From: Dave Hansen <dave.han...@linux.intel.com> There are times where the kernel is entered but there is no safe stack, like at SYSCALL entry. To obtain a safe stack, we have to clobber %rsp and store the clobbered value in 'rsp_scratch'.
Map this to userspace to allow us to do this stack switch before the CR3 switch. Signed-off-by: Dave Hansen <dave.han...@linux.intel.com> Cc: Andy Lutomirski <l...@kernel.org> Cc: Borislav Petkov <b...@alien8.de> Cc: Brian Gerst <brge...@gmail.com> Cc: Daniel Gruss <daniel.gr...@iaik.tugraz.at> Cc: Denys Vlasenko <dvlas...@redhat.com> Cc: H. Peter Anvin <h...@zytor.com> Cc: Hugh Dickins <hu...@google.com> Cc: Josh Poimboeuf <jpoim...@redhat.com> Cc: Kees Cook <keesc...@google.com> Cc: Linus Torvalds <torva...@linux-foundation.org> Cc: Michael Schwarz <michael.schw...@iaik.tugraz.at> Cc: Moritz Lipp <moritz.l...@iaik.tugraz.at> Cc: Peter Zijlstra <pet...@infradead.org> Cc: Richard Fellner <richard.fell...@student.tugraz.at> Cc: Thomas Gleixner <t...@linutronix.de> Cc: linux...@kvack.org Link: http://lkml.kernel.org/r/20171123003459.c0ff1...@viggo.jf.intel.com Signed-off-by: Ingo Molnar <mi...@kernel.org> --- arch/x86/kernel/process_64.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/arch/x86/kernel/process_64.c b/arch/x86/kernel/process_64.c index bafe65b08697..9a0220aa2bf9 100644 --- a/arch/x86/kernel/process_64.c +++ b/arch/x86/kernel/process_64.c @@ -59,7 +59,7 @@ #include <asm/unistd_32_ia32.h> #endif -__visible DEFINE_PER_CPU(unsigned long, rsp_scratch); +__visible DEFINE_PER_CPU_USER_MAPPED(unsigned long, rsp_scratch); /* Prints also some state that isn't saved in the pt_regs */ void __show_regs(struct pt_regs *regs, int all) -- 2.14.1
