diff options
Diffstat (limited to 'arch/x86/entry')
-rw-r--r-- | arch/x86/entry/calling.h | 38 | ||||
-rw-r--r-- | arch/x86/entry/common.c | 30 | ||||
-rw-r--r-- | arch/x86/entry/entry_32.S | 237 | ||||
-rw-r--r-- | arch/x86/entry/entry_64.S | 228 | ||||
-rw-r--r-- | arch/x86/entry/syscall_64.c | 25 | ||||
-rw-r--r-- | arch/x86/entry/syscalls/syscall_32.tbl | 6 | ||||
-rw-r--r-- | arch/x86/entry/syscalls/syscall_64.tbl | 2 | ||||
-rw-r--r-- | arch/x86/entry/syscalls/syscalltbl.sh | 35 | ||||
-rw-r--r-- | arch/x86/entry/thunk_32.S | 2 | ||||
-rw-r--r-- | arch/x86/entry/thunk_64.S | 9 | ||||
-rw-r--r-- | arch/x86/entry/vdso/Makefile | 23 | ||||
-rw-r--r-- | arch/x86/entry/vdso/vclock_gettime.c | 256 | ||||
-rw-r--r-- | arch/x86/entry/vdso/vdso.lds.S | 2 | ||||
-rw-r--r-- | arch/x86/entry/vdso/vdso32-setup.c | 7 | ||||
-rw-r--r-- | arch/x86/entry/vdso/vdso32/vdso32.lds.S | 2 | ||||
-rw-r--r-- | arch/x86/entry/vdso/vdsox32.lds.S | 1 | ||||
-rw-r--r-- | arch/x86/entry/vdso/vma.c | 4 | ||||
-rw-r--r-- | arch/x86/entry/vsyscall/Makefile | 2 | ||||
-rw-r--r-- | arch/x86/entry/vsyscall/vsyscall_64.c | 41 | ||||
-rw-r--r-- | arch/x86/entry/vsyscall/vsyscall_gtod.c | 83 |
20 files changed, 508 insertions, 525 deletions
diff --git a/arch/x86/entry/calling.h b/arch/x86/entry/calling.h index efb0d1b1f15f..515c0ceeb4a3 100644 --- a/arch/x86/entry/calling.h +++ b/arch/x86/entry/calling.h @@ -172,21 +172,6 @@ For 32-bit we have the following conventions - kernel is built with .endif .endm -/* - * This is a sneaky trick to help the unwinder find pt_regs on the stack. The - * frame pointer is replaced with an encoded pointer to pt_regs. The encoding - * is just setting the LSB, which makes it an invalid stack address and is also - * a signal to the unwinder that it's a pt_regs pointer in disguise. - * - * NOTE: This macro must be used *after* PUSH_AND_CLEAR_REGS because it corrupts - * the original rbp. - */ -.macro ENCODE_FRAME_POINTER ptregs_offset=0 -#ifdef CONFIG_FRAME_POINTER - leaq 1+\ptregs_offset(%rsp), %rbp -#endif -.endm - #ifdef CONFIG_PAGE_TABLE_ISOLATION /* @@ -329,6 +314,23 @@ For 32-bit we have the following conventions - kernel is built with #endif +/* + * Mitigate Spectre v1 for conditional swapgs code paths. + * + * FENCE_SWAPGS_USER_ENTRY is used in the user entry swapgs code path, to + * prevent a speculative swapgs when coming from kernel space. + * + * FENCE_SWAPGS_KERNEL_ENTRY is used in the kernel entry non-swapgs code path, + * to prevent the swapgs from getting speculatively skipped when coming from + * user space. + */ +.macro FENCE_SWAPGS_USER_ENTRY + ALTERNATIVE "", "lfence", X86_FEATURE_FENCE_SWAPGS_USER +.endm +.macro FENCE_SWAPGS_KERNEL_ENTRY + ALTERNATIVE "", "lfence", X86_FEATURE_FENCE_SWAPGS_KERNEL +.endm + .macro STACKLEAK_ERASE_NOCLOBBER #ifdef CONFIG_GCC_PLUGIN_STACKLEAK PUSH_AND_CLEAR_REGS @@ -358,3 +360,9 @@ For 32-bit we have the following conventions - kernel is built with .Lafter_call_\@: #endif .endm + +#ifdef CONFIG_PARAVIRT_XXL +#define GET_CR2_INTO(reg) GET_CR2_INTO_AX ; _ASM_MOV %_ASM_AX, reg +#else +#define GET_CR2_INTO(reg) _ASM_MOV %cr2, reg +#endif diff --git a/arch/x86/entry/common.c b/arch/x86/entry/common.c index 2418804e66b4..3f8e22615812 100644 --- a/arch/x86/entry/common.c +++ b/arch/x86/entry/common.c @@ -72,23 +72,18 @@ static long syscall_trace_enter(struct pt_regs *regs) struct thread_info *ti = current_thread_info(); unsigned long ret = 0; - bool emulated = false; u32 work; if (IS_ENABLED(CONFIG_DEBUG_ENTRY)) BUG_ON(regs != task_pt_regs(current)); - work = READ_ONCE(ti->flags) & _TIF_WORK_SYSCALL_ENTRY; + work = READ_ONCE(ti->flags); - if (unlikely(work & _TIF_SYSCALL_EMU)) - emulated = true; - - if ((emulated || (work & _TIF_SYSCALL_TRACE)) && - tracehook_report_syscall_entry(regs)) - return -1L; - - if (emulated) - return -1L; + if (work & (_TIF_SYSCALL_TRACE | _TIF_SYSCALL_EMU)) { + ret = tracehook_report_syscall_entry(regs); + if (ret || (work & _TIF_SYSCALL_EMU)) + return -1L; + } #ifdef CONFIG_SECCOMP /* @@ -290,15 +285,16 @@ __visible void do_syscall_64(unsigned long nr, struct pt_regs *regs) if (READ_ONCE(ti->flags) & _TIF_WORK_SYSCALL_ENTRY) nr = syscall_trace_enter(regs); - /* - * NB: Native and x32 syscalls are dispatched from the same - * table. The only functional difference is the x32 bit in - * regs->orig_ax, which changes the behavior of some syscalls. - */ - nr &= __SYSCALL_MASK; if (likely(nr < NR_syscalls)) { nr = array_index_nospec(nr, NR_syscalls); regs->ax = sys_call_table[nr](regs); +#ifdef CONFIG_X86_X32_ABI + } else if (likely((nr & __X32_SYSCALL_BIT) && + (nr & ~__X32_SYSCALL_BIT) < X32_NR_syscalls)) { + nr = array_index_nospec(nr & ~__X32_SYSCALL_BIT, + X32_NR_syscalls); + regs->ax = x32_sys_call_table[nr](regs); +#endif } syscall_return_slowpath(regs); diff --git a/arch/x86/entry/entry_32.S b/arch/x86/entry/entry_32.S index 7b23431be5cb..f83ca5aa8b77 100644 --- a/arch/x86/entry/entry_32.S +++ b/arch/x86/entry/entry_32.S @@ -63,11 +63,10 @@ * enough to patch inline, increasing performance. */ -#ifdef CONFIG_PREEMPT +#ifdef CONFIG_PREEMPTION # define preempt_stop(clobbers) DISABLE_INTERRUPTS(clobbers); TRACE_IRQS_OFF #else # define preempt_stop(clobbers) -# define resume_kernel restore_all_kernel #endif .macro TRACE_IRQS_IRET @@ -203,9 +202,104 @@ .Lend_\@: .endm -.macro SAVE_ALL pt_regs_ax=%eax switch_stacks=0 +#define CS_FROM_ENTRY_STACK (1 << 31) +#define CS_FROM_USER_CR3 (1 << 30) +#define CS_FROM_KERNEL (1 << 29) + +.macro FIXUP_FRAME + /* + * The high bits of the CS dword (__csh) are used for CS_FROM_*. + * Clear them in case hardware didn't do this for us. + */ + andl $0x0000ffff, 3*4(%esp) + +#ifdef CONFIG_VM86 + testl $X86_EFLAGS_VM, 4*4(%esp) + jnz .Lfrom_usermode_no_fixup_\@ +#endif + testl $SEGMENT_RPL_MASK, 3*4(%esp) + jnz .Lfrom_usermode_no_fixup_\@ + + orl $CS_FROM_KERNEL, 3*4(%esp) + + /* + * When we're here from kernel mode; the (exception) stack looks like: + * + * 5*4(%esp) - <previous context> + * 4*4(%esp) - flags + * 3*4(%esp) - cs + * 2*4(%esp) - ip + * 1*4(%esp) - orig_eax + * 0*4(%esp) - gs / function + * + * Lets build a 5 entry IRET frame after that, such that struct pt_regs + * is complete and in particular regs->sp is correct. This gives us + * the original 5 enties as gap: + * + * 12*4(%esp) - <previous context> + * 11*4(%esp) - gap / flags + * 10*4(%esp) - gap / cs + * 9*4(%esp) - gap / ip + * 8*4(%esp) - gap / orig_eax + * 7*4(%esp) - gap / gs / function + * 6*4(%esp) - ss + * 5*4(%esp) - sp + * 4*4(%esp) - flags + * 3*4(%esp) - cs + * 2*4(%esp) - ip + * 1*4(%esp) - orig_eax + * 0*4(%esp) - gs / function + */ + + pushl %ss # ss + pushl %esp # sp (points at ss) + addl $6*4, (%esp) # point sp back at the previous context + pushl 6*4(%esp) # flags + pushl 6*4(%esp) # cs + pushl 6*4(%esp) # ip + pushl 6*4(%esp) # orig_eax + pushl 6*4(%esp) # gs / function +.Lfrom_usermode_no_fixup_\@: +.endm + +.macro IRET_FRAME + testl $CS_FROM_KERNEL, 1*4(%esp) + jz .Lfinished_frame_\@ + + /* + * Reconstruct the 3 entry IRET frame right after the (modified) + * regs->sp without lowering %esp in between, such that an NMI in the + * middle doesn't scribble our stack. + */ + pushl %eax + pushl %ecx + movl 5*4(%esp), %eax # (modified) regs->sp + + movl 4*4(%esp), %ecx # flags + movl %ecx, -4(%eax) + + movl 3*4(%esp), %ecx # cs + andl $0x0000ffff, %ecx + movl %ecx, -8(%eax) + + movl 2*4(%esp), %ecx # ip + movl %ecx, -12(%eax) + + movl 1*4(%esp), %ecx # eax + movl %ecx, -16(%eax) + + popl %ecx + lea -16(%eax), %esp + popl %eax +.Lfinished_frame_\@: +.endm + +.macro SAVE_ALL pt_regs_ax=%eax switch_stacks=0 skip_gs=0 cld +.if \skip_gs == 0 PUSH_GS +.endif + FIXUP_FRAME pushl %fs pushl %es pushl %ds @@ -221,13 +315,13 @@ movl %edx, %es movl $(__KERNEL_PERCPU), %edx movl %edx, %fs +.if \skip_gs == 0 SET_KERNEL_GS %edx - +.endif /* Switch to kernel stack if necessary */ .if \switch_stacks > 0 SWITCH_TO_KERNEL_STACK .endif - .endm .macro SAVE_ALL_NMI cr3_reg:req @@ -247,22 +341,6 @@ .Lend_\@: .endm -/* - * This is a sneaky trick to help the unwinder find pt_regs on the stack. The - * frame pointer is replaced with an encoded pointer to pt_regs. The encoding - * is just clearing the MSB, which makes it an invalid stack address and is also - * a signal to the unwinder that it's a pt_regs pointer in disguise. - * - * NOTE: This macro must be used *after* SAVE_ALL because it corrupts the - * original rbp. - */ -.macro ENCODE_FRAME_POINTER -#ifdef CONFIG_FRAME_POINTER - mov %esp, %ebp - andl $0x7fffffff, %ebp -#endif -.endm - .macro RESTORE_INT_REGS popl %ebx popl %ecx @@ -375,9 +453,6 @@ * switch to it before we do any copying. */ -#define CS_FROM_ENTRY_STACK (1 << 31) -#define CS_FROM_USER_CR3 (1 << 30) - .macro SWITCH_TO_KERNEL_STACK ALTERNATIVE "", "jmp .Lend_\@", X86_FEATURE_XENPV @@ -391,13 +466,6 @@ * that register for the time this macro runs */ - /* - * The high bits of the CS dword (__csh) are used for - * CS_FROM_ENTRY_STACK and CS_FROM_USER_CR3. Clear them in case - * hardware didn't do this for us. - */ - andl $(0x0000ffff), PT_CS(%esp) - /* Are we on the entry stack? Bail out if not! */ movl PER_CPU_VAR(cpu_entry_area), %ecx addl $CPU_ENTRY_AREA_entry_stack + SIZEOF_entry_stack, %ecx @@ -755,7 +823,7 @@ ret_from_intr: andl $SEGMENT_RPL_MASK, %eax #endif cmpl $USER_RPL, %eax - jb resume_kernel # not returning to v8086 or userspace + jb restore_all_kernel # not returning to v8086 or userspace ENTRY(resume_userspace) DISABLE_INTERRUPTS(CLBR_ANY) @@ -765,18 +833,6 @@ ENTRY(resume_userspace) jmp restore_all END(ret_from_exception) -#ifdef CONFIG_PREEMPT -ENTRY(resume_kernel) - DISABLE_INTERRUPTS(CLBR_ANY) - cmpl $0, PER_CPU_VAR(__preempt_count) - jnz restore_all_kernel - testl $X86_EFLAGS_IF, PT_EFLAGS(%esp) # interrupts off (exception path) ? - jz restore_all_kernel - call preempt_schedule_irq - jmp restore_all_kernel -END(resume_kernel) -#endif - GLOBAL(__begin_SYSENTER_singlestep_region) /* * All code from here through __end_SYSENTER_singlestep_region is subject @@ -1019,6 +1075,7 @@ restore_all: /* Restore user state */ RESTORE_REGS pop=4 # skip orig_eax/error_code .Lirq_return: + IRET_FRAME /* * ARCH_HAS_MEMBARRIER_SYNC_CORE rely on IRET core serialization * when returning from IPI handler and when returning from @@ -1027,6 +1084,15 @@ restore_all: INTERRUPT_RETURN restore_all_kernel: +#ifdef CONFIG_PREEMPTION + DISABLE_INTERRUPTS(CLBR_ANY) + cmpl $0, PER_CPU_VAR(__preempt_count) + jnz .Lno_preempt + testl $X86_EFLAGS_IF, PT_EFLAGS(%esp) # interrupts off (exception path) ? + jz .Lno_preempt + call preempt_schedule_irq +.Lno_preempt: +#endif TRACE_IRQS_IRET PARANOID_EXIT_TO_KERNEL_MODE BUG_IF_WRONG_CR3 @@ -1104,6 +1170,30 @@ ENTRY(irq_entries_start) .endr END(irq_entries_start) +#ifdef CONFIG_X86_LOCAL_APIC + .align 8 +ENTRY(spurious_entries_start) + vector=FIRST_SYSTEM_VECTOR + .rept (NR_VECTORS - FIRST_SYSTEM_VECTOR) + pushl $(~vector+0x80) /* Note: always in signed byte range */ + vector=vector+1 + jmp common_spurious + .align 8 + .endr +END(spurious_entries_start) + +common_spurious: + ASM_CLAC + addl $-0x80, (%esp) /* Adjust vector into the [-256, -1] range */ + SAVE_ALL switch_stacks=1 + ENCODE_FRAME_POINTER + TRACE_IRQS_OFF + movl %esp, %eax + call smp_spurious_interrupt + jmp ret_from_intr +ENDPROC(common_spurious) +#endif + /* * the CPU automatically disables interrupts when executing an IRQ vector, * so IRQ-flags tracing has to follow that: @@ -1274,7 +1364,7 @@ ENTRY(xen_hypervisor_callback) ENTRY(xen_do_upcall) 1: mov %esp, %eax call xen_evtchn_do_upcall -#ifndef CONFIG_PREEMPT +#ifndef CONFIG_PREEMPTION call xen_maybe_preempt_hcall #endif jmp ret_from_intr @@ -1354,37 +1444,50 @@ BUILD_INTERRUPT3(hv_stimer0_callback_vector, HYPERV_STIMER0_VECTOR, ENTRY(page_fault) ASM_CLAC pushl $do_page_fault - ALIGN - jmp common_exception + jmp common_exception_read_cr2 END(page_fault) -common_exception: +common_exception_read_cr2: /* the function address is in %gs's slot on the stack */ - pushl %fs - pushl %es - pushl %ds - pushl %eax - movl $(__USER_DS), %eax - movl %eax, %ds - movl %eax, %es - movl $(__KERNEL_PERCPU), %eax - movl %eax, %fs - pushl %ebp - pushl %edi - pushl %esi - pushl %edx - pushl %ecx - pushl %ebx - SWITCH_TO_KERNEL_STACK + SAVE_ALL switch_stacks=1 skip_gs=1 + ENCODE_FRAME_POINTER - cld UNWIND_ESPFIX_STACK + + /* fixup %gs */ GS_TO_REG %ecx - movl PT_GS(%esp), %edi # get the function address + movl PT_GS(%esp), %edi + REG_TO_PTGS %ecx + SET_KERNEL_GS %ecx + + GET_CR2_INTO(%ecx) # might clobber %eax + + /* fixup orig %eax */ movl PT_ORIG_EAX(%esp), %edx # get the error code movl $-1, PT_ORIG_EAX(%esp) # no syscall to restart + + TRACE_IRQS_OFF + movl %esp, %eax # pt_regs pointer + CALL_NOSPEC %edi + jmp ret_from_exception +END(common_exception_read_cr2) + +common_exception: + /* the function address is in %gs's slot on the stack */ + SAVE_ALL switch_stacks=1 skip_gs=1 + ENCODE_FRAME_POINTER + UNWIND_ESPFIX_STACK + + /* fixup %gs */ + GS_TO_REG %ecx + movl PT_GS(%esp), %edi # get the function address REG_TO_PTGS %ecx SET_KERNEL_GS %ecx + + /* fixup orig %eax */ + movl PT_ORIG_EAX(%esp), %edx # get the error code + movl $-1, PT_ORIG_EAX(%esp) # no syscall to restart + TRACE_IRQS_OFF movl %esp, %eax # pt_regs pointer CALL_NOSPEC %edi @@ -1497,7 +1600,7 @@ END(general_protection) ENTRY(async_page_fault) ASM_CLAC pushl $do_async_page_fault - jmp common_exception + jmp common_exception_read_cr2 END(async_page_fault) #endif diff --git a/arch/x86/entry/entry_64.S b/arch/x86/entry/entry_64.S index 11aa3b2afa4d..b7c3ea4cb19d 100644 --- a/arch/x86/entry/entry_64.S +++ b/arch/x86/entry/entry_64.S @@ -8,7 +8,7 @@ * * entry.S contains the system-call and fault low-level handling routines. * - * Some of this is documented in Documentation/x86/entry_64.txt + * Some of this is documented in Documentation/x86/entry_64.rst * * A note on terminology: * - iret frame: Architecture defined interrupt frame from SS to RIP @@ -375,6 +375,18 @@ ENTRY(irq_entries_start) .endr END(irq_entries_start) + .align 8 +ENTRY(spurious_entries_start) + vector=FIRST_SYSTEM_VECTOR + .rept (NR_VECTORS - FIRST_SYSTEM_VECTOR) + UNWIND_HINT_IRET_REGS + pushq $(~vector+0x80) /* Note: always in signed byte range */ + jmp common_spurious + .align 8 + vector=vector+1 + .endr +END(spurious_entries_start) + .macro DEBUG_ENTRY_ASSERT_IRQS_OFF #ifdef CONFIG_DEBUG_ENTRY pushq %rax @@ -507,7 +519,7 @@ ENTRY(interrupt_entry) testb $3, CS-ORIG_RAX+8(%rsp) jz 1f SWAPGS - + FENCE_SWAPGS_USER_ENTRY /* * Switch to the thread stack. The IRET frame and orig_ax are * on the stack, as well as the return address. RDI..R12 are @@ -537,8 +549,10 @@ ENTRY(interrupt_entry) UNWIND_HINT_FUNC movq (%rdi), %rdi + jmp 2f 1: - + FENCE_SWAPGS_KERNEL_ENTRY +2: PUSH_AND_CLEAR_REGS save_ret=1 ENCODE_FRAME_POINTER 8 @@ -571,10 +585,20 @@ _ASM_NOKPROBE(interrupt_entry) /* Interrupt entry/exit. */ - /* - * The interrupt stubs push (~vector+0x80) onto the stack and - * then jump to common_interrupt. - */ +/* + * The interrupt stubs push (~vector+0x80) onto the stack and + * then jump to common_spurious/interrupt. + */ +common_spurious: + addq $-0x80, (%rsp) /* Adjust vector to [-256, -1] range */ + call interrupt_entry + UNWIND_HINT_REGS indirect=1 + call smp_spurious_interrupt /* rdi points to pt_regs */ + jmp ret_from_intr +END(common_spurious) +_ASM_NOKPROBE(common_spurious) + +/* common_interrupt is a hotpath. Align it */ .p2align CONFIG_X86_L1_CACHE_SHIFT common_interrupt: addq $-0x80, (%rsp) /* Adjust vector to [-256, -1] range */ @@ -640,7 +664,7 @@ GLOBAL(swapgs_restore_regs_and_return_to_usermode) /* Returning to kernel space */ retint_kernel: -#ifdef CONFIG_PREEMPT +#ifdef CONFIG_PREEMPTION /* Interrupts are off */ /* Check if we need preemption */ btl $9, EFLAGS(%rsp) /* were interrupts off? */ @@ -842,18 +866,84 @@ apicinterrupt IRQ_WORK_VECTOR irq_work_interrupt smp_irq_work_interrupt */ #define CPU_TSS_IST(x) PER_CPU_VAR(cpu_tss_rw) + (TSS_ist + (x) * 8) +.macro idtentry_part do_sym, has_error_code:req, read_cr2:req, paranoid:req, shift_ist=-1, ist_offset=0 + + .if \paranoid + call paranoid_entry + /* returned flag: ebx=0: need swapgs on exit, ebx=1: don't need it */ + .else + call error_entry + .endif + UNWIND_HINT_REGS + + .if \read_cr2 + /* + * Store CR2 early so subsequent faults cannot clobber it. Use R12 as + * intermediate storage as RDX can be clobbered in enter_from_user_mode(). + * GET_CR2_INTO can clobber RAX. + */ + GET_CR2_INTO(%r12); + .endif + + .if \shift_ist != -1 + TRACE_IRQS_OFF_DEBUG /* reload IDT in case of recursion */ + .else + TRACE_IRQS_OFF + .endif + + .if \paranoid == 0 + testb $3, CS(%rsp) + jz .Lfrom_kernel_no_context_tracking_\@ + CALL_enter_from_user_mode +.Lfrom_kernel_no_context_tracking_\@: + .endif + + movq %rsp, %rdi /* pt_regs pointer */ + + .if \has_error_code + movq ORIG_RAX(%rsp), %rsi /* get error code */ + movq $-1, ORIG_RAX(%rsp) /* no syscall to restart */ + .else + xorl %esi, %esi /* no error code */ + .endif + + .if \shift_ist != -1 + subq $\ist_offset, CPU_TSS_IST(\shift_ist) + .endif + + .if \read_cr2 + movq %r12, %rdx /* Move CR2 into 3rd argument */ + .endif + + call \do_sym + + .if \shift_ist != -1 + addq $\ist_offset, CPU_TSS_IST(\shift_ist) + .endif + + .if \paranoid + /* this procedure expect "no swapgs" flag in ebx */ + jmp paranoid_exit + .else + jmp error_exit + .endif + +.endm + /** * idtentry - Generate an IDT entry stub * @sym: Name of the generated entry point - * @do_sym: C function to be called - * @has_error_code: True if this IDT vector has an error code on the stack - * @paranoid: non-zero means that this vector may be invoked from + * @do_sym: C function to be called + * @has_error_code: True if this IDT vector has an error code on the stack + * @paranoid: non-zero means that this vector may be invoked from * kernel mode with user GSBASE and/or user CR3. * 2 is special -- see below. * @shift_ist: Set to an IST index if entries from kernel mode should - * decrement the IST stack so that nested entries get a + * decrement the IST stack so that nested entries get a * fresh stack. (This is for #DB, which has a nasty habit - * of recursing.) + * of recursing.) + * @create_gap: create a 6-word stack gap when coming from kernel mode. + * @read_cr2: load CR2 into the 3rd argument; done before calling any C code * * idtentry generates an IDT stub that sets up a usable kernel context, * creates struct pt_regs, and calls @do_sym. The stub has the following @@ -878,15 +968,19 @@ apicinterrupt IRQ_WORK_VECTOR irq_work_interrupt smp_irq_work_interrupt * @paranoid == 2 is special: the stub will never switch stacks. This is for * #DF: if the thread stack is somehow unusable, we'll still get a useful OOPS. */ -.macro idtentry sym do_sym has_error_code:req paranoid=0 shift_ist=-1 ist_offset=0 create_gap=0 +.macro idtentry sym do_sym has_error_code:req paranoid=0 shift_ist=-1 ist_offset=0 create_gap=0 read_cr2=0 ENTRY(\sym) UNWIND_HINT_IRET_REGS offset=\has_error_code*8 /* Sanity check */ - .if \shift_ist != -1 && \paranoid == 0 + .if \shift_ist != -1 && \paranoid != 1 .error "using shift_ist requires paranoid=1" .endif + .if \create_gap && \paranoid + .error "using create_gap requires paranoid=0" + .endif + ASM_CLAC .if \has_error_code == 0 @@ -912,47 +1006,7 @@ ENTRY(\sym) .Lfrom_usermode_no_gap_\@: .endif - .if \paranoid - call paranoid_entry - .else - call error_entry - .endif - UNWIND_HINT_REGS - /* returned flag: ebx=0: need swapgs on exit, ebx=1: don't need it */ - - .if \paranoid - .if \shift_ist != -1 - TRACE_IRQS_OFF_DEBUG /* reload IDT in case of recursion */ - .else - TRACE_IRQS_OFF - .endif - .endif - - movq %rsp, %rdi /* pt_regs pointer */ - - .if \has_error_code - movq ORIG_RAX(%rsp), %rsi /* get error code */ - movq $-1, ORIG_RAX(%rsp) /* no syscall to restart */ - .else - xorl %esi, %esi /* no error code */ - .endif - - .if \shift_ist != -1 - subq $\ist_offset, CPU_TSS_IST(\shift_ist) - .endif - - call \do_sym - - .if \shift_ist != -1 - addq $\ist_offset, CPU_TSS_IST(\shift_ist) - .endif - - /* these procedures expect "no swapgs" flag in ebx */ - .if \paranoid - jmp paranoid_exit - .else - jmp error_exit - .endif + idtentry_part \do_sym, \has_error_code, \read_cr2, \paranoid, \shift_ist, \ist_offset .if \paranoid == 1 /* @@ -961,21 +1015,9 @@ ENTRY(\sym) * run in real process context if user_mode(regs). */ .Lfrom_usermode_switch_stack_\@: - call error_entry - - movq %rsp, %rdi /* pt_regs pointer */ - - .if \has_error_code - movq ORIG_RAX(%rsp), %rsi /* get error code */ - movq $-1, ORIG_RAX(%rsp) /* no syscall to restart */ - .else - xorl %esi, %esi /* no error code */ + idtentry_part \do_sym, \has_error_code, \read_cr2, paranoid=0 .endif - call \do_sym - - jmp error_exit - .endif _ASM_NOKPROBE(\sym) END(\sym) .endm @@ -985,7 +1027,7 @@ idtentry overflow do_overflow has_error_code=0 idtentry bounds do_bounds has_error_code=0 idtentry invalid_op do_invalid_op has_error_code=0 idtentry device_not_available do_device_not_available has_error_code=0 -idtentry double_fault do_double_fault has_error_code=1 paranoid=2 +idtentry double_fault do_double_fault has_error_code=1 paranoid=2 read_cr2=1 idtentry coprocessor_segment_overrun do_coprocessor_segment_overrun has_error_code=0 idtentry invalid_TSS do_invalid_TSS has_error_code=1 idtentry segment_not_present do_segment_not_present has_error_code=1 @@ -1016,10 +1058,10 @@ ENTRY(native_load_gs_index) ENDPROC(native_load_gs_index) EXPORT_SYMBOL(native_load_gs_index) - _ASM_EXTABLE(.Lgs_change, bad_gs) + _ASM_EXTABLE(.Lgs_change, .Lbad_gs) .section .fixup, "ax" /* running with kernelgs */ -bad_gs: +.Lbad_gs: SWAPGS /* switch back to user gs */ .macro ZAP_GS /* This can't be a string because the preprocessor needs to see it. */ @@ -1073,7 +1115,7 @@ ENTRY(xen_do_hypervisor_callback) /* do_hypervisor_callback(struct *pt_regs) */ call xen_evtchn_do_upcall LEAVE_IRQ_STACK -#ifndef CONFIG_PREEMPT +#ifndef CONFIG_PREEMPTION call xen_maybe_preempt_hcall #endif jmp error_exit @@ -1142,6 +1184,11 @@ apicinterrupt3 HYPERV_STIMER0_VECTOR \ hv_stimer0_callback_vector hv_stimer0_vector_handler #endif /* CONFIG_HYPERV */ +#if IS_ENABLED(CONFIG_ACRN_GUEST) +apicinterrupt3 HYPERVISOR_CALLBACK_VECTOR \ + acrn_hv_callback_vector acrn_hv_vector_handler +#endif + idtentry debug do_debug has_error_code=0 paranoid=1 shift_ist=IST_INDEX_DB ist_offset=DB_STACK_OFFSET idtentry int3 do_int3 has_error_code=0 create_gap=1 idtentry stack_segment do_stack_segment has_error_code=1 @@ -1149,14 +1196,13 @@ idtentry stack_segment do_stack_segment has_error_code=1 #ifdef CONFIG_XEN_PV idtentry xennmi do_nmi has_error_code=0 idtentry xendebug do_debug has_error_code=0 -idtentry xenint3 do_int3 has_error_code=0 #endif idtentry general_protection do_general_protection has_error_code=1 -idtentry page_fault do_page_fault has_error_code=1 +idtentry page_fault do_page_fault has_error_code=1 read_cr2=1 #ifdef CONFIG_KVM_GUEST -idtentry async_page_fault do_async_page_fault has_error_code=1 +idtentry async_page_fault do_async_page_fault has_error_code=1 read_cr2=1 #endif #ifdef CONFIG_X86_MCE @@ -1194,6 +1240,13 @@ ENTRY(paranoid_entry) */ SAVE_AND_SWITCH_TO_KERNEL_CR3 scratch_reg=%rax save_reg=%r14 + /* + * The above SAVE_AND_SWITCH_TO_KERNEL_CR3 macro doesn't do an + * unconditional CR3 write, even in the PTI case. So do an lfence + * to prevent GS speculation, regardless of whether PTI is enabled. + */ + FENCE_SWAPGS_KERNEL_ENTRY + ret END(paranoid_entry) @@ -1244,6 +1297,7 @@ ENTRY(error_entry) * from user mode due to an IRET fault. */ SWAPGS + FENCE_SWAPGS_USER_ENTRY /* We have user CR3. Change to kernel CR3. */ SWITCH_TO_KERNEL_CR3 scratch_reg=%rax @@ -1255,18 +1309,11 @@ ENTRY(error_entry) movq %rax, %rsp /* switch stack */ ENCODE_FRAME_POINTER pushq %r12 - - /* - * We need to tell lockdep that IRQs are off. We can't do this until - * we fix gsbase, and we should do it before enter_from_user_mode - * (which can take locks). - */ - TRACE_IRQS_OFF - CALL_enter_from_user_mode ret +.Lerror_entry_done_lfence: + FENCE_SWAPGS_KERNEL_ENTRY .Lerror_entry_done: - TRACE_IRQS_OFF ret /* @@ -1283,7 +1330,7 @@ ENTRY(error_entry) cmpq %rax, RIP+8(%rsp) je .Lbstep_iret cmpq $.Lgs_change, RIP+8(%rsp) - jne .Lerror_entry_done + jne .Lerror_entry_done_lfence /* * hack: .Lgs_change can fail with user gsbase. If this happens, fix up @@ -1291,6 +1338,7 @@ ENTRY(error_entry) * .Lgs_change's error handler with kernel gsbase. */ SWAPGS + FENCE_SWAPGS_USER_ENTRY SWITCH_TO_KERNEL_CR3 scratch_reg=%rax jmp .Lerror_entry_done @@ -1305,6 +1353,7 @@ ENTRY(error_entry) * gsbase and CR3. Switch to kernel gsbase and CR3: */ SWAPGS + FENCE_SWAPGS_USER_ENTRY SWITCH_TO_KERNEL_CR3 scratch_reg=%rax /* @@ -1396,6 +1445,7 @@ ENTRY(nmi) swapgs cld + FENCE_SWAPGS_USER_ENTRY SWITCH_TO_KERNEL_CR3 scratch_reg=%rdx movq %rsp, %rdx movq PER_CPU_VAR(cpu_current_top_of_stack), %rsp @@ -1670,11 +1720,17 @@ nmi_restore: iretq END(nmi) +#ifndef CONFIG_IA32_EMULATION +/* + * This handles SYSCALL from 32-bit code. There is no way to program + * MSRs to fully disable 32-bit SYSCALL. + */ ENTRY(ignore_sysret) UNWIND_HINT_EMPTY mov $-ENOSYS, %eax sysret END(ignore_sysret) +#endif ENTRY(rewind_stack_do_exit) UNWIND_HINT_FUNC diff --git a/arch/x86/entry/syscall_64.c b/arch/x86/entry/syscall_64.c index d5252bc1e380..b1bf31713374 100644 --- a/arch/x86/entry/syscall_64.c +++ b/arch/x86/entry/syscall_64.c @@ -10,10 +10,13 @@ /* this is a lie, but it does not hurt as sys_ni_syscall just returns -EINVAL */ extern asmlinkage long sys_ni_syscall(const struct pt_regs *); #define __SYSCALL_64(nr, sym, qual) extern asmlinkage long sym(const struct pt_regs *); +#define __SYSCALL_X32(nr, sym, qual) __SYSCALL_64(nr, sym, qual) #include <asm/syscalls_64.h> #undef __SYSCALL_64 +#undef __SYSCALL_X32 #define __SYSCALL_64(nr, sym, qual) [nr] = sym, +#define __SYSCALL_X32(nr, sym, qual) asmlinkage const sys_call_ptr_t sys_call_table[__NR_syscall_max+1] = { /* @@ -23,3 +26,25 @@ asmlinkage const sys_call_ptr_t sys_call_table[__NR_syscall_max+1] = { [0 ... __NR_syscall_max] = &sys_ni_syscall, #include <asm/syscalls_64.h> }; + +#undef __SYSCALL_64 +#undef __SYSCALL_X32 + +#ifdef CONFIG_X86_X32_ABI + +#define __SYSCALL_64(nr, sym, qual) +#define __SYSCALL_X32(nr, sym, qual) [nr] = sym, + +asmlinkage const sys_call_ptr_t x32_sys_call_table[__NR_syscall_x32_max+1] = { + /* + * Smells like a compiler bug -- it doesn't work + * when the & below is removed. + */ + [0 ... __NR_syscall_x32_max] = &sys_ni_syscall, +#include <asm/syscalls_64.h> +}; + +#undef __SYSCALL_64 +#undef __SYSCALL_X32 + +#endif diff --git a/arch/x86/entry/syscalls/syscall_32.tbl b/arch/x86/entry/syscalls/syscall_32.tbl index ad968b7bac72..3fe02546aed3 100644 --- a/arch/x86/entry/syscalls/syscall_32.tbl +++ b/arch/x86/entry/syscalls/syscall_32.tbl @@ -186,11 +186,11 @@ 172 i386 prctl sys_prctl __ia32_sys_prctl 173 i386 rt_sigreturn sys_rt_sigreturn sys32_rt_sigreturn 174 i386 rt_sigaction sys_rt_sigaction __ia32_compat_sys_rt_sigaction -175 i386 rt_sigprocmask sys_rt_sigprocmask __ia32_sys_rt_sigprocmask +175 i386 rt_sigprocmask sys_rt_sigprocmask __ia32_compat_sys_rt_sigprocmask 176 i386 rt_sigpending sys_rt_sigpending __ia32_compat_sys_rt_sigpending 177 i386 rt_sigtimedwait sys_rt_sigtimedwait_time32 __ia32_compat_sys_rt_sigtimedwait_time32 178 i386 rt_sigqueueinfo sys_rt_sigqueueinfo __ia32_compat_sys_rt_sigqueueinfo -179 i386 rt_sigsuspend sys_rt_sigsuspend __ia32_sys_rt_sigsuspend +179 i386 rt_sigsuspend sys_rt_sigsuspend __ia32_compat_sys_rt_sigsuspend 180 i386 pread64 sys_pread64 __ia32_compat_sys_x86_pread 181 i386 pwrite64 sys_pwrite64 __ia32_compat_sys_x86_pwrite 182 i386 chown sys_chown16 __ia32_sys_chown16 @@ -438,3 +438,5 @@ 431 i386 fsconfig sys_fsconfig __ia32_sys_fsconfig 432 i386 fsmount sys_fsmount __ia32_sys_fsmount 433 i386 fspick sys_fspick __ia32_sys_fspick +434 i386 pidfd_open sys_pidfd_open __ia32_sys_pidfd_open +435 i386 clone3 sys_clone3 __ia32_sys_clone3 diff --git a/arch/x86/entry/syscalls/syscall_64.tbl b/arch/x86/entry/syscalls/syscall_64.tbl index b4e6f9e6204a..c29976eca4a8 100644 --- a/arch/x86/entry/syscalls/syscall_64.tbl +++ b/arch/x86/entry/syscalls/syscall_64.tbl @@ -355,6 +355,8 @@ 431 common fsconfig __x64_sys_fsconfig 432 common fsmount __x64_sys_fsmount 433 common fspick __x64_sys_fspick +434 common pidfd_open __x64_sys_pidfd_open +435 common clone3 __x64_sys_clone3/ptregs # # x32-specific system call numbers start at 512 to avoid cache impact diff --git a/arch/x86/entry/syscalls/syscalltbl.sh b/arch/x86/entry/syscalls/syscalltbl.sh index 94fcd1951aca..1af2be39e7d9 100644 --- a/arch/x86/entry/syscalls/syscalltbl.sh +++ b/arch/x86/entry/syscalls/syscalltbl.sh @@ -1,13 +1,13 @@ -#!/bin/sh +#!/bin/bash # SPDX-License-Identifier: GPL-2.0 in="$1" out="$2" syscall_macro() { - abi="$1" - nr="$2" - entry="$3" + local abi="$1" + local nr="$2" + local entry="$3" # Entry can be either just a function name or "function/qualifier" real_entry="${entry%%/*}" @@ -21,14 +21,14 @@ syscall_macro() { } emit() { - abi="$1" - nr="$2" - entry="$3" - compat="$4" - umlentry="" + local abi="$1" + local nr="$2" + local entry="$3" + local compat="$4" + local umlentry="" - if [ "$abi" = "64" -a -n "$compat" ]; then - echo "a compat entry for a 64-bit syscall makes no sense" >&2 + if [ "$abi" != "I386" -a -n "$compat" ]; then + echo "a compat entry ($abi: $compat) for a 64-bit syscall makes no sense" >&2 exit 1 fi @@ -62,14 +62,17 @@ grep '^[0-9]' "$in" | sort -n | ( while read nr abi name entry compat; do abi=`echo "$abi" | tr '[a-z]' '[A-Z]'` if [ "$abi" = "COMMON" -o "$abi" = "64" ]; then - # COMMON is the same as 64, except that we don't expect X32 - # programs to use it. Our expectation has nothing to do with - # any generated code, so treat them the same. emit 64 "$nr" "$entry" "$compat" + if [ "$abi" = "COMMON" ]; then + # COMMON means that this syscall exists in the same form for + # 64-bit and X32. + echo "#ifdef CONFIG_X86_X32_ABI" + emit X32 "$nr" "$entry" "$compat" + echo "#endif" + fi elif [ "$abi" = "X32" ]; then - # X32 is equivalent to 64 on an X32-compatible kernel. echo "#ifdef CONFIG_X86_X32_ABI" - emit 64 "$nr" "$entry" "$compat" + emit X32 "$nr" "$entry" "$compat" echo "#endif" elif [ "$abi" = "I386" ]; then emit "$abi" "$nr" "$entry" "$compat" diff --git a/arch/x86/entry/thunk_32.S b/arch/x86/entry/thunk_32.S index cb3464525b37..2713490611a3 100644 --- a/arch/x86/entry/thunk_32.S +++ b/arch/x86/entry/thunk_32.S @@ -34,7 +34,7 @@ THUNK trace_hardirqs_off_thunk,trace_hardirqs_off_caller,1 #endif -#ifdef CONFIG_PREEMPT +#ifdef CONFIG_PREEMPTION THUNK ___preempt_schedule, preempt_schedule THUNK ___preempt_schedule_notrace, preempt_schedule_notrace EXPORT_SYMBOL(___preempt_schedule) diff --git a/arch/x86/entry/thunk_64.S b/arch/x86/entry/thunk_64.S index cfdca8b42c70..ea5c4167086c 100644 --- a/arch/x86/entry/thunk_64.S +++ b/arch/x86/entry/thunk_64.S @@ -12,9 +12,7 @@ /* rdi: arg1 ... normal C conventions. rax is saved/restored. */ .macro THUNK name, func, put_ret_addr_in_rdi=0 - .globl \name - .type \name, @function -\name: + ENTRY(\name) pushq %rbp movq %rsp, %rbp @@ -35,6 +33,7 @@ call \func jmp .L_restore + ENDPROC(\name) _ASM_NOKPROBE(\name) .endm @@ -47,7 +46,7 @@ THUNK lockdep_sys_exit_thunk,lockdep_sys_exit #endif -#ifdef CONFIG_PREEMPT +#ifdef CONFIG_PREEMPTION THUNK ___preempt_schedule, preempt_schedule THUNK ___preempt_schedule_notrace, preempt_schedule_notrace EXPORT_SYMBOL(___preempt_schedule) @@ -56,7 +55,7 @@ #if defined(CONFIG_TRACE_IRQFLAGS) \ || defined(CONFIG_DEBUG_LOCK_ALLOC) \ - || defined(CONFIG_PREEMPT) + || defined(CONFIG_PREEMPTION) .L_restore: popq %r11 popq %r10 diff --git a/arch/x86/entry/vdso/Makefile b/arch/x86/entry/vdso/Makefile index 42fe42e82baf..0f2154106d01 100644 --- a/arch/x86/entry/vdso/Makefile +++ b/arch/x86/entry/vdso/Makefile @@ -3,6 +3,12 @@ # Building vDSO images for x86. # +# Absolute relocation type $(ARCH_REL_TYPE_ABS) needs to be defined before +# the inclusion of generic Makefile. +ARCH_REL_TYPE_ABS := R_X86_64_JUMP_SLOT|R_X86_64_GLOB_DAT|R_X86_64_RELATIVE| +ARCH_REL_TYPE_ABS += R_386_GLOB_DAT|R_386_JMP_SLOT|R_386_RELATIVE +include $(srctree)/lib/vdso/Makefile + KBUILD_CFLAGS += $(DISABLE_LTO) KASAN_SANITIZE := n UBSAN_SANITIZE := n @@ -50,7 +56,7 @@ VDSO_LDFLAGS_vdso.lds = -m elf_x86_64 -soname linux-vdso.so.1 --no-undefined \ -z max-page-size=4096 $(obj)/vdso64.so.dbg: $(obj)/vdso.lds $(vobjs) FORCE - $(call if_changed,vdso) + $(call if_changed,vdso_and_check) HOST_EXTRACFLAGS += -I$(srctree)/tools/include -I$(srctree)/include/uapi -I$(srctree)/arch/$(SUBARCH)/include/uapi hostprogs-y += vdso2c @@ -83,6 +89,7 @@ $(vobjs): KBUILD_CFLAGS := $(filter-out $(GCC_PLUGINS_CFLAGS) $(RETPOLINE_CFLAGS # CFLAGS_REMOVE_vdso-note.o = -pg CFLAGS_REMOVE_vclock_gettime.o = -pg +CFLAGS_REMOVE_vdso32/vclock_gettime.o = -pg CFLAGS_REMOVE_vgetcpu.o = -pg CFLAGS_REMOVE_vvar.o = -pg @@ -120,9 +127,9 @@ $(obj)/%.so: $(obj)/%.so.dbg FORCE $(call if_changed,objcopy) $(obj)/vdsox32.so.dbg: $(obj)/vdsox32.lds $(vobjx32s) FORCE - $(call if_changed,vdso) + $(call if_changed,vdso_and_check) -CPPFLAGS_vdso32.lds = $(CPPFLAGS_vdso.lds) +CPPFLAGS_vdso32/vdso32.lds = $(CPPFLAGS_vdso.lds) VDSO_LDFLAGS_vdso32.lds = -m elf_i386 -soname linux-gate.so.1 targets += vdso32/vdso32.lds @@ -159,7 +166,7 @@ $(obj)/vdso32.so.dbg: FORCE \ $(obj)/vdso32/note.o \ $(obj)/vdso32/system_call.o \ $(obj)/vdso32/sigreturn.o - $(call if_changed,vdso) + $(call if_changed,vdso_and_check) # # The DSO images are built using a special linker script. @@ -170,11 +177,13 @@ quiet_cmd_vdso = VDSO $@ -T $(filter %.lds,$^) $(filter %.o,$^) && \ sh $(srctree)/$(src)/checkundef.sh '$(NM)' '$@' -VDSO_LDFLAGS = -shared $(call ld-option, --hash-style=both) \ - $(call ld-option, --build-id) $(call ld-option, --eh-frame-hdr) \ - -Bsymbolic +VDSO_LDFLAGS = -shared --hash-style=both --build-id \ + $(call ld-option, --eh-frame-hdr) -Bsymbolic GCOV_PROFILE := n +quiet_cmd_vdso_and_check = VDSO $@ + cmd_vdso_and_check = $(cmd_vdso); $(cmd_vdso_check) + # # Install the unstripped copies of vdso*.so. If our toolchain supports # build-id, install .build-id links as well. diff --git a/arch/x86/entry/vdso/vclock_gettime.c b/arch/x86/entry/vdso/vclock_gettime.c index 4aed41f638bb..d9ff616bb0f6 100644 --- a/arch/x86/entry/vdso/vclock_gettime.c +++ b/arch/x86/entry/vdso/vclock_gettime.c @@ -1,251 +1,85 @@ // SPDX-License-Identifier: GPL-2.0-only /* - * Copyright 2006 Andi Kleen, SUSE Labs. - * * Fast user context implementation of clock_gettime, gettimeofday, and time. * + * Copyright 2006 Andi Kleen, SUSE Labs. + * Copyright 2019 ARM Limited + * * 32 Bit compat layer by Stefani Seibold <stefani@seibold.net> * sponsored by Rohde & Schwarz GmbH & Co. KG Munich/Germany - * - * The code should have no internal unresolved relocations. - * Check with readelf after changing. */ - -#include <uapi/linux/time.h> -#include <asm/vgtod.h> -#include <asm/vvar.h> -#include <asm/unistd.h> -#include <asm/msr.h> -#include <asm/pvclock.h> -#include <asm/mshyperv.h> -#include <linux/math64.h> #include <linux/time.h> #include <linux/kernel.h> +#include <linux/types.h> -#define gtod (&VVAR(vsyscall_gtod_data)) +#include "../../../../lib/vdso/gettimeofday.c" -extern int __vdso_clock_gettime(clockid_t clock, struct timespec *ts); -extern int __vdso_gettimeofday(struct timeval *tv, struct timezone *tz); +extern int __vdso_gettimeofday(struct __kernel_old_timeval *tv, struct timezone *tz); extern time_t __vdso_time(time_t *t); -#ifdef CONFIG_PARAVIRT_CLOCK -extern u8 pvclock_page[PAGE_SIZE] - __attribute__((visibility("hidden"))); -#endif - -#ifdef CONFIG_HYPERV_TSCPAGE -extern u8 hvclock_page[PAGE_SIZE] - __attribute__((visibility("hidden"))); -#endif - -#ifndef BUILD_VDSO32 - -notrace static long vdso_fallback_gettime(long clock, struct timespec *ts) +int __vdso_gettimeofday(struct __kernel_old_timeval *tv, struct timezone *tz) { - long ret; - asm ("syscall" : "=a" (ret), "=m" (*ts) : - "0" (__NR_clock_gettime), "D" (clock), "S" (ts) : - "rcx", "r11"); - return ret; + return __cvdso_gettimeofday(tv, tz); } -#else +int gettimeofday(struct __kernel_old_timeval *, struct timezone *) + __attribute__((weak, alias("__vdso_gettimeofday"))); -notrace static long vdso_fallback_gettime(long clock, struct timespec *ts) +time_t __vdso_time(time_t *t) { - long ret; - - asm ( - "mov %%ebx, %%edx \n" - "mov %[clock], %%ebx \n" - "call __kernel_vsyscall \n" - "mov %%edx, %%ebx \n" - : "=a" (ret), "=m" (*ts) - : "0" (__NR_clock_gettime), [clock] "g" (clock), "c" (ts) - : "edx"); - return ret; + return __cvdso_time(t); } -#endif +time_t time(time_t *t) __attribute__((weak, alias("__vdso_time"))); -#ifdef CONFIG_PARAVIRT_CLOCK -static notrace const struct pvclock_vsyscall_time_info *get_pvti0(void) -{ - return (const struct pvclock_vsyscall_time_info *)&pvclock_page; -} -static notrace u64 vread_pvclock(void) -{ - const struct pvclock_vcpu_time_info *pvti = &get_pvti0()->pvti; - u32 version; - u64 ret; - - /* - * Note: The kernel and hypervisor must guarantee that cpu ID - * number maps 1:1 to per-CPU pvclock time info. - * - * Because the hypervisor is entirely unaware of guest userspace - * preemption, it cannot guarantee that per-CPU pvclock time - * info is updated if the underlying CPU changes or that that - * version is increased whenever underlying CPU changes. - * - * On KVM, we are guaranteed that pvti updates for any vCPU are - * atomic as seen by *all* vCPUs. This is an even stronger - * guarantee than we get with a normal seqlock. - * - * On Xen, we don't appear to have that guarantee, but Xen still - * supplies a valid seqlock using the version field. - * - * We only do pvclock vdso timing at all if - * PVCLOCK_TSC_STABLE_BIT is set, and we interpret that bit to - * mean that all vCPUs have matching pvti and that the TSC is - * synced, so we can just look at vCPU 0's pvti. - */ - - do { - version = pvclock_read_begin(pvti); - - if (unlikely(!