_DECFG_LFENCE_SERIALIZE_BIT); + + /* + * Verify that the MSR write was successful (could be running + * under a hypervisor) and only then assume that LFENCE is + * serializing. + */ + ret = rdmsrl_safe(MSR_F10H_DECFG, &val); + if (!ret && (val & MSR_F10H_DECFG_LFENCE_SERIALIZE)) { + /* A serializing LFENCE stops RDTSC speculation */ + set_cpu_cap(c, X86_FEATURE_LFENCE_RDTSC); + } else { + /* MFENCE stops RDTSC speculation */ + set_cpu_cap(c, X86_FEATURE_MFENCE_RDTSC); + } } /* diff --git a/arch/x86/kernel/cpu/bugs.c b/arch/x86/kernel/cpu/bugs.c index ba0b2424c9b0..390b3dc3d438 100644 --- a/arch/x86/kernel/cpu/bugs.c +++ b/arch/x86/kernel/cpu/bugs.c @@ -10,6 +10,10 @@ */ #include <linux/init.h> #include <linux/utsname.h> +#include <linux/cpu.h> + +#include <asm/nospec-branch.h> +#include <asm/cmdline.h> #include <asm/bugs.h> #include <asm/processor.h> #include <asm/processor-flags.h> @@ -19,6 +23,9 @@ #include <asm/alternative.h> #include <asm/pgtable.h> #include <asm/set_memory.h> +#include <asm/intel-family.h> + +static void __init spectre_v2_select_mitigation(void); void __init check_bugs(void) { @@ -29,6 +36,9 @@ void __init check_bugs(void) print_cpu_info(&boot_cpu_data); } + /* Select the proper spectre mitigation before patching alternatives */ + spectre_v2_select_mitigation(); + #ifdef CONFIG_X86_32 /* * Check whether we are able to run this kernel safely on SMP. @@ -60,3 +70,214 @@ void __init check_bugs(void) set_memory_4k((unsigned long)__va(0), 1); #endif } + +/* The kernel command line selection */ +enum spectre_v2_mitigation_cmd { + SPECTRE_V2_CMD_NONE, + SPECTRE_V2_CMD_AUTO, + SPECTRE_V2_CMD_FORCE, + SPECTRE_V2_CMD_RETPOLINE, + SPECTRE_V2_CMD_RETPOLINE_GENERIC, + SPECTRE_V2_CMD_RETPOLINE_AMD, +}; + +static const char *spectre_v2_strings[] = { + [SPECTRE_V2_NONE] = "Vulnerable", + [SPECTRE_V2_RETPOLINE_MINIMAL] = "Vulnerable: Minimal generic ASM retpoline", + [SPECTRE_V2_RETPOLINE_MINIMAL_AMD] = "Vulnerable: Minimal AMD ASM retpoline", + [SPECTRE_V2_RETPOLINE_GENERIC] = "Mitigation: Full generic retpoline", + [SPECTRE_V2_RETPOLINE_AMD] = "Mitigation: Full AMD retpoline", +}; + +#undef pr_fmt +#define pr_fmt(fmt) "Spectre V2 mitigation: " fmt + +static enum spectre_v2_mitigation spectre_v2_enabled = SPECTRE_V2_NONE; + +static void __init spec2_print_if_insecure(const char *reason) +{ + if (boot_cpu_has_bug(X86_BUG_SPECTRE_V2)) + pr_info("%s\n", reason); +} + +static void __init spec2_print_if_secure(const char *reason) +{ + if (!boot_cpu_has_bug(X86_BUG_SPECTRE_V2)) + pr_info("%s\n", reason); +} + +static inline bool retp_compiler(void) +{ + return __is_defined(RETPOLINE); +} + +static inline bool match_option(const char *arg, int arglen, const char *opt) +{ + int len = strlen(opt); + + return len == arglen && !strncmp(arg, opt, len); +} + +static enum spectre_v2_mitigation_cmd __init spectre_v2_parse_cmdline(void) +{ + char arg[20]; + int ret; + + ret = cmdline_find_option(boot_command_line, "spectre_v2", arg, + sizeof(arg)); + if (ret > 0) { + if (match_option(arg, ret, "off")) { + goto disable; + } else if (match_option(arg, ret, "on")) { + spec2_print_if_secure("force enabled on command line."); + return SPECTRE_V2_CMD_FORCE; + } else if (match_option(arg, ret, "retpoline")) { + spec2_print_if_insecure("retpoline selected on command line."); + return SPECTRE_V2_CMD_RETPOLINE; + } else if (match_option(arg, ret, "retpoline,amd")) { + if (boot_cpu_data.x86_vendor != X86_VENDOR_AMD) { + pr_err("retpoline,amd selected but CPU is not AMD. Switching to AUTO select\n"); + return SPECTRE_V2_CMD_AUTO; + } + spec2_print_if_insecure("AMD retpoline selected on command line."); + return SPECTRE_V2_CMD_RETPOLINE_AMD; + } else if (match_option(arg, ret, "retpoline,generic")) { + spec2_print_if_insecure("generic retpoline selected on command line."); + return SPECTRE_V2_CMD_RETPOLINE_GENERIC; + } else if (match_option(arg, ret, "auto")) { + return SPECTRE_V2_CMD_AUTO; + } + } + + if (!cmdline_find_option_bool(boot_command_line, "nospectre_v2")) + return SPECTRE_V2_CMD_AUTO; +disable: + spec2_print_if_insecure("disabled on command line."); + return SPECTRE_V2_CMD_NONE; +} + +/* Check for Skylake-like CPUs (for RSB handling) */ +static bool __init is_skylake_era(void) +{ + if (boot_cpu_data.x86_vendor == X86_VENDOR_INTEL && + boot_cpu_data.x86 == 6) { + switch (boot_cpu_data.x86_model) { + case INTEL_FAM6_SKYLAKE_MOBILE: + case INTEL_FAM6_SKYLAKE_DESKTOP: + case INTEL_FAM6_SKYLAKE_X: + case INTEL_FAM6_KABYLAKE_MOBILE: + case INTEL_FAM6_KABYLAKE_DESKTOP: + return true; + } + } + return false; +} + +static void __init spectre_v2_select_mitigation(void) +{ + enum spectre_v2_mitigation_cmd cmd = spectre_v2_parse_cmdline(); + enum spectre_v2_mitigation mode = SPECTRE_V2_NONE; + + /* + * If the CPU is not affected and the command line mode is NONE or AUTO + * then nothing to do. + */ + if (!boot_cpu_has_bug(X86_BUG_SPECTRE_V2) && + (cmd == SPECTRE_V2_CMD_NONE || cmd == SPECTRE_V2_CMD_AUTO)) + return; + + switch (cmd) { + case SPECTRE_V2_CMD_NONE: + return; + + case SPECTRE_V2_CMD_FORCE: + /* FALLTRHU */ + case SPECTRE_V2_CMD_AUTO: + goto retpoline_auto; + + case SPECTRE_V2_CMD_RETPOLINE_AMD: + if (IS_ENABLED(CONFIG_RETPOLINE)) + goto retpoline_amd; + break; + case SPECTRE_V2_CMD_RETPOLINE_GENERIC: + if (IS_ENABLED(CONFIG_RETPOLINE)) + goto retpoline_generic; + break; + case SPECTRE_V2_CMD_RETPOLINE: + if (IS_ENABLED(CONFIG_RETPOLINE)) + goto retpoline_auto; + break; + } + pr_err("kernel not compiled with retpoline; no mitigation available!"); + return; + +retpoline_auto: + if (boot_cpu_data.x86_vendor == X86_VENDOR_AMD) { + retpoline_amd: + if (!boot_cpu_has(X86_FEATURE_LFENCE_RDTSC)) { + pr_err("LFENCE not serializing. Switching to generic retpoline\n"); + goto retpoline_generic; + } + mode = retp_compiler() ? SPECTRE_V2_RETPOLINE_AMD : + SPECTRE_V2_RETPOLINE_MINIMAL_AMD; + setup_force_cpu_cap(X86_FEATURE_RETPOLINE_AMD); + setup_force_cpu_cap(X86_FEATURE_RETPOLINE); + } else { + retpoline_generic: + mode = retp_compiler() ? SPECTRE_V2_RETPOLINE_GENERIC : + SPECTRE_V2_RETPOLINE_MINIMAL; + setup_force_cpu_cap(X86_FEATURE_RETPOLINE); + } + + spectre_v2_enabled = mode; + pr_info("%s\n", spectre_v2_strings[mode]); + + /* + * If neither SMEP or KPTI are available, there is a risk of + * hitting userspace addresses in the RSB after a context switch + * from a shallow call stack to a deeper one. To prevent this fill + * the entire RSB, even when using IBRS. + * + * Skylake era CPUs have a separate issue with *underflow* of the + * RSB, when they will predict 'ret' targets from the generic BTB. + * The proper mitigation for this is IBRS. If IBRS is not supported + * or deactivated in favour of retpolines the RSB fill on context + * switch is required. + */ + if ((!boot_cpu_has(X86_FEATURE_PTI) && + !boot_cpu_has(X86_FEATURE_SMEP)) || is_skylake_era()) { + setup_force_cpu_cap(X86_FEATURE_RSB_CTXSW); + pr_info("Filling RSB on context switch\n"); + } +} + +#undef pr_fmt + +#ifdef CONFIG_SYSFS +ssize_t cpu_show_meltdown(struct device *dev, + struct device_attribute *attr, char *buf) +{ + if (!boot_cpu_has_bug(X86_BUG_CPU_MELTDOWN)) + return sprintf(buf, "Not affected\n"); + if (boot_cpu_has(X86_FEATURE_PTI)) + return sprintf(buf, "Mitigation: PTI\n"); + return sprintf(buf, "Vulnerable\n"); +} + +ssize_t cpu_show_spectre_v1(struct device *dev, + struct device_attribute *attr, char *buf) +{ + if (!boot_cpu_has_bug(X86_BUG_SPECTRE_V1)) + return sprintf(buf, "Not affected\n"); + return sprintf(buf, "Vulnerable\n"); +} + +ssize_t cpu_show_spectre_v2(struct device *dev, + struct device_attribute *attr, char *buf) +{ + if (!boot_cpu_has_bug(X86_BUG_SPECTRE_V2)) + return sprintf(buf, "Not affected\n"); + + return sprintf(buf, "%s\n", spectre_v2_strings[spectre_v2_enabled]); +} +#endif diff --git a/arch/x86/kernel/cpu/common.c b/arch/x86/kernel/cpu/common.c index 39d7ea865207..ef29ad001991 100644 --- a/arch/x86/kernel/cpu/common.c +++ b/arch/x86/kernel/cpu/common.c @@ -926,6 +926,9 @@ static void __init early_identify_cpu(struct cpuinfo_x86 *c) if (c->x86_vendor != X86_VENDOR_AMD) setup_force_cpu_bug(X86_BUG_CPU_MELTDOWN); + setup_force_cpu_bug(X86_BUG_SPECTRE_V1); + setup_force_cpu_bug(X86_BUG_SPECTRE_V2); + fpu__init_system(c); #ifdef CONFIG_X86_32 diff --git a/arch/x86/kernel/cpu/intel_rdt.c b/arch/x86/kernel/cpu/intel_rdt.c index 88dcf8479013..99442370de40 100644 --- a/arch/x86/kernel/cpu/intel_rdt.c +++ b/arch/x86/kernel/cpu/intel_rdt.c @@ -525,10 +525,6 @@ 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); - kfree(d->ctrl_val); - kfree(d->rmid_busy_llc); - kfree(d->mbm_total); - kfree(d->mbm_local); list_del(&d->list); if (is_mbm_enabled()) cancel_delayed_work(&d->mbm_over); @@ -545,6 +541,10 @@ static void domain_remove_cpu(int cpu, struct rdt_resource *r) cancel_delayed_work(&d->cqm_limbo); } + kfree(d->ctrl_val); + kfree(d->rmid_busy_llc); + kfree(d->mbm_total); + kfree(d->mbm_local); kfree(d); return; } diff --git a/arch/x86/kernel/cpu/mcheck/mce.c b/arch/x86/kernel/cpu/mcheck/mce.c index b1d616d08eee..868e412b4f0c 100644 --- a/arch/x86/kernel/cpu/mcheck/mce.c +++ b/arch/x86/kernel/cpu/mcheck/mce.c @@ -1785,6 +1785,11 @@ static void unexpected_machine_check(struct pt_regs *regs, long error_code) void (*machine_check_vector)(struct pt_regs *, long error_code) = unexpected_machine_check; +dotraplinkage void do_mce(struct pt_regs *regs, long error_code) +{ + machine_check_vector(regs, error_code); +} + /* * Called for each booted CPU to set up machine checks. * Must be called with preempt off: diff --git a/arch/x86/kernel/cpu/microcode/intel.c b/arch/x86/kernel/cpu/microcode/intel.c index 8ccdca6d3f9e..d9e460fc7a3b 100644 --- a/arch/x86/kernel/cpu/microcode/intel.c +++ b/arch/x86/kernel/cpu/microcode/intel.c @@ -910,8 +910,17 @@ static bool is_blacklisted(unsigned int cpu) { struct cpuinfo_x86 *c = &cpu_data(cpu); - if (c->x86 == 6 && c->x86_model == INTEL_FAM6_BROADWELL_X) { - pr_err_once("late loading on model 79 is disabled.