From 2a172cc2491d54b70e5e54a19d2affa38f009a33 Mon Sep 17 00:00:00 2001 From: Hugh Dickins Date: Tue, 26 Sep 2017 18:43:07 -0700 Subject: [PATCH 024/103] kaiser: paranoid_entry pass cr3 need to paranoid_exit Neel Natu points out that paranoid_entry() was wrong to assume that an entry that did not need swapgs would not need SWITCH_KERNEL_CR3: paranoid_entry (used for debug breakpoint, int3, double fault or MCE; though I think it's only the MCE case that is cause for concern here) can break in at an awkward time, between cr3 switch and swapgs, but its handling always needs kernel gs and kernel cr3. Easy to fix in itself, but paranoid_entry() also needs to convey to paranoid_exit() (and my reading of macro idtentry says paranoid_entry and paranoid_exit are always paired) how to restore the prior state. The swapgs state is already conveyed by %ebx (0 or 1), so extend that also to convey when SWITCH_USER_CR3 will be needed (2 or 3). (Yes, I'd much prefer that 0 meant no swapgs, whereas it's the other way round: and a convention shared with error_entry() and error_exit(), which I don't want to touch. Perhaps I should have inverted the bit for switch cr3 too, but did not.) paranoid_exit() would be straightforward, except for TRACE_IRQS: it did TRACE_IRQS_IRETQ when doing swapgs, but TRACE_IRQS_IRETQ_DEBUG when not: which is it supposed to use when SWITCH_USER_CR3 is split apart from that? As best as I can determine, commit 5963e317b1e9 ("ftrace/x86: Do not change stacks in DEBUG when calling lockdep") missed the swapgs case, and should have used TRACE_IRQS_IRETQ_DEBUG there too (the discrepancy has nothing to do with the liberal use of _NO_STACK and _UNSAFE_STACK hereabouts: TRACE_IRQS_OFF_DEBUG has just been used in all cases); discrepancy lovingly preserved across several paranoid_exit() cleanups, but I'm now removing it. Neel further indicates that to use SWITCH_USER_CR3_NO_STACK there in paranoid_exit() is now not only unnecessary but unsafe: might corrupt syscall entry's unsafe_stack_register_backup of %rax. Just use SWITCH_USER_CR3: and delete SWITCH_USER_CR3_NO_STACK altogether, before we make the mistake of using it again. hughd adds: this commit fixes an issue in the Kaiser-without-PCIDs part of the series, and ought to be moved earlier, if you decided to make a release of Kaiser-without-PCIDs. Signed-off-by: Hugh Dickins Signed-off-by: Greg Kroah-Hartman --- arch/x86/entry/entry_64.S | 46 +++++++++++++++++++++++++++++++--------- arch/x86/entry/entry_64_compat.S | 2 +- arch/x86/include/asm/kaiser.h | 8 ------- 3 files changed, 37 insertions(+), 19 deletions(-) diff --git a/arch/x86/entry/entry_64.S b/arch/x86/entry/entry_64.S index e158fd5..41bf650 100644 --- a/arch/x86/entry/entry_64.S +++ b/arch/x86/entry/entry_64.S @@ -1053,7 +1053,11 @@ idtentry machine_check has_error_code=0 paranoid=1 do_sym=*machine_check_vec /* * Save all registers in pt_regs, and switch gs if needed. * Use slow, but surefire "are we in kernel?" check. - * Return: ebx=0: need swapgs on exit, ebx=1: otherwise + * + * Return: ebx=0: needs