diff options
38 files changed, 977 insertions, 554 deletions
diff --git a/Documentation/admin-guide/kernel-parameters.txt b/Documentation/admin-guide/kernel-parameters.txt index 90cefbd..512ccaf 100644 --- a/Documentation/admin-guide/kernel-parameters.txt +++ b/Documentation/admin-guide/kernel-parameters.txt @@ -2758,8 +2758,6 @@ norandmaps Don't use address space randomization. Equivalent to echo 0 > /proc/sys/kernel/randomize_va_space - noreplace-paravirt [X86,IA-64,PV_OPS] Don't patch paravirt_ops - noreplace-smp [X86-32,SMP] Don't replace SMP instructions with UP alternatives diff --git a/Documentation/speculation.txt b/Documentation/speculation.txt new file mode 100644 index 0000000..e9e6cba --- /dev/null +++ b/Documentation/speculation.txt @@ -0,0 +1,90 @@ +This document explains potential effects of speculation, and how undesirable +effects can be mitigated portably using common APIs. + +=========== +Speculation +=========== + +To improve performance and minimize average latencies, many contemporary CPUs +employ speculative execution techniques such as branch prediction, performing +work which may be discarded at a later stage. + +Typically speculative execution cannot be observed from architectural state, +such as the contents of registers. However, in some cases it is possible to +observe its impact on microarchitectural state, such as the presence or +absence of data in caches. Such state may form side-channels which can be +observed to extract secret information. + +For example, in the presence of branch prediction, it is possible for bounds +checks to be ignored by code which is speculatively executed. Consider the +following code: + + int load_array(int *array, unsigned int index) + { + if (index >= MAX_ARRAY_ELEMS) + return 0; + else + return array[index]; + } + +Which, on arm64, may be compiled to an assembly sequence such as: + + CMP <index>, #MAX_ARRAY_ELEMS + B.LT less + MOV <returnval>, #0 + RET + less: + LDR <returnval>, [<array>, <index>] + RET + +It is possible that a CPU mis-predicts the conditional branch, and +speculatively loads array[index], even if index >= MAX_ARRAY_ELEMS. This +value will subsequently be discarded, but the speculated load may affect +microarchitectural state which can be subsequently measured. + +More complex sequences involving multiple dependent memory accesses may +result in sensitive information being leaked. Consider the following +code, building on the prior example: + + int load_dependent_arrays(int *arr1, int *arr2, int index) + { + int val1, val2, + + val1 = load_array(arr1, index); + val2 = load_array(arr2, val1); + + return val2; + } + +Under speculation, the first call to load_array() may return the value +of an out-of-bounds address, while the second call will influence +microarchitectural state dependent on this value. This may provide an +arbitrary read primitive. + +==================================== +Mitigating speculation side-channels +==================================== + +The kernel provides a generic API to ensure that bounds checks are +respected even under speculation. Architectures which are affected by +speculation-based side-channels are expected to implement these +primitives. + +The array_index_nospec() helper in <linux/nospec.h> can be used to +prevent information from being leaked via side-channels. + +A call to array_index_nospec(index, size) returns a sanitized index +value that is bounded to [0, size) even under cpu speculation +conditions. + +This can be used to protect the earlier load_array() example: + + int load_array(int *array, unsigned int index) + { + if (index >= MAX_ARRAY_ELEMS) + return 0; + else { + index = array_index_nospec(index, MAX_ARRAY_ELEMS); + return array[index]; + } + } diff --git a/arch/x86/entry/common.c b/arch/x86/entry/common.c index 1e3883e..74f6eee 100644 --- a/arch/x86/entry/common.c +++ b/arch/x86/entry/common.c @@ -21,6 +21,7 @@ #include <linux/export.h> #include <linux/context_tracking.h> #include <linux/user-return-notifier.h> +#include <linux/nospec.h> #include <linux/uprobes.h> #include <linux/livepatch.h> #include <linux/syscalls.h> @@ -206,7 +207,7 @@ __visible inline void prepare_exit_to_usermode(struct pt_regs *regs) * special case only applies after poking regs and before the * very next return to user mode. */ - current->thread.status &= ~(TS_COMPAT|TS_I386_REGS_POKED); + ti->status &= ~(TS_COMPAT|TS_I386_REGS_POKED); #endif user_enter_irqoff(); @@ -282,7 +283,8 @@ __visible void do_syscall_64(struct pt_regs *regs) * regs->orig_ax, which changes the behavior of some syscalls. */ if (likely((nr & __SYSCALL_MASK) < NR_syscalls)) { - regs->ax = sys_call_table[nr & __SYSCALL_MASK]( + nr = array_index_nospec(nr & __SYSCALL_MASK, NR_syscalls); + regs->ax = sys_call_table[nr]( regs->di, regs->si, regs->dx, regs->r10, regs->r8, regs->r9); } @@ -304,7 +306,7 @@ static __always_inline void do_syscall_32_irqs_on(struct pt_regs *regs) unsigned int nr = (unsigned int)regs->orig_ax; #ifdef CONFIG_IA32_EMULATION - current->thread.status |= TS_COMPAT; + ti->status |= TS_COMPAT; #endif if (READ_ONCE(ti->flags) & _TIF_WORK_SYSCALL_ENTRY) { @@ -318,6 +320,7 @@ static __always_inline void do_syscall_32_irqs_on(struct pt_regs *regs) } if (likely(nr < IA32_NR_syscalls)) { + nr = array_index_nospec(nr, IA32_NR_syscalls); /* * It's possible that a 32-bit syscall implementation * takes a 64-bit parameter but nonetheless assumes that diff --git a/arch/x86/entry/entry_64.S b/arch/x86/entry/entry_64.S index a835704..c752abe 100644 --- a/arch/x86/entry/entry_64.S +++ b/arch/x86/entry/entry_64.S @@ -236,91 +236,20 @@ GLOBAL(entry_SYSCALL_64_after_hwframe) pushq %r9 /* pt_regs->r9 */ pushq %r10 /* pt_regs->r10 */ pushq %r11 /* pt_regs->r11 */ - sub $(6*8), %rsp /* pt_regs->bp, bx, r12-15 not saved */ - UNWIND_HINT_REGS extra=0 - - TRACE_IRQS_OFF - - /* - * If we need to do entry work or if we guess we'll need to do - * exit work, go straight to the slow path. - */ - movq PER_CPU_VAR(current_task), %r11 - testl $_TIF_WORK_SYSCALL_ENTRY|_TIF_ALLWORK_MASK, TASK_TI_flags(%r11) - jnz entry_SYSCALL64_slow_path - -entry_SYSCALL_64_fastpath: - /* - * Easy case: enable interrupts and issue the syscall. If the syscall - * needs pt_regs, we'll call a stub that disables interrupts again - * and jumps to the slow path. - */ - TRACE_IRQS_ON - ENABLE_INTERRUPTS(CLBR_NONE) -#if __SYSCALL_MASK == ~0 - cmpq $__NR_syscall_max, %rax -#else - andl $__SYSCALL_MASK, %eax - cmpl $__NR_syscall_max, %eax -#endif - ja 1f /* return -ENOSYS (already in pt_regs->ax) */ - movq %r10, %rcx - - /* - * This call instruction is handled specially in stub_ptregs_64. - * 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) -1: + pushq %rbx /* pt_regs->rbx */ + pushq %rbp /* pt_regs->rbp */ + pushq %r12 /* pt_regs->r12 */ + pushq %r13 /* pt_regs->r13 */ + pushq %r14 /* pt_regs->r14 */ + pushq %r15 /* pt_regs->r15 */ + UNWIND_HINT_REGS - /* - * If we get here, then we know that pt_regs is clean for SYSRET64. - * If we see that no exit work is required (which we are required - * to check with IRQs off), then we can go straight to SYSRET64. - */ - DISABLE_INTERRUPTS(CLBR_ANY) TRACE_IRQS_OFF - movq PER_CPU_VAR(current_task), %r11 - testl $_TIF_ALLWORK_MASK, TASK_TI_flags(%r11) - jnz 1f - - LOCKDEP_SYS_EXIT - TRACE_IRQS_ON /* user mode is traced as IRQs on */ - movq RIP(%rsp), %rcx - movq EFLAGS(%rsp), %r11 - addq $6*8, %rsp /* skip extra regs -- they were preserved */ - UNWIND_HINT_EMPTY - jmp .Lpop_c_regs_except_rcx_r11_and_sysret -1: - /* - * The fast path looked good when we started, but something changed - * along the way and we need to switch to the slow path. Calling - * raise(3) will trigger this, for example. IRQs are off. - */ - TRACE_IRQS_ON - ENABLE_INTERRUPTS(CLBR_ANY) - SAVE_EXTRA_REGS - movq %rsp, %rdi - call syscall_return_slowpath /* returns with IRQs disabled */ - jmp return_from_SYSCALL_64 - -entry_SYSCALL64_slow_path: /* IRQs are off. */ - SAVE_EXTRA_REGS movq %rsp, %rdi call do_syscall_64 /* returns with IRQs disabled */ -return_from_SYSCALL_64: TRACE_IRQS_IRETQ /* we're about to change IF */ /* @@ -393,7 +322,6 @@ syscall_return_via_sysret: /* rcx and r11 are already restored (see code above) */ UNWIND_HINT_EMPTY POP_EXTRA_REGS -.Lpop_c_regs_except_rcx_r11_and_sysret: popq %rsi /* skip r11 */ popq %r10 popq %r9 @@ -424,47 +352,6 @@ syscall_return_via_sysret: USERGS_SYSRET64 END(entry_SYSCALL_64) -ENTRY(stub_ptregs_64) - /* - * Syscalls marked as needing ptregs land here. - * If we are on the fast path, we need to save the extra regs, - * which we achieve by trying again on the slow path. If we are on - * the slow path, the extra regs are already saved. - * - * RAX stores a pointer to the C function implementing the syscall. - * IRQs are on. - */ - cmpq $.Lentry_SYSCALL_64_after_fastpath_call, (%rsp) - jne 1f - - /* - * Called from fast path -- disable IRQs again, pop return address - * and jump to slow path - */ - DISABLE_INTERRUPTS(CLBR_ANY) - TRACE_IRQS_OFF - popq %rax - UNWIND_HINT_REGS extra=0 - jmp entry_SYSCALL64_slow_path - -1: - JMP_NOSPEC %rax /* Called from C */ -END(stub_ptregs_64) - -.macro ptregs_stub func -ENTRY(ptregs_\func) - UNWIND_HINT_FUNC - leaq \func(%rip), %rax - jmp stub_ptregs_64 -END(ptregs_\func) -.endm - -/* Instantiate ptregs_stub for each ptregs-using syscall */ -#define __SYSCALL_64_QUAL_(sym) -#define __SYSCALL_64_QUAL_ptregs(sym) ptregs_stub sym -#define __SYSCALL_64(nr, sym, qual) __SYSCALL_64_QUAL_##qual(sym) -#include <asm/syscalls_64.h> - /* * %rdi: prev task * %rsi: next task diff --git a/arch/x86/entry/syscall_64.c b/arch/x86/entry/syscall_64.c index 9c09775..c176d2f 100644 --- a/arch/x86/entry/syscall_64.c +++ b/arch/x86/entry/syscall_64.c @@ -7,14 +7,11 @@ #include <asm/asm-offsets.h> #include <asm/syscall.h> -#define __SYSCALL_64_QUAL_(sym) sym -#define __SYSCALL_64_QUAL_ptregs(sym) ptregs_##sym - -#define __SYSCALL_64(nr, sym, qual) extern asmlinkage long __SYSCALL_64_QUAL_##qual(sym)(unsigned long, unsigned long, unsigned long, unsigned long, unsigned long, unsigned long); +#define __SYSCALL_64(nr, sym, qual) extern asmlinkage long sym(unsigned long, unsigned long, unsigned long, unsigned long, unsigned long, unsigned long); #include <asm/syscalls_64.h> #undef __SYSCALL_64 -#define __SYSCALL_64(nr, sym, qual) [nr] = __SYSCALL_64_QUAL_##qual(sym), +#define __SYSCALL_64(nr, sym, qual) [nr] = sym, extern long sys_ni_syscall(unsigned long, unsigned long, unsigned long, unsigned long, unsigned long, unsigned long); diff --git a/arch/x86/include/asm/barrier.h b/arch/x86/include/asm/barrier.h index 7fb3362..30d4061 100644 --- a/arch/x86/include/asm/barrier.h +++ b/arch/x86/include/asm/barrier.h @@ -24,6 +24,34 @@ #define wmb() asm volatile("sfence" ::: "memory") #endif +/** + * array_index_mask_nospec() - generate a mask that is ~0UL when the + * bounds check succeeds and 0 otherwise + * @index: array element index + * @size: number of elements in array + * + * Returns: + * 0 - (index < size) + */ +static inline unsigned long array_index_mask_nospec(unsigned long index, + unsigned long size) +{ + unsigned long mask; + + asm ("cmp %1,%2; sbb %0,%0;" + :"=r" (mask) + :"r"(size),"r" (index) + :"cc"); + return mask; +} + +/* Override the default implementation from linux/nospec.h. */ +#define array_index_mask_nospec array_index_mask_nospec + +/* Prevent speculative execution past this barrier. */ +#define barrier_nospec() alternative_2("", "mfence", X86_FEATURE_MFENCE_RDTSC, \ + "lfence", X86_FEATURE_LFENCE_RDTSC) + #ifdef CONFIG_X86_PPRO_FENCE #define dma_rmb() rmb() #else diff --git a/arch/x86/include/asm/fixmap.h b/arch/x86/include/asm/fixmap.h index 64c4a30..e203169 100644 --- a/arch/x86/include/asm/fixmap.h +++ b/arch/x86/include/asm/fixmap.h @@ -137,8 +137,10 @@ enum fixed_addresses { extern void reserve_top_address(unsigned long reserve); -#define FIXADDR_SIZE (__end_of_permanent_fixed_addresses << PAGE_SHIFT) -#define FIXADDR_START (FIXADDR_TOP - FIXADDR_SIZE) +#define FIXADDR_SIZE (__end_of_permanent_fixed_addresses << PAGE_SHIFT) +#define FIXADDR_START (FIXADDR_TOP - FIXADDR_SIZE) +#define FIXADDR_TOT_SIZE (__end_of_fixed_addresses << PAGE_SHIFT) +#define FIXADDR_TOT_START (FIXADDR_TOP - FIXADDR_TOT_SIZE) extern int fixmaps_set; diff --git a/arch/x86/include/asm/msr.h b/arch/x86/include/asm/msr.h index 07962f5..30df295 100644 --- a/arch/x86/include/asm/msr.h +++ b/arch/x86/include/asm/msr.h @@ -214,8 +214,7 @@ static __always_inline unsigned long long rdtsc_ordered(void) * that some other imaginary CPU is updating continuously with a * time stamp. */ - alternative_2("", "mfence", X86_FEATURE_MFENCE_RDTSC, - "lfence", X86_FEATURE_LFENCE_RDTSC); + barrier_nospec(); return rdtsc(); } diff --git a/arch/x86/include/asm/nospec-branch.h b/arch/x86/include/asm/nospec-branch.h index d15d471..4d57894 100644 --- a/arch/x86/include/asm/nospec-branch.h +++ b/arch/x86/include/asm/nospec-branch.h @@ -150,7 +150,7 @@ 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. + * CPUs with IBRS_ALL *might* it be avoided. */ static inline void vmexit_fill_RSB(void) { diff --git a/arch/x86/include/asm/pgtable_32_types.h b/arch/x86/include/asm/pgtable_32_types.h index ce245b0..0777e18 100644 --- a/arch/x86/include/asm/pgtable_32_types.h +++ b/arch/x86/include/asm/pgtable_32_types.h @@ -44,8 +44,9 @@ extern bool __vmalloc_start_set; /* set once high_memory is set */ */ #define CPU_ENTRY_AREA_PAGES (NR_CPUS * 40) -#define CPU_ENTRY_AREA_BASE \ - ((FIXADDR_START - PAGE_SIZE * (CPU_ENTRY_AREA_PAGES + 1)) & PMD_MASK) +#define CPU_ENTRY_AREA_BASE \ + ((FIXADDR_TOT_START - PAGE_SIZE * (CPU_ENTRY_AREA_PAGES + 1)) \ + & PMD_MASK) #define PKMAP_BASE \ ((CPU_ENTRY_AREA_BASE - PAGE_SIZE) & PMD_MASK) diff --git a/arch/x86/include/asm/processor.h b/arch/x86/include/asm/processor.h index 6207f2f..793bae7 100644 --- a/arch/x86/include/asm/processor.h +++ b/arch/x86/include/asm/processor.h @@ -460,8 +460,6 @@ struct thread_struct { unsigned short gsindex; #endif - u32 status; /* thread synchronous flags */ - #ifdef CONFIG_X86_64 unsigned long fsbase; unsigned long gsbase; diff --git a/arch/x86/include/asm/syscall.h b/arch/x86/include/asm/syscall.h index e3c95e8..03eedc2 100644 --- a/arch/x86/include/asm/syscall.h +++ b/arch/x86/include/asm/syscall.h @@ -60,7 +60,7 @@ static inline long syscall_get_error(struct task_struct *task, * TS_COMPAT is set for 32-bit syscall entries and then * remains set until we return to user mode. */ - if (task->thread.status & (TS_COMPAT|TS_I386_REGS_POKED)) + if (task->thread_info.status & (TS_COMPAT|TS_I386_REGS_POKED)) /* * Sign-extend the value so (int)-EFOO becomes (long)-EFOO * and will match correctly in comparisons. @@ -116,7 +116,7 @@ static inline void syscall_get_arguments(struct task_struct *task, unsigned long *args) { # ifdef CONFIG_IA32_EMULATION - if (task->thread.status & TS_COMPAT) + if (task->thread_info.status & TS_COMPAT) switch (i) { case 0: if (!n--) break; @@ -177,7 +177,7 @@ static inline void syscall_set_arguments(struct task_struct *task, const unsigned long *args) { # ifdef CONFIG_IA32_EMULATION - if (task->thread.status & TS_COMPAT) + if (task->thread_info.status & TS_COMPAT) switch (i) { case 0: if (!n--) break; diff --git a/arch/x86/include/asm/thread_info.h b/arch/x86/include/asm/thread_info.h index d25a638..a5d9521 100644 --- a/arch/x86/include/asm/thread_info.h +++ b/arch/x86/include/asm/thread_info.h @@ -55,6 +55,7 @@ struct task_struct; struct thread_info { unsigned long flags; /* low level flags */ + u32 status; /* thread synchronous flags */ }; #define INIT_THREAD_INFO(tsk) \ @@ -219,7 +220,7 @@ static inline int arch_within_stack_frames(const void * const stack, #define in_ia32_syscall() true #else #define in_ia32_syscall() (IS_ENABLED(CONFIG_IA32_EMULATION) && \ - current->thread.status & TS_COMPAT) + current_thread_info()->status & TS_COMPAT) #endif /* diff --git a/arch/x86/include/asm/tlbflush.h b/arch/x86/include/asm/tlbflush.h index d33e4a2..2b8f18c 100644 --- a/arch/x86/include/asm/tlbflush.h +++ b/arch/x86/include/asm/tlbflush.h @@ -174,6 +174,8 @@ struct tlb_state { struct mm_struct *loaded_mm; u16 loaded_mm_asid; u16 next_asid; + /* last user mm's ctx id */ + u64 last_ctx_id; /* * We can be in one of several states: diff --git a/arch/x86/include/asm/uaccess.h b/arch/x86/include/asm/uaccess.h index 574dff4..aae77eb 100644 --- a/arch/x86/include/asm/uaccess.h +++ b/arch/x86/include/asm/uaccess.h @@ -124,6 +124,11 @@ extern int __get_user_bad(void); #define __uaccess_begin() stac() #define __uaccess_end() clac() +#define __uaccess_begin_nospec() \ +({ \ + stac(); \ + barrier_nospec(); \ +}) /* * This is a type: either unsigned long, if the argument fits into @@ -445,7 +450,7 @@ do { \ ({ \ int __gu_err; \ __inttype(*(ptr)) __gu_val; \ - __uaccess_begin(); \ + __uaccess_begin_nospec(); \ __get_user_size(__gu_val, (ptr), (size), __gu_err, -EFAULT); \ __uaccess_end(); \ (x) = (__force __typeof__(*(ptr)))__gu_val; \ @@ -487,6 +492,10 @@ struct __large_struct { unsigned long buf[100]; }; __uaccess_begin(); \ barrier(); +#define uaccess_try_nospec do { \ + current->thread.uaccess_err = 0; \ + __uaccess_begin_nospec(); \ + #define uaccess_catch(err) \ __uaccess_end(); \ (err) |= (current->thread.uaccess_err ? -EFAULT : 0); \ @@ -548,7 +557,7 @@ struct __large_struct { unsigned long buf[100]; }; * get_user_ex(...); * } get_user_catch(err) */ -#define get_user_try uaccess_try +#define get_user_try uaccess_try_nospec #define get_user_catch(err) uaccess_catch(err) #define get_user_ex(x, ptr) do { \ @@ -582,7 +591,7 @@ extern void __cmpxchg_wrong_size(void) __typeof__(ptr) __uval = (uval); \ __typeof__(*(ptr)) __old = (old); \ __typeof__(*(ptr)) __new = (new); \ - __uaccess_begin(); \ + __uaccess_begin_nospec(); \ switch (size) { \ case 1: \ { \ diff --git a/arch/x86/include/asm/uaccess_32.h b/arch/x86/include/asm/uaccess_32.h index 7295040..ba2dc19 100644 --- a/arch/x86/include/asm/uaccess_32.h +++ b/arch/x86/include/asm/uaccess_32.h @@ -29,21 +29,21 @@ raw_copy_from_user(void *to, const void __user *from, unsigned long n) switch (n) { case 1: ret = 0; - __uaccess_begin(); + __uaccess_begin_nospec(); __get_user_asm_nozero(*(u8 *)to, from, ret, "b", "b", "=q", 1); __uaccess_end(); return ret; case 2: ret = 0; - __uaccess_begin(); + __uaccess_begin_nospec(); __get_user_asm_nozero(*(u16 *)to, from, ret, "w", "w", "=r", 2); __uaccess_end(); return ret; case 4: ret = 0; - __uaccess_begin(); + __uaccess_begin_nospec(); __get_user_asm_nozero(*(u32 *)to, from, ret, "l", "k", "=r", 4); __uaccess_end(); diff --git a/arch/x86/include/asm/uaccess_64.h b/arch/x86/include/asm/uaccess_64.h index f07ef3c..62546b3 100644 --- a/arch/x86/include/asm/uaccess_64.h +++ b/arch/x86/include/asm/uaccess_64.h @@ -55,31 +55,31 @@ raw_copy_from_user(void *dst, const void __user *src, unsigned long size) return copy_user_generic(dst, (__force void *)src, size); switch (size) { case 1: - __uaccess_begin(); + __uaccess_begin_nospec(); __get_user_asm_nozero(*(u8 *)dst, (u8 __user *)src, ret, "b", "b", "=q", 1); __uaccess_end(); return ret; case 2: - __uaccess_begin(); + __uaccess_begin_nospec(); __get_user_asm_nozero(*(u16 *)dst, (u16 __user *)src, ret, "w", "w", "=r", 2); __uaccess_end(); return ret; case 4: - __uaccess_begin(); + __uaccess_begin_nospec(); __get_user_asm_nozero(*(u32 *)dst, (u32 __user *)src, ret, "l", "k", "=r", 4); __uaccess_end(); return ret; case 8: - __uaccess_begin(); + __uaccess_begin_nospec(); __get_user_asm_nozero(*(u64 *)dst, (u64 __user *)src, ret, "q", "", "=r", 8); __uaccess_end(); return ret; case 10: - __uaccess_begin(); + __uaccess_begin_nospec(); __get_user_asm_nozero(*(u64 *)dst, (u64 __user *)src, ret, "q", "", "=r", 10); if (likely(!ret)) @@ -89,7 +89,7 @@ raw_copy_from_user(void *dst, const void __user *src, unsigned long size) __uaccess_end(); return ret; case 16: - __uaccess_begin(); + __uaccess_begin_nospec(); __get_user_asm_nozero(*(u64 *)dst, (u64 __user *)src, ret, "q", "", "=r", 16); if (likely(!ret)) diff --git a/arch/x86/kernel/alternative.c b/arch/x86/kernel/alternative.c index 30571fd..a481763 100644 --- a/arch/x86/kernel/alternative.c +++ b/arch/x86/kernel/alternative.c @@ -46,17 +46,6 @@ static int __init setup_noreplace_smp(char *str) } __setup("noreplace-smp", setup_noreplace_smp); -#ifdef CONFIG_PARAVIRT -static int __initdata_or_module noreplace_paravirt = 0; - -static int __init setup_noreplace_paravirt(char *str) -{ - noreplace_paravirt = 1; - return 1; -} -__setup("noreplace-paravirt", setup_noreplace_paravirt); -#endif - #define DPRINTK(fmt, args...) \ do { \ if (debug_alternative) \ @@ -599,9 +588,6 @@ void __init_or_module apply_paravirt(struct paravirt_patch_site *start, struct paravirt_patch_site *p; char insnbuf[MAX_PATCH_LEN]; - if (noreplace_paravirt) - return; - for (p = start; p < end; p++) { unsigned int used; diff --git a/arch/x86/kernel/cpu/bugs.c b/arch/x86/kernel/cpu/bugs.c index 3bfb2b2..71949bf 100644 --- a/arch/x86/kernel/cpu/bugs.c +++ b/arch/x86/kernel/cpu/bugs.c @@ -103,7 +103,7 @@ bool retpoline_module_ok(bool has_retpoline) if (spectre_v2_enabled == SPECTRE_V2_NONE || has_retpoline) return true; - pr_err("System may be vunerable to spectre v2\n"); + pr_err("System may be vulnerable to spectre v2\n"); spectre_v2_bad_module = true; return false; } @@ -119,13 +119,13 @@ static inline const char *spectre_v2_module_string(void) { return ""; } static void __init spec2_print_if_insecure(const char *reason) { if (boot_cpu_has_bug(X86_BUG_SPECTRE_V2)) - pr_info("%s\n", reason); + pr_info("%s selected on command line.