diff --git a/Documentation/ABI/testing/sysfs-devices-system-cpu b/Documentation/ABI/testing/sysfs-devices-system-cpu index d6d862db3b5d..bfd29bc8d37a 100644 --- a/Documentation/ABI/testing/sysfs-devices-system-cpu +++ b/Documentation/ABI/testing/sysfs-devices-system-cpu @@ -375,3 +375,19 @@ Contact: Linux kernel mailing list Description: information about CPUs heterogeneity. cpu_capacity: capacity of cpu#. + +What: /sys/devices/system/cpu/vulnerabilities + /sys/devices/system/cpu/vulnerabilities/meltdown + /sys/devices/system/cpu/vulnerabilities/spectre_v1 + /sys/devices/system/cpu/vulnerabilities/spectre_v2 +Date: January 2018 +Contact: Linux kernel mailing list +Description: Information about CPU vulnerabilities + + The files are named after the code names of CPU + vulnerabilities. The output of those files reflects the + state of the CPUs in the system. Possible output values: + + "Not affected" CPU is not affected by the vulnerability + "Vulnerable" CPU is affected and no mitigation in effect + "Mitigation: $M" CPU is affected and mitigation $M is in effect diff --git a/Documentation/admin-guide/kernel-parameters.txt b/Documentation/admin-guide/kernel-parameters.txt index faccc582c0f9..46b26bfee27b 100644 --- a/Documentation/admin-guide/kernel-parameters.txt +++ b/Documentation/admin-guide/kernel-parameters.txt @@ -2623,6 +2623,11 @@ nosmt [KNL,S390] Disable symmetric multithreading (SMT). Equivalent to smt=1. + nospectre_v2 [X86] Disable all mitigations for the Spectre variant 2 + (indirect branch prediction) vulnerability. System may + allow data leaks with this option, which is equivalent + to spectre_v2=off. + noxsave [BUGS=X86] Disables x86 extended register state save and restore using xsave. The kernel will fallback to enabling legacy floating-point and sse state. @@ -2709,8 +2714,6 @@ steal time is computed, but won't influence scheduler behaviour - nopti [X86-64] Disable kernel page table isolation - nolapic [X86-32,APIC] Do not enable or use the local APIC. nolapic_timer [X86-32,APIC] Do not use the local APIC timer. @@ -3291,11 +3294,20 @@ pt. [PARIDE] See Documentation/blockdev/paride.txt. - pti= [X86_64] - Control user/kernel address space isolation: - on - enable - off - disable - auto - default setting + pti= [X86_64] Control Page Table Isolation of user and + kernel address spaces. Disabling this feature + removes hardening, but improves performance of + system calls and interrupts. + + on - unconditionally enable + off - unconditionally disable + auto - kernel detects whether your CPU model is + vulnerable to issues that PTI mitigates + + Not specifying this option is equivalent to pti=auto. + + nopti [X86_64] + Equivalent to pti=off pty.legacy_count= [KNL] Number of legacy pty's. Overwrites compiled-in @@ -3946,6 +3958,29 @@ sonypi.*= [HW] Sony Programmable I/O Control Device driver See Documentation/laptops/sonypi.txt + spectre_v2= [X86] Control mitigation of Spectre variant 2 + (indirect branch speculation) vulnerability. + + on - unconditionally enable + off - unconditionally disable + auto - kernel detects whether your CPU model is + vulnerable + + Selecting 'on' will, and 'auto' may, choose a + mitigation method at run time according to the + CPU, the available microcode, the setting of the + CONFIG_RETPOLINE configuration option, and the + compiler with which the kernel was built. + + Specific mitigations can also be selected manually: + + retpoline - replace indirect branches + retpoline,generic - google's original retpoline + retpoline,amd - AMD-specific minimal thunk + + Not specifying this option is equivalent to + spectre_v2=auto. + spia_io_base= [HW,MTD] spia_fio_base= spia_pedr= diff --git a/Documentation/x86/pti.txt b/Documentation/x86/pti.txt new file mode 100644 index 000000000000..d11eff61fc9a --- /dev/null +++ b/Documentation/x86/pti.txt @@ -0,0 +1,186 @@ +Overview +======== + +Page Table Isolation (pti, previously known as KAISER[1]) is a +countermeasure against attacks on the shared user/kernel address +space such as the "Meltdown" approach[2]. + +To mitigate this class of attacks, we create an independent set of +page tables for use only when running userspace applications. When +the kernel is entered via syscalls, interrupts or exceptions, the +page tables are switched to the full "kernel" copy. When the system +switches back to user mode, the user copy is used again. + +The userspace page tables contain only a minimal amount of kernel +data: only what is needed to enter/exit the kernel such as the +entry/exit functions themselves and the interrupt descriptor table +(IDT). There are a few strictly unnecessary things that get mapped +such as the first C function when entering an interrupt (see +comments