diff options
author | Andy Lutomirski <luto@kernel.org> | 2016-03-09 19:00:30 -0800 |
---|---|---|
committer | Ingo Molnar <mingo@kernel.org> | 2016-03-10 09:48:13 +0100 |
commit | f2b375756c839ff655a3e0b45e339f8fbf973093 (patch) | |
tree | b7e4af1375fe03f342aea24fb20da5a1accf0426 /arch/x86/entry | |
parent | 8bb5643686d2898bec181c407651cf84e77d413f (diff) | |
download | talos-obmc-linux-f2b375756c839ff655a3e0b45e339f8fbf973093.tar.gz talos-obmc-linux-f2b375756c839ff655a3e0b45e339f8fbf973093.zip |
x86/entry: Vastly simplify SYSENTER TF (single-step) handling
Due to a blatant design error, SYSENTER doesn't clear TF (single-step).
As a result, if a user does SYSENTER with TF set, we will single-step
through the kernel until something clears TF. There is absolutely
nothing we can do to prevent this short of turning off SYSENTER [1].
Simplify the handling considerably with two changes:
1. We already sanitize EFLAGS in SYSENTER to clear NT and AC. We can
add TF to that list of flags to sanitize with no overhead whatsoever.
2. Teach do_debug() to ignore single-step traps in the SYSENTER prologue.
That's all we need to do.
Don't get too excited -- our handling is still buggy on 32-bit
kernels. There's nothing wrong with the SYSENTER code itself, but
the #DB prologue has a clever fixup for traps on the very first
instruction of entry_SYSENTER_32, and the fixup doesn't work quite
correctly. The next two patches will fix that.
[1] We could probably prevent it by forcing BTF on at all times and
making sure we clear TF before any branches in the SYSENTER
code. Needless to say, this is a bad idea.
Signed-off-by: Andy Lutomirski <luto@kernel.org>
Cc: Andrew Cooper <andrew.cooper3@citrix.com>
Cc: Andy Lutomirski <luto@amacapital.net>
Cc: Borislav Petkov <bp@alien8.de>
Cc: Brian Gerst <brgerst@gmail.com>
Cc: Denys Vlasenko <dvlasenk@redhat.com>
Cc: H. Peter Anvin <hpa@zytor.com>
Cc: Linus Torvalds <torvalds@linux-foundation.org>
Cc: Oleg Nesterov <oleg@redhat.com>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: Thomas Gleixner <tglx@linutronix.de>
Link: http://lkml.kernel.org/r/a30d2ea06fe4b621fe6a9ef911b02c0f38feb6f2.1457578375.git.luto@kernel.org
Signed-off-by: Ingo Molnar <mingo@kernel.org>
Diffstat (limited to 'arch/x86/entry')
-rw-r--r-- | arch/x86/entry/entry_32.S | 42 | ||||
-rw-r--r-- | arch/x86/entry/entry_64_compat.S | 9 |
2 files changed, 38 insertions, 13 deletions
diff --git a/arch/x86/entry/entry_32.S b/arch/x86/entry/entry_32.S index 76109068149f..b2e1d446bdf8 100644 --- a/arch/x86/entry/entry_32.S +++ b/arch/x86/entry/entry_32.S @@ -287,7 +287,26 @@ need_resched: END(resume_kernel) #endif - # SYSENTER call handler stub +GLOBAL(__begin_SYSENTER_singlestep_region) +/* + * All code from here through __end_SYSENTER_singlestep_region is subject + * to being single-stepped if a user program sets TF and executes SYSENTER. + * There is absolutely nothing that we can do to prevent this from happening + * (thanks Intel!). To keep our handling of this situation as simple as + * possible, we handle TF just like AC and NT, except that our #DB handler + * will ignore all of the single-step traps generated in this range. + */ + +#ifdef CONFIG_XEN +/* + * Xen doesn't set %esp to be precisely what the normal SYSENTER + * entry point expects, so fix it up before using the normal path. + */ +ENTRY(xen_sysenter_target) + addl $5*4, %esp /* remove xen-provided frame */ + jmp sysenter_past_esp +#endif + ENTRY(entry_SYSENTER_32) movl TSS_sysenter_sp0(%esp), %esp sysenter_past_esp: @@ -301,19 +320,25 @@ sysenter_past_esp: SAVE_ALL pt_regs_ax=$-ENOSYS /* save rest */ /* - * SYSENTER doesn't filter flags, so we need to clear NT and AC - * ourselves. To save a few cycles, we can check whether + * SYSENTER doesn't filter flags, so we need to clear NT, AC + * and TF ourselves. To save a few cycles, we can check whether * either was set instead of doing an unconditional popfq. * This needs to happen before enabling interrupts so that * we don't get preempted with NT set. * + * If TF is set, we will single-step all the way to here -- do_debug + * will ignore all the traps. (Yes, this is slow, but so is + * single-stepping in general. This allows us to avoid having + * a more complicated code to handle the case where a user program + * forces us to single-step through the SYSENTER entry code.) + * * NB.: .Lsysenter_fix_flags is a label with the code under it moved * out-of-line as an optimization: NT is unlikely to be set in the * majority of the cases and instead of polluting the I$ unnecessarily, * we're keeping that code behind a branch which will predict as * not-taken and therefore its instructions won't be fetched. */ - testl $X86_EFLAGS_NT|X86_EFLAGS_AC, PT_EFLAGS(%esp) + testl $X86_EFLAGS_NT|X86_EFLAGS_AC|X86_EFLAGS_TF, PT_EFLAGS(%esp) jnz .Lsysenter_fix_flags .Lsysenter_flags_fixed: @@ -369,6 +394,7 @@ sysenter_past_esp: pushl $X86_EFLAGS_FIXED popfl jmp .Lsysenter_flags_fixed +GLOBAL(__end_SYSENTER_singlestep_region) ENDPROC(entry_SYSENTER_32) # system call handler stub @@ -651,14 +677,6 @@ ENTRY(spurious_interrupt_bug) END(spurious_interrupt_bug) #ifdef CONFIG_XEN -/* - * Xen doesn't set %esp to be precisely what the normal SYSENTER - * entry point expects, so fix it up before using the normal path. - */ -ENTRY(xen_sysenter_target) - addl $5*4, %esp /* remove xen-provided frame */ - jmp sysenter_past_esp - ENTRY(xen_hypervisor_callback) pushl $-1 /* orig_ax = -1 => not a system call */ SAVE_ALL diff --git a/arch/x86/entry/entry_64_compat.S b/arch/x86/entry/entry_64_compat.S index da5c19443e0b..cbb5e6943d9b 100644 --- a/arch/x86/entry/entry_64_compat.S +++ b/arch/x86/entry/entry_64_compat.S @@ -94,13 +94,19 @@ ENTRY(entry_SYSENTER_compat) * This needs to happen before enabling interrupts so that * we don't get preempted with NT set. * + * If TF is set, we will single-step all the way to here -- do_debug + * will ignore all the traps. (Yes, this is slow, but so is + * single-stepping in general. This allows us to avoid having + * a more complicated code to handle the case where a user program + * forces us to single-step through the SYSENTER entry code.) + * * NB.: .Lsysenter_fix_flags is a label with the code under it moved * out-of-line as an optimization: NT is unlikely to be set in the * majority of the cases and instead of polluting the I$ unnecessarily, * we're keeping that code behind a branch which will predict as * not-taken and therefore its instructions won't be fetched. */ - testl $X86_EFLAGS_NT|X86_EFLAGS_AC, EFLAGS(%rsp) + testl $X86_EFLAGS_NT|X86_EFLAGS_AC|X86_EFLAGS_TF, EFLAGS(%rsp) jnz .Lsysenter_fix_flags .Lsysenter_flags_fixed: @@ -121,6 +127,7 @@ ENTRY(entry_SYSENTER_compat) pushq $X86_EFLAGS_FIXED popfq jmp .Lsysenter_flags_fixed +GLOBAL(__end_entry_SYSENTER_compat) ENDPROC(entry_SYSENTER_compat) /* |