\n"); + /* + * Late loading on model 79 with microcode revision less than 0x0b000021 + * may result in a system hang. This behavior is documented in item + * BDF90, #334165 (Intel Xeon Processor E7-8800/4800 v4 Product Family). + */ + if (c->x86 == 6 && + c->x86_model == INTEL_FAM6_BROADWELL_X && + c->x86_mask == 0x01 && + c->microcode < 0x0b000021) { + pr_err_once("Erratum BDF90: late loading with revision < 0x0b000021 (0x%x) disabled.\n", c->microcode); + pr_err_once("Please consider either early loading through initrd/built-in or a potential BIOS update.\n"); return true; } diff --git a/arch/x86/kernel/cpu/scattered.c b/arch/x86/kernel/cpu/scattered.c index 05459ad3db46..d0e69769abfd 100644 --- a/arch/x86/kernel/cpu/scattered.c +++ b/arch/x86/kernel/cpu/scattered.c @@ -21,7 +21,6 @@ struct cpuid_bit { static const struct cpuid_bit cpuid_bits[] = { { X86_FEATURE_APERFMPERF, CPUID_ECX, 0, 0x00000006, 0 }, { X86_FEATURE_EPB, CPUID_ECX, 3, 0x00000006, 0 }, - { X86_FEATURE_INTEL_PT, CPUID_EBX, 25, 0x00000007, 0 }, { X86_FEATURE_AVX512_4VNNIW, CPUID_EDX, 2, 0x00000007, 0 }, { X86_FEATURE_AVX512_4FMAPS, CPUID_EDX, 3, 0x00000007, 0 }, { X86_FEATURE_CAT_L3, CPUID_EBX, 1, 0x00000010, 0 }, diff --git a/arch/x86/kernel/ftrace_32.S b/arch/x86/kernel/ftrace_32.S index b6c6468e10bc..4c8440de3355 100644 --- a/arch/x86/kernel/ftrace_32.S +++ b/arch/x86/kernel/ftrace_32.S @@ -8,6 +8,7 @@ #include <asm/segment.h> #include <asm/export.h> #include <asm/ftrace.h> +#include <asm/nospec-branch.h> #ifdef CC_USING_FENTRY # define function_hook __fentry__ @@ -197,7 +198,8 @@ ftrace_stub: movl 0x4(%ebp), %edx subl $MCOUNT_INSN_SIZE, %eax - call *ftrace_trace_function + movl ftrace_trace_function, %ecx + CALL_NOSPEC %ecx popl %edx popl %ecx @@ -241,5 +243,5 @@ return_to_handler: movl %eax, %ecx popl %edx popl %eax - jmp *%ecx + JMP_NOSPEC %ecx #endif diff --git a/arch/x86/kernel/ftrace_64.S b/arch/x86/kernel/ftrace_64.S index c832291d948a..ef61f540cf0a 100644 --- a/arch/x86/kernel/ftrace_64.S +++ b/arch/x86/kernel/ftrace_64.S @@ -7,7 +7,8 @@ #include <asm/ptrace.h> #include <asm/ftrace.h> #include <asm/export.h> - +#include <asm/nospec-branch.h> +#include <asm/unwind_hints.h> .code64 .section .entry.text, "ax" @@ -20,7 +21,6 @@ EXPORT_SYMBOL(__fentry__) EXPORT_SYMBOL(mcount) #endif -/* All cases save the original rbp (8 bytes) */ #ifdef CONFIG_FRAME_POINTER # ifdef CC_USING_FENTRY /* Save parent and function stack frames (rip and rbp) */ @@ -31,7 +31,7 @@ EXPORT_SYMBOL(mcount) # endif #else /* No need to save a stack frame */ -# define MCOUNT_FRAME_SIZE 8 +# define MCOUNT_FRAME_SIZE 0 #endif /* CONFIG_FRAME_POINTER */ /* Size of stack used to save mcount regs in save_mcount_regs */ @@ -64,10 +64,10 @@ EXPORT_SYMBOL(mcount) */ .macro save_mcount_regs added=0 - /* Always save the original rbp */ +#ifdef CONFIG_FRAME_POINTER + /* Save the original rbp */ pushq %rbp -#ifdef CONFIG_FRAME_POINTER /* * Stack traces will stop at the ftrace trampoline if the frame pointer * is not set up properly. If fentry is used, we need to save a frame @@ -105,7 +105,11 @@ EXPORT_SYMBOL(mcount) * Save the original RBP. Even though the mcount ABI does not * require this, it helps out callers. */ +#ifdef CONFIG_FRAME_POINTER movq MCOUNT_REG_SIZE-8(%rsp), %rdx +#else + movq %rbp, %rdx +#endif movq %rdx, RBP(%rsp) /* Copy the parent address into %rsi (second parameter) */ @@ -148,7 +152,7 @@ EXPORT_SYMBOL(mcount) ENTRY(function_hook) retq -END(function_hook) +ENDPROC(function_hook) ENTRY(ftrace_caller) /* save_mcount_regs fills in first two parameters */ @@ -184,7 +188,7 @@ GLOBAL(ftrace_graph_call) /* This is weak to keep gas from relaxing the jumps */ WEAK(ftrace_stub) retq -END(ftrace_caller) +ENDPROC(ftrace_caller) ENTRY(ftrace_regs_caller) /* Save the current flags before any operations that can change them */ @@ -255,7 +259,7 @@ GLOBAL(ftrace_regs_caller_end) jmp ftrace_epilogue -END(ftrace_regs_caller) +ENDPROC(ftrace_regs_caller) #else /* ! CONFIG_DYNAMIC_FTRACE */ @@ -286,8 +290,8 @@ trace: * ip and parent ip are used and the list function is called when * function tracing is enabled. */ - call *ftrace_trace_function - + movq ftrace_trace_function, %r8 + CALL_NOSPEC %r8 restore_mcount_regs jmp fgraph_trace @@ -313,9 +317,10 @@ ENTRY(ftrace_graph_caller) restore_mcount_regs retq -END(ftrace_graph_caller) +ENDPROC(ftrace_graph_caller) -GLOBAL(return_to_handler) +ENTRY(return_to_handler) + UNWIND_HINT_EMPTY subq $24, %rsp /* Save the return values */ @@ -329,5 +334,6 @@ GLOBAL(return_to_handler) movq 8(%rsp), %rdx movq (%rsp), %rax addq $24, %rsp - jmp *%rdi + JMP_NOSPEC %rdi +END(return_to_handler) #endif diff --git a/arch/x86/kernel/head64.c b/arch/x86/kernel/head64.c index 6a5d757b9cfd..7ba5d819ebe3 100644 --- a/arch/x86/kernel/head64.c +++ b/arch/x86/kernel/head64.c @@ -157,8 +157,8 @@ unsigned long __head __startup_64(unsigned long physaddr, p = fixup_pointer(&phys_base, physaddr); *p += load_delta - sme_get_me_mask(); - /* Encrypt the kernel (if SME is active) */ - sme_encrypt_kernel(); + /* Encrypt the kernel and related (if SME is active) */ + sme_encrypt_kernel(bp); /* * Return the SME encryption mask (if SME is active) to be used as a diff --git a/arch/x86/kernel/idt.c b/arch/x86/kernel/idt.c index d985cef3984f..56d99be3706a 100644 --- a/arch/x86/kernel/idt.c +++ b/arch/x86/kernel/idt.c @@ -56,7 +56,7 @@ struct idt_data { * Early traps running on the DEFAULT_STACK because the other interrupt * stacks work only after cpu_init(). */ -static const __initdata struct idt_data early_idts[] = { +static const __initconst struct idt_data early_idts[] = { INTG(X86_TRAP_DB, debug), SYSG(X86_TRAP_BP, int3), #ifdef CONFIG_X86_32 @@ -70,7 +70,7 @@ static const __initdata struct idt_data early_idts[] = { * the traps which use them are reinitialized with IST after cpu_init() has * set up TSS. */ -static const __initdata struct idt_data def_idts[] = { +static const __initconst struct idt_data def_idts[] = { INTG(X86_TRAP_DE, divide_error), INTG(X86_TRAP_NMI, nmi), INTG(X86_TRAP_BR, bounds), @@ -108,7 +108,7 @@ static const __initdata struct idt_data def_idts[] = { /* * The APIC and SMP idt entries */ -static const __initdata struct idt_data apic_idts[] = { +static const __initconst struct idt_data apic_idts[] = { #ifdef CONFIG_SMP INTG(RESCHEDULE_VECTOR, reschedule_interrupt), INTG(CALL_FUNCTION_VECTOR, call_function_interrupt), @@ -150,7 +150,7 @@ static const __initdata struct idt_data apic_idts[] = { * Early traps running on the DEFAULT_STACK because the other interrupt * stacks work only after cpu_init(). */ -static const __initdata struct idt_data early_pf_idts[] = { +static const __initconst struct idt_data early_pf_idts[] = { INTG(X86_TRAP_PF, page_fault), }; @@ -158,7 +158,7 @@ static const __initdata struct idt_data early_pf_idts[] = { * Override for the debug_idt. Same as the default, but with interrupt * stack set to DEFAULT_STACK (0). Required for NMI trap handling. */ -static const __initdata struct idt_data dbg_idts[] = { +static const __initconst struct idt_data dbg_idts[] = { INTG(X86_TRAP_DB, debug), INTG(X86_TRAP_BP, int3), }; @@ -180,7 +180,7 @@ gate_desc debug_idt_table[IDT_ENTRIES] __page_aligned_bss; * The exceptions which use Interrupt stacks. They are setup after * cpu_init() when the TSS has been initialized. */ -static const __initdata struct idt_data ist_idts[] = { +static const __initconst struct idt_data ist_idts[] = { ISTG(X86_TRAP_DB, debug, DEBUG_STACK), ISTG(X86_TRAP_NMI, nmi, NMI_STACK), SISTG(X86_TRAP_BP, int3, DEBUG_STACK), diff --git a/arch/x86/kernel/irq_32.c b/arch/x86/kernel/irq_32.c index a83b3346a0e1..c1bdbd3d3232 100644 --- a/arch/x86/kernel/irq_32.c +++ b/arch/x86/kernel/irq_32.c @@ -20,6 +20,7 @@ #include <linux/mm.h> #include <asm/apic.h> +#include <asm/nospec-branch.h> #ifdef CONFIG_DEBUG_STACKOVERFLOW @@ -55,11 +56,11 @@ DEFINE_PER_CPU(struct irq_stack *, softirq_stack); static void call_on_stack(void *func, void *stack) { asm volatile("xchgl %%ebx,%%esp \n" - "call *%%edi \n" + CALL_NOSPEC "movl %%ebx,%%esp \n" : "=b" (stack) : "0" (stack), - "D"(func) + [thunk_target] "D"(func) : "memory", "cc", "edx", "ecx", "eax"); } @@ -95,11 +96,11 @@ static inline int execute_on_irq_stack(int overflow, struct irq_desc *desc) call_on_stack(print_stack_overflow, isp); asm volatile("xchgl %%ebx,%%esp \n" - "call *%%edi \n" + CALL_NOSPEC "movl %%ebx,%%esp \n" : "=a" (arg1), "=b" (isp) : "0" (desc), "1" (isp), - "D" (desc->handle_irq) + [thunk_target] "D" (desc->handle_irq) : "memory", "cc", "ecx"); return 1; } diff --git a/arch/x86/kernel/irqinit.c b/arch/x86/kernel/irqinit.c index 8da3e909e967..a539410c4ea9 100644 --- a/arch/x86/kernel/irqinit.c +++ b/arch/x86/kernel/irqinit.c @@ -61,6 +61,9 @@ void __init init_ISA_irqs(void) struct irq_chip *chip = legacy_pic->chip; int i; +#if defined(CONFIG_X86_64) || defined(CONFIG_X86_LOCAL_APIC) + init_bsp_APIC(); +#endif legacy_pic->init(0); for (i = 0; i < nr_legacy_irqs(); i++) diff --git a/arch/x86/kernel/kprobes/opt.c b/arch/x86/kernel/kprobes/opt.c index e941136e24d8..203d398802a3 100644 --- a/arch/x86/kernel/kprobes/opt.c +++ b/arch/x86/kernel/kprobes/opt.c @@ -40,6 +40,7 @@ #include <asm/debugreg.h> #include <asm/set_memory.h> #include <asm/sections.h> +#include <asm/nospec-branch.h> #include "common.h" @@ -203,7 +204,7 @@ static int copy_optimized_instructions(u8 *dest, u8 *src, u8 *real) } /* Check whether insn is indirect jump */ -static int insn_is_indirect_jump(struct insn *insn) +static int __insn_is_indirect_jump(struct insn *insn) { return ((insn->opcode.bytes[0] == 0xff && (X86_MODRM_REG(insn->modrm.value) & 6) == 4) || /* Jump */ @@ -237,6 +238,26 @@ static int insn_jump_into_range(struct insn *insn, unsigned long start, int len) return (start <= target && target <= start + len); } +static int insn_is_indirect_jump(struct insn *insn) +{ + int ret = __insn_is_indirect_jump(insn); + +#ifdef CONFIG_RETPOLINE + /* + * Jump to x86_indirect_thunk_* is treated as an indirect jump. + * Note that even with CONFIG_RETPOLINE=y, the kernel compiled with + * older gcc may use indirect jump. So we add this check instead of + * replace indirect-jump check. + */ + if (!ret) + ret = insn_jump_into_range(insn, + (unsigned long)__indirect_thunk_start, + (unsigned long)__indirect_thunk_end - + (unsigned long)__indirect_thunk_start); +#endif + return ret; +} + /* Decode whole function to ensure any instructions don't jump into target */ static int can_optimize(unsigned long paddr) { diff --git a/arch/x86/kernel/process.c b/arch/x86/kernel/process.c index 832a6acd730f..cb368c2a22ab 100644 --- a/arch/x86/kernel/process.c +++ b/arch/x86/kernel/process.c @@ -380,19 +380,24 @@ void stop_this_cpu(void *dummy) disable_local_APIC(); mcheck_cpu_clear(this_cpu_ptr(&cpu_info)); + /* + * Use wbinvd on processors that support SME. This provides support + * for performing a successful kexec when going from SME inactive + * to SME active (or vice-versa). The cache must be cleared so that + * if there are entries with the same physical address, both with and + * without the encryption bit, they don't race each other when flushed + * and potentially end up with the wrong entry being committed to + * memory. + */ + if (boot_cpu_has(X86_FEATURE_SME)) + native_wbinvd(); for (;;) { /* - * Use wbinvd followed by hlt to stop the processor. This - * provides support for kexec on a processor that supports - * SME. With kexec, going from SME inactive to SME active - * requires clearing cache entries so that addresses without - * the encryption bit set don't corrupt the same physical - * address that has the encryption bit set when caches are - * flushed. To achieve this a wbinvd is performed followed by - * a hlt. Even if the processor is not in the kexec/SME - * scenario this only adds a wbinvd to a halting processor. + * Use native_halt() so that memory contents don't change + * (stack usage and variables) after possibly issuing the + * native_wbinvd() above. */ - asm volatile("wbinvd; hlt" : : : "memory"); + native_halt(); } } diff --git a/arch/x86/kernel/setup.c b/arch/x86/kernel/setup.c index 145810b0edf6..68d7ab81c62f 100644 --- a/arch/x86/kernel/setup.c +++ b/arch/x86/kernel/setup.c @@ -364,16 +364,6 @@ static void __init reserve_initrd(void) !ramdisk_image || !ramdisk_size) return; /* No initrd provided by bootloader */ - /* - * If SME is active, this memory will be marked encrypted by the - * kernel when it is accessed (including relocation). However, the - * ramdisk image was loaded decrypted by the bootloader, so make - * sure that it is encrypted before accessing it. For SEV the - * ramdisk will already be encrypted, so only do this for SME. - */ - if (sme_active()) - sme_early_encrypt(ramdisk_image, ramdisk_end - ramdisk_image); - initrd_start = 0; mapped_size = memblock_mem_size(max_pfn_mapped); diff --git a/arch/x86/kernel/tboot.c b/arch/x86/kernel/tboot.c index a4eb27918ceb..a2486f444073 100644 --- a/arch/x86/kernel/tboot.c +++ b/arch/x86/kernel/tboot.c @@ -138,6 +138,17 @@ static int map_tboot_page(unsigned long vaddr, unsigned long pfn, return -1; set_pte_at(&tboot_mm, vaddr, pte, pfn_pte(pfn, prot)); pte_unmap(pte); + + /* + * PTI poisons low addresses in the kernel page tables in the + * name of making them unusable for userspace. To execute + * code at such a low address, the poison must be cleared. + * + * Note: 'pgd' actually gets set in p4d_alloc() _or_ + * pud_alloc() depending on 4/5-level paging. + */ + pgd->pgd &= ~_PAGE_NX; + return 0; } diff --git a/arch/x86/kernel/tsc.c b/arch/x86/kernel/tsc.c index 8ea117f8142e..e169e85db434 100644 --- a/arch/x86/kernel/tsc.c +++ b/arch/x86/kernel/tsc.c @@ -602,7 +602,6 @@ unsigned long native_calibrate_tsc(void) case INTEL_FAM6_KABYLAKE_DESKTOP: crystal_khz = 24000; /* 24.0 MHz */ break; - case INTEL_FAM6_SKYLAKE_X: case INTEL_FAM6_ATOM_DENVERTON: crystal_khz = 25000; /* 25.0 MHz */ break; @@ -612,6 +611,8 @@ unsigned long native_calibrate_tsc(void) } } + if (crystal_khz == 0) + return 0; /* * TSC frequency determined by CPUID is a "hardware reported" * frequency and is the most accurate one so far we have. This @@ -1315,6 +1316,12 @@ void __init tsc_init(void) (unsigned long)cpu_khz / 1000, (unsigned long)cpu_khz % 1000); + if (cpu_khz != tsc_khz) { + pr_info("Detected %lu.%03lu MHz TSC", + (unsigned long)tsc_khz / 1000, + (unsigned long)tsc_khz % 1000); + } + /* Sanitize TSC ADJUST before cyc2ns gets initialized */ tsc_store_and_check_tsc_adjust(true); diff --git a/arch/x86/kernel/unwind_orc.c b/arch/x86/kernel/unwind_orc.c index be86a865087a..1f9188f5357c 100644 --- a/arch/x86/kernel/unwind_orc.c +++ b/arch/x86/kernel/unwind_orc.c @@ -74,8 +74,50 @@ static struct orc_entry *orc_module_find(unsigned long ip) } #endif +#ifdef CONFIG_DYNAMIC_FTRACE +static struct orc_entry *orc_find(unsigned long ip); + +/* + * Ftrace dynamic trampolines do not have orc entries of their own. + * But they are copies of the ftrace entries that are static and + * defined in ftrace_*.S, which do have orc entries. + * + * If the undwinder comes across a ftrace trampoline, then find the + * ftrace function that was used to create it, and use that ftrace + * function's orc entrie, as the placement of the return code in + * the stack will be identical. + */ +static struct orc_entry *orc_ftrace_find(unsigned long ip) +{ + struct ftrace_ops *ops; + unsigned long caller; + + ops = ftrace_ops_trampoline(ip); + if (!ops) + return NULL; + + if (ops->flags & FTRACE_OPS_FL_SAVE_REGS) + caller = (unsigned long)ftrace_regs_call; + else + caller = (unsigned long)ftrace_call; + + /* Prevent unlikely recursion */ + if (ip == caller) + return NULL; + + return orc_find(caller); +} +#else +static struct orc_entry *orc_ftrace_find(unsigned long ip) +{ + return NULL; +} +#endif + static struct orc_entry *orc_find(unsigned long ip) { + static struct orc_entry *orc; + if (!orc_init) return NULL; @@ -111,7 +153,11 @@ static struct orc_entry *orc_find(unsigned long ip) __stop_orc_unwind_ip - __start_orc_unwind_ip, ip); /* Module lookup: */ - return orc_module_find(ip); + orc = orc_module_find(ip); + if (orc) + return orc; + + return orc_ftrace_find(ip); } static void orc_sort_swap(void *_a, void *_b, int size) diff --git a/arch/x86/kernel/vmlinux.lds.S b/arch/x86/kernel/vmlinux.lds.S index 1e413a9326aa..9b138a06c1a4 100644 --- a/arch/x86/kernel/vmlinux.lds.S +++ b/arch/x86/kernel/vmlinux.lds.S @@ -124,6 +124,12 @@ SECTIONS ASSERT(. - _entry_trampoline == PAGE_SIZE, "entry trampoline is too big"); #endif +#ifdef CONFIG_RETPOLINE + __indirect_thunk_start = .; + *(.text.