in pti.c). + +This approach helps to ensure that side-channel attacks leveraging +the paging structures do not function when PTI is enabled. It can be +enabled by setting CONFIG_PAGE_TABLE_ISOLATION=y at compile time. +Once enabled at compile-time, it can be disabled at boot with the +'nopti' or 'pti=' kernel parameters (see kernel-parameters.txt). + +Page Table Management +===================== + +When PTI is enabled, the kernel manages two sets of page tables. +The first set is very similar to the single set which is present in +kernels without PTI. This includes a complete mapping of userspace +that the kernel can use for things like copy_to_user(). + +Although _complete_, the user portion of the kernel page tables is +crippled by setting the NX bit in the top level. This ensures +that any missed kernel->user CR3 switch will immediately crash +userspace upon executing its first instruction. + +The userspace page tables map only the kernel data needed to enter +and exit the kernel. This data is entirely contained in the 'struct +cpu_entry_area' structure which is placed in the fixmap which gives +each CPU's copy of the area a compile-time-fixed virtual address. + +For new userspace mappings, the kernel makes the entries in its +page tables like normal. The only difference is when the kernel +makes entries in the top (PGD) level. In addition to setting the +entry in the main kernel PGD, a copy of the entry is made in the +userspace page tables' PGD. + +This sharing at the PGD level also inherently shares all the lower +layers of the page tables. This leaves a single, shared set of +userspace page tables to manage. One PTE to lock, one set of +accessed bits, dirty bits, etc... + +Overhead +======== + +Protection against side-channel attacks is important. But, +this protection comes at a cost: + +1. Increased Memory Use + a. Each process now needs an order-1 PGD instead of order-0. + (Consumes an additional 4k per process). + b. The 'cpu_entry_area' structure must be 2MB in size and 2MB + aligned so that it can be mapped by setting a single PMD + entry. This consumes nearly 2MB of RAM once the kernel + is decompressed, but no space in the kernel image itself. + +2. Runtime Cost + a. CR3 manipulation to switch between the page table copies + must be done at interrupt, syscall, and exception entry + and exit (it can be skipped when the kernel is interrupted, + though.) Moves to CR3 are on the order of a hundred + cycles, and are required at every entry and exit. + b. A "trampoline" must be used for SYSCALL entry. This + trampoline depends on a smaller set of resources than the + non-PTI SYSCALL entry code, so requires mapping fewer + things into the userspace page tables. The downside is + that stacks must be switched at entry time. + d. Global pages are disabled for all kernel structures not + mapped into both kernel and userspace page tables. This + feature of the MMU allows different processes to share TLB + entries mapping the kernel. Losing the feature means more + TLB misses after a context switch. The actual loss of + performance is very small, however, never exceeding 1%. + d. Process Context IDentifiers (PCID) is a CPU feature that + allows us to skip flushing the entire TLB when switching page + tables by setting a special bit in CR3 when the page tables + are changed. This makes switching the page tables (at context + switch, or kernel entry/exit) cheaper. But, on systems with + PCID support, the context switch code must flush both the user + and kernel entries out of the TLB. The user PCID TLB flush is + deferred until the exit to userspace, minimizing the cost. + See intel.com/sdm for the gory PCID/INVPCID details. + e. The userspace page tables must be populated for each new + process. Even without PTI, the shared kernel mappings + are created by copying top-level (PGD) entries into each + new process. But, with PTI, there are now *two* kernel + mappings: one in the kernel page tables that maps everything + and one for the entry/exit structures. At fork(), we need to + copy both. + f. In addition to the fork()-time copying, there must also + be an update to the userspace PGD any time a set_pgd() is done + on a PGD used to map userspace. This ensures that the kernel + and userspace copies always map the same userspace + memory. + g. On systems without PCID support, each CR3 write flushes + the entire TLB. That means that each syscall, interrupt + or exception flushes the TLB. + h. INVPCID is a TLB-flushing instruction which allows flushing + of TLB entries for non-current PCIDs. Some systems support + PCIDs, but do not support INVPCID. On these systems, addresses + can only be flushed from the TLB for the current PCID. When + flushing a