\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); + pr_info("%s selected on command line.\n", reason); } static inline bool retp_compiler(void) @@ -140,42 +140,68 @@ static inline bool match_option(const char *arg, int arglen, const char *opt) return len == arglen && !strncmp(arg, opt, len); } +static const struct { + const char *option; + enum spectre_v2_mitigation_cmd cmd; + bool secure; +} mitigation_options[] = { + { "off", SPECTRE_V2_CMD_NONE, false }, + { "on", SPECTRE_V2_CMD_FORCE, true }, + { "retpoline", SPECTRE_V2_CMD_RETPOLINE, false }, + { "retpoline,amd", SPECTRE_V2_CMD_RETPOLINE_AMD, false }, + { "retpoline,generic", SPECTRE_V2_CMD_RETPOLINE_GENERIC, false }, + { "auto", SPECTRE_V2_CMD_AUTO, false }, +}; + 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")) { + int ret, i; + enum spectre_v2_mitigation_cmd cmd = SPECTRE_V2_CMD_AUTO; + + if (cmdline_find_option_bool(boot_command_line, "nospectre_v2")) + return SPECTRE_V2_CMD_NONE; + else { + ret = cmdline_find_option(boot_command_line, "spectre_v2", arg, + sizeof(arg)); + if (ret < 0) return SPECTRE_V2_CMD_AUTO; + + for (i = 0; i < ARRAY_SIZE(mitigation_options); i++) { + if (!match_option(arg, ret, mitigation_options[i].option)) + continue; + cmd = mitigation_options[i].cmd; + break; } + + if (i >= ARRAY_SIZE(mitigation_options)) { + pr_err("unknown option (%s). Switching to AUTO select\n", + mitigation_options[i].option); + return SPECTRE_V2_CMD_AUTO; + } + } + + if ((cmd == SPECTRE_V2_CMD_RETPOLINE || + cmd == SPECTRE_V2_CMD_RETPOLINE_AMD || + cmd == SPECTRE_V2_CMD_RETPOLINE_GENERIC) && + !IS_ENABLED(CONFIG_RETPOLINE)) { + pr_err("%s selected but not compiled in. Switching to AUTO select\n", + mitigation_options[i].option); + return SPECTRE_V2_CMD_AUTO; } - if (!cmdline_find_option_bool(boot_command_line, "nospectre_v2")) + if (cmd == SPECTRE_V2_CMD_RETPOLINE_AMD && + 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; -disable: - spec2_print_if_insecure("disabled on command line."); - return SPECTRE_V2_CMD_NONE; + } + + if (mitigation_options[i].secure) + spec2_print_if_secure(mitigation_options[i].option); + else + spec2_print_if_insecure(mitigation_options[i].option); + + return cmd; } /* Check for Skylake-like CPUs (for RSB handling) */ @@ -213,10 +239,10 @@ static void __init spectre_v2_select_mitigation(void) return; case SPECTRE_V2_CMD_FORCE: - /* FALLTRHU */ case SPECTRE_V2_CMD_AUTO: - goto retpoline_auto; - + if (IS_ENABLED(CONFIG_RETPOLINE)) + goto retpoline_auto; + break; case SPECTRE_V2_CMD_RETPOLINE_AMD: if (IS_ENABLED(CONFIG_RETPOLINE)) goto retpoline_amd; @@ -297,7 +323,7 @@ ssize_t cpu_show_spectre_v1(struct device *dev, { if (!boot_cpu_has_bug(X86_BUG_SPECTRE_V1)) return sprintf(buf, "Not affected\n"); - return sprintf(buf, "Vulnerable\n"); + return sprintf(buf, "Mitigation: __user pointer sanitization\n"); } ssize_t cpu_show_spectre_v2(struct device *dev, diff --git a/arch/x86/kernel/cpu/common.c b/arch/x86/kernel/cpu/common.c index c7c996a..d63f4b57 100644 --- a/arch/x86/kernel/cpu/common.c +++ b/arch/x86/kernel/cpu/common.c @@ -750,6 +750,26 @@ static void apply_forced_caps(struct cpuinfo_x86 *c) } } +static void init_speculation_control(struct cpuinfo_x86 *c) +{ + /* + * The Intel SPEC_CTRL CPUID bit implies IBRS and IBPB support, + * and they also have a different bit for STIBP support. Also, + * a hypervisor might have set the individual AMD bits even on + * Intel CPUs, for finer-grained selection of what's available. + * + * We use the AMD bits in 0x8000_0008 EBX as the generic hardware + * features, which are visible in /proc/cpuinfo and used by the + * kernel. So set those accordingly from the Intel bits. + */ + if (cpu_has(c, X86_FEATURE_SPEC_CTRL)) { + set_cpu_cap(c, X86_FEATURE_IBRS); + set_cpu_cap(c, X86_FEATURE_IBPB); + } + if (cpu_has(c, X86_FEATURE_INTEL_STIBP)) + set_cpu_cap(c, X86_FEATURE_STIBP); +} + void get_cpu_cap(struct cpuinfo_x86 *c) { u32 eax, ebx, ecx, edx; @@ -844,6 +864,7 @@ void get_cpu_cap(struct cpuinfo_x86 *c) c->x86_capability[CPUID_8000_000A_EDX] = cpuid_edx(0x8000000a); init_scattered_cpuid_features(c); + init_speculation_control(c); /* * Clear/Set all flags overridden by options, after probe. @@ -879,7 +900,7 @@ static void identify_cpu_without_cpuid(struct cpuinfo_x86 *c) #endif } -static const __initdata struct x86_cpu_id cpu_no_speculation[] = { +static const __initconst struct x86_cpu_id cpu_no_speculation[] = { { X86_VENDOR_INTEL, 6, INTEL_FAM6_ATOM_CEDARVIEW, X86_FEATURE_ANY }, { X86_VENDOR_INTEL, 6, INTEL_FAM6_ATOM_CLOVERVIEW, X86_FEATURE_ANY }, { X86_VENDOR_INTEL, 6, INTEL_FAM6_ATOM_LINCROFT, X86_FEATURE_ANY }, @@ -892,7 +913,7 @@ static const __initdata struct x86_cpu_id cpu_no_speculation[] = { {} }; -static const __initdata struct x86_cpu_id cpu_no_meltdown[] = { +static const __initconst struct x86_cpu_id cpu_no_meltdown[] = { { X86_VENDOR_AMD }, {} }; diff --git a/arch/x86/kernel/cpu/intel.c b/arch/x86/kernel/cpu/intel.c index 6936d14..319bf98 100644 --- a/arch/x86/kernel/cpu/intel.c +++ b/arch/x86/kernel/cpu/intel.c @@ -175,28 +175,17 @@ static void early_init_intel(struct cpuinfo_x86 *c) if (c->x86 >= 6 && !cpu_has(c, X86_FEATURE_IA64)) c->microcode = intel_get_microcode_revision(); - /* - * The Intel SPEC_CTRL CPUID bit implies IBRS and IBPB support, - * and they also have a different bit for STIBP support. Also, - * a hypervisor might have set the individual AMD bits even on - * Intel CPUs, for finer-grained selection of what's available. - */ - if (cpu_has(c, X86_FEATURE_SPEC_CTRL)) { - set_cpu_cap(c, X86_FEATURE_IBRS); - set_cpu_cap(c, X86_FEATURE_IBPB); - } - if (cpu_has(c, X86_FEATURE_INTEL_STIBP)) - set_cpu_cap(c, X86_FEATURE_STIBP); - /* Now if any of them are set, check the blacklist and clear the lot */ - if ((cpu_has(c, X86_FEATURE_IBRS) || cpu_has(c, X86_FEATURE_IBPB) || + if ((cpu_has(c, X86_FEATURE_SPEC_CTRL) || + cpu_has(c, X86_FEATURE_INTEL_STIBP) || + cpu_has(c, X86_FEATURE_IBRS) || cpu_has(c, X86_FEATURE_IBPB) || cpu_has(c, X86_FEATURE_STIBP)) && bad_spectre_microcode(c)) { pr_warn("Intel Spectre v2 broken microcode detected; disabling Speculation Control\n"); - clear_cpu_cap(c, X86_FEATURE_IBRS); - clear_cpu_cap(c, X86_FEATURE_IBPB); - clear_cpu_cap(c, X86_FEATURE_STIBP); - clear_cpu_cap(c, X86_FEATURE_SPEC_CTRL); - clear_cpu_cap(c, X86_FEATURE_INTEL_STIBP); + setup_clear_cpu_cap(X86_FEATURE_IBRS); + setup_clear_cpu_cap(X86_FEATURE_IBPB); + setup_clear_cpu_cap(X86_FEATURE_STIBP); + setup_clear_cpu_cap(X86_FEATURE_SPEC_CTRL); + setup_clear_cpu_cap(X86_FEATURE_INTEL_STIBP); } /* diff --git a/arch/x86/kernel/process_64.c b/arch/x86/kernel/process_64.c index c754662..9eb448c 100644 --- a/arch/x86/kernel/process_64.c +++ b/arch/x86/kernel/process_64.c @@ -557,7 +557,7 @@ static void __set_personality_x32(void) * Pretend to come from a x32 execve. */ task_pt_regs(current)->orig_ax = __NR_x32_execve | __X32_SYSCALL_BIT; - current->thread.status &= ~TS_COMPAT; + current_thread_info()->status &= ~TS_COMPAT; #endif } @@ -571,7 +571,7 @@ static void __set_personality_ia32(void) current->personality |= force_personality32; /* Prepare the first "return" to user space */ task_pt_regs(current)->orig_ax = __NR_ia32_execve; - current->thread.status |= TS_COMPAT; + current_thread_info()->status |= TS_COMPAT; #endif } diff --git a/arch/x86/kernel/ptrace.c b/arch/x86/kernel/ptrace.c index f37d181..ed5c4cd 100644 --- a/arch/x86/kernel/ptrace.c +++ b/arch/x86/kernel/ptrace.c @@ -935,7 +935,7 @@ static int putreg32(struct task_struct *child, unsigned regno, u32 value) */ regs->orig_ax = value; if (syscall_get_nr(child, regs) >= 0) - child->thread.status |= TS_I386_REGS_POKED; + child->thread_info.status |= TS_I386_REGS_POKED; break; case offsetof(struct user32, regs.eflags): diff --git a/arch/x86/kernel/signal.c b/arch/x86/kernel/signal.c index b9e00e8..4cdc0b2 100644 --- a/arch/x86/kernel/signal.c +++ b/arch/x86/kernel/signal.c @@ -787,7 +787,7 @@ static inline unsigned long get_nr_restart_syscall(const struct pt_regs *regs) * than the tracee. */ #ifdef CONFIG_IA32_EMULATION - if (current->thread.status & (TS_COMPAT|TS_I386_REGS_POKED)) + if (current_thread_info()->status & (TS_COMPAT|TS_I386_REGS_POKED)) return __NR_ia32_restart_syscall; #endif #ifdef CONFIG_X86_X32_ABI diff --git a/arch/x86/kvm/cpuid.c b/arch/x86/kvm/cpuid.c index 0099e10..13f5d42 100644 --- a/arch/x86/kvm/cpuid.c +++ b/arch/x86/kvm/cpuid.c @@ -67,9 +67,7 @@ u64 kvm_supported_xcr0(void) #define F(x) bit(X86_FEATURE_##x) -/* These are scattered features in cpufeatures.h. */ -#define KVM_CPUID_BIT_AVX512_4VNNIW 2 -#define KVM_CPUID_BIT_AVX512_4FMAPS 3 +/* For scattered features from cpufeatures.h; we currently expose none */ #define KF(x) bit(KVM_CPUID_BIT_##x) int kvm_update_cpuid(struct kvm_vcpu *vcpu) @@ -367,6 +365,10 @@ static inline int __do_cpuid_ent(struct kvm_cpuid_entry2 *entry, u32 function, F(3DNOWPREFETCH) | F(OSVW) | 0 /* IBS */ | F(XOP) | 0 /* SKINIT, WDT, LWP */ | F(FMA4) | F(TBM); + /* cpuid 0x80000008.ebx */ + const u32 kvm_cpuid_8000_0008_ebx_x86_features = + F(IBPB) | F(IBRS); + /* cpuid 0xC0000001.edx */ const u32 kvm_cpuid_C000_0001_edx_x86_features = F(XSTORE) | F(XSTORE_EN) | F(XCRYPT) | F(XCRYPT_EN) | @@ -392,7 +394,8 @@ static inline int __do_cpuid_ent(struct kvm_cpuid_entry2 *entry, u32 function, /* cpuid 7.0.edx*/ const u32 kvm_cpuid_7_0_edx_x86_features = - KF(AVX512_4VNNIW) | KF(AVX512_4FMAPS); + F(AVX512_4VNNIW) | F(AVX512_4FMAPS) | F(SPEC_CTRL) | + F(ARCH_CAPABILITIES); /* all calls to cpuid_count() should be made on the same cpu */ get_cpu(); @@ -477,7 +480,7 @@ static inline int __do_cpuid_ent(struct kvm_cpuid_entry2 *entry, u32 function, if (!tdp_enabled || !boot_cpu_has(X86_FEATURE_OSPKE)) entry->ecx &= ~F(PKU); entry->edx &= kvm_cpuid_7_0_edx_x86_features; - entry->edx &= get_scattered_cpuid_leaf(7, 0, CPUID_EDX); + cpuid_mask(&entry->edx, CPUID_7_EDX); } else { entry->ebx = 0; entry->ecx = 0; @@ -627,7 +630,14 @@ static inline int __do_cpuid_ent(struct kvm_cpuid_entry2 *entry, u32 function, if (!g_phys_as) g_phys_as = phys_as; entry->eax = g_phys_as | (virt_as << 8); - entry->ebx = entry->edx = 0; + entry->edx = 0; + /* IBRS and IBPB aren't necessarily present in hardware cpuid */ + if (boot_cpu_has(X86_FEATURE_IBPB)) + entry->ebx |= F(IBPB); + if (boot_cpu_has(X86_FEATURE_IBRS)) + entry->ebx |= F(IBRS); + entry->ebx &= kvm_cpuid_8000_0008_ebx_x86_features; + cpuid_mask(&entry->ebx, CPUID_8000_0008_EBX); break; } case 