diff options
Diffstat (limited to 'arch/x86/entry')
| -rw-r--r-- | arch/x86/entry/calling.h | 11 | ||||
| -rw-r--r-- | arch/x86/entry/entry_64_fred.S | 38 | ||||
| -rw-r--r-- | arch/x86/entry/syscalls/syscall_64.tbl | 1 | ||||
| -rw-r--r-- | arch/x86/entry/vsyscall/vsyscall_64.c | 17 |
4 files changed, 48 insertions, 19 deletions
diff --git a/arch/x86/entry/calling.h b/arch/x86/entry/calling.h index 94519688b007..77e2d920a640 100644 --- a/arch/x86/entry/calling.h +++ b/arch/x86/entry/calling.h @@ -99,7 +99,7 @@ For 32-bit we have the following conventions - kernel is built with .endif .endm -.macro CLEAR_REGS clear_bp=1 +.macro CLEAR_REGS clear_callee=1 /* * Sanitize registers of values that a speculation attack might * otherwise want to exploit. The lower registers are likely clobbered @@ -113,20 +113,19 @@ For 32-bit we have the following conventions - kernel is built with xorl %r9d, %r9d /* nospec r9 */ xorl %r10d, %r10d /* nospec r10 */ xorl %r11d, %r11d /* nospec r11 */ + .if \clear_callee xorl %ebx, %ebx /* nospec rbx */ - .if \clear_bp xorl %ebp, %ebp /* nospec rbp */ - .endif xorl %r12d, %r12d /* nospec r12 */ xorl %r13d, %r13d /* nospec r13 */ xorl %r14d, %r14d /* nospec r14 */ xorl %r15d, %r15d /* nospec r15 */ - + .endif .endm -.macro PUSH_AND_CLEAR_REGS rdx=%rdx rcx=%rcx rax=%rax save_ret=0 clear_bp=1 unwind_hint=1 +.macro PUSH_AND_CLEAR_REGS rdx=%rdx rcx=%rcx rax=%rax save_ret=0 clear_callee=1 unwind_hint=1 PUSH_REGS rdx=\rdx, rcx=\rcx, rax=\rax, save_ret=\save_ret unwind_hint=\unwind_hint - CLEAR_REGS clear_bp=\clear_bp + CLEAR_REGS clear_callee=\clear_callee .endm .macro POP_REGS pop_rdi=1 diff --git a/arch/x86/entry/entry_64_fred.S b/arch/x86/entry/entry_64_fred.S index 29c5c32c16c3..fafbd3e68cb8 100644 --- a/arch/x86/entry/entry_64_fred.S +++ b/arch/x86/entry/entry_64_fred.S @@ -16,7 +16,7 @@ .macro FRED_ENTER UNWIND_HINT_END_OF_STACK - ENDBR + ANNOTATE_NOENDBR PUSH_AND_CLEAR_REGS movq %rsp, %rdi /* %rdi -> pt_regs */ .endm @@ -97,8 +97,7 @@ SYM_FUNC_START(asm_fred_entry_from_kvm) push %rdi /* fred_ss handed in by the caller */ push %rbp pushf - mov $__KERNEL_CS, %rax - push %rax + push $__KERNEL_CS /* * Unlike the IDT event delivery, FRED _always_ pushes an error code @@ -112,18 +111,37 @@ SYM_FUNC_START(asm_fred_entry_from_kvm) push %rax /* Return RIP */ push $0 /* Error code, 0 for IRQ/NMI */ - PUSH_AND_CLEAR_REGS clear_bp=0 unwind_hint=0 + PUSH_AND_CLEAR_REGS clear_callee=0 unwind_hint=0 + movq %rsp, %rdi /* %rdi -> pt_regs */ + /* + * At this point: {rdi, rsi, rdx, rcx, r8, r9}, {r10, r11}, {rax, rdx} + * are clobbered, which corresponds to: arguments, extra caller-saved + * and return. All registers a C function is allowed to clobber. + * + * Notably, the callee-saved registers: {rbx, r12, r13, r14, r15} + * are untouched, with the exception of rbp, which carries the stack + * frame and will be restored before exit. + * + * Further calling another C function will not alter this state. + */ call __fred_entry_from_kvm /* Call the C entry point */ - POP_REGS - ERETS -1: + /* - * Objtool doesn't understand what ERETS does, this hint tells it that - * yes, we'll reach here and with what stack state. A save/restore pair - * isn't strictly needed, but it's the simplest form. + * When FRED, use ERETS to potentially clear NMIs, otherwise simply + * restore the stack pointer. + */ + ALTERNATIVE "nop; nop; mov %rbp, %rsp", \ + __stringify(add $C_PTREGS_SIZE, %rsp; ERETS), \ + X86_FEATURE_FRED + +1: /* + * Objtool doesn't understand ERETS, and the cfi register state is + * different from initial_func_cfi due to PUSH_REGS. Tell it the state + * is similar to where UNWIND_HINT_SAVE is. */ UNWIND_HINT_RESTORE + pop %rbp RET diff --git a/arch/x86/entry/syscalls/syscall_64.tbl b/arch/x86/entry/syscalls/syscall_64.tbl index 92cf0fe2291e..ced2a1deecd7 100644 --- a/arch/x86/entry/syscalls/syscall_64.tbl +++ b/arch/x86/entry/syscalls/syscall_64.tbl @@ -345,6 +345,7 @@ 333 common io_pgetevents sys_io_pgetevents 334 common rseq sys_rseq 335 common uretprobe sys_uretprobe +336 common uprobe sys_uprobe # don't use numbers 387 through 423, add new calls after the last # 'common' entry 424 common pidfd_send_signal sys_pidfd_send_signal diff --git a/arch/x86/entry/vsyscall/vsyscall_64.c b/arch/x86/entry/vsyscall/vsyscall_64.c index c9103a6fa06e..6e6c0a740837 100644 --- a/arch/x86/entry/vsyscall/vsyscall_64.c +++ b/arch/x86/entry/vsyscall/vsyscall_64.c @@ -124,7 +124,12 @@ bool emulate_vsyscall(unsigned long error_code, if ((error_code & (X86_PF_WRITE | X86_PF_USER)) != X86_PF_USER) return false; - if (!(error_code & X86_PF_INSTR)) { + /* + * Assume that faults at regs->ip are because of an + * instruction fetch. Return early and avoid + * emulation for faults during data accesses: + */ + if (address != regs->ip) { /* Failed vsyscall read */ if (vsyscall_mode == EMULATE) return false; @@ -137,12 +142,18 @@ bool emulate_vsyscall(unsigned long error_code, } /* + * X86_PF_INSTR is only set when NX is supported. When + * available, use it to double-check that the emulation code + * is only being used for instruction fetches: + */ + if (cpu_feature_enabled(X86_FEATURE_NX)) + WARN_ON_ONCE(!(error_code & X86_PF_INSTR)); + + /* * 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. */ - WARN_ON_ONCE(address != regs->ip); - if (vsyscall_mode == NONE) { warn_bad_vsyscall(KERN_INFO, regs, "vsyscall attempted with vsyscall=none"); |