4.14-stable review patch. If anyone has any objections, please let me know.
------------------
From: Andy Lutomirski luto@kernel.org
commit 1a79797b58cddfa948420a7553241c79c013e3ca upstream.
This will simplify future changes that want scratch variables early in the SYSENTER handler -- they'll be able to spill registers to the stack. It also lets us get rid of a SWAPGS_UNSAFE_STACK user.
This does not depend on CONFIG_IA32_EMULATION=y because we'll want the stack space even without IA32 emulation.
As far as I can tell, the reason that this wasn't done from day 1 is that we use IST for #DB and #BP, which is IMO rather nasty and causes a lot more problems than it solves. But, since #DB uses IST, we don't actually need a real stack for SYSENTER (because SYSENTER with TF set will invoke #DB on the IST stack rather than the SYSENTER stack).
I want to remove IST usage from these vectors some day, and this patch is a prerequisite for that as well.
Signed-off-by: Andy Lutomirski luto@kernel.org Signed-off-by: Thomas Gleixner tglx@linutronix.de Reviewed-by: Thomas Gleixner tglx@linutronix.de Reviewed-by: Borislav Petkov bp@suse.de Cc: Boris Ostrovsky boris.ostrovsky@oracle.com Cc: Borislav Petkov bp@alien8.de Cc: Borislav Petkov bpetkov@suse.de Cc: Brian Gerst brgerst@gmail.com Cc: Dave Hansen dave.hansen@intel.com Cc: Dave Hansen dave.hansen@linux.intel.com Cc: David Laight David.Laight@aculab.com Cc: Denys Vlasenko dvlasenk@redhat.com Cc: Eduardo Valentin eduval@amazon.com Cc: Greg KH gregkh@linuxfoundation.org Cc: H. Peter Anvin hpa@zytor.com Cc: Josh Poimboeuf jpoimboe@redhat.com Cc: Juergen Gross jgross@suse.com Cc: Linus Torvalds torvalds@linux-foundation.org Cc: Peter Zijlstra peterz@infradead.org Cc: Rik van Riel riel@redhat.com Cc: Will Deacon will.deacon@arm.com Cc: aliguori@amazon.com Cc: daniel.gruss@iaik.tugraz.at Cc: hughd@google.com Cc: keescook@google.com Link: https://lkml.kernel.org/r/20171204150605.312726423@linutronix.de Signed-off-by: Ingo Molnar mingo@kernel.org Signed-off-by: Greg Kroah-Hartman gregkh@linuxfoundation.org
--- arch/x86/entry/entry_64_compat.S | 2 +- arch/x86/include/asm/processor.h | 3 --- arch/x86/kernel/asm-offsets.c | 5 +++++ arch/x86/kernel/asm-offsets_32.c | 5 ----- arch/x86/kernel/cpu/common.c | 4 +++- arch/x86/kernel/process.c | 2 -- arch/x86/kernel/traps.c | 3 +-- 7 files changed, 10 insertions(+), 14 deletions(-)
--- a/arch/x86/entry/entry_64_compat.S +++ b/arch/x86/entry/entry_64_compat.S @@ -48,7 +48,7 @@ */ ENTRY(entry_SYSENTER_compat) /* Interrupts are off on entry. */ - SWAPGS_UNSAFE_STACK + SWAPGS movq PER_CPU_VAR(cpu_current_top_of_stack), %rsp
/* --- a/arch/x86/include/asm/processor.h +++ b/arch/x86/include/asm/processor.h @@ -339,14 +339,11 @@ struct tss_struct { */ unsigned long io_bitmap[IO_BITMAP_LONGS + 1];
-#ifdef CONFIG_X86_32 /* * Space for the temporary SYSENTER stack. */ unsigned long SYSENTER_stack_canary; unsigned long SYSENTER_stack[64]; -#endif - } ____cacheline_aligned;
DECLARE_PER_CPU_SHARED_ALIGNED(struct tss_struct, cpu_tss); --- a/arch/x86/kernel/asm-offsets.c +++ b/arch/x86/kernel/asm-offsets.c @@ -93,4 +93,9 @@ void common(void) {
BLANK(); DEFINE(PTREGS_SIZE, sizeof(struct pt_regs)); + + /* Offset from cpu_tss to SYSENTER_stack */ + OFFSET(CPU_TSS_SYSENTER_stack, tss_struct, SYSENTER_stack); + /* Size of SYSENTER_stack */ + DEFINE(SIZEOF_SYSENTER_stack, sizeof(((struct tss_struct *)0)->SYSENTER_stack)); } --- a/arch/x86/kernel/asm-offsets_32.c +++ b/arch/x86/kernel/asm-offsets_32.c @@ -50,11 +50,6 @@ void foo(void) DEFINE(TSS_sysenter_sp0, offsetof(struct tss_struct, x86_tss.sp0) - offsetofend(struct tss_struct, SYSENTER_stack));
- /* Offset from cpu_tss to SYSENTER_stack */ - OFFSET(CPU_TSS_SYSENTER_stack, tss_struct, SYSENTER_stack); - /* Size of SYSENTER_stack */ - DEFINE(SIZEOF_SYSENTER_stack, sizeof(((struct tss_struct *)0)->SYSENTER_stack)); - #ifdef CONFIG_CC_STACKPROTECTOR BLANK(); OFFSET(stack_canary_offset, stack_canary, canary); --- a/arch/x86/kernel/cpu/common.c +++ b/arch/x86/kernel/cpu/common.c @@ -1361,7 +1361,9 @@ void syscall_init(void) * AMD doesn't allow SYSENTER in long mode (either 32- or 64-bit). */ wrmsrl_safe(MSR_IA32_SYSENTER_CS, (u64)__KERNEL_CS); - wrmsrl_safe(MSR_IA32_SYSENTER_ESP, 0ULL); + wrmsrl_safe(MSR_IA32_SYSENTER_ESP, + (unsigned long)this_cpu_ptr(&cpu_tss) + + offsetofend(struct tss_struct, SYSENTER_stack)); wrmsrl_safe(MSR_IA32_SYSENTER_EIP, (u64)entry_SYSENTER_compat); #else wrmsrl(MSR_CSTAR, (unsigned long)ignore_sysret); --- a/arch/x86/kernel/process.c +++ b/arch/x86/kernel/process.c @@ -71,9 +71,7 @@ __visible DEFINE_PER_CPU_SHARED_ALIGNED( */ .io_bitmap = { [0 ... IO_BITMAP_LONGS] = ~0 }, #endif -#ifdef CONFIG_X86_32 .SYSENTER_stack_canary = STACK_END_MAGIC, -#endif }; EXPORT_PER_CPU_SYMBOL(cpu_tss);
--- a/arch/x86/kernel/traps.c +++ b/arch/x86/kernel/traps.c @@ -794,14 +794,13 @@ dotraplinkage void do_debug(struct pt_re debug_stack_usage_dec();
exit: -#if defined(CONFIG_X86_32) /* * This is the most likely code path that involves non-trivial use * of the SYSENTER stack. Check that we haven't overrun it. */ WARN(this_cpu_read(cpu_tss.SYSENTER_stack_canary) != STACK_END_MAGIC, "Overran or corrupted SYSENTER stack\n"); -#endif + ist_exit(regs); } NOKPROBE_SYMBOL(do_debug);