0x80000019: diff --git a/arch/x86/kvm/cpuid.h b/arch/x86/kvm/cpuid.h index c2cea66..9a327d5 100644 --- a/arch/x86/kvm/cpuid.h +++ b/arch/x86/kvm/cpuid.h @@ -54,6 +54,7 @@ static const struct cpuid_reg reverse_cpuid[] = { [CPUID_8000_000A_EDX] = {0x8000000a, 0, CPUID_EDX}, [CPUID_7_ECX] = { 7, 0, CPUID_ECX}, [CPUID_8000_0007_EBX] = {0x80000007, 0, CPUID_EBX}, + [CPUID_7_EDX] = { 7, 0, CPUID_EDX}, }; static __always_inline struct cpuid_reg x86_feature_cpuid(unsigned x86_feature) diff --git a/arch/x86/kvm/svm.c b/arch/x86/kvm/svm.c index f40d0da..4e3c795 100644 --- a/arch/x86/kvm/svm.c +++ b/arch/x86/kvm/svm.c @@ -184,6 +184,8 @@ struct vcpu_svm { u64 gs_base; } host; + u64 spec_ctrl; + u32 *msrpm; ulong nmi_iret_rip; @@ -249,6 +251,8 @@ static const struct svm_direct_access_msrs { { .index = MSR_CSTAR, .always = true }, { .index = MSR_SYSCALL_MASK, .always = true }, #endif + { .index = MSR_IA32_SPEC_CTRL, .always = false }, + { .index = MSR_IA32_PRED_CMD, .always = false }, { .index = MSR_IA32_LASTBRANCHFROMIP, .always = false }, { .index = MSR_IA32_LASTBRANCHTOIP, .always = false }, { .index = MSR_IA32_LASTINTFROMIP, .always = false }, @@ -529,6 +533,7 @@ struct svm_cpu_data { struct kvm_ldttss_desc *tss_desc; struct page *save_area; + struct vmcb *current_vmcb; }; static DEFINE_PER_CPU(struct svm_cpu_data *, svm_data); @@ -880,6 +885,25 @@ static bool valid_msr_intercept(u32 index) return false; } +static bool msr_write_intercepted(struct kvm_vcpu *vcpu, unsigned msr) +{ + u8 bit_write; + unsigned long tmp; + u32 offset; + u32 *msrpm; + + msrpm = is_guest_mode(vcpu) ? to_svm(vcpu)->nested.msrpm: + to_svm(vcpu)->msrpm; + + offset = svm_msrpm_offset(msr); + bit_write = 2 * (msr & 0x0f) + 1; + tmp = msrpm[offset]; + + BUG_ON(offset == MSR_INVALID); + + return !!test_bit(bit_write, &tmp); +} + static void set_msr_interception(u32 *msrpm, unsigned msr, int read, int write) { @@ -1582,6 +1606,8 @@ static void svm_vcpu_reset(struct kvm_vcpu *vcpu, bool init_event) u32 dummy; u32 eax = 1; + svm->spec_ctrl = 0; + if (!init_event) { svm->vcpu.arch.apic_base = APIC_DEFAULT_PHYS_BASE | MSR_IA32_APICBASE_ENABLE; @@ -1703,11 +1729,17 @@ static void svm_free_vcpu(struct kvm_vcpu *vcpu) __free_pages(virt_to_page(svm->nested.msrpm), MSRPM_ALLOC_ORDER); kvm_vcpu_uninit(vcpu); kmem_cache_free(kvm_vcpu_cache, svm); + /* + * The vmcb page can be recycled, causing a false negative in + * svm_vcpu_load(). So do a full IBPB now. + */ + indirect_branch_prediction_barrier(); } static void svm_vcpu_load(struct kvm_vcpu *vcpu, int cpu) { struct vcpu_svm *svm = to_svm(vcpu); + struct svm_cpu_data *sd = per_cpu(svm_data, cpu); int i; if (unlikely(cpu != vcpu->cpu)) { @@ -1736,6 +1768,10 @@ static void svm_vcpu_load(struct kvm_vcpu *vcpu, int cpu) if (static_cpu_has(X86_FEATURE_RDTSCP)) wrmsrl(MSR_TSC_AUX, svm->tsc_aux); + if (sd->current_vmcb != svm->vmcb) { + sd->current_vmcb = svm->vmcb; + indirect_branch_prediction_barrier(); + } avic_vcpu_load(vcpu, cpu); } @@ -3593,6 +3629,13 @@ static int svm_get_msr(struct kvm_vcpu *vcpu, struct msr_data *msr_info) case MSR_VM_CR: msr_info->data = svm->nested.vm_cr_msr; break; + case MSR_IA32_SPEC_CTRL: + if (!msr_info->host_initiated && + !guest_cpuid_has(vcpu, X86_FEATURE_IBRS)) + return 1; + + msr_info->data = svm->spec_ctrl; + break; case MSR_IA32_UCODE_REV: msr_info->data = 0x01000065; break; @@ -3684,6 +3727,49 @@ static int svm_set_msr(struct kvm_vcpu *vcpu, struct msr_data *msr) case MSR_IA32_TSC: kvm_write_tsc(vcpu, msr); break; + case MSR_IA32_SPEC_CTRL: + if (!msr->host_initiated && + !guest_cpuid_has(vcpu, X86_FEATURE_IBRS)) + return 1; + + /* The STIBP bit doesn't fault even if it's not advertised */ + if (data & ~(SPEC_CTRL_IBRS | SPEC_CTRL_STIBP)) + return 1; + + svm->spec_ctrl = data; + + if (!data) + break; + + /* + * For non-nested: + * When it's written (to non-zero) for the first time, pass + * it through. + * + * For nested: + * The handling of the MSR bitmap for L2 guests is done in + * nested_svm_vmrun_msrpm. + * We update the L1 MSR bit as well since it will end up + * touching the MSR anyway now. + */ + set_msr_interception(svm->msrpm, MSR_IA32_SPEC_CTRL, 1, 1); + break; + case MSR_IA32_PRED_CMD: + if (!msr->host_initiated && + !guest_cpuid_has(vcpu, X86_FEATURE_IBPB)) + return 1; + + if (data & ~PRED_CMD_IBPB) + return 1; + + if (!data) + break; + + wrmsrl(MSR_IA32_PRED_CMD, PRED_CMD_IBPB); + if (is_guest_mode(vcpu)) + break; + set_msr_interception(svm->msrpm, MSR_IA32_PRED_CMD, 0, 1); + break; case MSR_STAR: svm->vmcb->save.star = data; break; @@ -4936,6 +5022,15 @@ static void svm_vcpu_run(struct kvm_vcpu *vcpu) local_irq_enable(); + /* + * If this vCPU has touched SPEC_CTRL, restore the guest's value if + * it's non-zero. Since vmentry is serialising on affected CPUs, there + * is no need to worry about the conditional branch over the wrmsr + * being speculatively taken. + */ + if (svm->spec_ctrl) + wrmsrl(MSR_IA32_SPEC_CTRL, svm->spec_ctrl); + asm volatile ( "push %%" _ASM_BP "; \n\t" "mov %c[rbx](%[svm]), %%" _ASM_BX " \n\t" @@ -5028,6 +5123,27 @@ static void svm_vcpu_run(struct kvm_vcpu *vcpu) #endif ); + /* + * We do not use IBRS in the kernel. If this vCPU has used the + * SPEC_CTRL MSR it may have left it on; save the value and + * turn it off. This is much more efficient than blindly adding + * it to the atomic save/restore list. Especially as the former + * (Saving guest MSRs on vmexit) doesn't even exist in KVM. + * + * For non-nested case: + * If the L01 MSR bitmap does not intercept the MSR, then we need to + * save it. + * + * For nested case: + * If the L02 MSR bitmap does not intercept the MSR, then we need to + * save it. + */ + if (!msr_write_intercepted(vcpu, MSR_IA32_SPEC_CTRL)) + rdmsrl(MSR_IA32_SPEC_CTRL, svm->spec_ctrl); + + if (svm->spec_ctrl) + wrmsrl(MSR_IA32_SPEC_CTRL, 0); + /* Eliminate branch target predictions from guest mode */ vmexit_fill_RSB(); diff --git a/arch/x86/kvm/vmx.c b/arch/x86/kvm/vmx.c index a8b96dc..bee4c49 100644 --- a/arch/x86/kvm/vmx.c +++ b/arch/x86/kvm/vmx.c @@ -34,6 +34,7 @@ #include <linux/tboot.h> #include <linux/hrtimer.h> #include <linux/frame.h> +#include <linux/nospec.h> #include "kvm_cache_regs.h" #include "x86.h" @@ -111,6 +112,14 @@ static u64 __read_mostly host_xss; static bool __read_mostly enable_pml = 1; module_param_named(pml, enable_pml, bool, S_IRUGO); +#define MSR_TYPE_R 1 +#define MSR_TYPE_W 2 +#define MSR_TYPE_RW 3 + +#define MSR_BITMAP_MODE_X2APIC 1 +#define MSR_BITMAP_MODE_X2APIC_APICV 2 +#define MSR_BITMAP_MODE_LM 4 + #define KVM_VMX_TSC_MULTIPLIER_MAX 0xffffffffffffffffULL /* Guest_tsc -> host_tsc conversion requires 64-bit division. */ @@ -185,7 +194,6 @@ module_param(ple_window_max, int, S_IRUGO); extern const ulong vmx_return; #define NR_AUTOLOAD_MSRS 8 -#define VMCS02_POOL_SIZE 1 struct vmcs { u32 revision_id; @@ -210,6 +218,7 @@ struct loaded_vmcs { int soft_vnmi_blocked; ktime_t entry_time; s64 vnmi_blocked_time; + unsigned long *msr_bitmap; struct list_head loaded_vmcss_on_cpu_link; }; @@ -226,7 +235,7 @@ struct shared_msr_entry { * stored in guest memory specified by VMPTRLD, but is opaque to the guest, * which must access it using VMREAD/VMWRITE/VMCLEAR instructions. * More than one of these structures may exist, if L1 runs multiple L2 guests. - * nested_vmx_run() will use the data here to build a vmcs02: a VMCS for the + * nested_vmx_run() will use the data here to build the vmcs02: a VMCS for the * underlying hardware which will be used to run L2. * This structure is packed to ensure that its layout is identical across * machines (necessary for live migration). @@ -409,13 +418,6 @@ struct __packed vmcs12 { */ #define VMCS12_SIZE 0x1000 -/* Used to remember the last vmcs02 used for some recently used vmcs12s */ -struct vmcs02_list { - struct list_head list; - gpa_t vmptr; - struct loaded_vmcs vmcs02; -}; - /* * The nested_vmx structure is part of vcpu_vmx, and holds information we need * for correct emulation of VMX (i.e., nested VMX) on this vcpu. @@ -440,15 +442,15 @@ struct nested_vmx { */ bool sync_shadow_vmcs; - /* vmcs02_list cache of VMCSs recently used to run L2 guests */ - struct list_head vmcs02_pool; - int vmcs02_num; bool change_vmcs01_virtual_x2apic_mode; /* L2 must run next, and mustn't decide to exit to L1. */ bool nested_run_pending; + + struct loaded_vmcs vmcs02; + /* - * Guest pages referred to in vmcs02 with host-physical pointers, so - * we must keep them pinned while L2 runs. + * Guest pages referred to in the vmcs02 with host-physical + * pointers, so we must keep them pinned while L2 runs. */ struct page *apic_access_page; struct page *virtual_apic_page; @@ -457,8 +459,6 @@ struct nested_vmx { bool pi_pending; u16 posted_intr_nv; - unsigned long *msr_bitmap; - struct hrtimer preemption_timer; bool preemption_timer_expired; @@ -581,6 +581,7 @@ struct vcpu_vmx { struct kvm_vcpu vcpu; unsigned long host_rsp; u8 fail; + u8 msr_bitmap_mode; u32 exit_intr_info; u32 idt_vectoring_info; ulong rflags; @@ -592,6 +593,10 @@ struct vcpu_vmx { u64 msr_host_kernel_gs_base; u64 msr_guest_kernel_gs_base; #endif + + u64 arch_capabilities; + u64 spec_ctrl; + u32 vm_entry_controls_shadow; u32 vm_exit_controls_shadow; u32 secondary_exec_control; @@ -898,21 +903,18 @@ static const unsigned short vmcs_field_to_offset_table[] = { static inline short vmcs_field_to_offset(unsigned long field) { - BUILD_BUG_ON(ARRAY_SIZE(vmcs_field_to_offset_table) > SHRT_MAX); + const size_t size = ARRAY_SIZE(vmcs_field_to_offset_table); + unsigned short offset; - if (field >= ARRAY_SIZE(vmcs_field_to_offset_table)) + BUILD_BUG_ON(size > SHRT_MAX); + if (field >= size) 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) + field = array_index_nospec(field, size); + offset = vmcs_field_to_offset_table[field]; + if (offset == 0) return -ENOENT; - - return vmcs_field_to_offset_table[field]; + return offset; } static inline struct vmcs12 *get_vmcs12(struct kvm_vcpu *vcpu) @@ -935,6 +937,9 @@ static bool vmx_get_nmi_mask(struct kvm_vcpu *vcpu); static void vmx_set_nmi_mask(struct kvm_vcpu *vcpu, bool masked); static bool nested_vmx_is_page_fault_vmexit(struct vmcs12 *vmcs12, u16 error_code); +static void vmx_update_msr_bitmap(struct kvm_vcpu *vcpu); +static void __always_inline vmx_disable_intercept_for_msr(unsigned long *msr_bitmap, + u32 msr, int type); static DEFINE_PER_CPU(struct vmcs *, vmxarea); static DEFINE_PER_CPU(struct vmcs *, current_vmcs); @@ -954,12 +959,6 @@ static DEFINE_PER_CPU(spinlock_t, blocked_vcpu_on_cpu_lock); enum { VMX_IO_BITMAP_A, VMX_IO_BITMAP_B, - VMX_MSR_BITMAP_LEGACY, - VMX_MSR_BITMAP_LONGMODE, - VMX_MSR_BITMAP_LEGACY_X2APIC_APICV, - VMX_MSR_BITMAP_LONGMODE_X2APIC_APICV, - VMX_MSR_BITMAP_LEGACY_X2APIC, - VMX_MSR_BITMAP_LONGMODE_X2APIC, VMX_VMREAD_BITMAP, VMX_VMWRITE_BITMAP, VMX_BITMAP_NR @@ -969,12 +968,6 @@ static unsigned long *vmx_bitmap[VMX_BITMAP_NR]; #define vmx_io_bitmap_a (vmx_bitmap[VMX_IO_BITMAP_A]) #define vmx_io_bitmap_b (vmx_bitmap[VMX_IO_BITMAP_B]) -#define vmx_msr_bitmap_legacy (vmx_bitmap[VMX_MSR_BITMAP_LEGACY]) -#define vmx_msr_bitmap_longmode (vmx_bitmap[VMX_MSR_BITMAP_LONGMODE]) -#define vmx_msr_bitmap_legacy_x2apic_apicv (vmx_bitmap[VMX_MSR_BITMAP_LEGACY_X2APIC_APICV]) -#define vmx_msr_bitmap_longmode_x2apic_apicv (vmx_bitmap[VMX_MSR_BITMAP_LONGMODE_X2APIC_APICV]) -#define vmx_msr_bitmap_legacy_x2apic (vmx_bitmap[VMX_MSR_BITMAP_LEGACY_X2APIC]) -#define vmx_msr_bitmap_longmode_x2apic (vmx_bitmap[VMX_MSR_BITMAP_LONGMODE_X2APIC]) #define vmx_vmread_bitmap (vmx_bitmap[VMX_VMREAD_BITMAP]) #define vmx_vmwrite_bitmap (vmx_bitmap[VMX_VMWRITE_BITMAP]) @@ -1918,6 +1911,52 @@ static void update_exception_bitmap(struct kvm_vcpu *vcpu) vmcs_write32(EXCEPTION_BITMAP, eb); } +/* + * Check if MSR is intercepted for currently loaded MSR bitmap. + */ +static bool msr_write_intercepted(struct kvm_vcpu *vcpu, u32 msr) +{ + unsigned long *msr_bitmap; + int f = sizeof(unsigned long); + + if (!cpu_has_vmx_msr_bitmap()) + return true; + + msr_bitmap = to_vmx(vcpu)->loaded_vmcs->msr_bitmap; + + if (msr <= 0x1fff) { + return !!test_bit(msr, msr_bitmap + 0x800 / f); + } else if ((msr >= 0xc0000000) && (msr <= 0xc0001fff)) { + msr &= 0x1fff; + return !!test_bit(msr, msr_bitmap + 0xc00 / f); + } + + return true; +} + +/* + * Check if MSR is intercepted for L01 MSR bitmap. + */ +static bool msr_write_intercepted_l01(struct kvm_vcpu *vcpu, u32 msr) +{ + unsigned long *msr_bitmap; + int f = sizeof(unsigned long); + + if (!cpu_has_vmx_msr_bitmap()) + return true; + + msr_bitmap = to_vmx(vcpu)->vmcs01.msr_bitmap; + + if (msr <= 0x1fff) { + return !!test_bit(msr, msr_bitmap + 0x800 / f); + } else if ((msr >= 0xc0000000) && (msr <= 0xc0001fff)) { + msr &= 0x1fff; + return !!test_bit(msr, msr_bitmap + 0xc00 / f); + } + + return true; +} + static void clear_atomic_switch_msr_special(struct vcpu_vmx *vmx, unsigned long entry, unsigned long exit) { @@ -2296,6 +2335,7 @@ static void vmx_vcpu_load(struct kvm_vcpu *vcpu, int cpu) if (per_cpu(current_vmcs, cpu) != vmx->loaded_vmcs->vmcs) { per_cpu(current_vmcs, cpu) = vmx->loaded_vmcs->vmcs; vmcs_load(vmx->loaded_vmcs->vmcs); + indirect_branch_prediction_barrier(); } if (!already_loaded) { @@ -2572,36 +2612,6 @@ static void move_msr_up(struct vcpu_vmx *vmx, int from, int to) vmx->guest_msrs[from] = tmp; } -static void vmx_set_msr_bitmap(struct kvm_vcpu *vcpu) -{ - unsigned long *msr_bitmap; - - if (is_guest_mode(vcpu)) - msr_bitmap = to_vmx(vcpu)->nested.msr_bitmap; - else if (cpu_has_secondary_exec_ctrls() && - (vmcs_read32(SECONDARY_VM_EXEC_CONTROL) & - SECONDARY_EXEC_VIRTUALIZE_X2APIC_MODE)) { - if (enable_apicv && kvm_vcpu_apicv_active(vcpu)) { - if (is_long_mode(vcpu)) - msr_bitmap = vmx_msr_bitmap_longmode_x2apic_apicv; - else - msr_bitmap = vmx_msr_bitmap_legacy_x2apic_apicv; - } else { - if (is_long_mode(vcpu)) - msr_bitmap = vmx_msr_bitmap_longmode_x2apic; - else - msr_bitmap = vmx_msr_bitmap_legacy_x2apic; - } - } else { - if (is_long_mode(vcpu)) - msr_bitmap = vmx_msr_bitmap_longmode; - else - msr_bitmap = vmx_msr_bitmap_legacy; - } - - vmcs_write64(MSR_BITMAP, __pa(msr_bitmap)); -} - /* * Set up the vmcs to automatically save and restore system * msrs. Don't touch the 64-bit msrs if the guest is in legacy @@ -2642,7 +2652,7 @@ static void setup_msrs(struct vcpu_vmx *vmx) vmx->save_nmsrs = save_nmsrs; if (cpu_has_vmx_msr_bitmap()) - vmx_set_msr_bitmap(&vmx->vcpu); + vmx_update_msr_bitmap(&vmx->vcpu); } /* @@ -3276,6 +3286,20 @@ static int vmx_get_msr(struct kvm_vcpu *vcpu, struct msr_data *msr_info) case MSR_IA32_TSC: msr_info->data = guest_read_tsc(vcpu); break; + case MSR_IA32_SPEC_CTRL: + if (!msr_info->host_initiated && + !guest_cpuid_has(vcpu, X86_FEATURE_IBRS) && + !guest_cpuid_has(vcpu, X86_FEATURE_SPEC_CTRL)) + return 1; + + msr_info->data = to_vmx(vcpu)->spec_ctrl; + break; + case MSR_IA32_ARCH_CAPABILITIES: + if (!msr_info->host_initiated && + !guest_cpuid_has(vcpu, X86_FEATURE_ARCH_CAPABILITIES)) + return 1; + msr_info->data = to_vmx(vcpu)->arch_capabilities; + break; case MSR_IA32_SYSENTER_CS: msr_info->data = vmcs_read32(GUEST_SYSENTER_CS); break; @@ -3383,6 +3407,70 @@ static int vmx_set_msr(struct kvm_vcpu *vcpu, struct msr_data *msr_info) case MSR_IA32_TSC: kvm_write_tsc(vcpu, msr_info); break; + case MSR_IA32_SPEC_CTRL: + if (!msr_info->host_initiated && + !guest_cpuid_has(vcpu, X86_FEATURE_IBRS) && + !guest_cpuid_has(vcpu, X86_FEATURE_SPEC_CTRL)) + return 1; + + /* The STIBP bit doesn't fault even if it's not advertised */ + if (data & ~(SPEC_CTRL_IBRS | SPEC_CTRL_STIBP)) + return 1; + + vmx->spec_ctrl = data; + + if (!data) + break; + + /* + * For non-nested: + * When it's written (to non-zero) for the first time, pass + * it through. + * + * For nested: + * The handling of the MSR bitmap for L2 guests is done in + * nested_vmx_merge_msr_bitmap. We should not touch the + * vmcs02.msr_bitmap here since it gets completely overwritten + * in the merging. We update the vmcs01 here for L1 as well + * since it will end up touching the MSR anyway now. + */ + vmx_disable_intercept_for_msr(vmx->vmcs01.msr_bitmap, + MSR_IA32_SPEC_CTRL, + MSR_TYPE_RW); + break; + case MSR_IA32_PRED_CMD: + if (!msr_info->host_initiated && + !guest_cpuid_has(vcpu, X86_FEATURE_IBPB) && + !guest_cpuid_has(vcpu, X86_FEATURE_SPEC_CTRL)) + return 1; + + if (data & ~PRED_CMD_IBPB) + return 1; + + if (!data) + break; + + wrmsrl(MSR_IA32_PRED_CMD, PRED_CMD_IBPB); + + /* + * For non-nested: + * When it's written (to non-zero) for the first time, pass + * it through. + * + * For nested: + * The handling of the MSR bitmap for L2 guests is done in + * nested_vmx_merge_msr_bitmap. We should not touch the + * vmcs02.msr_bitmap here since it gets completely overwritten + * in the merging. + */ + vmx_disable_intercept_for_msr(vmx->vmcs01.msr_bitmap, MSR_IA32_PRED_CMD, + MSR_TYPE_W); + break; + case MSR_IA32_ARCH_CAPABILITIES: + if (!msr_info->host_initiated) + return 1; + vmx->arch_capabilities = data; + break; case MSR_IA32_CR_PAT: if (vmcs_config.vmentry_ctrl & VM_ENTRY_LOAD_IA32_PAT) { if (!kvm_mtrr_valid(vcpu, MSR_IA32_CR_PAT, data)) @@ -3837,11 +3925,6 @@ static struct vmcs *alloc_vmcs_cpu(int cpu) return vmcs; } -static struct vmcs *alloc_vmcs(void) -{ - return alloc_vmcs_cpu(raw_smp_processor_id()); -} - static void free_vmcs(struct vmcs *vmcs) { free_pages((unsigned long)vmcs, vmcs_config.order); @@ -3857,9 +3940,38 @@ static void free_loaded_vmcs(struct loaded_vmcs *loaded_vmcs) loaded_vmcs_clear(loaded_vmcs); free_vmcs(loaded_vmcs->vmcs); loaded_vmcs->vmcs = NULL; + if (loaded_vmcs->msr_bitmap) + free_page((unsigned long)loaded_vmcs->msr_bitmap); WARN_ON(loaded_vmcs->shadow_vmcs != NULL); } +static struct vmcs *alloc_vmcs(void) +{ + return alloc_vmcs_cpu(raw_smp_processor_id()); +} + +static int alloc_loaded_vmcs(struct loaded_vmcs *loaded_vmcs) +{ + loaded_vmcs->vmcs = alloc_vmcs(); + if (!loaded_vmcs->vmcs) + return -ENOMEM; + + loaded_vmcs->shadow_vmcs = NULL; + loaded_vmcs_init(loaded_vmcs); + + if (cpu_has_vmx_msr_bitmap()) { + loaded_vmcs->msr_bitmap = (unsigned long *)__get_free_page(GFP_KERNEL); + if (!loaded_vmcs->msr_bitmap) + goto out_vmcs; + memset(loaded_vmcs->msr_bitmap, 0xff, PAGE_SIZE); + } + return 0; + +out_vmcs: + free_loaded_vmcs(loaded_vmcs); + return -ENOMEM; +} + static void free_kvm_area(void) { int cpu; @@ -4918,10 +5030,8 @@ static void free_vpid(int vpid) spin_unlock(&vmx_vpid_lock); } -#define MSR_TYPE_R 1 -#define MSR_TYPE_W 2 -static void __vmx_disable_intercept_for_msr(unsigned long *msr_bitmap, - u32 msr, int type) +static void __always_inline vmx_disable_intercept_for_msr(unsigned long *msr_bitmap, + u32 msr, int type) { int f = sizeof(unsigned long); @@ -4955,6 +5065,50 @@ static void __vmx_disable_intercept_for_msr(unsigned long *msr_bitmap, } } +static void __always_inline vmx_enable_intercept_for_msr(unsigned long *msr_bitmap, + u32 msr, int type) +{ + int f = sizeof(unsigned long); + + if (!cpu_has_vmx_msr_bitmap()) + return; + + /* + * See Intel PRM Vol. 3, 20.6.9 (MSR-Bitmap Address). Early manuals + * have the write-low and read-high bitmap offsets the wrong way round. + * We can control MSRs 0x00000000-0x00001fff and 0xc0000000-0xc0001fff. + */ + if (msr <= 0x1fff) { + if (type & MSR_TYPE_R) + /* read-low */ + __set_bit(msr, msr_bitmap + 0x000 / f); + + if (type & MSR_TYPE_W) + /* write-low */ + __set_bit(msr, msr_bitmap + 0x800 / f); + + } else if ((msr >= 0xc0000000) && (msr <= 0xc0001fff)) { + msr &= 0x1fff; + if (type & MSR_TYPE_R) + /* read-high */ + __set_bit(msr, msr_bitmap + 0x400 / f); + + if (type & MSR_TYPE_W) + /* write-high */ + __set_bit(msr, msr_bitmap + 0xc00 / f); + + } +} + +static void __always_inline vmx_set_intercept_for_msr(unsigned long *msr_bitmap, + u32 msr, int type, bool value) +{ + if (value) + vmx_enable_intercept_for_msr(msr_bitmap, msr, type); + else + vmx_disable_intercept_for_msr(msr_bitmap, msr, type); +} + /* * If a msr is allowed by L0, we should check whether it is allowed by L1. * The corresponding bit will be cleared unless both of L0 and L1 allow it. @@ -5001,30 +5155,70 @@ static void nested_vmx_disable_intercept_for_msr(unsigned long *msr_bitmap_l1, } } -static void vmx_disable_intercept_for_msr(u32 msr, bool longmode_only) +static u8 vmx_msr_bitmap_mode(struct kvm_vcpu *vcpu) { - if (!longmode_only) - __vmx_disable_intercept_for_msr(vmx_msr_bitmap_legacy, - msr, MSR_TYPE_R | MSR_TYPE_W); - __vmx_disable_intercept_for_msr(vmx_msr_bitmap_longmode, - msr, MSR_TYPE_R | MSR_TYPE_W); + u8 mode = 0; + + if (cpu_has_secondary_exec_ctrls() && + (vmcs_read32(SECONDARY_VM_EXEC_CONTROL) & + SECONDARY_EXEC_VIRTUALIZE_X2APIC_MODE)) { + mode |= MSR_BITMAP_MODE_X2APIC; + if (enable_apicv && kvm_vcpu_apicv_active(vcpu)) + mode |= MSR_BITMAP_MODE_X2APIC_APICV; + } + + if (is_long_mode(vcpu)) + mode |= MSR_BITMAP_MODE_LM; + + return mode; } -static void vmx_disable_intercept_msr_x2apic(u32 msr, int type, bool apicv_active) +#define X2APIC_MSR(r) (APIC_BASE_MSR + ((r) >> 4)) + +static void vmx_update_msr_bitmap_x2apic(unsigned long *msr_bitmap, + u8 mode) { - if (apicv_active) { - __vmx_disable_intercept_for_msr(vmx_msr_bitmap_legacy_x2apic_apicv, - msr, type); - __vmx_disable_intercept_for_msr(vmx_msr_bitmap_longmode_x2apic_apicv, - msr, type); - } else { - __vmx_disable_intercept_for_msr(vmx_msr_bitmap_legacy_x2apic, - msr, type); - __vmx_disable_intercept_for_msr(vmx_msr_bitmap_longmode_x2apic, - msr, type); + int msr; + + for (msr = 0x800; msr <= 0x8ff; msr += BITS_PER_LONG) { + unsigned word = msr / BITS_PER_LONG; + msr_bitmap[word] = (mode & MSR_BITMAP_MODE_X2APIC_APICV) ? 