kernel address, we need to flush all PCIDs, so a + single kernel address flush will require a TLB-flushing CR3 + write upon the next use of every PCID. + +Possible Future Work +==================== +1. We can be more careful about not actually writing to CR3 + unless its value is actually changed. +2. Allow PTI to be enabled/disabled at runtime in addition to the + boot-time switching. + +Testing +======== + +To test stability of PTI, the following test procedure is recommended, +ideally doing all of these in parallel: + +1. Set CONFIG_DEBUG_ENTRY=y +2. Run several copies of all of the tools/testing/selftests/x86/ tests + (excluding MPX and protection_keys) in a loop on multiple CPUs for + several minutes. These tests frequently uncover corner cases in the + kernel entry code. In general, old kernels might cause these tests + themselves to crash, but they should never crash the kernel. +3. Run the 'perf' tool in a mode (top or record) that generates many + frequent performance monitoring non-maskable interrupts (see "NMI" + in /proc/interrupts). This exercises the NMI entry/exit code which + is known to trigger bugs in code paths that did not expect to be + interrupted, including nested NMIs. Using "-c" boosts the rate of + NMIs, and using two -c with separate counters encourages nested NMIs + and less deterministic behavior. + + while true; do perf record -c 10000 -e instructions,cycles -a sleep 10; done + +4. Launch a KVM virtual machine. +5. Run 32-bit binaries on systems supporting the SYSCALL instruction. + This has been a lightly-tested code path and needs extra scrutiny. + +Debugging +========= + +Bugs in PTI cause a few different signatures of crashes +that are worth noting here. + + * Failures of the selftests/x86 code. Usually a bug in one of the + more obscure corners of entry_64.S + * Crashes in early boot, especially around CPU bringup. Bugs + in the trampoline code or mappings cause these. + * Crashes at the first interrupt. Caused by bugs in entry_64.S, + like screwing up a page table switch. Also caused by + incorrectly mapping the IRQ handler entry code. + * Crashes at the first NMI. The NMI code is separate from main + interrupt handlers and can have bugs that do not affect + normal interrupts. Also caused by incorrectly mapping NMI + code. NMIs that interrupt the entry code must be very + careful and can be the cause of crashes that show up when + running perf. + * Kernel crashes at the first exit to userspace. entry_64.S + bugs, or failing to map some of the exit code. + * Crashes at first interrupt that interrupts userspace. The paths + in entry_64.S that return to userspace are sometimes separate + from the ones that return to the kernel. + * Double faults: overflowing the kernel stack because of page + faults upon page faults. Caused by touching non-pti-mapped + data in the entry code, or forgetting to switch to kernel + CR3 before calling into C functions which are not pti-mapped. + * Userspace segfaults early in boot, sometimes manifesting + as mount(8) failing to mount the rootfs. These have + tended to be TLB invalidation issues. Usually invalidating + the wrong PCID, or otherwise missing an invalidation. + +1. https://gruss.cc/files/kaiser.pdf +2. https://meltdownattack.com/meltdown.pdf diff --git a/arch/x86/Kconfig b/arch/x86/Kconfig index ff4e9cd99854..20da391b5f32 100644 --- a/arch/x86/Kconfig +++ b/arch/x86/Kconfig @@ -88,6 +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 @@ -428,6 +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..e98f8e2e3708 100644 --- a/arch/x86/Makefile +++ b/arch/x86/Makefile @@ -230,6 +230,16 @@ 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 + else + $(warning CONFIG_RETPOLINE=y, but not supported by the compiler. Toolchain update recommended.) + 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 #include #include +#include /* * 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 #include +#include #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 #include +#include #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 #include +#include ## 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< #include #include +#include .section .entry.text, "ax" @@ -290,7 +291,7 @@ 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 +920,7 @@ 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..4f8e1d35a97c 100644 --- a/arch/x86/entry/entry_64.S +++ b/arch/x86/entry/entry_64.S @@ -37,6 +37,7 @@ #include #include #include +#include #include #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 @@ -521,7 +527,7 @@ 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() 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/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 #include #include +#include #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..f275447862f4 100644 --- a/arch/x86/include/asm/cpufeatures.h +++ b/arch/x86/include/asm/cpufeatures.h @@ -203,6 +203,8 @@ #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 */ @@ -342,5 +344,7 @@ #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/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 #include #include +#include /* * 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..402a11c803c3 --- /dev/null +++ b/arch/x86/include/asm/nospec-branch.h @@ -0,0 +1,214 @@ +/* SPDX-License-Identifier: GPL-2.0 */ + +#ifndef __NOSPEC_BRANCH_H__ +#define __NOSPEC_BRANCH_H__ + +#include +#include +#include + +/* + * Fill the CPU return stack buffer. + * + * Each entry in the RSB, if used for a speculative 'ret', contains an + * infinite 'pause; 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 ") 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; \ + jmp 773b; \ +772: \ + call 774f; \ +775: /* speculation trap */ \ + pause; \ + 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 + 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" \ + " 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, +}; + +/* + * 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 = RSB_CLEAR_LOOPS / 2; + + 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 + : "r" (loops) : "memory" ); +#endif +} +#endif /* __ASSEMBLY__ */ +#endif /* __NOSPEC_BRANCH_H__ */ 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/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 #include #include +#include #include #include @@ -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/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 @@ recompute_jump(struct alt_instr *a, u8 *orig_insn, u8 *repl_insn, u8 *insnbuf) 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/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..e4dc26185aa7 100644 --- a/arch/x86/kernel/cpu/bugs.c +++ b/arch/x86/kernel/cpu/bugs.c @@ -10,6 +10,10 @@ */ #include #include +#include + +#include +#include #include #include #include @@ -20,6 +24,8 @@ #include #include +static void __init spectre_v2_select_mitigation(void); + void __init check_bugs(void) { identify_boot_cpu(); @@ -29,6 +35,9 @@ 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 +69,179 @@ 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; +} + +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]); +} + +#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/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 #include #include +#include #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..7cb8ba08beb9 100644 --- a/arch/x86/kernel/ftrace_64.S +++ b/arch/x86/kernel/ftrace_64.S @@ -7,7 +7,7 @@ #include #include #include - +#include .code64 .section .entry.text, "ax" @@ -286,8 +286,8 @@ 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 @@ -329,5 +329,5 @@ GLOBAL(return_to_handler) movq 8(%rsp), %rdx movq (%rsp), %rax addq $24, %rsp - jmp *%rdi + JMP_NOSPEC %rdi #endif 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 #include +#include #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/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/kvm/svm.c b/arch/x86/kvm/svm.c index 3158dac87f82..f40d0da1f1d3 100644 --- a/arch/x86/kvm/svm.c +++ b/arch/x86/kvm/svm.c @@ -45,6 +45,7 @@ #include #include #include +#include #include #include "trace.h" @@ -5027,6 +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 3f89f6783aa5..c829d89e2e63 100644 --- a/arch/x86/kvm/vmx.c +++ b/arch/x86/kvm/vmx.c @@ -50,6 +50,7 @@ #include #include #include +#include #include "trace.h" #include "pmu.h" @@ -9490,6 +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/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 #include #include - +#include + /* * 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..cb45c6cb465f --- /dev/null +++ b/arch/x86/lib/retpoline.S @@ -0,0 +1,48 @@ +/* SPDX-License-Identifier: GPL-2.0 */ + +#include +#include +#include +#include +#include +#include +#include + +.macro THUNK reg + .section .text.__x86.indirect_thunk.