(pvti->flags & PVCLOCK_TSC_STABLE_BIT))) - return U64_MAX; - - ret = __pvclock_read_cycles(pvti, rdtsc_ordered()); - } while (pvclock_read_retry(pvti, version)); - - return ret; -} -#endif -#ifdef CONFIG_HYPERV_TSCPAGE -static notrace u64 vread_hvclock(void) -{ - const struct ms_hyperv_tsc_page *tsc_pg = - (const struct ms_hyperv_tsc_page *)&hvclock_page; +#if defined(CONFIG_X86_64) && !defined(BUILD_VDSO32_64) +/* both 64-bit and x32 use these */ +extern int __vdso_clock_gettime(clockid_t clock, struct __kernel_timespec *ts); +extern int __vdso_clock_getres(clockid_t clock, struct __kernel_timespec *res); - return hv_read_tsc_page(tsc_pg); -} -#endif - -notrace static inline u64 vgetcyc(int mode) +int __vdso_clock_gettime(clockid_t clock, struct __kernel_timespec *ts) { - if (mode == VCLOCK_TSC) - return (u64)rdtsc_ordered(); - - /* - * For any memory-mapped vclock type, we need to make sure that gcc - * doesn't cleverly hoist a load before the mode check. Otherwise we - * might end up touching the memory-mapped page even if the vclock in - * question isn't enabled, which will segfault. Hence the barriers. - */ -#ifdef CONFIG_PARAVIRT_CLOCK - if (mode == VCLOCK_PVCLOCK) { - barrier(); - return vread_pvclock(); - } -#endif -#ifdef CONFIG_HYPERV_TSCPAGE - if (mode == VCLOCK_HVCLOCK) { - barrier(); - return vread_hvclock(); - } -#endif - return U64_MAX; + return __cvdso_clock_gettime(clock, ts); } -notrace static int do_hres(clockid_t clk, struct timespec *ts) -{ - struct vgtod_ts *base = >od->basetime[clk]; - u64 cycles, last, sec, ns; - unsigned int seq; - - do { - seq = gtod_read_begin(gtod); - cycles = vgetcyc(gtod->vclock_mode); - ns = base->nsec; - last = gtod->cycle_last; - if (unlikely((s64)cycles < 0)) - return vdso_fallback_gettime(clk, ts); - if (cycles > last) - ns += (cycles - last) * gtod->mult; - ns >>= gtod->shift; - sec = base->sec; - } while (unlikely(gtod_read_retry(gtod, seq))); - - /* - * Do this outside the loop: a race inside the loop could result - * in __iter_div_u64_rem() being extremely slow. - */ - ts->tv_sec = sec + __iter_div_u64_rem(ns, NSEC_PER_SEC, &ns); - ts->tv_nsec = ns; - - return 0; -} +int clock_gettime(clockid_t, struct __kernel_timespec *) + __attribute__((weak, alias("__vdso_clock_gettime"))); -notrace static void do_coarse(clockid_t clk, struct timespec *ts) +int __vdso_clock_getres(clockid_t clock, + struct __kernel_timespec *res) { - struct vgtod_ts *base = >od->basetime[clk]; - unsigned int seq; - - do { - seq = gtod_read_begin(gtod); - ts->tv_sec = base->sec; - ts->tv_nsec = base->nsec; - } while (unlikely(gtod_read_retry(gtod, seq))); + return __cvdso_clock_getres(clock, res); } +int clock_getres(clockid_t, struct __kernel_timespec *) + __attribute__((weak, alias("__vdso_clock_getres"))); -notrace int __vdso_clock_gettime(clockid_t clock, struct timespec *ts) +#else +/* i386 only */ +extern int __vdso_clock_gettime(clockid_t clock, struct old_timespec32 *ts); +extern int __vdso_clock_getres(clockid_t clock, struct old_timespec32 *res); + +int __vdso_clock_gettime(clockid_t clock, struct old_timespec32 *ts) { - unsigned int msk; - - /* Sort out negative (CPU/FD) and invalid clocks */ - if (unlikely((unsigned int) clock >= MAX_CLOCKS)) - return vdso_fallback_gettime(clock, ts); - - /* - * Convert the clockid to a bitmask and use it to check which - * clocks are handled in the VDSO directly. - */ - msk = 1U << clock; - if (likely(msk & VGTOD_HRES)) { - return do_hres(clock, ts); - } else if (msk & VGTOD_COARSE) { - do_coarse(clock, ts); - return 0; - } - return vdso_fallback_gettime(clock, ts); + return __cvdso_clock_gettime32(clock, ts); } -int clock_gettime(clockid_t, struct timespec *) +int clock_gettime(clockid_t, struct old_timespec32 *) __attribute__((weak, alias("__vdso_clock_gettime"))); -notrace int __vdso_gettimeofday(struct timeval *tv, struct timezone *tz) +int __vdso_clock_gettime64(clockid_t clock, struct __kernel_timespec *ts) { - if (likely(tv != NULL)) { - struct timespec *ts = (struct timespec *) tv; - - do_hres(CLOCK_REALTIME, ts); - tv->tv_usec /= 1000; - } - if (unlikely(tz != NULL)) { - tz->tz_minuteswest = gtod->tz_minuteswest; - tz->tz_dsttime = gtod->tz_dsttime; - } - - return 0; + return __cvdso_clock_gettime(clock, ts); } -int gettimeofday(struct timeval *, struct timezone *) - __attribute__((weak, alias("__vdso_gettimeofday"))); -/* - * This will break when the xtime seconds get inaccurate, but that is - * unlikely - */ -notrace time_t __vdso_time(time_t *t) -{ - /* This is atomic on x86 so we don't need any locks. */ - time_t result = READ_ONCE(gtod->basetime[CLOCK_REALTIME].sec); +int clock_gettime64(clockid_t, struct __kernel_timespec *) + __attribute__((weak, alias("__vdso_clock_gettime64"))); - if (t) - *t = result; - return result; +int __vdso_clock_getres(clockid_t clock, struct old_timespec32 *res) +{ + return __cvdso_clock_getres_time32(clock, res); } -time_t time(time_t *t) - __attribute__((weak, alias("__vdso_time"))); + +int clock_getres(clockid_t, struct old_timespec32 *) + __attribute__((weak, alias("__vdso_clock_getres"))); +#endif diff --git a/arch/x86/entry/vdso/vdso.lds.S b/arch/x86/entry/vdso/vdso.lds.S index d3a2dce4cfa9..36b644e16272 100644 --- a/arch/x86/entry/vdso/vdso.lds.S +++ b/arch/x86/entry/vdso/vdso.lds.S @@ -25,6 +25,8 @@ VERSION { __vdso_getcpu; time; __vdso_time; + clock_getres; + __vdso_clock_getres; local: *; }; } diff --git a/arch/x86/entry/vdso/vdso32-setup.c b/arch/x86/entry/vdso/vdso32-setup.c index 42d4c89f990e..240626e7f55a 100644 --- a/arch/x86/entry/vdso/vdso32-setup.c +++ b/arch/x86/entry/vdso/vdso32-setup.c @@ -65,9 +65,6 @@ subsys_initcall(sysenter_setup); /* Register vsyscall32 into the ABI table */ #include <linux/sysctl.h> -static const int zero; -static const int one = 1; - static struct ctl_table abi_table2[] = { { .procname = "vsyscall32", @@ -75,8 +72,8 @@ static struct ctl_table abi_table2[] = { .maxlen = sizeof(int), .mode = 0644, .proc_handler = proc_dointvec_minmax, - .extra1 = (int *)&zero, - .extra2 = (int *)&one, + .extra1 = SYSCTL_ZERO, + .extra2 = SYSCTL_ONE, }, {} }; diff --git a/arch/x86/entry/vdso/vdso32/vdso32.lds.S b/arch/x86/entry/vdso/vdso32/vdso32.lds.S index 422764a81d32..c7720995ab1a 100644 --- a/arch/x86/entry/vdso/vdso32/vdso32.lds.S +++ b/arch/x86/entry/vdso/vdso32/vdso32.lds.S @@ -26,6 +26,8 @@ VERSION __vdso_clock_gettime; __vdso_gettimeofday; __vdso_time; + __vdso_clock_getres; + __vdso_clock_gettime64; }; LINUX_2.5 { diff --git a/arch/x86/entry/vdso/vdsox32.lds.S b/arch/x86/entry/vdso/vdsox32.lds.S index 05cd1c5c4a15..16a8050a4fb6 100644 --- a/arch/x86/entry/vdso/vdsox32.lds.S +++ b/arch/x86/entry/vdso/vdsox32.lds.S @@ -21,6 +21,7 @@ VERSION { __vdso_gettimeofday; __vdso_getcpu; __vdso_time; + __vdso_clock_getres; local: *; }; } diff --git a/arch/x86/entry/vdso/vma.c b/arch/x86/entry/vdso/vma.c index 8db1f594e8b1..f5937742b290 100644 --- a/arch/x86/entry/vdso/vma.c +++ b/arch/x86/entry/vdso/vma.c @@ -22,7 +22,7 @@ #include <asm/page.h> #include <asm/desc.h> #include <asm/cpufeature.h> -#include <asm/mshyperv.h> +#include <clocksource/hyperv_timer.h> #if defined(CONFIG_X86_64) unsigned int __read_mostly vdso64_enabled = 1; @@ -122,7 +122,7 @@ static vm_fault_t vvar_fault(const struct vm_special_mapping *sm, if (tsc_pg && vclock_was_used(VCLOCK_HVCLOCK)) return vmf_insert_pfn(vma, vmf->address, - vmalloc_to_pfn(tsc_pg)); + virt_to_phys(tsc_pg) >> PAGE_SHIFT); } return VM_FAULT_SIGBUS; diff --git a/arch/x86/entry/vsyscall/Makefile b/arch/x86/entry/vsyscall/Makefile index 1ac4dd116c26..93c1b3e949a7 100644 --- a/arch/x86/entry/vsyscall/Makefile +++ b/arch/x86/entry/vsyscall/Makefile @@ -2,7 +2,5 @@ # # Makefile for the x86 low level vsyscall code # -obj-y := vsyscall_gtod.o - obj-$(CONFIG_X86_VSYSCALL_EMULATION) += vsyscall_64.o vsyscall_emu_64.o diff --git a/arch/x86/entry/vsyscall/vsyscall_64.c b/arch/x86/entry/vsyscall/vsyscall_64.c index d9d81ad7a400..e7c596dea947 100644 --- a/arch/x86/entry/vsyscall/vsyscall_64.c +++ b/arch/x86/entry/vsyscall/vsyscall_64.c @@ -42,9 +42,11 @@ #define CREATE_TRACE_POINTS #include "vsyscall_trace.h" -static enum { EMULATE, NONE } vsyscall_mode = +static enum { EMULATE, XONLY, NONE } vsyscall_mode __ro_after_init = #ifdef CONFIG_LEGACY_VSYSCALL_NONE NONE; +#elif defined(CONFIG_LEGACY_VSYSCALL_XONLY) + XONLY; #else EMULATE; #endif @@ -54,6 +56,8 @@ static int __init vsyscall_setup(char *str) if (str) { if (!strcmp("emulate", str)) vsyscall_mode = EMULATE; + else if (!strcmp("xonly", str)) + vsyscall_mode = XONLY; else if (!strcmp("none", str)) vsyscall_mode = NONE; else @@ -106,14 +110,15 @@ static bool write_ok_or_segv(unsigned long ptr, size_t size) thread->cr2 = ptr; thread->trap_nr = X86_TRAP_PF; - force_sig_fault(SIGSEGV, SEGV_MAPERR, (void __user *)ptr, current); + force_sig_fault(SIGSEGV, SEGV_MAPERR, (void __user *)ptr); return false; } else { return true; } } -bool emulate_vsyscall(struct pt_regs *regs, unsigned long address) +bool emulate_vsyscall(unsigned long error_code, + struct pt_regs *regs, unsigned long address) { struct task_struct *tsk; unsigned long caller; @@ -122,6 +127,22 @@ bool emulate_vsyscall(struct pt_regs *regs, unsigned long address) long ret; unsigned long orig_dx; + /* Write faults or kernel-privilege faults never get fixed up. */ + if ((error_code & (X86_PF_WRITE | X86_PF_USER)) != X86_PF_USER) + return false; + + if (!(error_code & X86_PF_INSTR)) { + /* Failed vsyscall read */ + if (vsyscall_mode == EMULATE) + return false; + + /* + * User code tried and failed to read the vsyscall page. + */ + warn_bad_vsyscall(KERN_INFO, regs, "vsyscall read attempt denied -- look up the vsyscall kernel parameter if you need a workaround"); + return false; + } + /* * No point in checking CS -- the only way to get here is a user mode * trap to a high address, which means that we're in 64-bit user code. @@ -268,7 +289,7 @@ do_ret: return true; sigsegv: - force_sig(SIGSEGV, current); + force_sig(SIGSEGV); return true; } @@ -284,7 +305,7 @@ static const char *gate_vma_name(struct vm_area_struct *vma) static const struct vm_operations_struct gate_vma_ops = { .name = gate_vma_name, }; -static struct vm_area_struct gate_vma = { +static struct vm_area_struct gate_vma __ro_after_init = { .vm_start = VSYSCALL_ADDR, .vm_end = VSYSCALL_ADDR + PAGE_SIZE, .vm_page_prot = PAGE_READONLY_EXEC, @@ -357,12 +378,20 @@ void __init map_vsyscall(void) extern char __vsyscall_page; unsigned long physaddr_vsyscall = __pa_symbol(&__vsyscall_page); - if (vsyscall_mode != NONE) { + /* + * For full emulation, the page needs to exist for real. In + * execute-only mode, there is no PTE at all backing the vsyscall + * page. + */ + if (vsyscall_mode == EMULATE) { __set_fixmap(VSYSCALL_PAGE, physaddr_vsyscall, PAGE_KERNEL_VVAR); set_vsyscall_pgtable_user_bits(swapper_pg_dir); } + if (vsyscall_mode == XONLY) + gate_vma.vm_flags = VM_EXEC; + BUILD_BUG_ON((unsigned long)__fix_to_virt(VSYSCALL_PAGE) != (unsigned long)VSYSCALL_ADDR); } diff --git a/arch/x86/entry/vsyscall/vsyscall_gtod.c b/arch/x86/entry/vsyscall/vsyscall_gtod.c deleted file mode 100644 index cfcdba082feb..000000000000 --- a/arch/x86/entry/vsyscall/vsyscall_gtod.c +++ /dev/null @@ -1,83 +0,0 @@ -// SPDX-License-Identifier: GPL-2.0 -/* - * Copyright (C) 2001 Andrea Arcangeli <andrea@suse.de> SuSE - * Copyright 2003 Andi Kleen, SuSE Labs. - * - * Modified for x86 32 bit architecture by - * Stefani Seibold <stefani@seibold.net> - * sponsored by Rohde & Schwarz GmbH & Co. KG Munich/Germany - * - * Thanks to hpa@transmeta.com for some useful hint. - * Special thanks to Ingo Molnar for his early experience with - * a different vsyscall implementation for Linux/IA32 and for the name. - * - */ - -#include <linux/timekeeper_internal.h> -#include <asm/vgtod.h> -#include <asm/vvar.h> - -int vclocks_used __read_mostly; - -DEFINE_VVAR(struct vsyscall_gtod_data, vsyscall_gtod_data); - -void update_vsyscall_tz(void) -{ - vsyscall_gtod_data.tz_minuteswest = sys_tz.tz_minuteswest; - vsyscall_gtod_data.tz_dsttime = sys_tz.tz_dsttime; -} - -void update_vsyscall(struct timekeeper *tk) -{ - int vclock_mode = tk->tkr_mono.clock->archdata.vclock_mode; - struct vsyscall_gtod_data *vdata = &vsyscall_gtod_data; - struct vgtod_ts *base; - u64 nsec; - - /* Mark the new vclock used. */ - BUILD_BUG_ON(VCLOCK_MAX >= 32); - WRITE_ONCE(vclocks_used, READ_ONCE(vclocks_used) | (1 << vclock_mode)); - - gtod_write_begin(vdata); - - /* copy vsyscall data */ - vdata->vclock_mode = vclock_mode; - vdata->cycle_last = tk->tkr_mono.cycle_last; - vdata->mask = tk->tkr_mono.mask; - vdata->mult = tk->tkr_mono.mult; - vdata->shift = tk->tkr_mono.shift; - - base = &vdata->basetime[CLOCK_REALTIME]; - base->sec = tk->xtime_sec; - base->nsec = tk->tkr_mono.xtime_nsec; - - base = &vdata->basetime[CLOCK_TAI]; - base->sec = tk->xtime_sec + (s64)tk->tai_offset; - base->nsec = tk->tkr_mono.xtime_nsec; - - base = &vdata->basetime[CLOCK_MONOTONIC]; - base->sec = tk->xtime_sec + tk->wall_to_monotonic.tv_sec; - nsec = tk->tkr_mono.xtime_nsec; - nsec += ((u64)tk->wall_to_monotonic.tv_nsec << tk->tkr_mono.shift); - while (nsec >= (((u64)NSEC_PER_SEC) << tk->tkr_mono.shift)) { - nsec -= ((u64)NSEC_PER_SEC) << tk->tkr_mono.shift; - base->sec++; - } - base->nsec = nsec; - - base = &vdata->basetime[CLOCK_REALTIME_COARSE]; - base->sec = tk->xtime_sec; - base->nsec = tk->tkr_mono.xtime_nsec >> tk->tkr_mono.shift; - - base = &vdata->basetime[CLOCK_MONOTONIC_COARSE]; - base->sec = tk->xtime_sec + tk->wall_to_monotonic.tv_sec; - nsec = tk->tkr_mono.xtime_nsec >> tk->tkr_mono.shift; - nsec += tk->wall_to_monotonic.tv_nsec; - while (nsec >= NSEC_PER_SEC) { - nsec -= NSEC_PER_SEC; - base->sec++; - } - base->nsec = nsec; - - gtod_write_end(vdata); -} |