__x86.indirect_thunk) + __indirect_thunk_end = .; +#endif + /* End of text section */ _etext = .; } :text = 0x9090 diff --git a/arch/x86/kvm/mmu.c b/arch/x86/kvm/mmu.c index c4deb1f34faa..2b8eb4da4d08 100644 --- a/arch/x86/kvm/mmu.c +++ b/arch/x86/kvm/mmu.c @@ -3781,7 +3781,8 @@ static int kvm_arch_setup_async_pf(struct kvm_vcpu *vcpu, gva_t gva, gfn_t gfn) bool kvm_can_do_async_pf(struct kvm_vcpu *vcpu) { if (unlikely(!lapic_in_kernel(vcpu) || - kvm_event_needs_reinjection(vcpu))) + kvm_event_needs_reinjection(vcpu) || + vcpu->arch.exception.pending)) return false; if (!vcpu->arch.apf.delivery_as_pf_vmexit && is_guest_mode(vcpu)) @@ -5465,30 +5466,34 @@ static void mmu_destroy_caches(void) int kvm_mmu_module_init(void) { + int ret = -ENOMEM; + kvm_mmu_clear_all_pte_masks(); pte_list_desc_cache = kmem_cache_create("pte_list_desc", sizeof(struct pte_list_desc), 0, SLAB_ACCOUNT, NULL); if (!pte_list_desc_cache) - goto nomem; + goto out; mmu_page_header_cache = kmem_cache_create("kvm_mmu_page_header", sizeof(struct kvm_mmu_page), 0, SLAB_ACCOUNT, NULL); if (!mmu_page_header_cache) - goto nomem; + goto out; if (percpu_counter_init(&kvm_total_used_mmu_pages, 0, GFP_KERNEL)) - goto nomem; + goto out; - register_shrinker(&mmu_shrinker); + ret = register_shrinker(&mmu_shrinker); + if (ret) + goto out; return 0; -nomem: +out: mmu_destroy_caches(); - return -ENOMEM; + return ret; } /* diff --git a/arch/x86/kvm/svm.c b/arch/x86/kvm/svm.c index eb714f1cdf7e..f40d0da1f1d3 100644 --- a/arch/x86/kvm/svm.c +++ b/arch/x86/kvm/svm.c @@ -45,6 +45,7 @@ #include <asm/debugreg.h> #include <asm/kvm_para.h> #include <asm/irq_remapping.h> +#include <asm/nospec-branch.h> #include <asm/virtext.h> #include "trace.h" @@ -361,7 +362,6 @@ static void recalc_intercepts(struct vcpu_svm *svm) { struct vmcb_control_area *c, *h; struct nested_state *g; - u32 h_intercept_exceptions; mark_dirty(svm->vmcb, VMCB_INTERCEPTS); @@ -372,14 +372,9 @@ static void recalc_intercepts(struct vcpu_svm *svm) h = &svm->nested.hsave->control; g = &svm->nested; - /* No need to intercept #UD if L1 doesn't intercept it */ - h_intercept_exceptions = - h->intercept_exceptions & ~(1U << UD_VECTOR); - c->intercept_cr = h->intercept_cr | g->intercept_cr; c->intercept_dr = h->intercept_dr | g->intercept_dr; - c->intercept_exceptions = - h_intercept_exceptions | g->intercept_exceptions; + c->intercept_exceptions = h->intercept_exceptions | g->intercept_exceptions; c->intercept = h->intercept | g->intercept; } @@ -2202,7 +2197,6 @@ static int ud_interception(struct vcpu_svm *svm) { int er; - WARN_ON_ONCE(is_guest_mode(&svm->vcpu)); er = emulate_instruction(&svm->vcpu, EMULTYPE_TRAP_UD); if (er == EMULATE_USER_EXIT) return 0; @@ -4986,6 +4980,25 @@ static void svm_vcpu_run(struct kvm_vcpu *vcpu) "mov %%r14, %c[r14](%[svm]) \n\t" "mov %%r15, %c[r15](%[svm]) \n\t" #endif + /* + * Clear host registers marked as clobbered to prevent + * speculative use. + */ + "xor %%" _ASM_BX ", %%" _ASM_BX " \n\t" + "xor %%" _ASM_CX ", %%" _ASM_CX " \n\t" + "xor %%" _ASM_DX ", %%" _ASM_DX " \n\t" + "xor %%" _ASM_SI ", %%" _ASM_SI " \n\t" + "xor %%" _ASM_DI ", %%" _ASM_DI " \n\t" +#ifdef CONFIG_X86_64 + "xor %%r8, %%r8 \n\t" + "xor %%r9, %%r9 \n\t" + "xor %%r10, %%r10 \n\t" + "xor %%r11, %%r11 \n\t" + "xor %%r12, %%r12 \n\t" + "xor %%r13, %%r13 \n\t" + "xor %%r14, %%r14 \n\t" + "xor %%r15, %%r15 \n\t" +#endif "pop %%" _ASM_BP : : [svm]"a"(svm), @@ -5015,6 +5028,9 @@ static void svm_vcpu_run(struct kvm_vcpu *vcpu) #endif ); + /* Eliminate branch target predictions from guest mode */ + vmexit_fill_RSB(); + #ifdef CONFIG_X86_64 wrmsrl(MSR_GS_BASE, svm->host.gs_base); #else diff --git a/arch/x86/kvm/vmx.c b/arch/x86/kvm/vmx.c index 023afa0c8887..c829d89e2e63 100644 --- a/arch/x86/kvm/vmx.c +++ b/arch/x86/kvm/vmx.c @@ -50,6 +50,7 @@ #include <asm/apic.h> #include <asm/irq_remapping.h> #include <asm/mmu_context.h> +#include <asm/nospec-branch.h> #include "trace.h" #include "pmu.h" @@ -899,8 +900,16 @@ static inline short vmcs_field_to_offset(unsigned long field) { BUILD_BUG_ON(ARRAY_SIZE(vmcs_field_to_offset_table) > SHRT_MAX); - if (field >= ARRAY_SIZE(vmcs_field_to_offset_table) || - vmcs_field_to_offset_table[field] == 0) + if (field >= ARRAY_SIZE(vmcs_field_to_offset_table)) + return -ENOENT; + + /* + * FIXME: Mitigation for CVE-2017-5753. To be replaced with a + * generic mechanism. + */ + asm("lfence"); + + if (vmcs_field_to_offset_table[field] == 0) return -ENOENT; return vmcs_field_to_offset_table[field]; @@ -1887,7 +1896,7 @@ static void update_exception_bitmap(struct kvm_vcpu *vcpu) { u32 eb; - eb = (1u << PF_VECTOR) | (1u << MC_VECTOR) | + eb = (1u << PF_VECTOR) | (1u << UD_VECTOR) | (1u << MC_VECTOR) | (1u << DB_VECTOR) | (1u << AC_VECTOR); if ((vcpu->guest_debug & (KVM_GUESTDBG_ENABLE | KVM_GUESTDBG_USE_SW_BP)) == @@ -1905,8 +1914,6 @@ static void update_exception_bitmap(struct kvm_vcpu *vcpu) */ if (is_guest_mode(vcpu)) eb |= get_vmcs12(vcpu)->exception_bitmap; - else - eb |= 1u << UD_VECTOR; vmcs_write32(EXCEPTION_BITMAP, eb); } @@ -5917,7 +5924,6 @@ static int handle_exception(struct kvm_vcpu *vcpu) return 1; /* already handled by vmx_vcpu_run() */ if (is_invalid_opcode(intr_info)) { - WARN_ON_ONCE(is_guest_mode(vcpu)); er = emulate_instruction(vcpu, EMULTYPE_TRAP_UD); if (er == EMULATE_USER_EXIT) return 0; @@ -9415,6 +9421,7 @@ static void __noclone vmx_vcpu_run(struct kvm_vcpu *vcpu) /* Save guest registers, load host registers, keep flags */ "mov %0, %c[wordsize](%%" _ASM_SP ") \n\t" "pop %0 \n\t" + "setbe %c[fail](%0)\n\t" "mov %%" _ASM_AX ", %c[rax](%0) \n\t" "mov %%" _ASM_BX ", %c[rbx](%0) \n\t" __ASM_SIZE(pop) " %c[rcx](%0) \n\t" @@ -9431,12 +9438,23 @@ static void __noclone vmx_vcpu_run(struct kvm_vcpu *vcpu) "mov %%r13, %c[r13](%0) \n\t" "mov %%r14, %c[r14](%0) \n\t" "mov %%r15, %c[r15](%0) \n\t" + "xor %%r8d, %%r8d \n\t" + "xor %%r9d, %%r9d \n\t" + "xor %%r10d, %%r10d \n\t" + "xor %%r11d, %%r11d \n\t" + "xor %%r12d, %%r12d \n\t" + "xor %%r13d, %%r13d \n\t" + "xor %%r14d, %%r14d \n\t" + "xor %%r15d, %%r15d \n\t" #endif "mov %%cr2, %%" _ASM_AX " \n\t" "mov %%" _ASM_AX ", %c[cr2](%0) \n\t" + "xor %%eax, %%eax \n\t" + "xor %%ebx, %%ebx \n\t" + "xor %%esi, %%esi \n\t" + "xor %%edi, %%edi \n\t" "pop %%" _ASM_BP "; pop %%" _ASM_DX " \n\t" - "setbe %c[fail](%0) \n\t" ".pushsection .rodata \n\t" ".global vmx_return \n\t" "vmx_return: " _ASM_PTR " 2b \n\t" @@ -9473,6 +9491,9 @@ static void __noclone vmx_vcpu_run(struct kvm_vcpu *vcpu) #endif ); + /* Eliminate branch target predictions from guest mode */ + vmexit_fill_RSB(); + /* MSR_IA32_DEBUGCTLMSR is zeroed on vmexit. Restore it if needed */ if (debugctlmsr) update_debugctlmsr(debugctlmsr); diff --git a/arch/x86/kvm/x86.c b/arch/x86/kvm/x86.c index 1cec2c62a0b0..c53298dfbf50 100644 --- a/arch/x86/kvm/x86.c +++ b/arch/x86/kvm/x86.c @@ -7496,13 +7496,13 @@ EXPORT_SYMBOL_GPL(kvm_task_switch); int kvm_valid_sregs(struct kvm_vcpu *vcpu, struct kvm_sregs *sregs) { - if ((sregs->efer & EFER_LME) && (sregs->cr0 & X86_CR0_PG_BIT)) { + if ((sregs->efer & EFER_LME) && (sregs->cr0 & X86_CR0_PG)) { /* * When EFER.LME and CR0.PG are set, the processor is in * 64-bit mode (though maybe in a 32-bit code segment). * CR4.PAE and EFER.LMA must be set. */ - if (!(sregs->cr4 & X86_CR4_PAE_BIT) + if (!(sregs->cr4 & X86_CR4_PAE) || !(sregs->efer & EFER_LMA)) return -EINVAL; } else { diff --git a/arch/x86/lib/Makefile b/arch/x86/lib/Makefile index 7b181b61170e..f23934bbaf4e 100644 --- a/arch/x86/lib/Makefile +++ b/arch/x86/lib/Makefile @@ -26,6 +26,7 @@ lib-y += memcpy_$(BITS).o lib-$(CONFIG_RWSEM_XCHGADD_ALGORITHM) += rwsem.o lib-$(CONFIG_INSTRUCTION_DECODER) += insn.o inat.o insn-eval.o lib-$(CONFIG_RANDOMIZE_BASE) += kaslr.o +lib-$(CONFIG_RETPOLINE) += retpoline.o obj-y += msr.o msr-reg.o msr-reg-export.o hweight.o diff --git a/arch/x86/lib/checksum_32.S b/arch/x86/lib/checksum_32.S index 4d34bb548b41..46e71a74e612 100644 --- a/arch/x86/lib/checksum_32.S +++ b/arch/x86/lib/checksum_32.S @@ -29,7 +29,8 @@ #include <asm/errno.h> #include <asm/asm.h> #include <asm/export.h> - +#include <asm/nospec-branch.h> + /* * computes a partial checksum, e.g. for TCP/UDP fragments */ @@ -156,7 +157,7 @@ ENTRY(csum_partial) negl %ebx lea 45f(%ebx,%ebx,2), %ebx testl %esi, %esi - jmp *%ebx + JMP_NOSPEC %ebx # Handle 2-byte-aligned regions 20: addw (%esi), %ax @@ -439,7 +440,7 @@ ENTRY(csum_partial_copy_generic) andl $-32,%edx lea 3f(%ebx,%ebx), %ebx testl %esi, %esi - jmp *%ebx + JMP_NOSPEC %ebx 1: addl $64,%esi addl $64,%edi SRC(movb -32(%edx),%bl) ; SRC(movb (%edx),%bl) diff --git a/arch/x86/lib/retpoline.S b/arch/x86/lib/retpoline.S new file mode 100644 index 000000000000..dfb2ba91b670 --- /dev/null +++ b/arch/x86/lib/retpoline.S @@ -0,0 +1,49 @@ +/* SPDX-License-Identifier: GPL-2.0 */ + +#include <linux/stringify.h> +#include <linux/linkage.h> +#include <asm/dwarf2.h> +#include <asm/cpufeatures.h> +#include <asm/alternative-asm.h> +#include <asm/export.h> +#include <asm/nospec-branch.h> + +.macro THUNK reg + .section .text.