swapgs but not SWITCH_USER_CR3 in paranoid_exit + * ebx=1: needs neither swapgs nor SWITCH_USER_CR3 in paranoid_exit + * ebx=2: needs both swapgs and SWITCH_USER_CR3 in paranoid_exit + * ebx=3: needs SWITCH_USER_CR3 but not swapgs in paranoid_exit */ ENTRY(paranoid_entry) cld @@ -1065,9 +1069,26 @@ ENTRY(paranoid_entry) testl %edx, %edx js 1f /* negative -> in kernel */ SWAPGS - SWITCH_KERNEL_CR3 xorl %ebx, %ebx -1: ret +1: +#ifdef CONFIG_KAISER + /* + * We might have come in between a swapgs and a SWITCH_KERNEL_CR3 + * on entry, or between a SWITCH_USER_CR3 and a swapgs on exit. + * Do a conditional SWITCH_KERNEL_CR3: this could safely be done + * unconditionally, but we need to find out whether the reverse + * should be done on return (conveyed to paranoid_exit in %ebx). + */ + movq %cr3, %rax + testl $KAISER_SHADOW_PGD_OFFSET, %eax + jz 2f + orl $2, %ebx + andq $(~(X86_CR3_PCID_ASID_MASK | KAISER_SHADOW_PGD_OFFSET)), %rax + orq x86_cr3_pcid_noflush, %rax + movq %rax, %cr3 +2: +#endif + ret END(paranoid_entry) /* @@ -1080,20 +1101,25 @@ END(paranoid_entry) * be complicated. Fortunately, we there's no good reason * to try to handle preemption here. * - * On entry, ebx is "no swapgs" flag (1: don't need swapgs, 0: need it) + * On entry: ebx=0: needs swapgs but not SWITCH_USER_CR3 + * ebx=1: needs neither swapgs nor SWITCH_USER_CR3 + * ebx=2: needs both swapgs and SWITCH_USER_CR3 + * ebx=3: needs SWITCH_USER_CR3 but not swapgs */ ENTRY(paranoid_exit) DISABLE_INTERRUPTS(CLBR_NONE) TRACE_IRQS_OFF_DEBUG - testl %ebx, %ebx /* swapgs needed? */ + TRACE_IRQS_IRETQ_DEBUG +#ifdef CONFIG_KAISER + testl $2, %ebx /* SWITCH_USER_CR3 needed? */ + jz paranoid_exit_no_switch + SWITCH_USER_CR3 +paranoid_exit_no_switch: +#endif + testl $1, %ebx /* swapgs needed? */ jnz paranoid_exit_no_swapgs - TRACE_IRQS_IRETQ - SWITCH_USER_CR3_NO_STACK SWAPGS_UNSAFE_STACK - jmp paranoid_exit_restore paranoid_exit_no_swapgs: - TRACE_IRQS_IRETQ_DEBUG -paranoid_exit_restore: RESTORE_EXTRA_REGS RESTORE_C_REGS REMOVE_PT_GPREGS_FROM_STACK 8 diff --git a/arch/x86/entry/entry_64_compat.S b/arch/x86/entry/entry_64_compat.S index 0eb5801..d76a976 100644 --- a/arch/x86/entry/entry_64_compat.S +++ b/arch/x86/entry/entry_64_compat.S @@ -343,7 +343,7 @@ ENTRY(entry_INT80_compat) /* Go back to user mode. */ TRACE_IRQS_ON - SWITCH_USER_CR3_NO_STACK + SWITCH_USER_CR3 SWAPGS jmp restore_regs_and_iret END(entry_INT80_compat) diff --git a/arch/x86/include/asm/kaiser.h b/arch/x86/include/asm/kaiser.h index 48d8d70..3dc5f4c 100644 --- a/arch/x86/include/asm/kaiser.h +++ b/arch/x86/include/asm/kaiser.h @@ -63,20 +63,12 @@ _SWITCH_TO_KERNEL_CR3 %rax movq PER_CPU_VAR(unsafe_stack_register_backup), %rax .endm -.macro SWITCH_USER_CR3_NO_STACK -movq %rax, PER_CPU_VAR(unsafe_stack_register_backup) -_SWITCH_TO_USER_CR3 %rax %al -movq PER_CPU_VAR(unsafe_stack_register_backup), %rax -.endm - #else /* CONFIG_KAISER */ .macro SWITCH_KERNEL_CR3 reg .endm .macro SWITCH_USER_CR3 reg regb .endm -.macro SWITCH_USER_CR3_NO_STACK -.endm .macro SWITCH_KERNEL_CR3_NO_STACK .endm -- 2.7.4