x86/stackprotector/32: Make the canary into a regular percpu variable

On 32-bit kernels, the stackprotector canary is quite nasty -- it is
stored at %gs:(20), which is nasty because 32-bit kernels use %fs for
percpu storage.  It's even nastier because it means that whether %gs
contains userspace state or kernel state while running kernel code
depends on whether stackprotector is enabled (this is
CONFIG_X86_32_LAZY_GS), and this setting radically changes the way
that segment selectors work.  Supporting both variants is a
maintenance and testing mess.

Merely rearranging so that percpu and the stack canary
share the same segment would be messy as the 32-bit percpu address
layout isn't currently compatible with putting a variable at a fixed
offset.

Fortunately, GCC 8.1 added options that allow the stack canary to be
accessed as %fs:__stack_chk_guard, effectively turning it into an ordinary
percpu variable.  This lets us get rid of all of the code to manage the
stack canary GDT descriptor and the CONFIG_X86_32_LAZY_GS mess.

(That name is special.  We could use any symbol we want for the
 %fs-relative mode, but for CONFIG_SMP=n, gcc refuses to let us use any
 name other than __stack_chk_guard.)

Forcibly disable stackprotector on older compilers that don't support
the new options and turn the stack canary into a percpu variable. The
"lazy GS" approach is now used for all 32-bit configurations.

Also makes load_gs_index() work on 32-bit kernels. On 64-bit kernels,
it loads the GS selector and updates the user GSBASE accordingly. (This
is unchanged.) On 32-bit kernels, it loads the GS selector and updates
GSBASE, which is now always the user base. This means that the overall
effect is the same on 32-bit and 64-bit, which avoids some ifdeffery.

 [ bp: Massage commit message. ]

Signed-off-by: Andy Lutomirski <luto@kernel.org>
Signed-off-by: Borislav Petkov <bp@suse.de>
Link: https://lkml.kernel.org/r/c0ff7dba14041c7e5d1cae5d4df052f03759bef3.1613243844.git.luto@kernel.org

1 files changed, 4 insertions, 52 deletions

diff --git a/arch/x86/entry/entry_32.S b/arch/x86/entry/entry_32.S
index df8c017e6161..eb0cb662bca5 100644
--- a/arch/x86/entry/entry_32.S
+++ b/arch/x86/entry/entry_32.S
@@ -20,7 +20,7 @@
  *	1C(%esp) - %ds
  *	20(%esp) - %es
  *	24(%esp) - %fs
- *	28(%esp) - %gs		saved iff !CONFIG_X86_32_LAZY_GS
+ *	28(%esp) - unused -- was %gs on old stackprotector kernels
  *	2C(%esp) - orig_eax
  *	30(%esp) - %eip
  *	34(%esp) - %cs
@@ -56,14 +56,9 @@
 /*
  * User gs save/restore
  *
- * %gs is used for userland TLS and kernel only uses it for stack
- * canary which is required to be at %gs:20 by gcc.  Read the comment
- * at the top of stackprotector.h for more info.
- *
- * Local labels 98 and 99 are used.
+ * This is leftover junk from CONFIG_X86_32_LAZY_GS.  A subsequent patch
+ * will remove it entirely.
  */
-#ifdef CONFIG_X86_32_LAZY_GS
-
  /* unfortunately push/pop can't be no-op */
 .macro PUSH_GS
 	pushl	$0
@@ -86,49 +81,6 @@
 .macro SET_KERNEL_GS reg
 .endm
 
-#else	/* CONFIG_X86_32_LAZY_GS */
-
-.macro PUSH_GS
-	pushl	%gs
-.endm
-
-.macro POP_GS pop=0
-98:	popl	%gs
-  .if \pop <> 0
-	add	$\pop, %esp
-  .endif
-.endm
-.macro POP_GS_EX
-.pushsection .fixup, "ax"
-99:	movl	$0, (%esp)
-	jmp	98b
-.popsection
-	_ASM_EXTABLE(98b, 99b)
-.endm
-
-.macro PTGS_TO_GS
-98:	mov	PT_GS(%esp), %gs
-.endm
-.macro PTGS_TO_GS_EX
-.pushsection .fixup, "ax"
-99:	movl	$0, PT_GS(%esp)
-	jmp	98b
-.popsection
-	_ASM_EXTABLE(98b, 99b)
-.endm
-
-.macro GS_TO_REG reg
-	movl	%gs, \reg
-.endm
-.macro REG_TO_PTGS reg
-	movl	\reg, PT_GS(%esp)
-.endm
-.macro SET_KERNEL_GS reg
-	movl	$(__KERNEL_STACK_CANARY), \reg
-	movl	\reg, %gs
-.endm
-
-#endif /* CONFIG_X86_32_LAZY_GS */
 
 /* Unconditionally switch to user cr3 */
 .macro SWITCH_TO_USER_CR3 scratch_reg:req
@@ -779,7 +731,7 @@ SYM_CODE_START(__switch_to_asm)
 
 #ifdef CONFIG_STACKPROTECTOR
 	movl	TASK_stack_canary(%edx), %ebx
-	movl	%ebx, PER_CPU_VAR(stack_canary)+stack_canary_offset
+	movl	%ebx, PER_CPU_VAR(__stack_chk_guard)
 #endif
 
 #ifdef CONFIG_RETPOLINE