\reg + +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(reg) EXPORT_SYMBOL(__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/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/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/drivers/base/Kconfig b/drivers/base/Kconfig index bdc87907d6a1..2415ad9f6dd4 100644 --- a/drivers/base/Kconfig +++ b/drivers/base/Kconfig @@ -236,6 +236,9 @@ config GENERIC_CPU_DEVICES config GENERIC_CPU_AUTOPROBE bool +config GENERIC_CPU_VULNERABILITIES + bool + config SOC_BUS bool select GLOB diff --git a/drivers/base/cpu.c b/drivers/base/cpu.c index 58a9b608d821..d99038487a0d 100644 --- a/drivers/base/cpu.c +++ b/drivers/base/cpu.c @@ -511,10 +511,58 @@ static void __init cpu_dev_register_generic(void) #endif } +#ifdef CONFIG_GENERIC_CPU_VULNERABILITIES + +ssize_t __weak cpu_show_meltdown(struct device *dev, + struct device_attribute *attr, char *buf) +{ + return sprintf(buf, "Not affected\n"); +} + +ssize_t __weak cpu_show_spectre_v1(struct device *dev, + struct device_attribute *attr, char *buf) +{ + return sprintf(buf, "Not affected\n"); +} + +ssize_t __weak cpu_show_spectre_v2(struct device *dev, + struct device_attribute *attr, char *buf) +{ + return sprintf(buf, "Not affected\n"); +} + +static DEVICE_ATTR(meltdown, 0444, cpu_show_meltdown, NULL); +static DEVICE_ATTR(spectre_v1, 0444, cpu_show_spectre_v1, NULL); +static DEVICE_ATTR(spectre_v2, 0444, cpu_show_spectre_v2, NULL); + +static struct attribute *cpu_root_vulnerabilities_attrs[] = { + &dev_attr_meltdown.attr, + &dev_attr_spectre_v1.attr, + &dev_attr_spectre_v2.attr, + NULL +}; + +static const struct attribute_group cpu_root_vulnerabilities_group = { + .name = "vulnerabilities", + .attrs = cpu_root_vulnerabilities_attrs, +}; + +static void __init cpu_register_vulnerabilities(void) +{ + if (sysfs_create_group(&cpu_subsys.dev_root->kobj, + &cpu_root_vulnerabilities_group)) + pr_err("Unable to register CPU vulnerabilities\n"); +} + +#else +static inline void cpu_register_vulnerabilities(void) { } +#endif + void __init cpu_dev_init(void) { if (subsys_system_register(&cpu_subsys, cpu_root_attr_groups)) panic("Failed to register CPU subsystem"); cpu_dev_register_generic(); + cpu_register_vulnerabilities(); } diff --git a/include/linux/cpu.h b/include/linux/cpu.h index a04ef7c15c6a..7b01bc11c692 100644 --- a/include/linux/cpu.h +++ b/include/linux/cpu.h @@ -47,6 +47,13 @@ extern void cpu_remove_dev_attr(struct device_attribute *attr); extern int cpu_add_dev_attr_group(struct attribute_group *attrs); extern void cpu_remove_dev_attr_group(struct attribute_group *attrs); +extern ssize_t cpu_show_meltdown(struct device *dev, + struct device_attribute *attr, char *buf); +extern ssize_t cpu_show_spectre_v1(struct device *dev, + struct device_attribute *attr, char *buf); +extern ssize_t cpu_show_spectre_v2(struct device *dev, + struct device_attribute *attr, char *buf); + extern __printf(4, 5) struct device *cpu_device_create(struct device *parent, void *drvdata, const struct attribute_group **groups, diff --git a/security/Kconfig b/security/Kconfig index 3d4debd0257e..b0cb9a5f9448 100644 --- a/security/Kconfig +++ b/security/Kconfig @@ -63,7 +63,7 @@ config PAGE_TABLE_ISOLATION ensuring that the majority of kernel addresses are not mapped into userspace. - See Documentation/x86/pagetable-isolation.txt for more details. + See Documentation/x86/pti.txt for more details. config SECURITY_INFINIBAND bool "Infiniband Security Hooks" diff --git a/tools/objtool/check.c b/tools/objtool/check.c index 9b341584eb1b..f40d46e24bcc 100644 --- a/tools/objtool/check.c +++ b/tools/objtool/check.c @@ -427,6 +427,40 @@ static void add_ignores(struct objtool_file *file) } } +/* + * FIXME: For now, just ignore any alternatives which add retpolines. This is + * a temporary hack, as it doesn't allow ORC to unwind from inside a retpoline. + * But it at least allows objtool to understand the control flow *around* the + * retpoline. + */ +static int add_nospec_ignores(struct objtool_file *file) +{ + struct section *sec; + struct rela *rela; + struct instruction *insn; + + sec = find_section_by_name(file->elf, ".rela.discard.nospec"); + if (!sec) + return 0; + + list_for_each_entry(rela, &sec->rela_list, list) { + if (rela->sym->type != STT_SECTION) { + WARN("unexpected relocation symbol type in %s", sec->name); + return -1; + } + + insn = find_insn(file, rela->sym->sec, rela->addend); + if (!insn) { + WARN("bad .discard.nospec entry"); + return -1; + } + + insn->ignore_alts = true; + } + + return 0; +} + /* * Find the destination instructions for all jumps. */ @@ -456,6 +490,13 @@ static int add_jump_destinations(struct objtool_file *file) } else if (rela->sym->sec->idx) { dest_sec = rela->sym->sec; dest_off = rela->sym->sym.st_value + rela->addend + 4; + } else if (strstr(rela->sym->name, "_indirect_thunk_")) { + /* + * Retpoline jumps are really dynamic jumps in + * disguise, so convert them accordingly. + */ + insn->type = INSN_JUMP_DYNAMIC; + continue; } else { /* sibling call */ insn->jump_dest = 0; @@ -502,11 +543,18 @@ static int add_call_destinations(struct objtool_file *file) dest_off = insn->offset + insn->len + insn->immediate; insn->call_dest = find_symbol_by_offset(insn->sec, dest_off); + /* + * FIXME: Thanks to retpolines, it's now considered + * normal for a function to