__x86.indirect_thunk + +ENTRY(__x86_indirect_thunk_\reg) + CFI_STARTPROC + JMP_NOSPEC %\reg + CFI_ENDPROC +ENDPROC(__x86_indirect_thunk_\reg) +.endm + +/* + * Despite being an assembler file we can't just use .irp here + * because __KSYM_DEPS__ only uses the C preprocessor and would + * only see one instance of "__x86_indirect_thunk_\reg" rather + * than one per register with the correct names. So we do it + * the simple and nasty way... + */ +#define __EXPORT_THUNK(sym) _ASM_NOKPROBE(sym); EXPORT_SYMBOL(sym) +#define EXPORT_THUNK(reg) __EXPORT_THUNK(__x86_indirect_thunk_ ## reg) +#define GENERATE_THUNK(reg) THUNK reg ; EXPORT_THUNK(reg) + +GENERATE_THUNK(_ASM_AX) +GENERATE_THUNK(_ASM_BX) +GENERATE_THUNK(_ASM_CX) +GENERATE_THUNK(_ASM_DX) +GENERATE_THUNK(_ASM_SI) +GENERATE_THUNK(_ASM_DI) +GENERATE_THUNK(_ASM_BP) +GENERATE_THUNK(_ASM_SP) +#ifdef CONFIG_64BIT +GENERATE_THUNK(r8) +GENERATE_THUNK(r9) +GENERATE_THUNK(r10) +GENERATE_THUNK(r11) +GENERATE_THUNK(r12) +GENERATE_THUNK(r13) +GENERATE_THUNK(r14) +GENERATE_THUNK(r15) +#endif diff --git a/arch/x86/mm/fault.c b/arch/x86/mm/fault.c index 06fe3d51d385..b3e40773dce0 100644 --- a/arch/x86/mm/fault.c +++ b/arch/x86/mm/fault.c @@ -172,14 +172,15 @@ is_prefetch(struct pt_regs *regs, unsigned long error_code, unsigned long addr) * 6. T1 : reaches here, sees vma_pkey(vma)=5, when we really * faulted on a pte with its pkey=4. */ -static void fill_sig_info_pkey(int si_code, siginfo_t *info, u32 *pkey) +static void fill_sig_info_pkey(int si_signo, int si_code, siginfo_t *info, + u32 *pkey) { /* This is effectively an #ifdef */ if (!boot_cpu_has(X86_FEATURE_OSPKE)) return; /* Fault not from Protection Keys: nothing to do */ - if (si_code != SEGV_PKUERR) + if ((si_code != SEGV_PKUERR) || (si_signo != SIGSEGV)) return; /* * force_sig_info_fault() is called from a number of @@ -218,7 +219,7 @@ force_sig_info_fault(int si_signo, int si_code, unsigned long address, lsb = PAGE_SHIFT; info.si_addr_lsb = lsb; - fill_sig_info_pkey(si_code, &info, pkey); + fill_sig_info_pkey(si_signo, si_code, &info, pkey); force_sig_info(si_signo, &info, tsk); } diff --git a/arch/x86/mm/kasan_init_64.c b/arch/x86/mm/kasan_init_64.c index 47388f0c0e59..af6f2f9c6a26 100644 --- a/arch/x86/mm/kasan_init_64.c +++ b/arch/x86/mm/kasan_init_64.c @@ -21,10 +21,14 @@ extern struct range pfn_mapped[E820_MAX_ENTRIES]; static p4d_t tmp_p4d_table[PTRS_PER_P4D] __initdata __aligned(PAGE_SIZE); -static __init void *early_alloc(size_t size, int nid) +static __init void *early_alloc(size_t size, int nid, bool panic) { - return memblock_virt_alloc_try_nid_nopanic(size, size, - __pa(MAX_DMA_ADDRESS), BOOTMEM_ALLOC_ACCESSIBLE, nid); + if (panic) + return memblock_virt_alloc_try_nid(size, size, + __pa(MAX_DMA_ADDRESS), BOOTMEM_ALLOC_ACCESSIBLE, nid); + else + return memblock_virt_alloc_try_nid_nopanic(size, size, + __pa(MAX_DMA_ADDRESS), BOOTMEM_ALLOC_ACCESSIBLE, nid); } static void __init kasan_populate_pmd(pmd_t *pmd, unsigned long addr, @@ -38,14 +42,14 @@ static void __init kasan_populate_pmd(pmd_t *pmd, unsigned long addr, if (boot_cpu_has(X86_FEATURE_PSE) && ((end - addr) == PMD_SIZE) && IS_ALIGNED(addr, PMD_SIZE)) { - p = early_alloc(PMD_SIZE, nid); + p = early_alloc(PMD_SIZE, nid, false); if (p && pmd_set_huge(pmd, __pa(p), PAGE_KERNEL)) return; else if (p) memblock_free(__pa(p), PMD_SIZE); } - p = early_alloc(PAGE_SIZE, nid); + p = early_alloc(PAGE_SIZE, nid, true); pmd_populate_kernel(&init_mm, pmd, p); } @@ -57,7 +61,7 @@ static void __init kasan_populate_pmd(pmd_t *pmd, unsigned long addr, if (!pte_none(*pte)) continue; - p = early_alloc(PAGE_SIZE, nid); + p = early_alloc(PAGE_SIZE, nid, true); entry = pfn_pte(PFN_DOWN(__pa(p)), PAGE_KERNEL); set_pte_at(&init_mm, addr, pte, entry); } while (pte++, addr += PAGE_SIZE, addr != end); @@ -75,14 +79,14 @@ static void __init kasan_populate_pud(pud_t *pud, unsigned long addr, if (boot_cpu_has(X86_FEATURE_GBPAGES) && ((end - addr) == PUD_SIZE) && IS_ALIGNED(addr, PUD_SIZE)) { - p = early_alloc(PUD_SIZE, nid); + p = early_alloc(PUD_SIZE, nid, false); if (p && pud_set_huge(pud, __pa(p), PAGE_KERNEL)) return; else if (p) memblock_free(__pa(p), PUD_SIZE); } - p = early_alloc(PAGE_SIZE, nid); + p = early_alloc(PAGE_SIZE, nid, true); pud_populate(&init_mm, pud, p); } @@ -101,7 +105,7 @@ static void __init kasan_populate_p4d(p4d_t *p4d, unsigned long addr, unsigned long next; if (p4d_none(*p4d)) { - void *p = early_alloc(PAGE_SIZE, nid); + void *p = early_alloc(PAGE_SIZE, nid, true); p4d_populate(&init_mm, p4d, p); } @@ -122,7 +126,7 @@ static void __init kasan_populate_pgd(pgd_t *pgd, unsigned long addr, unsigned long next; if (pgd_none(*pgd)) { - p = early_alloc(PAGE_SIZE, nid); + p = early_alloc(PAGE_SIZE, nid, true); pgd_populate(&init_mm, pgd, p); } diff --git a/arch/x86/mm/mem_encrypt.c b/arch/x86/mm/mem_encrypt.c index 391b13402e40..e1d61e8500f9 100644 --- a/arch/x86/mm/mem_encrypt.c +++ b/arch/x86/mm/mem_encrypt.c @@ -464,37 +464,62 @@ void swiotlb_set_mem_attributes(void *vaddr, unsigned long size) set_memory_decrypted((unsigned long)vaddr, size >> PAGE_SHIFT); } -static void __init sme_clear_pgd(pgd_t *pgd_base, unsigned long start, - unsigned long end) +struct sme_populate_pgd_data { + void *pgtable_area; + pgd_t *pgd; + + pmdval_t pmd_flags; + pteval_t pte_flags; + unsigned long paddr; + + unsigned long vaddr; + unsigned long vaddr_end; +}; + +static void __init sme_clear_pgd(struct sme_populate_pgd_data *ppd) { unsigned long pgd_start, pgd_end, pgd_size; pgd_t *pgd_p; - pgd_start = start & PGDIR_MASK; - pgd_end = end & PGDIR_MASK; + pgd_start = ppd->vaddr & PGDIR_MASK; + pgd_end = ppd->vaddr_end & PGDIR_MASK; - pgd_size = (((pgd_end - pgd_start) / PGDIR_SIZE) + 1); - pgd_size *= sizeof(pgd_t); + pgd_size = (((pgd_end - pgd_start) / PGDIR_SIZE) + 1) * sizeof(pgd_t); - pgd_p = pgd_base + pgd_index(start); + pgd_p = ppd->pgd + pgd_index(ppd->vaddr); memset(pgd_p, 0, pgd_size); } -#define PGD_FLAGS _KERNPG_TABLE_NOENC -#define P4D_FLAGS _KERNPG_TABLE_NOENC -#define PUD_FLAGS _KERNPG_TABLE_NOENC -#define PMD_FLAGS (__PAGE_KERNEL_LARGE_EXEC & ~_PAGE_GLOBAL) +#define PGD_FLAGS _KERNPG_TABLE_NOENC +#define P4D_FLAGS _KERNPG_TABLE_NOENC +#define PUD_FLAGS _KERNPG_TABLE_NOENC +#define PMD_FLAGS _KERNPG_TABLE_NOENC + +#define PMD_FLAGS_LARGE (__PAGE_KERNEL_LARGE_EXEC & ~_PAGE_GLOBAL) + +#define PMD_FLAGS_DEC PMD_FLAGS_LARGE +#define PMD_FLAGS_DEC_WP ((PMD_FLAGS_DEC & ~_PAGE_CACHE_MASK) | \ + (_PAGE_PAT | _PAGE_PWT)) + +#define PMD_FLAGS_ENC (PMD_FLAGS_LARGE | _PAGE_ENC) + +#define PTE_FLAGS (__PAGE_KERNEL_EXEC & ~_PAGE_GLOBAL) + +#define PTE_FLAGS_DEC PTE_FLAGS +#define PTE_FLAGS_DEC_WP ((PTE_FLAGS_DEC & ~_PAGE_CACHE_MASK) | \ + (_PAGE_PAT | _PAGE_PWT)) + +#define PTE_FLAGS_ENC (PTE_FLAGS | _PAGE_ENC) -static void __init *sme_populate_pgd(pgd_t *pgd_base, void *pgtable_area, - unsigned long vaddr, pmdval_t pmd_val) +static pmd_t __init *sme_prepare_pgd(struct sme_populate_pgd_data *ppd) { pgd_t *pgd_p; p4d_t *p4d_p; pud_t *pud_p; pmd_t *pmd_p; - pgd_p = pgd_base + pgd_index(vaddr); + pgd_p = ppd->pgd + pgd_index(ppd->vaddr); if (native_pgd_val(*pgd_p)) { if (IS_ENABLED(CONFIG_X86_5LEVEL)) p4d_p = (p4d_t *)(native_pgd_val(*pgd_p) & ~PTE_FLAGS_MASK); @@ -504,15 +529,15 @@ static void __init *sme_populate_pgd(pgd_t *pgd_base, void *pgtable_area, pgd_t pgd; if (IS_ENABLED(CONFIG_X86_5LEVEL)) { - p4d_p = pgtable_area; + p4d_p = ppd->pgtable_area; memset(p4d_p, 0, sizeof(*p4d_p) * PTRS_PER_P4D); - pgtable_area += sizeof(*p4d_p) * PTRS_PER_P4D; + ppd->pgtable_area += sizeof(*p4d_p) * PTRS_PER_P4D; pgd = native_make_pgd((pgdval_t)p4d_p + PGD_FLAGS); } else { - pud_p = pgtable_area; + pud_p = ppd->pgtable_area; memset(pud_p, 0, sizeof(*pud_p) * PTRS_PER_PUD); - pgtable_area += sizeof(*pud_p) * PTRS_PER_PUD; + ppd->pgtable_area += sizeof(*pud_p) * PTRS_PER_PUD; pgd = native_make_pgd((pgdval_t)pud_p + PGD_FLAGS); } @@ -520,58 +545,160 @@ static void __init *sme_populate_pgd(pgd_t *pgd_base, void *pgtable_area, } if (IS_ENABLED(CONFIG_X86_5LEVEL)) { - p4d_p += p4d_index(vaddr); + p4d_p += p4d_index(ppd->vaddr); if (native_p4d_val(*p4d_p)) { pud_p = (pud_t *)(native_p4d_val(*p4d_p) & ~PTE_FLAGS_MASK); } else { p4d_t p4d; - pud_p = pgtable_area; + pud_p = ppd->pgtable_area; memset(pud_p, 0, sizeof(*pud_p) * PTRS_PER_PUD); - pgtable_area += sizeof(*pud_p) * PTRS_PER_PUD; + ppd->pgtable_area += sizeof(*pud_p) * PTRS_PER_PUD; p4d = native_make_p4d((pudval_t)pud_p + P4D_FLAGS); native_set_p4d(p4d_p, p4d); } } - pud_p += pud_index(vaddr); + pud_p += pud_index(ppd->vaddr); if (native_pud_val(*pud_p)) { if (native_pud_val(*pud_p) & _PAGE_PSE) - goto out; + return NULL; pmd_p = (pmd_t *)(native_pud_val(*pud_p) & ~PTE_FLAGS_MASK); } else { pud_t pud; - pmd_p = pgtable_area; + pmd_p = ppd->pgtable_area; memset(pmd_p, 0, sizeof(*pmd_p) * PTRS_PER_PMD); - pgtable_area += sizeof(*pmd_p) * PTRS_PER_PMD; + ppd->pgtable_area += sizeof(*pmd_p) * PTRS_PER_PMD; pud = native_make_pud((pmdval_t)pmd_p + PUD_FLAGS); native_set_pud(pud_p, pud); } - pmd_p += pmd_index(vaddr); + return pmd_p; +} + +static void __init sme_populate_pgd_large(struct sme_populate_pgd_data *ppd) +{ + pmd_t *pmd_p; + + pmd_p = sme_prepare_pgd(ppd); + if (!pmd_p) + return; + + pmd_p += pmd_index(ppd->vaddr); if (!native_pmd_val(*pmd_p) || !