Merge tag 'x86_core_for_v5.16_rc1' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip

Pull x86 core updates from Borislav Petkov:

 - Do not #GP on userspace use of CLI/STI but pretend it was a NOP to
   keep old userspace from breaking. Adjust the corresponding iopl
   selftest to that.

 - Improve stack overflow warnings to say which stack got overflowed and
   raise the exception stack sizes to 2 pages since overflowing the
   single page of exception stack is very easy to do nowadays with all
   the tracing machinery enabled. With that, rip out the custom mapping
   of AMD SEV's too.

 - A bunch of changes in preparation for FGKASLR like supporting more
   than 64K section headers in the relocs tool, correct ORC lookup table
   size to cover the whole kernel .text and other adjustments.

* tag 'x86_core_for_v5.16_rc1' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip:
  selftests/x86/iopl: Adjust to the faked iopl CLI/STI usage
  vmlinux.lds.h: Have ORC lookup cover entire _etext - _stext
  x86/boot/compressed: Avoid duplicate malloc() implementations
  x86/boot: Allow a "silent" kaslr random byte fetch
  x86/tools/relocs: Support >64K section headers
  x86/sev: Make the #VC exception stacks part of the default stacks storage
  x86: Increase exception stack sizes
  x86/mm/64: Improve stack overflow warnings
  x86/iopl: Fake iopl(3) CLI/STI usage

2 files changed, 17 insertions, 10 deletions

diff --git a/arch/x86/mm/cpu_entry_area.c b/arch/x86/mm/cpu_entry_area.c
index f5e1e60c9095..6c2f1b76a0b6 100644
--- a/arch/x86/mm/cpu_entry_area.c
+++ b/arch/x86/mm/cpu_entry_area.c
@@ -110,6 +110,13 @@ static void __init percpu_setup_exception_stacks(unsigned int cpu)
 	cea_map_stack(NMI);
 	cea_map_stack(DB);
 	cea_map_stack(MCE);
+
+	if (IS_ENABLED(CONFIG_AMD_MEM_ENCRYPT)) {
+		if (cc_platform_has(CC_ATTR_GUEST_STATE_ENCRYPT)) {
+			cea_map_stack(VC);
+			cea_map_stack(VC2);
+		}
+	}
 }
 #else
 static inline void percpu_setup_exception_stacks(unsigned int cpu)
diff --git a/arch/x86/mm/fault.c b/arch/x86/mm/fault.c
index 84a2c8c4af73..4bfed53e210e 100644
--- a/arch/x86/mm/fault.c
+++ b/arch/x86/mm/fault.c
@@ -32,6 +32,7 @@
 #include <asm/pgtable_areas.h>		/* VMALLOC_START, ...		*/
 #include <asm/kvm_para.h>		/* kvm_handle_async_pf		*/
 #include <asm/vdso.h>			/* fixup_vdso_exception()	*/
+#include <asm/irq_stack.h>
 
 #define CREATE_TRACE_POINTS
 #include <asm/trace/exceptions.h>
@@ -631,6 +632,9 @@ static noinline void
 page_fault_oops(struct pt_regs *regs, unsigned long error_code,
 		unsigned long address)
 {
+#ifdef CONFIG_VMAP_STACK
+	struct stack_info info;
+#endif
 	unsigned long flags;
 	int sig;
 
@@ -649,9 +653,7 @@ page_fault_oops(struct pt_regs *regs, unsigned long error_code,
 	 * that we're in vmalloc space to avoid this.
 	 */
 	if (is_vmalloc_addr((void *)address) &&
-	    (((unsigned long)current->stack - 1 - address < PAGE_SIZE) ||
-	     address - ((unsigned long)current->stack + THREAD_SIZE) < PAGE_SIZE)) {
-		unsigned long stack = __this_cpu_ist_top_va(DF) - sizeof(void *);
+	    get_stack_guard_info((void *)address, &info)) {
 		/*
 		 * We're likely to be running with very little stack space
 		 * left.  It's plausible that we'd hit this condition but
@@ -662,13 +664,11 @@ page_fault_oops(struct pt_regs *regs, unsigned long error_code,
 		 * and then double-fault, though, because we're likely to
 		 * break the console driver and lose most of the stack dump.
 		 */
-		asm volatile ("movq %[stack], %%rsp\n\t"
-			      "call handle_stack_overflow\n\t"
-			      "1: jmp 1b"
-			      : ASM_CALL_CONSTRAINT
-			      : "D" ("kernel stack overflow (page fault)"),
-				"S" (regs), "d" (address),
-				[stack] "rm" (stack));
+		call_on_stack(__this_cpu_ist_top_va(DF) - sizeof(void*),
+			      handle_stack_overflow,
+			      ASM_CALL_ARG3,
+			      , [arg1] "r" (regs), [arg2] "r" (address), [arg3] "r" (&info));
+
 		unreachable();
 	}
 #endif