0 : ~0; + msr_bitmap[word + (0x800 / sizeof(long))] = ~0; + } + + if (mode & MSR_BITMAP_MODE_X2APIC) { + /* + * TPR reads and writes can be virtualized even if virtual interrupt + * delivery is not in use. + */ + vmx_disable_intercept_for_msr(msr_bitmap, X2APIC_MSR(APIC_TASKPRI), MSR_TYPE_RW); + if (mode & MSR_BITMAP_MODE_X2APIC_APICV) { + vmx_enable_intercept_for_msr(msr_bitmap, X2APIC_MSR(APIC_TMCCT), MSR_TYPE_R); + vmx_disable_intercept_for_msr(msr_bitmap, X2APIC_MSR(APIC_EOI), MSR_TYPE_W); + vmx_disable_intercept_for_msr(msr_bitmap, X2APIC_MSR(APIC_SELF_IPI), MSR_TYPE_W); + } } } +static void vmx_update_msr_bitmap(struct kvm_vcpu *vcpu) +{ + struct vcpu_vmx *vmx = to_vmx(vcpu); + unsigned long *msr_bitmap = vmx->vmcs01.msr_bitmap; + u8 mode = vmx_msr_bitmap_mode(vcpu); + u8 changed = mode ^ vmx->msr_bitmap_mode; + + if (!changed) + return; + + vmx_set_intercept_for_msr(msr_bitmap, MSR_KERNEL_GS_BASE, MSR_TYPE_RW, + !(mode & MSR_BITMAP_MODE_LM)); + + if (changed & (MSR_BITMAP_MODE_X2APIC | MSR_BITMAP_MODE_X2APIC_APICV)) + vmx_update_msr_bitmap_x2apic(msr_bitmap, mode); + + vmx->msr_bitmap_mode = mode; +} + static bool vmx_get_enable_apicv(struct kvm_vcpu *vcpu) { return enable_apicv; @@ -5274,7 +5468,7 @@ static void vmx_refresh_apicv_exec_ctrl(struct kvm_vcpu *vcpu) } if (cpu_has_vmx_msr_bitmap()) - vmx_set_msr_bitmap(vcpu); + vmx_update_msr_bitmap(vcpu); } static u32 vmx_exec_control(struct vcpu_vmx *vmx) @@ -5461,7 +5655,7 @@ static void vmx_vcpu_setup(struct vcpu_vmx *vmx) vmcs_write64(VMWRITE_BITMAP, __pa(vmx_vmwrite_bitmap)); } if (cpu_has_vmx_msr_bitmap()) - vmcs_write64(MSR_BITMAP, __pa(vmx_msr_bitmap_legacy)); + vmcs_write64(MSR_BITMAP, __pa(vmx->vmcs01.msr_bitmap)); vmcs_write64(VMCS_LINK_POINTER, -1ull); /* 22.3.1.5 */ @@ -5539,6 +5733,8 @@ static void vmx_vcpu_setup(struct vcpu_vmx *vmx) ++vmx->nmsrs; } + if (boot_cpu_has(X86_FEATURE_ARCH_CAPABILITIES)) + rdmsrl(MSR_IA32_ARCH_CAPABILITIES, vmx->arch_capabilities); vm_exit_controls_init(vmx, vmcs_config.vmexit_ctrl); @@ -5567,6 +5763,7 @@ static void vmx_vcpu_reset(struct kvm_vcpu *vcpu, bool init_event) u64 cr0; vmx->rmode.vm86_active = 0; + vmx->spec_ctrl = 0; vmx->vcpu.arch.regs[VCPU_REGS_RDX] = get_rdx_init_val(); kvm_set_cr8(vcpu, 0); @@ -6744,7 +6941,7 @@ void vmx_enable_tdp(void) static __init int hardware_setup(void) { - int r = -ENOMEM, i, msr; + int r = -ENOMEM, i; rdmsrl_safe(MSR_EFER, &host_efer); @@ -6764,9 +6961,6 @@ static __init int hardware_setup(void) memset(vmx_io_bitmap_b, 0xff, PAGE_SIZE); - memset(vmx_msr_bitmap_legacy, 0xff, PAGE_SIZE); - memset(vmx_msr_bitmap_longmode, 0xff, PAGE_SIZE); - if (setup_vmcs_config(&vmcs_config) < 0) { r = -EIO; goto out; @@ -6835,42 +7029,8 @@ static __init int hardware_setup(void) kvm_tsc_scaling_ratio_frac_bits = 48; } - vmx_disable_intercept_for_msr(MSR_FS_BASE, false); - vmx_disable_intercept_for_msr(MSR_GS_BASE, false); - vmx_disable_intercept_for_msr(MSR_KERNEL_GS_BASE, true); - vmx_disable_intercept_for_msr(MSR_IA32_SYSENTER_CS, false); - vmx_disable_intercept_for_msr(MSR_IA32_SYSENTER_ESP, false); - vmx_disable_intercept_for_msr(MSR_IA32_SYSENTER_EIP, false); - - memcpy(vmx_msr_bitmap_legacy_x2apic_apicv, - vmx_msr_bitmap_legacy, PAGE_SIZE); - memcpy(vmx_msr_bitmap_longmode_x2apic_apicv, - vmx_msr_bitmap_longmode, PAGE_SIZE); - memcpy(vmx_msr_bitmap_legacy_x2apic, - vmx_msr_bitmap_legacy, PAGE_SIZE); - memcpy(vmx_msr_bitmap_longmode_x2apic, - vmx_msr_bitmap_longmode, PAGE_SIZE); - set_bit(0, vmx_vpid_bitmap); /* 0 is reserved for host */ - for (msr = 0x800; msr <= 0x8ff; msr++) { - if (msr == 0x839 /* TMCCT */) - continue; - vmx_disable_intercept_msr_x2apic(msr, MSR_TYPE_R, true); - } - - /* - * TPR reads and writes can be virtualized even if virtual interrupt - * delivery is not in use. - */ - vmx_disable_intercept_msr_x2apic(0x808, MSR_TYPE_W, true); - vmx_disable_intercept_msr_x2apic(0x808, MSR_TYPE_R | MSR_TYPE_W, false); - - /* EOI */ - vmx_disable_intercept_msr_x2apic(0x80b, MSR_TYPE_W, true); - /* SELF-IPI */ - vmx_disable_intercept_msr_x2apic(0x83f, MSR_TYPE_W, true); - if (enable_ept) vmx_enable_tdp(); else @@ -6974,94 +7134,6 @@ static int handle_monitor(struct kvm_vcpu *vcpu) } /* - * To run an L2 guest, we need a vmcs02 based on the L1-specified vmcs12. - * We could reuse a single VMCS for all the L2 guests, but we also want the - * option to allocate a separate vmcs02 for each separate loaded vmcs12 - this - * allows keeping them loaded on the processor, and in the future will allow - * optimizations where prepare_vmcs02 doesn't need to set all the fields on - * every entry if they never change. - * So we keep, in vmx->nested.vmcs02_pool, a cache of size VMCS02_POOL_SIZE - * (>=0) with a vmcs02 for each recently loaded vmcs12s, most recent first. - * - * The following functions allocate and free a vmcs02 in this pool. - */ - -/* Get a VMCS from the pool to use as vmcs02 for the current vmcs12. */ -static struct loaded_vmcs *nested_get_current_vmcs02(struct vcpu_vmx *vmx) -{ - struct vmcs02_list *item; - list_for_each_entry(item, &vmx->nested.vmcs02_pool, list) - if (item->vmptr == vmx->nested.current_vmptr) { - list_move(&item->list, &vmx->nested.vmcs02_pool); - return &item->vmcs02; - } - - if (vmx->nested.vmcs02_num >= max(VMCS02_POOL_SIZE, 1)) { - /* Recycle the least recently used VMCS. */ - item = list_last_entry(&vmx->nested.vmcs02_pool, - struct vmcs02_list, list); - item->vmptr = vmx->nested.current_vmptr; - list_move(&item->list, &vmx->nested.vmcs02_pool); - return &item->vmcs02; - } - - /* Create a new VMCS */ - item = kzalloc(sizeof(struct vmcs02_list), GFP_KERNEL); - if (!item) - return NULL; - item->vmcs02.vmcs = alloc_vmcs(); - item->vmcs02.shadow_vmcs = NULL; - if (!item->vmcs02.vmcs) { - kfree(item); - return NULL; - } - loaded_vmcs_init(&item->vmcs02); - item->vmptr = vmx->nested.current_vmptr; - list_add(&(item->list), &(vmx->nested.vmcs02_pool)); - vmx->nested.vmcs02_num++; - return &item->vmcs02; -} - -/* Free and remove from pool a vmcs02 saved for a vmcs12 (if there is one) */ -static void nested_free_vmcs02(struct vcpu_vmx *vmx, gpa_t vmptr) -{ - struct vmcs02_list *item; - list_for_each_entry(item, &vmx->nested.vmcs02_pool, list) - if (item->vmptr == vmptr) { - free_loaded_vmcs(&item->vmcs02); - list_del(&item->list); - kfree(item); - vmx->nested.vmcs02_num--; - return; - } -} - -/* - * Free all VMCSs saved for this vcpu, except the one pointed by - * vmx->loaded_vmcs. We must be running L1, so vmx->loaded_vmcs - * must be &vmx->vmcs01. - */ -static void nested_free_all_saved_vmcss(struct vcpu_vmx *vmx) -{ - struct vmcs02_list *item, *n; - - WARN_ON(vmx->loaded_vmcs != &vmx->vmcs01); - list_for_each_entry_safe(item, n, &vmx->nested.vmcs02_pool, list) { - /* - * Something will leak if the above WARN triggers. Better than - * a use-after-free. - */ - if (vmx->loaded_vmcs == &item->vmcs02) - continue; - - free_loaded_vmcs(&item->vmcs02); - list_del(&item->list); - kfree(item); - vmx->nested.vmcs02_num--; - } -} - -/* * The following 3 functions, nested_vmx_succeed()/failValid()/failInvalid(), * set the success or error code of an emulated VMX instruction, as specified * by Vol 2B, VMX Instruction Reference, "Conventions". @@ -7241,13 +7313,11 @@ static int enter_vmx_operation(struct kvm_vcpu *vcpu) { struct vcpu_vmx *vmx = to_vmx(vcpu); struct vmcs *shadow_vmcs; + int r; - if (cpu_has_vmx_msr_bitmap()) { - vmx->nested.msr_bitmap = - (unsigned long *)__get_free_page(GFP_KERNEL); - if (!vmx->nested.msr_bitmap) - goto out_msr_bitmap; - } + r = alloc_loaded_vmcs(&vmx->nested.vmcs02); + if (r < 0) + goto out_vmcs02; vmx->nested.cached_vmcs12 = kmalloc(VMCS12_SIZE, GFP_KERNEL); if (!vmx->nested.cached_vmcs12) @@ -7264,9 +7334,6 @@ static int enter_vmx_operation(struct kvm_vcpu *vcpu) vmx->vmcs01.shadow_vmcs = shadow_vmcs; } - INIT_LIST_HEAD(&(vmx->nested.vmcs02_pool)); - vmx->nested.vmcs02_num = 0; - hrtimer_init(&vmx->nested.preemption_timer, CLOCK_MONOTONIC, HRTIMER_MODE_REL_PINNED); vmx->nested.preemption_timer.function = vmx_preemption_timer_fn; @@ -7278,9 +7345,9 @@ out_shadow_vmcs: kfree(vmx->nested.cached_vmcs12); out_cached_vmcs12: - free_page((unsigned long)vmx->nested.msr_bitmap); + free_loaded_vmcs(&vmx->nested.vmcs02); -out_msr_bitmap: +out_vmcs02: return -ENOMEM; } @@ -7423,10 +7490,6 @@ static void free_nested(struct vcpu_vmx *vmx) free_vpid(vmx->nested.vpid02); vmx->nested.posted_intr_nv = -1; vmx->nested.current_vmptr = -1ull; - if (vmx->nested.msr_bitmap) { - free_page((unsigned long)vmx->nested.msr_bitmap); - vmx->nested.msr_bitmap = NULL; - } if (enable_shadow_vmcs) { vmx_disable_shadow_vmcs(vmx); vmcs_clear(vmx->vmcs01.shadow_vmcs); @@ -7434,7 +7497,7 @@ static void free_nested(struct vcpu_vmx *vmx) vmx->vmcs01.shadow_vmcs = NULL; } kfree(vmx->nested.cached_vmcs12); - /* Unpin physical memory we referred to in current vmcs02 */ + /* Unpin physical memory we referred to in the vmcs02 */ if (vmx->nested.apic_access_page) { kvm_release_page_dirty(vmx->nested.apic_access_page); vmx->nested.apic_access_page = NULL; @@ -7450,7 +7513,7 @@ static void free_nested(struct vcpu_vmx *vmx) vmx->nested.pi_desc = NULL; } - nested_free_all_saved_vmcss(vmx); + free_loaded_vmcs(&vmx->nested.vmcs02); } /* Emulate the VMXOFF instruction */ @@ -7493,8 +7556,6 @@ static int handle_vmclear(struct kvm_vcpu *vcpu) vmptr + offsetof(struct vmcs12, launch_state), &zero, sizeof(zero)); - nested_free_vmcs02(vmx, vmptr); - nested_vmx_succeed(vcpu); return kvm_skip_emulated_instruction(vcpu); } @@ -8406,10 +8467,11 @@ static bool nested_vmx_exit_reflected(struct kvm_vcpu *vcpu, u32 exit_reason) /* * The host physical addresses of some pages of guest memory - * are loaded into VMCS02 (e.g. L1's Virtual APIC Page). The CPU - * may write to these pages via their host physical address while - * L2 is running, bypassing any address-translation-based dirty - * tracking (e.g. EPT write protection). + * are loaded into the vmcs02 (e.g. vmcs12's Virtual APIC + * Page). The CPU may write to these pages via their host + * physical address while L2 is running, bypassing any + * address-translation-based dirty tracking (e.g. EPT write + * protection). * * Mark them dirty on every exit from L2 to prevent them from * getting out of sync with dirty tracking. @@ -8943,7 +9005,7 @@ static void vmx_set_virtual_x2apic_mode(struct kvm_vcpu *vcpu, bool