(native_pmd_val(*pmd_p) & _PAGE_PSE)) - native_set_pmd(pmd_p, native_make_pmd(pmd_val)); + native_set_pmd(pmd_p, native_make_pmd(ppd->paddr | ppd->pmd_flags)); +} -out: - return pgtable_area; +static void __init sme_populate_pgd(struct sme_populate_pgd_data *ppd) +{ + pmd_t *pmd_p; + pte_t *pte_p; + + pmd_p = sme_prepare_pgd(ppd); + if (!pmd_p) + return; + + pmd_p += pmd_index(ppd->vaddr); + if (native_pmd_val(*pmd_p)) { + if (native_pmd_val(*pmd_p) & _PAGE_PSE) + return; + + pte_p = (pte_t *)(native_pmd_val(*pmd_p) & ~PTE_FLAGS_MASK); + } else { + pmd_t pmd; + + pte_p = ppd->pgtable_area; + memset(pte_p, 0, sizeof(*pte_p) * PTRS_PER_PTE); + ppd->pgtable_area += sizeof(*pte_p) * PTRS_PER_PTE; + + pmd = native_make_pmd((pteval_t)pte_p + PMD_FLAGS); + native_set_pmd(pmd_p, pmd); + } + + pte_p += pte_index(ppd->vaddr); + if (!native_pte_val(*pte_p)) + native_set_pte(pte_p, native_make_pte(ppd->paddr | ppd->pte_flags)); +} + +static void __init __sme_map_range_pmd(struct sme_populate_pgd_data *ppd) +{ + while (ppd->vaddr < ppd->vaddr_end) { + sme_populate_pgd_large(ppd); + + ppd->vaddr += PMD_PAGE_SIZE; + ppd->paddr += PMD_PAGE_SIZE; + } +} + +static void __init __sme_map_range_pte(struct sme_populate_pgd_data *ppd) +{ + while (ppd->vaddr < ppd->vaddr_end) { + sme_populate_pgd(ppd); + + ppd->vaddr += PAGE_SIZE; + ppd->paddr += PAGE_SIZE; + } +} + +static void __init __sme_map_range(struct sme_populate_pgd_data *ppd, + pmdval_t pmd_flags, pteval_t pte_flags) +{ + unsigned long vaddr_end; + + ppd->pmd_flags = pmd_flags; + ppd->pte_flags = pte_flags; + + /* Save original end value since we modify the struct value */ + vaddr_end = ppd->vaddr_end; + + /* If start is not 2MB aligned, create PTE entries */ + ppd->vaddr_end = ALIGN(ppd->vaddr, PMD_PAGE_SIZE); + __sme_map_range_pte(ppd); + + /* Create PMD entries */ + ppd->vaddr_end = vaddr_end & PMD_PAGE_MASK; + __sme_map_range_pmd(ppd); + + /* If end is not 2MB aligned, create PTE entries */ + ppd->vaddr_end = vaddr_end; + __sme_map_range_pte(ppd); +} + +static void __init sme_map_range_encrypted(struct sme_populate_pgd_data *ppd) +{ + __sme_map_range(ppd, PMD_FLAGS_ENC, PTE_FLAGS_ENC); +} + +static void __init sme_map_range_decrypted(struct sme_populate_pgd_data *ppd) +{ + __sme_map_range(ppd, PMD_FLAGS_DEC, PTE_FLAGS_DEC); +} + +static void __init sme_map_range_decrypted_wp(struct sme_populate_pgd_data *ppd) +{ + __sme_map_range(ppd, PMD_FLAGS_DEC_WP, PTE_FLAGS_DEC_WP); } static unsigned long __init sme_pgtable_calc(unsigned long len) { - unsigned long p4d_size, pud_size, pmd_size; + unsigned long p4d_size, pud_size, pmd_size, pte_size; unsigned long total; /* * Perform a relatively simplistic calculation of the pagetable - * entries that are needed. That mappings will be covered by 2MB - * PMD entries so we can conservatively calculate the required + * entries that are needed. Those mappings will be covered mostly + * by 2MB PMD entries so we can conservatively calculate the required * number of P4D, PUD and PMD structures needed to perform the - * mappings. Incrementing the count for each covers the case where - * the addresses cross entries. + * mappings. For mappings that are not 2MB aligned, PTE mappings + * would be needed for the start and end portion of the address range + * that fall outside of the 2MB alignment. This results in, at most, + * two extra pages to hold PTE entries for each range that is mapped. + * Incrementing the count for each covers the case where the addresses + * cross entries. */ if (IS_ENABLED(CONFIG_X86_5LEVEL)) { p4d_size = (ALIGN(len, PGDIR_SIZE) / PGDIR_SIZE) + 1; @@ -585,8 +712,9 @@ static unsigned long __init sme_pgtable_calc(unsigned long len) } pmd_size = (ALIGN(len, PUD_SIZE) / PUD_SIZE) + 1; pmd_size *= sizeof(pmd_t) * PTRS_PER_PMD; + pte_size = 2 * sizeof(pte_t) * PTRS_PER_PTE; - total = p4d_size + pud_size + pmd_size; + total = p4d_size + pud_size + pmd_size + pte_size; /* * Now calculate the added pagetable structures needed to populate @@ -610,29 +738,29 @@ static unsigned long __init sme_pgtable_calc(unsigned long len) return total; } -void __init sme_encrypt_kernel(void) +void __init __nostackprotector sme_encrypt_kernel(struct boot_params *bp) { unsigned long workarea_start, workarea_end, workarea_len; unsigned long execute_start, execute_end, execute_len; unsigned long kernel_start, kernel_end, kernel_len; + unsigned long initrd_start, initrd_end, initrd_len; + struct sme_populate_pgd_data ppd; unsigned long pgtable_area_len; - unsigned long paddr, pmd_flags; unsigned long decrypted_base; - void *pgtable_area; - pgd_t *pgd; if (!sme_active()) return; /* - * Prepare for encrypting the kernel by building new pagetables with - * the necessary attributes needed to encrypt the kernel in place. + * Prepare for encrypting the kernel and initrd by building new + * pagetables with the necessary attributes needed to encrypt the + * kernel in place. * * One range of virtual addresses will map the memory occupied - * by the kernel as encrypted. + * by the kernel and initrd as encrypted. * * Another range of virtual addresses will map the memory occupied - * by the kernel as decrypted and write-protected. + * by the kernel and initrd as decrypted and write-protected. * * The use of write-protect attribute will prevent any of the * memory from being cached. @@ -643,6 +771,20 @@ void __init sme_encrypt_kernel(void) kernel_end = ALIGN(__pa_symbol(_end), PMD_PAGE_SIZE); kernel_len = kernel_end - kernel_start; + initrd_start = 0; + initrd_end = 0; + initrd_len = 0; +#ifdef CONFIG_BLK_DEV_INITRD + initrd_len = (unsigned long)bp->hdr.ramdisk_size | + ((unsigned long)bp->ext_ramdisk_size << 32); + if (initrd_len) { + initrd_start = (unsigned long)bp->hdr.ramdisk_image | + ((unsigned long)bp->ext_ramdisk_image << 32); + initrd_end = PAGE_ALIGN(initrd_start + initrd_len); + initrd_len = initrd_end - initrd_start; + } +#endif + /* Set the encryption workarea to be immediately after the kernel */ workarea_start = kernel_end; @@ -665,16 +807,21 @@ void __init sme_encrypt_kernel(void) */ pgtable_area_len = sizeof(pgd_t) * PTRS_PER_PGD; pgtable_area_len += sme_pgtable_calc(execute_end - kernel_start) * 2; + if (initrd_len) + pgtable_area_len += sme_pgtable_calc(initrd_len) * 2; /* PUDs and PMDs needed in the current pagetables for the workarea */ pgtable_area_len += sme_pgtable_calc(execute_len + pgtable_area_len); /* * The total workarea includes the executable encryption area and - * the pagetable area. + * the pagetable area. The start of the workarea is already 2MB + * aligned, align the end of the workarea on a 2MB boundary so that + * we don't try to create/allocate PTE entries from the workarea + * before it is mapped. */ workarea_len = execute_len + pgtable_area_len; - workarea_end = workarea_start + workarea_len; + workarea_end = ALIGN(workarea_start + workarea_len, PMD_PAGE_SIZE); /* * Set the address to the start of where newly created pagetable @@ -683,45 +830,30 @@ void __init sme_encrypt_kernel(void) * pagetables and when the new encrypted and decrypted kernel * mappings are populated. */ - pgtable_area = (void *)execute_end; + ppd.pgtable_area = (void *)execute_end; /* * Make sure the current pagetable structure has entries for * addressing the workarea. */ - pgd = (pgd_t *)native_read_cr3_pa(); - paddr = workarea_start; - while (paddr < workarea_end) { - pgtable_area = sme_populate_pgd(pgd, pgtable_area, - paddr, - paddr + PMD_FLAGS); - - paddr += PMD_PAGE_SIZE; - } + ppd.pgd = (pgd_t *)native_read_cr3_pa(); + ppd.paddr = workarea_start; + ppd.vaddr = workarea_start; + ppd.vaddr_end = workarea_end; + sme_map_range_decrypted(&ppd); /* Flush the TLB - no globals so cr3 is enough */ native_write_cr3(__native_read_cr3()); /* * A new pagetable structure is being built to allow for the kernel - * to be encrypted. It starts with an empty PGD that will then be - * populated with new PUDs and PMDs as the encrypted and decrypted - * kernel mappings are created. + * and initrd to be encrypted. It starts with an empty PGD that will + * then be populated with new PUDs and PMDs as the encrypted and + * decrypted kernel mappings are created. */ - pgd = pgtable_area; - memset(pgd, 0, sizeof(*pgd) * PTRS_PER_PGD); - pgtable_area += sizeof(*pgd) * PTRS_PER_PGD; - - /* Add encrypted kernel (identity) mappings */ - pmd_flags = PMD_FLAGS | _PAGE_ENC; - paddr = kernel_start; - while (paddr < kernel_end) { - pgtable_area = sme_populate_pgd(pgd, pgtable_area, - paddr, - paddr + pmd_flags); - - paddr += PMD_PAGE_SIZE; - } + ppd.pgd = ppd.pgtable_area; + memset(ppd.pgd, 0, sizeof(pgd_t) * PTRS_PER_PGD); + ppd.pgtable_area += sizeof(pgd_t) * PTRS_PER_PGD; /* * A different PGD index/entry must be used to get different @@ -730,47 +862,79 @@ void __init sme_encrypt_kernel(void) * the base of the mapping. */ decrypted_base = (pgd_index(workarea_end) + 1) & (PTRS_PER_PGD - 1); + if (initrd_len) { + unsigned long check_base; + + check_base = (pgd_index(initrd_end) + 1) & (PTRS_PER_PGD - 1); + decrypted_base = max(decrypted_base, check_base); + } decrypted_base <<= PGDIR_SHIFT; + /* Add encrypted kernel (identity) mappings */ + ppd.paddr = kernel_start; + ppd.vaddr = kernel_start; + ppd.vaddr_end = kernel_end; + sme_map_range_encrypted(&ppd); + /* Add decrypted, write-protected kernel (non-identity) mappings */ - pmd_flags = (PMD_FLAGS & ~_PAGE_CACHE_MASK) | (_PAGE_PAT | _PAGE_PWT); - paddr = kernel_start; - while (paddr < kernel_end) { - pgtable_area = sme_populate_pgd(pgd, pgtable_area, - paddr + decrypted_base, - paddr + pmd_flags); - - paddr += PMD_PAGE_SIZE; + ppd.paddr = kernel_start; + ppd.vaddr = kernel_start + decrypted_base; + ppd.vaddr_end = kernel_end + decrypted_base; + sme_map_range_decrypted_wp(&ppd); + + if (initrd_len) { + /* Add encrypted initrd (identity) mappings */ + ppd.paddr = initrd_start; + ppd.vaddr = initrd_start; + ppd.vaddr_end = initrd_end; + sme_map_range_encrypted(&ppd); + /* + * Add decrypted, write-protected initrd (non-identity) mappings + */ + ppd.paddr = initrd_start; + ppd.vaddr = initrd_start + decrypted_base; + ppd.vaddr_end = initrd_end + decrypted_base; + sme_map_range_decrypted_wp(&ppd); } /* Add decrypted workarea mappings to both kernel mappings */ - paddr = workarea_start; - while (paddr < workarea_end) { - pgtable_area = sme_populate_pgd(pgd, pgtable_area, - paddr, - paddr + PMD_FLAGS); + ppd.paddr = workarea_start; + ppd.vaddr = workarea_start; + ppd.vaddr_end = workarea_end; + sme_map_range_decrypted(&ppd); - pgtable_area = sme_populate_pgd(pgd, pgtable_area, - paddr + decrypted_base, - paddr + PMD_FLAGS); - - paddr += PMD_PAGE_SIZE; - } + ppd.paddr = workarea_start; + ppd.vaddr = workarea_start + decrypted_base; + ppd.vaddr_end = workarea_end + decrypted_base; + sme_map_range_decrypted(&ppd); /* Perform the encryption */ sme_encrypt_execute(kernel_start, kernel_start + decrypted_base, - kernel_len, workarea_start, (unsigned long)pgd); + kernel_len, workarea_start, (unsigned long)ppd.pgd); + + if (initrd_len) + sme_encrypt_execute(initrd_start, initrd_start + decrypted_base, + initrd_len, workarea_start, + (unsigned long)ppd.pgd); /* * At this point we are running encrypted. Remove the mappings for * the decrypted areas - all that is needed for this is to remove * the PGD entry/entries. */ - sme_clear_pgd(pgd, kernel_start + decrypted_base, - kernel_end + decrypted_base); + ppd.vaddr = kernel_start + decrypted_base; + ppd.vaddr_end = kernel_end + decrypted_base; + sme_clear_pgd(&ppd); + + if (initrd_len) { + ppd.vaddr = initrd_start + decrypted_base; + ppd.vaddr_end = initrd_end + decrypted_base; + sme_clear_pgd(&ppd); + } - sme_clear_pgd(pgd, workarea_start + decrypted_base, - workarea_end + decrypted_base); + ppd.vaddr = workarea_start + decrypted_base; + ppd.vaddr_end = workarea_end + decrypted_base; + sme_clear_pgd(&ppd); /* Flush the TLB - no globals so cr3 is enough */ native_write_cr3(__native_read_cr3()); diff --git a/arch/x86/mm/mem_encrypt_boot.S b/arch/x86/mm/mem_encrypt_boot.S index 730e6d541df1..01f682cf77a8 100644 --- a/arch/x86/mm/mem_encrypt_boot.S +++ b/arch/x86/mm/mem_encrypt_boot.S @@ -22,9 +22,9 @@ ENTRY(sme_encrypt_execute) /* * Entry parameters: - * RDI - virtual address for the encrypted kernel mapping - * RSI - virtual address for the decrypted kernel mapping - * RDX - length of kernel + * RDI - virtual address for the encrypted mapping + * RSI - virtual address for the decrypted mapping + * RDX - length to encrypt * RCX - virtual address of the encryption workarea, including: * - stack page (PAGE_SIZE) * - encryption routine page (PAGE_SIZE) @@ -41,9 +41,9 @@ ENTRY(sme_encrypt_execute) addq $PAGE_SIZE, %rax /* Workarea encryption routine */ push %r12 - movq %rdi, %r10 /* Encrypted kernel */ - movq %rsi, %r11 /* Decrypted kernel */ - movq %rdx, %r12 /* Kernel length */ + movq %rdi, %r10 /* Encrypted area */ + movq %rsi, %r11 /* Decrypted area */ + movq %rdx, %r12 /* Area length */ /* Copy encryption routine into the workarea */ movq %rax, %rdi /* Workarea encryption routine */ @@ -52,10 +52,10 @@ ENTRY(sme_encrypt_execute) rep movsb /* Setup registers for call */ - movq %r10, %rdi /* Encrypted kernel */ - movq %r11, %rsi /* Decrypted kernel */ + movq %r10, %rdi /* Encrypted area */ + movq %r11, %rsi /* Decrypted area */ movq %r8, %rdx /* Pagetables used for encryption */ - movq %r12, %rcx /* Kernel length */ + movq %r12, %rcx /* Area length */ movq %rax, %r8 /* Workarea encryption routine */ addq $PAGE_SIZE, %r8 /* Workarea intermediate copy buffer */ @@ -71,7 +71,7 @@ ENDPROC(sme_encrypt_execute) ENTRY(__enc_copy) /* - * Routine used to encrypt kernel. + * Routine used to encrypt memory in place. * This routine must be run outside of the kernel proper since * the kernel will be encrypted during the process. So this * routine is defined here and then copied to an area outside @@ -79,19 +79,19 @@ ENTRY(__enc_copy) * during execution. * * On entry the registers must be: - * RDI - virtual address for the encrypted kernel mapping - * RSI - virtual address for the decrypted kernel mapping + * RDI - virtual address for the encrypted mapping + * RSI - virtual address for the decrypted mapping * RDX - address of the pagetables to use for encryption - * RCX - length of kernel + * RCX - length of area * R8 - intermediate copy buffer * * RAX - points to this routine * - * The kernel will be encrypted by copying from the non-encrypted - * kernel space to an intermediate buffer and then copying from the - * intermediate buffer back to the encrypted kernel space. The physical - * addresses of the two kernel space mappings are the same which - * results in the kernel being encrypted "in place". + * The area will be encrypted by copying from the non-encrypted + * memory space to an intermediate buffer and then copying from the + * intermediate buffer back to the encrypted memory space. The physical + * addresses of the two mappings are the same which results in the area + * being encrypted "in place". */ /* Enable the new page tables */ mov %rdx, %cr3 @@ -103,47 +103,55 @@ ENTRY(__enc_copy) orq $X86_CR4_PGE, %rdx mov %rdx, %cr4 + push %r15 + push %r12 + + movq %rcx, %r9 /* Save area length */ + movq %rdi, %r10 /* Save encrypted area address */ + movq %rsi, %r11 /* Save decrypted area address */ + /* Set the PAT register PA5 entry to write-protect */ - push %rcx movl $MSR_IA32_CR_PAT, %ecx rdmsr - push %rdx /* Save original PAT value */ + mov %rdx, %r15 /* Save original PAT value */ andl $0xffff00ff, %edx /* Clear PA5 */ orl $0x00000500, %edx /* Set PA5 to WP */ wrmsr - pop %rdx /* RDX contains original PAT value */ - pop %rcx - - movq %rcx, %r9 /* Save kernel length */ - movq %rdi, %r10 /* Save encrypted kernel address */ - movq %rsi, %r11 /* Save decrypted kernel address */ wbinvd /* Invalidate any cache entries */ - /* Copy/encrypt 2MB at a time */ + /* Copy/encrypt up to 2MB at a time */ + movq $PMD_PAGE_SIZE, %r12 1: - movq %r11, %rsi /* Source - decrypted kernel */ + cmpq %r12, %r9 + jnb 2f + movq %r9, %r12 + +2: + movq %r11, %rsi /* Source - decrypted area */ movq %r8, %rdi /* Dest - intermediate copy buffer */ - movq $PMD_PAGE_SIZE, %rcx /* 2MB length */ + movq %r12, %rcx rep movsb movq %r8, %rsi /* Source - intermediate copy buffer */ - movq %r10, %rdi /* Dest - encrypted kernel */ - movq $PMD_PAGE_SIZE, %rcx /* 2MB length */ + movq %r10, %rdi /* Dest - encrypted area */ + movq %r12, %rcx rep movsb - addq $PMD_PAGE_SIZE, %r11 - addq $PMD_PAGE_SIZE, %r10 - subq $PMD_PAGE_SIZE, %r9 /* Kernel length decrement */ + addq %r12, %r11 + addq %r12, %r10 + subq %r12, %r9 /* Kernel length decrement */ jnz 1b /* Kernel length not zero? */ /* Restore PAT register */ - push %rdx /* Save original PAT value */ movl $MSR_IA32_CR_PAT, %ecx rdmsr - pop %rdx /* Restore original PAT value */ + mov %r15, %rdx /* Restore original PAT value */ wrmsr + pop %r12 + pop %r15 + ret .L__enc_copy_end: ENDPROC(__enc_copy) diff --git a/arch/x86/mm/pti.c b/arch/x86/mm/pti.c index 43d4a4a29037..ce38f165489b 100644 --- a/arch/x86/mm/pti.c +++ b/arch/x86/mm/pti.c @@ -149,7 +149,7 @@ pgd_t __pti_set_user_pgd(pgd_t *pgdp, pgd_t pgd) * * Returns a pointer to a P4D on success, or NULL on failure. */ -static p4d_t *pti_user_pagetable_walk_p4d(unsigned long address) +static __init p4d_t *pti_user_pagetable_walk_p4d(unsigned long address) { pgd_t *pgd = kernel_to_user_pgdp(pgd_offset_k(address)); gfp_t gfp = (GFP_KERNEL | __GFP_NOTRACK | __GFP_ZERO); @@ -164,12 +164,7 @@ static p4d_t *pti_user_pagetable_walk_p4d(unsigned long address) if (!new_p4d_page) return NULL; - if (pgd_none(*pgd)) { - set_pgd(pgd, __pgd(_KERNPG_TABLE | __pa(new_p4d_page))); - new_p4d_page = 0; - } - if (new_p4d_page) - free_page(new_p4d_page); + set_pgd(pgd, __pgd(_KERNPG_TABLE | __pa(new_p4d_page))); } BUILD_BUG_ON(pgd_large(*pgd) != 0); @@ -182,7 +177,7 @@ static p4d_t *pti_user_pagetable_walk_p4d(unsigned long address) * * Returns a pointer to a PMD on success, or NULL on failure. */ -static pmd_t *pti_user_pagetable_walk_pmd(unsigned long address) +static __init pmd_t *pti_user_pagetable_walk_pmd(unsigned long address) { gfp_t gfp = (GFP_KERNEL | __GFP_NOTRACK | __GFP_ZERO); p4d_t *p4d = pti_user_pagetable_walk_p4d(address); @@ -194,12 +189,7 @@ static pmd_t *pti_user_pagetable_walk_pmd(unsigned long address) if (!new_pud_page) return NULL; - if (p4d_none(*p4d)) { - set_p4d(p4d, __p4d(_KERNPG_TABLE | __pa(new_pud_page))); - new_pud_page = 0; - } - if (new_pud_page) - free_page(new_pud_page); + set_p4d(p4d, __p4d(_KERNPG_TABLE | __pa(new_pud_page))); } pud = pud_offset(p4d, address); @@ -213,12 +203,7 @@ static pmd_t *pti_user_pagetable_walk_pmd(unsigned long address) if (!new_pmd_page) return NULL; - if (pud_none(*pud)) { - set_pud(pud, __pud(_KERNPG_TABLE | __pa(new_pmd_page))); - new_pmd_page = 0; - } - if (new_pmd_page) - free_page(new_pmd_page); + set_pud(pud, __pud(_KERNPG_TABLE | __pa(new_pmd_page))); } return pmd_offset(pud, address); @@ -251,12 +236,7 @@ static __init pte_t *pti_user_pagetable_walk_pte(unsigned long address) if (!new_pte_page) return NULL; - if (pmd_none(*pmd)) { - set_pmd(pmd, __pmd(_KERNPG_TABLE | __pa(new_pte_page))); - new_pte_page = 0; - } - if (new_pte_page) - free_page(new_pte_page); + set_pmd(pmd, __pmd(_KERNPG_TABLE | __pa(new_pte_page))); } pte = pte_offset_kernel(pmd, address); diff --git a/arch/x86/pci/common.c b/arch/x86/pci/common.c index 7a5350d08cef..563049c483a1 100644 --- a/arch/x86/pci/common.c +++ b/arch/x86/pci/common.c @@ -594,6 +594,11 @@ char *__init pcibios_setup(char *str) } else if (!strcmp(str, "nocrs")) { pci_probe |= PCI_ROOT_NO_CRS; return NULL; +#ifdef CONFIG_PHYS_ADDR_T_64BIT + } else if (!strcmp(str, "big_root_window")) { + pci_probe |= PCI_BIG_ROOT_WINDOW; + return NULL; +#endif } else if (!strcmp(str, "earlydump")) { pci_early_dump_regs = 1; return NULL; diff --git a/arch/x86/pci/fixup.c b/arch/x86/pci/fixup.c index e663d6bf1328..54ef19e90705 100644 --- a/arch/x86/pci/fixup.c +++ b/arch/x86/pci/fixup.c @@ -662,10 +662,14 @@ DECLARE_PCI_FIXUP_EARLY(PCI_VENDOR_ID_INTEL, 0x2033, quirk_no_aersid); */ static void pci_amd_enable_64bit_bar(struct pci_dev *dev) { - unsigned i; - u32 base, limit, high; + static const char *name = "PCI Bus 0000:00"; struct resource *res, *conflict; + u32 base, limit, high; struct pci_dev *other; + unsigned i; + + if (!(pci_probe & PCI_BIG_ROOT_WINDOW)) + return; /* Check that we are the only device of that type */ other = pci_get_device(dev->vendor, dev->device, NULL); @@ -699,22 +703,30 @@ static void pci_amd_enable_64bit_bar(struct pci_dev *dev) if (!res) return; - res->name = "PCI Bus 0000:00"; + /* + * Allocate a 256GB window directly below the 0xfd00000000 hardware + * limit (see AMD Family 15h Models 30h-3Fh BKDG, sec 2.4.6). + */ + res->name = name; res->flags = IORESOURCE_PREFETCH | IORESOURCE_MEM | IORESOURCE_MEM_64 | IORESOURCE_WINDOW; - res->start = 0x100000000ull; + res->start = 0xbd00000000ull; res->end = 0xfd00000000ull - 1; - /* Just grab the free area behind system memory for this */ - while ((conflict = request_resource_conflict(&iomem_resource, res))) { - if (conflict->end >= res->end) { - kfree(res); + conflict = request_resource_conflict(&iomem_resource, res); + if (conflict) { + kfree(res); + if (conflict->name != name) return; - } - res->start = conflict->end + 1; - } - dev_info(&dev->dev, "adding root bus resource %pR\n", res); + /* We are resuming from suspend; just reenable the window */ + res = conflict; + } else { + dev_info(&dev->dev, "adding root bus resource %pR (tainting kernel)\n", + res); + add_taint(TAINT_FIRMWARE_WORKAROUND, LOCKDEP_STILL_OK); + pci_bus_add_resource(dev->bus, res, 0); + } base = ((res->start >> 8) & AMD_141b_MMIO_BASE_MMIOBASE_MASK) | AMD_141b_MMIO_BASE_RE_MASK | AMD_141b_MMIO_BASE_WE_MASK; @@ -726,13 +738,16 @@ static void pci_amd_enable_64bit_bar(struct pci_dev *dev) pci_write_config_dword(dev, AMD_141b_MMIO_HIGH(i), high); pci_write_config_dword(dev, AMD_141b_MMIO_LIMIT(i), limit); pci_write_config_dword(dev, AMD_141b_MMIO_BASE(i), base); - - pci_bus_add_resource(dev->bus, res, 0); } DECLARE_PCI_FIXUP_FINAL(PCI_VENDOR_ID_AMD, 0x1401, pci_amd_enable_64bit_bar); DECLARE_PCI_FIXUP_FINAL(PCI_VENDOR_ID_AMD, 0x141b, pci_amd_enable_64bit_bar); DECLARE_PCI_FIXUP_FINAL(PCI_VENDOR_ID_AMD, 0x1571, pci_amd_enable_64bit_bar); DECLARE_PCI_FIXUP_FINAL(PCI_VENDOR_ID_AMD, 0x15b1, pci_amd_enable_64bit_bar); DECLARE_PCI_FIXUP_FINAL(PCI_VENDOR_ID_AMD, 0x1601, pci_amd_enable_64bit_bar); +DECLARE_PCI_FIXUP_RESUME(PCI_VENDOR_ID_AMD, 0x1401, pci_amd_enable_64bit_bar); +DECLARE_PCI_FIXUP_RESUME(PCI_VENDOR_ID_AMD, 0x141b, pci_amd_enable_64bit_bar); +DECLARE_PCI_FIXUP_RESUME(PCI_VENDOR_ID_AMD, 0x1571, pci_amd_enable_64bit_bar); +DECLARE_PCI_FIXUP_RESUME(PCI_VENDOR_ID_AMD, 0x15b1, pci_amd_enable_64bit_bar); +DECLARE_PCI_FIXUP_RESUME(PCI_VENDOR_ID_AMD, 0x1601, pci_amd_enable_64bit_bar); #endif diff --git a/arch/x86/platform/efi/efi_64.c b/arch/x86/platform/efi/efi_64.c index d87ac96e37ed..2dd15e967c3f 100644 --- a/arch/x86/platform/efi/efi_64.c +++ b/arch/x86/platform/efi/efi_64.c @@ -135,7 +135,9 @@ pgd_t * __init efi_call_phys_prolog(void) pud[j] = *pud_offset(p4d_k, vaddr); } } + pgd_offset_k(pgd * PGDIR_SIZE)->pgd &= ~_PAGE_NX; } + out: __flush_tlb_all(); diff --git a/arch/x86/platform/intel-mid/device_libs/platform_bt.c b/arch/x86/platform/intel-mid/device_libs/platform_bt.c index dc036e511f48..5a0483e7bf66 100644 --- a/arch/x86/platform/intel-mid/device_libs/platform_bt.c +++ b/arch/x86/platform/intel-mid/device_libs/platform_bt.c @@ -60,7 +60,7 @@ static int __init tng_bt_sfi_setup(struct bt_sfi_data *ddata) return 0; } -static const struct bt_sfi_data tng_bt_sfi_data __initdata = { +static struct bt_sfi_data tng_bt_sfi_data __initdata = { .setup = tng_bt_sfi_setup, }; diff --git a/arch/x86/xen/mmu_pv.c b/arch/x86/xen/mmu_pv.c index 4d62c071b166..d85076223a69 100644 --- a/arch/x86/xen/mmu_pv.c +++ b/arch/x86/xen/mmu_pv.c @@ -1325,20 +1325,18 @@ static void xen_flush_tlb_others(const struct cpumask *cpus, { struct { struct mmuext_op op; -#ifdef CONFIG_SMP - DECLARE_BITMAP(mask, num_processors); -#else DECLARE_BITMAP(mask, NR_CPUS); -#endif } *args; struct multicall_space mcs; + const size_t mc_entry_size = sizeof(args->op) + + sizeof(args->mask[0]) * BITS_TO_LONGS(num_possible_cpus()); trace_xen_mmu_flush_tlb_others(cpus, info->mm, info->start, info->end); if (cpumask_empty(cpus)) return; /* nothing to do */ - mcs = xen_mc_entry(sizeof(*args)); + mcs = xen_mc_entry(mc_entry_size); args = mcs.args; args->op.arg2.vcpumask = to_cpumask(args->mask); diff --git a/arch/x86/xen/xen-ops.h b/arch/x86/xen/xen-ops.h index 75011b80660f..3b34745d0a52 100644 --- a/arch/x86/xen/xen-ops.h +++ b/arch/x86/xen/xen-ops.h @@ -72,7 +72,7 @@ u64 xen_clocksource_read(void); void xen_setup_cpu_clockevents(void); void xen_save_time_memory_area(void); void xen_restore_time_memory_area(void); -void __init xen_init_time_ops(void); +void __ref xen_init_time_ops(void); void __init xen_hvm_init_time_ops(void); irqreturn_t xen_debug_interrupt(int irq, void *dev_id); |