call within itself. So + * disable this warning for now. + */ +#if 0 if (!insn->call_dest) { WARN_FUNC("can't find call dest symbol at offset 0x%lx", insn->sec, insn->offset, dest_off); return -1; } +#endif } else if (rela->sym->type == STT_SECTION) { insn->call_dest = find_symbol_by_offset(rela->sym->sec, rela->addend+4); @@ -671,12 +719,6 @@ static int add_special_section_alts(struct objtool_file *file) return ret; list_for_each_entry_safe(special_alt, tmp, &special_alts, list) { - alt = malloc(sizeof(*alt)); - if (!alt) { - WARN("malloc failed"); - ret = -1; - goto out; - } orig_insn = find_insn(file, special_alt->orig_sec, special_alt->orig_off); @@ -687,6 +729,10 @@ static int add_special_section_alts(struct objtool_file *file) goto out; } + /* Ignore retpoline alternatives. */ + if (orig_insn->ignore_alts) + continue; + new_insn = NULL; if (!special_alt->group || special_alt->new_len) { new_insn = find_insn(file, special_alt->new_sec, @@ -712,6 +758,13 @@ static int add_special_section_alts(struct objtool_file *file) goto out; } + alt = malloc(sizeof(*alt)); + if (!alt) { + WARN("malloc failed"); + ret = -1; + goto out; + } + alt->insn = new_insn; list_add_tail(&alt->list, &orig_insn->alts); @@ -1028,6 +1081,10 @@ static int decode_sections(struct objtool_file *file) add_ignores(file); + ret = add_nospec_ignores(file); + if (ret) + return ret; + ret = add_jump_destinations(file); if (ret) return ret; diff --git a/tools/objtool/check.h b/tools/objtool/check.h index 47d9ea70a83d..dbadb304a410 100644 --- a/tools/objtool/check.h +++ b/tools/objtool/check.h @@ -44,7 +44,7 @@ struct instruction { unsigned int len; unsigned char type; unsigned long immediate; - bool alt_group, visited, dead_end, ignore, hint, save, restore; + bool alt_group, visited, dead_end, ignore, hint, save, restore, ignore_alts; struct symbol *call_dest; struct instruction *jump_dest; struct list_head alts; diff --git a/tools/testing/selftests/x86/Makefile b/tools/testing/selftests/x86/Makefile index 939a337128db..5d4f10ac2af2 100644 --- a/tools/testing/selftests/x86/Makefile +++ b/tools/testing/selftests/x86/Makefile @@ -7,7 +7,7 @@ include ../lib.mk TARGETS_C_BOTHBITS := single_step_syscall sysret_ss_attrs syscall_nt ptrace_syscall test_mremap_vdso \ check_initial_reg_state sigreturn ldt_gdt iopl mpx-mini-test ioperm \ - protection_keys test_vdso + protection_keys test_vdso test_vsyscall TARGETS_C_32BIT_ONLY := entry_from_vm86 syscall_arg_fault test_syscall_vdso unwind_vdso \ test_FCMOV test_FCOMI test_FISTTP \ vdso_restorer diff --git a/tools/testing/selftests/x86/test_vsyscall.c b/tools/testing/selftests/x86/test_vsyscall.c new file mode 100644 index 000000000000..7a744fa7b786 --- /dev/null +++ b/tools/testing/selftests/x86/test_vsyscall.c @@ -0,0 +1,500 @@ +/* SPDX-License-Identifier: GPL-2.0 */ + +#define _GNU_SOURCE + +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include + +#ifdef __x86_64__ +# define VSYS(x) (x) +#else +# define VSYS(x) 0 +#endif + +#ifndef SYS_getcpu +# ifdef __x86_64__ +# define SYS_getcpu 309 +# else +# define SYS_getcpu 318 +# endif +#endif + +static void sethandler(int sig, void (*handler)(int, siginfo_t *, void *), + int flags) +{ + struct sigaction sa; + memset(&sa, 0, sizeof(sa)); + sa.sa_sigaction = handler; + sa.sa_flags = SA_SIGINFO | flags; + sigemptyset(&sa.sa_mask); + if (sigaction(sig, &sa, 0)) + err(1, "sigaction"); +} + +/* vsyscalls and vDSO */ +bool should_read_vsyscall = false; + +typedef long (*gtod_t)(struct timeval *tv, struct timezone *tz); +gtod_t vgtod = (gtod_t)VSYS(0xffffffffff600000); +gtod_t vdso_gtod; + +typedef int (*vgettime_t)(clockid_t, struct timespec *); +vgettime_t vdso_gettime; + +typedef long (*time_func_t)(time_t *t); +time_func_t vtime = (time_func_t)VSYS(0xffffffffff600400); +time_func_t vdso_time; + +typedef long (*getcpu_t)(unsigned *, unsigned *, void *); +getcpu_t vgetcpu = (getcpu_t)VSYS(0xffffffffff600800); +getcpu_t vdso_getcpu; + +static void init_vdso(void) +{ + void *vdso = dlopen("linux-vdso.so.1", RTLD_LAZY | RTLD_LOCAL | RTLD_NOLOAD); + if (!vdso) + vdso = dlopen("linux-gate.so.1", RTLD_LAZY | RTLD_LOCAL | RTLD_NOLOAD); + if (!vdso) { + printf("[WARN]\tfailed to find vDSO\n"); + return; + } + + vdso_gtod = (gtod_t)dlsym(vdso, "__vdso_gettimeofday"); + if (!vdso_gtod) + printf("[WARN]\tfailed to find gettimeofday in vDSO\n"); + + vdso_gettime = (vgettime_t)dlsym(vdso, "__vdso_clock_gettime"); + if (!vdso_gettime) + printf("[WARN]\tfailed to find clock_gettime in vDSO\n"); + + vdso_time = (time_func_t)dlsym(vdso, "__vdso_time"); + if (!vdso_time) + printf("[WARN]\tfailed to find time in vDSO\n"); + + vdso_getcpu = (getcpu_t)dlsym(vdso, "__vdso_getcpu"); + if (!vdso_getcpu) { + /* getcpu() was