set) } vmcs_write32(SECONDARY_VM_EXEC_CONTROL, sec_exec_control); - vmx_set_msr_bitmap(vcpu); + vmx_update_msr_bitmap(vcpu); } static void vmx_set_apic_access_page_addr(struct kvm_vcpu *vcpu, hpa_t hpa) @@ -9373,6 +9435,15 @@ static void __noclone vmx_vcpu_run(struct kvm_vcpu *vcpu) vmx_arm_hv_timer(vcpu); + /* + * If this vCPU has touched SPEC_CTRL, restore the guest's value if + * it's non-zero. Since vmentry is serialising on affected CPUs, there + * is no need to worry about the conditional branch over the wrmsr + * being speculatively taken. + */ + if (vmx->spec_ctrl) + wrmsrl(MSR_IA32_SPEC_CTRL, vmx->spec_ctrl); + vmx->__launched = vmx->loaded_vmcs->launched; asm( /* Store host registers */ @@ -9491,6 +9562,27 @@ static void __noclone vmx_vcpu_run(struct kvm_vcpu *vcpu) #endif ); + /* + * We do not use IBRS in the kernel. If this vCPU has used the + * SPEC_CTRL MSR it may have left it on; save the value and + * turn it off. This is much more efficient than blindly adding + * it to the atomic save/restore list. Especially as the former + * (Saving guest MSRs on vmexit) doesn't even exist in KVM. + * + * For non-nested case: + * If the L01 MSR bitmap does not intercept the MSR, then we need to + * save it. + * + * For nested case: + * If the L02 MSR bitmap does not intercept the MSR, then we need to + * save it. + */ + if (!msr_write_intercepted(vcpu, MSR_IA32_SPEC_CTRL)) + rdmsrl(MSR_IA32_SPEC_CTRL, vmx->spec_ctrl); + + if (vmx->spec_ctrl) + wrmsrl(MSR_IA32_SPEC_CTRL, 0); + /* Eliminate branch target predictions from guest mode */ vmexit_fill_RSB(); @@ -9604,6 +9696,7 @@ static struct kvm_vcpu *vmx_create_vcpu(struct kvm *kvm, unsigned int id) { int err; struct vcpu_vmx *vmx = kmem_cache_zalloc(kvm_vcpu_cache, GFP_KERNEL); + unsigned long *msr_bitmap; int cpu; if (!vmx) @@ -9636,13 +9729,20 @@ static struct kvm_vcpu *vmx_create_vcpu(struct kvm *kvm, unsigned int id) if (!vmx->guest_msrs) goto free_pml; - vmx->loaded_vmcs = &vmx->vmcs01; - vmx->loaded_vmcs->vmcs = alloc_vmcs(); - vmx->loaded_vmcs->shadow_vmcs = NULL; - if (!vmx->loaded_vmcs->vmcs) + err = alloc_loaded_vmcs(&vmx->vmcs01); + if (err < 0) goto free_msrs; - loaded_vmcs_init(vmx->loaded_vmcs); + msr_bitmap = vmx->vmcs01.msr_bitmap; + vmx_disable_intercept_for_msr(msr_bitmap, MSR_FS_BASE, MSR_TYPE_RW); + vmx_disable_intercept_for_msr(msr_bitmap, MSR_GS_BASE, MSR_TYPE_RW); + vmx_disable_intercept_for_msr(msr_bitmap, MSR_KERNEL_GS_BASE, MSR_TYPE_RW); + vmx_disable_intercept_for_msr(msr_bitmap, MSR_IA32_SYSENTER_CS, MSR_TYPE_RW); + vmx_disable_intercept_for_msr(msr_bitmap, MSR_IA32_SYSENTER_ESP, MSR_TYPE_RW); + vmx_disable_intercept_for_msr(msr_bitmap, MSR_IA32_SYSENTER_EIP, MSR_TYPE_RW); + vmx->msr_bitmap_mode = 0; + + vmx->loaded_vmcs = &vmx->vmcs01; cpu = get_cpu(); vmx_vcpu_load(&vmx->vcpu, cpu); vmx->vcpu.cpu = cpu; @@ -10105,10 +10205,25 @@ static inline bool nested_vmx_merge_msr_bitmap(struct kvm_vcpu *vcpu, int msr; struct page *page; unsigned long *msr_bitmap_l1; - unsigned long *msr_bitmap_l0 = to_vmx(vcpu)->nested.msr_bitmap; + unsigned long *msr_bitmap_l0 = to_vmx(vcpu)->nested.vmcs02.msr_bitmap; + /* + * pred_cmd & spec_ctrl are trying to verify two things: + * + * 1. L0 gave a permission to L1 to actually passthrough the MSR. This + * ensures that we do not accidentally generate an L02 MSR bitmap + * from the L12 MSR bitmap that is too permissive. + * 2. That L1 or L2s have actually used the MSR. This avoids + * unnecessarily merging of the bitmap if the MSR is unused. This + * works properly because we only update the L01 MSR bitmap lazily. + * So even if L0 should pass L1 these MSRs, the L01 bitmap is only + * updated to reflect this when L1 (or its L2s) actually write to + * the MSR. + */ + bool pred_cmd = msr_write_intercepted_l01(vcpu, MSR_IA32_PRED_CMD); + bool spec_ctrl = msr_write_intercepted_l01(vcpu, MSR_IA32_SPEC_CTRL); - /* This shortcut is ok because we support only x2APIC MSRs so far. */ - if (!nested_cpu_has_virt_x2apic_mode(vmcs12)) + if (!nested_cpu_has_virt_x2apic_mode(vmcs12) && + !pred_cmd && !spec_ctrl) return false; page = kvm_vcpu_gpa_to_page(vcpu, vmcs12->msr_bitmap); @@ -10141,6 +10256,19 @@ static inline bool nested_vmx_merge_msr_bitmap(struct kvm_vcpu *vcpu, MSR_TYPE_W); } } + + if (spec_ctrl) + nested_vmx_disable_intercept_for_msr( + msr_bitmap_l1, msr_bitmap_l0, + MSR_IA32_SPEC_CTRL, + MSR_TYPE_R | MSR_TYPE_W); + + if (pred_cmd) + nested_vmx_disable_intercept_for_msr( + msr_bitmap_l1, msr_bitmap_l0, + MSR_IA32_PRED_CMD, + MSR_TYPE_W); + kunmap(page); kvm_release_page_clean(page); @@ -10682,6 +10810,9 @@ static int prepare_vmcs02(struct kvm_vcpu *vcpu, struct vmcs12 *vmcs12, if (kvm_has_tsc_control) decache_tsc_multiplier(vmx); + if (cpu_has_vmx_msr_bitmap()) + vmcs_write64(MSR_BITMAP, __pa(vmx->nested.vmcs02.msr_bitmap)); + if (enable_vpid) { /* * There is no direct mapping between vpid02 and vpid12, the @@ -10903,20 +11034,15 @@ static int enter_vmx_non_root_mode(struct kvm_vcpu *vcpu, bool from_vmentry) { struct vcpu_vmx *vmx = to_vmx(vcpu); struct vmcs12 *vmcs12 = get_vmcs12(vcpu); - struct loaded_vmcs *vmcs02; u32 msr_entry_idx; u32 exit_qual; - vmcs02 = nested_get_current_vmcs02(vmx); - if (!vmcs02) - return -ENOMEM; - enter_guest_mode(vcpu); if (!(vmcs12->vm_entry_controls & VM_ENTRY_LOAD_DEBUG_CONTROLS)) vmx->nested.vmcs01_debugctl = vmcs_read64(GUEST_IA32_DEBUGCTL); - vmx_switch_vmcs(vcpu, vmcs02); + vmx_switch_vmcs(vcpu, &vmx->nested.vmcs02); vmx_segment_cache_clear(vmx); if (prepare_vmcs02(vcpu, vmcs12, from_vmentry, &exit_qual)) { @@ -11485,7 +11611,7 @@ static void load_vmcs12_host_state(struct kvm_vcpu *vcpu, vmcs_write64(GUEST_IA32_DEBUGCTL, 0); if (cpu_has_vmx_msr_bitmap()) - vmx_set_msr_bitmap(vcpu); + vmx_update_msr_bitmap(vcpu); if (nested_vmx_load_msr(vcpu, vmcs12->vm_exit_msr_load_addr, vmcs12->vm_exit_msr_load_count)) @@ -11534,10 +11660,6 @@ static void nested_vmx_vmexit(struct kvm_vcpu *vcpu, u32 exit_reason, vm_exit_controls_reset_shadow(vmx); vmx_segment_cache_clear(vmx); - /* if no vmcs02 cache requested, remove the one we used */ - if (VMCS02_POOL_SIZE == 0) - nested_free_vmcs02(vmx, vmx->nested.current_vmptr); - /* Update any VMCS fields that might have changed while L2 ran */ vmcs_write32(VM_EXIT_MSR_LOAD_COUNT, vmx->msr_autoload.nr); vmcs_write32(VM_ENTRY_MSR_LOAD_COUNT, vmx->msr_autoload.nr); diff --git a/arch/x86/kvm/x86.c b/arch/x86/kvm/x86.c index 5040ff9..f9c5171 100644 --- a/arch/x86/kvm/x86.c +++ b/arch/x86/kvm/x86.c @@ -1009,6 +1009,7 @@ static u32 msrs_to_save[] = { #endif MSR_IA32_TSC, MSR_IA32_CR_PAT, MSR_VM_HSAVE_PA, MSR_IA32_FEATURE_CONTROL, MSR_IA32_BNDCFGS, MSR_TSC_AUX, + MSR_IA32_SPEC_CTRL, MSR_IA32_ARCH_CAPABILITIES }; static unsigned num_msrs_to_save; diff --git a/arch/x86/lib/getuser.S b/arch/x86/lib/getuser.S index c97d935..49b167f 100644 --- a/arch/x86/lib/getuser.S +++ b/arch/x86/lib/getuser.S @@ -40,6 +40,8 @@ ENTRY(__get_user_1) mov PER_CPU_VAR(current_task), %_ASM_DX cmp TASK_addr_limit(%_ASM_DX),%_ASM_AX jae bad_get_user + sbb %_ASM_DX, %_ASM_DX /* array_index_mask_nospec() */ + and %_ASM_DX, %_ASM_AX ASM_STAC 1: movzbl (%_ASM_AX),%edx xor %eax,%eax @@ -54,6 +56,8 @@ ENTRY(__get_user_2) mov PER_CPU_VAR(current_task), %_ASM_DX cmp TASK_addr_limit(%_ASM_DX),%_ASM_AX jae bad_get_user + sbb %_ASM_DX, %_ASM_DX /* array_index_mask_nospec() */ + and %_ASM_DX, %_ASM_AX ASM_STAC 2: movzwl -1(%_ASM_AX),%edx xor %eax,%eax @@ -68,6 +72,8 @@ ENTRY(__get_user_4) mov PER_CPU_VAR(current_task), %_ASM_DX cmp TASK_addr_limit(%_ASM_DX),%_ASM_AX jae bad_get_user + sbb %_ASM_DX, %_ASM_DX /* array_index_mask_nospec() */ + and %_ASM_DX, %_ASM_AX ASM_STAC 3: movl -3(%_ASM_AX),%edx xor %eax,%eax @@ -83,6 +89,8 @@ ENTRY(__get_user_8) mov PER_CPU_VAR(current_task), %_ASM_DX cmp TASK_addr_limit(%_ASM_DX),%_ASM_AX jae bad_get_user + sbb %_ASM_DX, %_ASM_DX /* array_index_mask_nospec() */ + and %_ASM_DX, %_ASM_AX ASM_STAC 4: movq -7(%_ASM_AX),%rdx xor %eax,%eax @@ -94,6 +102,8 @@ ENTRY(__get_user_8) mov PER_CPU_VAR(current_task), %_ASM_DX cmp TASK_addr_limit(%_ASM_DX),%_ASM_AX jae bad_get_user_8 + sbb %_ASM_DX, %_ASM_DX /* array_index_mask_nospec() */ + and %_ASM_DX, %_ASM_AX ASM_STAC 4: movl -7(%_ASM_AX),%edx 5: movl -3(%_ASM_AX),%ecx diff --git a/arch/x86/lib/usercopy_32.c b/arch/x86/lib/usercopy_32.c index 1b377f7..7add8ba 100644 --- a/arch/x86/lib/usercopy_32.c +++ b/arch/x86/lib/usercopy_32.c @@ -331,12 +331,12 @@ do { \ unsigned long __copy_user_ll(void *to, const void *from, unsigned long n) { - stac(); + __uaccess_begin_nospec(); if (movsl_is_ok(to, from, n)) __copy_user(to, from, n); else n = __copy_user_intel(to, from, n); - clac(); + __uaccess_end(); return n; } EXPORT_SYMBOL(__copy_user_ll); @@ -344,7 +344,7 @@ EXPORT_SYMBOL(__copy_user_ll); unsigned long __copy_from_user_ll_nocache_nozero(void *to, const void __user *from, unsigned long n) { - stac(); + __uaccess_begin_nospec(); #ifdef CONFIG_X86_INTEL_USERCOPY if (n > 64 && static_cpu_has(X86_FEATURE_XMM2)) n = __copy_user_intel_nocache(to, from, n); @@ -353,7 +353,7 @@ unsigned long __copy_from_user_ll_nocache_nozero(void *to, const void __user *fr #else __copy_user(to, from, n); #endif - clac(); + __uaccess_end(); return n; } EXPORT_SYMBOL(__copy_from_user_ll_nocache_nozero); diff --git a/arch/x86/mm/tlb.c b/arch/x86/mm/tlb.c index 5bfe61a..012d026 100644 --- a/arch/x86/mm/tlb.c +++ b/arch/x86/mm/tlb.c @@ -6,13 +6,14 @@ #include <linux/interrupt.h> #include <linux/export.h> #include <linux/cpu.h> +#include <linux/debugfs.h> #include <asm/tlbflush.h> #include <asm/mmu_context.h> +#include <asm/nospec-branch.h> #include <asm/cache.h> #include <asm/apic.h> #include <asm/uv/uv.h> -#include <linux/debugfs.h> /* * TLB flushing, formerly SMP-only @@ -247,6 +248,27 @@ void switch_mm_irqs_off(struct mm_struct *prev, struct mm_struct *next, } else { u16 new_asid; bool need_flush; + u64 last_ctx_id = this_cpu_read(cpu_tlbstate.last_ctx_id); + + /* + * Avoid user/user BTB poisoning by flushing the branch + * predictor when switching between processes. This stops + * one process from doing Spectre-v2 attacks on another. + * + * As an optimization, flush indirect branches only when + * switching into processes that disable dumping. This + * protects high value processes like gpg, without having + * too high performance overhead. IBPB is *expensive*! + * + * This will not flush branches when switching into kernel + * threads. It will also not flush if we switch to idle + * thread and back to the same process. It will flush if we + * switch to a different non-dumpable process. + */ + if (tsk && tsk->mm && + tsk->mm->context.ctx_id != last_ctx_id && + get_dumpable(tsk->mm) != SUID_DUMP_USER) + indirect_branch_prediction_barrier(); if (IS_ENABLED(CONFIG_VMAP_STACK)) { /* @@ -292,6 +314,14 @@ void switch_mm_irqs_off(struct mm_struct *prev, struct mm_struct *next, trace_tlb_flush_rcuidle(TLB_FLUSH_ON_TASK_SWITCH, 0); } + /* + * Record last user mm's context id, so we can avoid + * flushing branch buffer with IBPB if we switch back + * to the same user. + */ + if (next != &init_mm) + this_cpu_write(cpu_tlbstate.last_ctx_id, next->context.ctx_id); + this_cpu_write(cpu_tlbstate.loaded_mm, next); this_cpu_write(cpu_tlbstate.loaded_mm_asid, new_asid); } @@ -369,6 +399,7 @@ void initialize_tlbstate_and_flush(void) write_cr3(build_cr3(mm->pgd, 0)); /* Reinitialize tlbstate. */ + this_cpu_write(cpu_tlbstate.last_ctx_id, mm->context.ctx_id); this_cpu_write(cpu_tlbstate.loaded_mm_asid, 0); this_cpu_write(cpu_tlbstate.next_asid, 1); this_cpu_write(cpu_tlbstate.ctxs[0].ctx_id, mm->context.ctx_id); diff --git a/include/linux/fdtable.h b/include/linux/fdtable.h index 1c65817..41615f3 100644 --- a/include/linux/fdtable.h +++ b/include/linux/fdtable.h @@ -10,6 +10,7 @@ #include <linux/compiler.h> #include <linux/spinlock.h> #include <linux/rcupdate.h> +#include <linux/nospec.h> #include <linux/types.h> #include <linux/init.h> #include <linux/fs.h> @@ -82,8 +83,10 @@ static inline struct file *__fcheck_files(struct files_struct *files, unsigned i { struct fdtable *fdt = rcu_dereference_raw(files->fdt); - if (fd < fdt->max_fds) + if (fd < fdt->max_fds) { + fd = array_index_nospec(fd, fdt->max_fds); return rcu_dereference_raw(fdt->fd[fd]); + } return NULL; } diff --git a/include/linux/init.h b/include/linux/init.h index ea1b311..506a981 100644 --- a/include/linux/init.h +++ b/include/linux/init.h @@ -5,6 +5,13 @@ #include <linux/compiler.h> #include <linux/types.h> +/* Built-in __init functions needn't be compiled with retpoline */ +#if defined(RETPOLINE) && !defined(MODULE) +#define __noretpoline __attribute__((indirect_branch("keep"))) +#else +#define __noretpoline +#endif + /* These macros are used to mark some functions or * initialized data (doesn't apply to uninitialized data) * as `initialization' functions. The kernel can take this @@ -40,7 +47,7 @@ /* These are for everybody (although not all archs will actually discard it in modules) */ -#define __init __section(.init.text) __cold __latent_entropy +#define __init __section(.init.text) __cold __latent_entropy __noretpoline #define __initdata __section(.init.data) #define __initconst __section(.init.rodata) #define __exitdata __section(.exit.data) diff --git a/include/linux/nospec.h b/include/linux/nospec.h new file mode 100644 index 0000000..b99bced --- /dev/null +++ b/include/linux/nospec.h @@ -0,0 +1,72 @@ +// SPDX-License-Identifier: GPL-2.0 +// Copyright(c) 2018 Linus Torvalds. All rights reserved. +// Copyright(c) 2018 Alexei Starovoitov. All rights reserved. +// Copyright(c) 2018 Intel Corporation. All rights reserved. + +#ifndef _LINUX_NOSPEC_H +#define _LINUX_NOSPEC_H + +/** + * array_index_mask_nospec() - generate a ~0 mask when index < size, 0 otherwise + * @index: array element index + * @size: number of elements in array + * + * When @index is out of bounds (@index >= @size), the sign bit will be + * set. Extend the sign bit to all bits and invert, giving a result of + * zero for an out of bounds index, or ~0 if within bounds [0, @size). + */ +#ifndef array_index_mask_nospec +static inline unsigned long array_index_mask_nospec(unsigned long index, + unsigned long size) +{ + /* + * Warn developers about inappropriate array_index_nospec() usage. + * + * Even if the CPU speculates past the WARN_ONCE branch, the + * sign bit of @index is taken into account when generating the + * mask. + * + * This warning is compiled out when the compiler can infer that + * @index and @size are less than LONG_MAX. + */ + if (WARN_ONCE(index > LONG_MAX || size > LONG_MAX, + "array_index_nospec() limited to range of [0, LONG_MAX]\n")) + return 0; + + /* + * Always calculate and emit the mask even if the compiler + * thinks the mask is not needed. The compiler does not take + * into account the value of @index under speculation. + */ + OPTIMIZER_HIDE_VAR(index); + return ~(long)(index | (size - 1UL - index)) >> (BITS_PER_LONG - 1); +} +#endif + +/* + * array_index_nospec - sanitize an array index after a bounds check + * + * For a code sequence like: + * + * if (index < size) { + * index = array_index_nospec(index, size); + * val = array[index]; + * } + * + * ...if the CPU speculates past the bounds check then + * array_index_nospec() will clamp the index within the range of [0, + * size). + */ +#define array_index_nospec(index, size) \ +({ \ + typeof(index) _i = (index); \ + typeof(size) _s = (size); \ + unsigned long _mask = array_index_mask_nospec(_i, _s); \ + \ + BUILD_BUG_ON(sizeof(_i) > sizeof(long)); \ + BUILD_BUG_ON(sizeof(_s) > sizeof(long)); \ + \ + _i &= _mask; \ + _i; \ +}) +#endif /* _LINUX_NOSPEC_H */ diff --git a/net/wireless/nl80211.c b/net/wireless/nl80211.c index ab0c687..9c0dcc8 100644 --- a/net/wireless/nl80211.c +++ b/net/wireless/nl80211.c @@ -16,6 +16,7 @@ #include <linux/nl80211.h> #include <linux/rtnetlink.h> #include <linux/netlink.h> +#include <linux/nospec.h> #include <linux/etherdevice.h> #include <net/net_namespace.h> #include <net/genetlink.h> @@ -2080,20 +2081,22 @@ static const struct nla_policy txq_params_policy[NL80211_TXQ_ATTR_MAX + 1] = { static int parse_txq_params(struct nlattr *tb[], struct ieee80211_txq_params *txq_params) { + u8 ac; + if (!tb[NL80211_TXQ_ATTR_AC] || !tb[NL80211_TXQ_ATTR_TXOP] || !tb[NL80211_TXQ_ATTR_CWMIN] || !tb[NL80211_TXQ_ATTR_CWMAX] || !tb[NL80211_TXQ_ATTR_AIFS]) return -EINVAL; - txq_params->ac = nla_get_u8(tb[NL80211_TXQ_ATTR_AC]); + ac = nla_get_u8(tb[NL80211_TXQ_ATTR_AC]); txq_params->txop = nla_get_u16(tb[NL80211_TXQ_ATTR_TXOP]); txq_params->cwmin = nla_get_u16(tb[NL80211_TXQ_ATTR_CWMIN]); txq_params->cwmax = nla_get_u16(tb[NL80211_TXQ_ATTR_CWMAX]); txq_params->aifs = nla_get_u8(tb[NL80211_TXQ_ATTR_AIFS]); - if (txq_params->ac >= NL80211_NUM_ACS) + if (ac >= NL80211_NUM_ACS) return -EINVAL; - + txq_params->ac = array_index_nospec(ac, NL80211_NUM_ACS); return 0; } diff --git a/tools/objtool/check.c b/tools/objtool/check.c index 524becf..b00b189 100644 --- a/tools/objtool/check.c +++ b/tools/objtool/check.c @@ -544,18 +544,14 @@ 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); + + if (!insn->call_dest && !insn->ignore) { + WARN_FUNC("unsupported intra-function call", + insn->sec, insn->offset); + WARN("If this is a retpoline, please patch it in with alternatives and annotate it with ANNOTATE_NOSPEC_ALTERNATIVE."); return -1; } -#endif + } else if (rela->sym->type == STT_SECTION) { insn->call_dest = find_symbol_by_offset(rela->sym->sec, rela->addend+4); @@ -599,7 +595,7 @@ static int handle_group_alt(struct objtool_file *file, struct instruction *orig_insn, struct instruction **new_insn) { - struct instruction *last_orig_insn, *last_new_insn, *insn, *fake_jump; + struct instruction *last_orig_insn, *last_new_insn, *insn, *fake_jump = NULL; unsigned long dest_off; last_orig_insn = NULL; @@ -615,28 +611,30 @@ static int handle_group_alt(struct objtool_file *file, last_orig_insn = insn; } - if (!next_insn_same_sec(file, last_orig_insn)) { - WARN("%s: don't know how to handle alternatives at end of section", - special_alt->orig_sec->name); - return -1; - } - - fake_jump = malloc(sizeof(*fake_jump)); - if (!fake_jump) { - WARN("malloc failed"); - return -1; + if (next_insn_same_sec(file, last_orig_insn)) { + fake_jump = malloc(sizeof(*fake_jump)); + if (!fake_jump) { + WARN("malloc failed"); + return -1; + } + memset(fake_jump, 0, sizeof(*fake_jump)); + INIT_LIST_HEAD(&fake_jump->alts); + clear_insn_state(&fake_jump->state); + + fake_jump->sec = special_alt->new_sec; + fake_jump->offset = -1; + fake_jump->type = INSN_JUMP_UNCONDITIONAL; + fake_jump->jump_dest = list_next_entry(last_orig_insn, list); + fake_jump->ignore = true; } - memset(fake_jump, 0, sizeof(*fake_jump)); - INIT_LIST_HEAD(&fake_jump->alts); - clear_insn_state(&fake_jump->state); - - fake_jump->sec = special_alt->new_sec; - fake_jump->offset = -1; - fake_jump->type = INSN_JUMP_UNCONDITIONAL; - fake_jump->jump_dest = list_next_entry(last_orig_insn, list); - fake_jump->ignore = true; if (!special_alt->new_len) { + if (!fake_jump) { + WARN("%s: empty alternative at end of section", + special_alt->orig_sec->name); + return -1; + } + *new_insn = fake_jump; return 0; } @@ -649,6 +647,8 @@ static int handle_group_alt(struct objtool_file *file, last_new_insn = insn; + insn->ignore = orig_insn->ignore_alts; + if (insn->type != INSN_JUMP_CONDITIONAL && insn->type != INSN_JUMP_UNCONDITIONAL) continue; @@ -657,8 +657,14 @@ static int handle_group_alt(struct objtool_file *file, continue; dest_off = insn->offset + insn->len + insn->immediate; - if (dest_off == special_alt->new_off + special_alt->new_len) + if (dest_off == special_alt->new_off + special_alt->new_len) { + if (!fake_jump) { + WARN("%s: alternative jump to end of section", + special_alt->orig_sec->name); + return -1; + } insn->jump_dest = fake_jump; + } if (!insn->jump_dest) { WARN_FUNC("can't find alternative jump destination", @@ -673,7 +679,8 @@ static int handle_group_alt(struct objtool_file *file, return -1; } - list_add(&fake_jump->list, &last_new_insn->list); + if (fake_jump) + list_add(&fake_jump->list, &last_new_insn->list); return 0; } @@ -730,10 +737,6 @@ 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, @@ -1090,11 +1093,11 @@ static int decode_sections(struct objtool_file *file) if (ret) return ret; - ret = add_call_destinations(file); + ret = add_special_section_alts(file); if (ret) return ret; - ret = add_special_section_alts(file); + ret = add_call_destinations(file); if (ret) return ret; @@ -1721,10 +1724,12 @@ static int validate_branch(struct objtool_file *file, struct instruction *first, insn->visited = true; - list_for_each_entry(alt, &insn->alts, list) { - ret = validate_branch(file, alt->insn, state); - if (ret) - return 1; + if (!insn->ignore_alts) { + list_for_each_entry(alt, &insn->alts, list) { + ret = validate_branch(file, alt->insn, state); + if (ret) + return 1; + } } switch (insn->type) { diff --git a/tools/objtool/orc_gen.c b/tools/objtool/orc_gen.c index e61fe70..18384d9 100644 --- a/tools/objtool/orc_gen.c +++ b/tools/objtool/orc_gen.c @@ -98,6 +98,11 @@ static int create_orc_entry(struct section *u_sec, struct section *ip_relasec, struct orc_entry *orc; struct rela *rela; + if (!insn_sec->sym) { + WARN("missing symbol for section %s", insn_sec->name); + return -1; + } + /* populate ORC data */ orc = (struct orc_entry *)u_sec->data->d_buf + idx; memcpy(orc, o, sizeof(*orc)); |