Re: [PATCH v2] module: Don't wait for GOING modules

[Luis Chamberlain]

On Wed, Jan 18, 2023 at 09:02:52PM +0100, Borislav Petkov wrote:
> On Tue, Jan 17, 2023 at 04:04:22PM -0800, Luis Chamberlain wrote:
> > and now I'm seeing this while trying to build v5.1:
> > 
> > ld: arch/x86/boot/compressed/pgtable_64.o:(.bss+0x0): multiple definition of `__force_order';
> > arch/x86/boot/compressed/kaslr_64.o:(.bss+0x0): first defined here
> 
> You need to backport 
> 
> aa5cacdc29d7 ("x86/asm: Replace __force_order with a memory clobber")
> 
> for that.
> 
> Happens when building older kernels with newer toolchain.

Thanks that certainly helps. FWIW if someone needs it, I had to remove
the double colons on write cr0 and cr4 to compile, but this crashed :(
Any ideas?

diff --git a/arch/x86/boot/compressed/kaslr_64.c b/arch/x86/boot/compressed/kaslr_64.c
index 748456c365f4..9557c5a15b91 100644
--- a/arch/x86/boot/compressed/kaslr_64.c
+++ b/arch/x86/boot/compressed/kaslr_64.c
@@ -29,9 +29,6 @@
 #define __PAGE_OFFSET __PAGE_OFFSET_BASE
 #include "../../mm/ident_map.c"
 
-/* Used by pgtable.h asm code to force instruction serialization. */
-unsigned long __force_order;
-
 /* Used to track our page table allocation area. */
 struct alloc_pgt_data {
 	unsigned char *pgt_buf;
diff --git a/arch/x86/boot/compressed/pgtable_64.c b/arch/x86/boot/compressed/pgtable_64.c
index f8debf7aeb4c..7471b48524cb 100644
--- a/arch/x86/boot/compressed/pgtable_64.c
+++ b/arch/x86/boot/compressed/pgtable_64.c
@@ -5,15 +5,6 @@
 #include "pgtable.h"
 #include "../string.h"
 
-/*
- * __force_order is used by special_insns.h asm code to force instruction
- * serialization.
- *
- * It is not referenced from the code, but GCC < 5 with -fPIE would fail
- * due to an undefined symbol. Define it to make these ancient GCCs work.
- */
-unsigned long __force_order;
-
 #define BIOS_START_MIN		0x20000U	/* 128K, less than this is insane */
 #define BIOS_START_MAX		0x9f000U	/* 640K, absolute maximum */
 
diff --git a/arch/x86/include/asm/special_insns.h b/arch/x86/include/asm/special_insns.h
index 0a3c4cab39db..5586e4cf62d3 100644
--- a/arch/x86/include/asm/special_insns.h
+++ b/arch/x86/include/asm/special_insns.h
@@ -7,49 +7,50 @@
 
 #include <asm/nops.h>
 
+#define __FORCE_ORDER "m"(*(unsigned int *)0x1000UL)
+
 /*
- * Volatile isn't enough to prevent the compiler from reordering the
- * read/write functions for the control registers and messing everything up.
- * A memory clobber would solve the problem, but would prevent reordering of
- * all loads stores around it, which can hurt performance. Solution is to
- * use a variable and mimic reads and writes to it to enforce serialization
+ * The compiler should not reorder volatile asm statements with respect to each
+ * other: they should execute in program order. However GCC 4.9.x and 5.x have
+ * a bug (which was fixed in 8.1, 7.3 and 6.5) where they might reorder
+ * volatile asm. The write functions are not affected since they have memory
+ * clobbers preventing reordering. To prevent reads from being reordered with
+ * respect to writes, use a dummy memory operand
  */
-extern unsigned long __force_order;
-
 static inline unsigned long native_read_cr0(void)
 {
 	unsigned long val;
-	asm volatile("mov %%cr0,%0\n\t" : "=r" (val), "=m" (__force_order));
+	asm volatile("mov %%cr0,%0\n\t" : "=r" (val) : __FORCE_ORDER);
 	return val;
 }
 
 static inline void native_write_cr0(unsigned long val)
 {
-	asm volatile("mov %0,%%cr0": : "r" (val), "m" (__force_order));
+	asm volatile("mov %0,%%cr0": : "r" (val) : "memory");
 }
 
 static inline unsigned long native_read_cr2(void)
 {
 	unsigned long val;
-	asm volatile("mov %%cr2,%0\n\t" : "=r" (val), "=m" (__force_order));
+	asm volatile("mov %%cr2,%0\n\t" : "=r" (val) : __FORCE_ORDER);
 	return val;
 }
 
 static inline void native_write_cr2(unsigned long val)
 {
-	asm volatile("mov %0,%%cr2": : "r" (val), "m" (__force_order));
+	asm volatile("mov %0,%%cr2": : "r" (val) : "memory");
 }
 
 static inline unsigned long __native_read_cr3(void)
 {
 	unsigned long val;
-	asm volatile("mov %%cr3,%0\n\t" : "=r" (val), "=m" (__force_order));
+	asm volatile("mov %%cr3,%0\n\t" : "=r" (val) : __FORCE_ORDER);
 	return val;
 }
 
 static inline void native_write_cr3(unsigned long val)
 {
-	asm volatile("mov %0,%%cr3": : "r" (val), "m" (__force_order));
+	asm volatile("mov %0,%%cr3": : "r" (val) : "memory");
 }
 
 static inline unsigned long native_read_cr4(void)
@@ -64,17 +65,17 @@ static inline unsigned long native_read_cr4(void)
 	asm volatile("1: mov %%cr4, %0\n"
 		     "2:\n"
 		     _ASM_EXTABLE(1b, 2b)
-		     : "=r" (val), "=m" (__force_order) : "0" (0));
+		     : "=r" (val) : "0" (0), __FORCE_ORDER);
 #else
 	/* CR4 always exists on x86_64. */
-	asm volatile("mov %%cr4,%0\n\t" : "=r" (val), "=m" (__force_order));
+	asm volatile("mov %%cr4,%0\n\t" : "=r" (val) : __FORCE_ORDER);
 #endif
 	return val;
 }
 
 static inline void native_write_cr4(unsigned long val)
 {
-	asm volatile("mov %0,%%cr4": : "r" (val), "m" (__force_order));
+	asm volatile("mov %0,%%cr4": : "r" (val) : "memory");
 }
 
 #ifdef CONFIG_X86_64
-- 
2.35.1