never wired up in the 32-bit vDSO. */ + printf("[%s]\tfailed to find getcpu in vDSO\n", + sizeof(long) == 8 ? "WARN" : "NOTE"); + } +} + +static int init_vsys(void) +{ +#ifdef __x86_64__ + int nerrs = 0; + FILE *maps; + char line[128]; + bool found = false; + + maps = fopen("/proc/self/maps", "r"); + if (!maps) { + printf("[WARN]\tCould not open /proc/self/maps -- assuming vsyscall is r-x\n"); + should_read_vsyscall = true; + return 0; + } + + while (fgets(line, sizeof(line), maps)) { + char r, x; + void *start, *end; + char name[128]; + if (sscanf(line, "%p-%p %c-%cp %*x %*x:%*x %*u %s", + &start, &end, &r, &x, name) != 5) + continue; + + if (strcmp(name, "[vsyscall]")) + continue; + + printf("\tvsyscall map: %s", line); + + if (start != (void *)0xffffffffff600000 || + end != (void *)0xffffffffff601000) { + printf("[FAIL]\taddress range is nonsense\n"); + nerrs++; + } + + printf("\tvsyscall permissions are %c-%c\n", r, x); + should_read_vsyscall = (r == 'r'); + if (x != 'x') { + vgtod = NULL; + vtime = NULL; + vgetcpu = NULL; + } + + found = true; + break; + } + + fclose(maps); + + if (!found) { + printf("\tno vsyscall map in /proc/self/maps\n"); + should_read_vsyscall = false; + vgtod = NULL; + vtime = NULL; + vgetcpu = NULL; + } + + return nerrs; +#else + return 0; +#endif +} + +/* syscalls */ +static inline long sys_gtod(struct timeval *tv, struct timezone *tz) +{ + return syscall(SYS_gettimeofday, tv, tz); +} + +static inline int sys_clock_gettime(clockid_t id, struct timespec *ts) +{ + return syscall(SYS_clock_gettime, id, ts); +} + +static inline long sys_time(time_t *t) +{ + return syscall(SYS_time, t); +} + +static inline long sys_getcpu(unsigned * cpu, unsigned * node, + void* cache) +{ + return syscall(SYS_getcpu, cpu, node, cache); +} + +static jmp_buf jmpbuf; + +static void sigsegv(int sig, siginfo_t *info, void *ctx_void) +{ + siglongjmp(jmpbuf, 1); +} + +static double tv_diff(const struct timeval *a, const struct timeval *b) +{ + return (double)(a->tv_sec - b->tv_sec) + + (double)((int)a->tv_usec - (int)b->tv_usec) * 1e-6; +} + +static int check_gtod(const struct timeval *tv_sys1, + const struct timeval *tv_sys2, + const struct timezone *tz_sys, + const char *which, + const struct timeval *tv_other, + const struct timezone *tz_other) +{ + int nerrs = 0; + double d1, d2; + + if (tz_other && (tz_sys->tz_minuteswest != tz_other->tz_minuteswest || tz_sys->tz_dsttime != tz_other->tz_dsttime)) { + printf("[FAIL] %s tz mismatch\n", which); + nerrs++; + } + + d1 = tv_diff(tv_other, tv_sys1); + d2 = tv_diff(tv_sys2, tv_other); + printf("\t%s time offsets: %lf %lf\n", which, d1, d2); + + if (d1 < 0 || d2 < 0) { + printf("[FAIL]\t%s time was inconsistent with the syscall\n", which); + nerrs++; + } else { + printf("[OK]\t%s gettimeofday()'s timeval was okay\n", which); + } + + return nerrs; +} + +static int test_gtod(void) +{ + struct timeval tv_sys1, tv_sys2, tv_vdso, tv_vsys; + struct timezone tz_sys, tz_vdso, tz_vsys; + long ret_vdso = -1; + long ret_vsys = -1; + int nerrs = 0; + + printf("[RUN]\ttest gettimeofday()\n"); + + if (sys_gtod(&tv_sys1, &tz_sys) != 0) + err(1, "syscall gettimeofday"); + if (vdso_gtod) + ret_vdso = vdso_gtod(&tv_vdso, &tz_vdso); + if (vgtod) + ret_vsys = vgtod(&tv_vsys, &tz_vsys); + if (sys_gtod(&tv_sys2, &tz_sys) != 0) + err(1, "syscall gettimeofday"); + + if (vdso_gtod) { + if (ret_vdso == 0) { + nerrs += check_gtod(&tv_sys1, &tv_sys2, &tz_sys, "vDSO", &tv_vdso, &tz_vdso); + } else { + printf("[FAIL]\tvDSO gettimeofday() failed: %ld\n", ret_vdso); + nerrs++; + } + } + + if (vgtod) { + if (ret_vsys == 0) { + nerrs += check_gtod(&tv_sys1, &tv_sys2, &tz_sys, "vsyscall", &tv_vsys, &tz_vsys); + } else { + printf("[FAIL]\tvsys gettimeofday() failed: %ld\n", ret_vsys); + nerrs++; + } + } + + return nerrs; +} + +static int test_time(void) { + int nerrs = 0; + + printf("[RUN]\ttest time()\n"); + long t_sys1, t_sys2, t_vdso = 0, t_vsys = 0; + long t2_sys1 = -1, t2_sys2 = -1, t2_vdso = -1, t2_vsys = -1; + t_sys1 = sys_time(&t2_sys1); + if (vdso_time) + t_vdso = vdso_time(&t2_vdso); + if (vtime) + t_vsys = vtime(&t2_vsys); + t_sys2 = sys_time(&t2_sys2); + if (t_sys1 < 0 || t_sys1 != t2_sys1 || t_sys2 < 0 || t_sys2 != t2_sys2) { + printf("[FAIL]\tsyscall failed (ret1:%ld output1:%ld ret2:%ld output2:%ld)\n", t_sys1, t2_sys1, t_sys2, t2_sys2); + nerrs++; + return nerrs; + } + + if (vdso_time) { + if (t_vdso < 0 || t_vdso != t2_vdso) { + printf("[FAIL]\tvDSO failed (ret:%ld output:%ld)\n", t_vdso, t2_vdso); + nerrs++; + } else if (t_vdso < t_sys1 || t_vdso > t_sys2) { + printf("[FAIL]\tvDSO returned the wrong time (%ld %ld %ld)\n", t_sys1, t_vdso, t_sys2); + nerrs++; + } else { + printf("[OK]\tvDSO time() is okay\n"); + } + } + + if (vtime) { + if (t_vsys < 0 || t_vsys != t2_vsys) { + printf("[FAIL]\tvsyscall failed (ret:%ld output:%ld)\n", t_vsys, t2_vsys); + nerrs++; + } else if (t_vsys < t_sys1 || t_vsys > t_sys2) { + printf("[FAIL]\tvsyscall returned the wrong time (%ld %ld %ld)\n", t_sys1, t_vsys, t_sys2); + nerrs++; + } else { + printf("[OK]\tvsyscall time() is okay\n"); + } + } + + return nerrs; +} + +static int test_getcpu(int cpu) +{ + int nerrs = 0; + long ret_sys, ret_vdso = -1, ret_vsys = -1; + + printf("[RUN]\tgetcpu() on CPU %d\n", cpu); + + cpu_set_t cpuset; + CPU_ZERO(&cpuset); + CPU_SET(cpu, &cpuset); + if (sched_setaffinity(0, sizeof(cpuset), &cpuset) != 0) { + printf("[SKIP]\tfailed to force CPU %d\n", cpu); + return nerrs; + } + + unsigned cpu_sys, cpu_vdso, cpu_vsys, node_sys, node_vdso, node_vsys; + unsigned node = 0; + bool have_node = false; + ret_sys = sys_getcpu(&cpu_sys, &node_sys, 0); + if (vdso_getcpu) + ret_vdso = vdso_getcpu(&cpu_vdso, &node_vdso, 0); + if (vgetcpu) + ret_vsys = vgetcpu(&cpu_vsys, &node_vsys, 0); + + if (ret_sys == 0) { + if (cpu_sys != cpu) { + printf("[FAIL]\tsyscall reported CPU %hu but should be %d\n", cpu_sys, cpu); + nerrs++; + } + + have_node = true; + node = node_sys; + } + + if (vdso_getcpu) { + if (ret_vdso) { + printf("[FAIL]\tvDSO getcpu() failed\n"); + nerrs++; + } else { + if (!have_node) { + have_node = true; + node = node_vdso; + } + + if (cpu_vdso != cpu) { + printf("[FAIL]\tvDSO reported CPU %hu but should be %d\n", cpu_vdso, cpu); + nerrs++; + } else { + printf("[OK]\tvDSO reported correct CPU\n"); + } + + if (node_vdso != node) { + printf("[FAIL]\tvDSO reported node %hu but should be %hu\n", node_vdso, node); + nerrs++; + } else { + printf("[OK]\tvDSO reported correct node\n"); + } + } + } + + if (vgetcpu) { + if (ret_vsys) { + printf("[FAIL]\tvsyscall getcpu() failed\n"); + nerrs++; + } else { + if (!have_node) { + have_node = true; + node = node_vsys; + } + + if (cpu_vsys != cpu) { + printf("[FAIL]\tvsyscall reported CPU %hu but should be %d\n", cpu_vsys, cpu); + nerrs++; + } else { + printf("[OK]\tvsyscall reported correct CPU\n"); + } + + if (node_vsys != node) { + printf("[FAIL]\tvsyscall reported node %hu but should be %hu\n", node_vsys, node); + nerrs++; + } else { + printf("[OK]\tvsyscall reported correct node\n"); + } + } + } + + return nerrs; +} + +static int test_vsys_r(void) +{ +#ifdef __x86_64__ + printf("[RUN]\tChecking read access to the vsyscall page\n"); + bool can_read; + if (sigsetjmp(jmpbuf, 1) == 0) { + *(volatile int *)0xffffffffff600000; + can_read = true; + } else { + can_read = false; + } + + if (can_read && !should_read_vsyscall) { + printf("[FAIL]\tWe have read access, but we shouldn't\n"); + return 1; + } else if (!can_read && should_read_vsyscall) { + printf("[FAIL]\tWe don't have read access, but we should\n"); + return 1; + } else { + printf("[OK]\tgot expected result\n"); + } +#endif + + return 0; +} + + +#ifdef __x86_64__ +#define X86_EFLAGS_TF (1UL << 8) +static volatile sig_atomic_t num_vsyscall_traps; + +static unsigned long get_eflags(void) +{ + unsigned long eflags; + asm volatile ("pushfq\n\tpopq %0" : "=rm" (eflags)); + return eflags; +} + +static void set_eflags(unsigned long eflags) +{ + asm volatile ("pushq %0\n\tpopfq" : : "rm" (eflags) : "flags"); +} + +static void sigtrap(int sig, siginfo_t *info, void *ctx_void) +{ + ucontext_t *ctx = (ucontext_t *)ctx_void; + unsigned long ip = ctx->uc_mcontext.gregs[REG_RIP]; + + if (((ip ^ 0xffffffffff600000UL) & ~0xfffUL) == 0) + num_vsyscall_traps++; +} + +static int test_native_vsyscall(void) +{ + time_t tmp; + bool is_native; + + if (!vtime) + return 0; + + printf("[RUN]\tchecking for native vsyscall\n"); + sethandler(SIGTRAP, sigtrap, 0); + set_eflags(get_eflags() | X86_EFLAGS_TF); + vtime(&tmp); + set_eflags(get_eflags() & ~X86_EFLAGS_TF); + + /* + * If vsyscalls are emulated, we expect a single trap in the + * vsyscall page -- the call instruction will trap with RIP + * pointing to the entry point before emulation takes over. + * In native mode, we expect two traps, since whatever code + * the vsyscall page contains will be more than just a ret + * instruction. + */ + is_native = (num_vsyscall_traps > 1); + + printf("\tvsyscalls are %s (%d instructions in vsyscall page)\n", + (is_native ? "native" : "emulated"), + (int)num_vsyscall_traps); + + return 0; +} +#endif + +int main(int argc, char **argv) +{ + int nerrs = 0; + + init_vdso(); + nerrs += init_vsys(); + + nerrs += test_gtod(); + nerrs += test_time(); + nerrs += test_getcpu(0); + nerrs += test_getcpu(1); + + sethandler(SIGSEGV, sigsegv, 0); + nerrs += test_vsys_r(); + +#ifdef __x86_64__ + nerrs += test_native_vsyscall(); +#endif + + return nerrs ? 1 : 0; +}