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, 16 insertions, 63 deletions

diff --git a/arch/x86/include/asm/stackprotector.h b/arch/x86/include/asm/stackprotector.h
index 7fb482f0f25b..b6ffe58c70fa 100644
--- a/arch/x86/include/asm/stackprotector.h
+++ b/arch/x86/include/asm/stackprotector.h
@@ -5,30 +5,23 @@
  * Stack protector works by putting predefined pattern at the start of
  * the stack frame and verifying that it hasn't been overwritten when
  * returning from the function.  The pattern is called stack canary
- * and unfortunately gcc requires it to be at a fixed offset from %gs.
- * On x86_64, the offset is 40 bytes and on x86_32 20 bytes.  x86_64
- * and x86_32 use segment registers differently and thus handles this
- * requirement differently.
+ * and unfortunately gcc historically required it to be at a fixed offset
+ * from the percpu segment base.  On x86_64, the offset is 40 bytes.
  *
- * On x86_64, %gs is shared by percpu area and stack canary.  All
- * percpu symbols are zero based and %gs points to the base of percpu
- * area.  The first occupant of the percpu area is always
- * fixed_percpu_data which contains stack_canary at offset 40.  Userland
- * %gs is always saved and restored on kernel entry and exit using
- * swapgs, so stack protector doesn't add any complexity there.
+ * The same segment is shared by percpu area and stack canary.  On
+ * x86_64, percpu symbols are zero based and %gs (64-bit) points to the
+ * base of percpu area.  The first occupant of the percpu area is always
+ * fixed_percpu_data which contains stack_canary at the approproate
+ * offset.  On x86_32, the stack canary is just a regular percpu
+ * variable.
  *
- * On x86_32, it's slightly more complicated.  As in x86_64, %gs is
- * used for userland TLS.  Unfortunately, some processors are much
- * slower at loading segment registers with different value when
- * entering and leaving the kernel, so the kernel uses %fs for percpu
- * area and manages %gs lazily so that %gs is switched only when
- * necessary, usually during task switch.
+ * Putting percpu data in %fs on 32-bit is a minor optimization compared to
+ * using %gs.  Since 32-bit userspace normally has %fs == 0, we are likely
+ * to load 0 into %fs on exit to usermode, whereas with percpu data in
+ * %gs, we are likely to load a non-null %gs on return to user mode.
  *
- * As gcc requires the stack canary at %gs:20, %gs can't be managed
- * lazily if stack protector is enabled, so the kernel saves and
- * restores userland %gs on kernel entry and exit.  This behavior is
- * controlled by CONFIG_X86_32_LAZY_GS and accessors are defined in
- * system.h to hide the details.
+ * Once we are willing to require GCC 8.1 or better for 64-bit stackprotector
+ * support, we can remove some of this complexity.
  */
 
 #ifndef _ASM_STACKPROTECTOR_H
@@ -45,14 +38,6 @@
 #include <linux/sched.h>
 
 /*
- * 24 byte read-only segment initializer for stack canary.  Linker
- * can't handle the address bit shifting.  Address will be set in
- * head_32 for boot CPU and setup_per_cpu_areas() for others.
- */
-#define GDT_STACK_CANARY_INIT						\
-	[GDT_ENTRY_STACK_CANARY] = GDT_ENTRY_INIT(0x4090, 0, 0x18),
-
-/*
  * Initialize the stackprotector canary value.
  *
  * NOTE: this must only be called from functions that never return
@@ -86,7 +71,7 @@ static __always_inline void boot_init_stack_canary(void)
 #ifdef CONFIG_X86_64
 	this_cpu_write(fixed_percpu_data.stack_canary, canary);
 #else
-	this_cpu_write(stack_canary.canary, canary);
+	this_cpu_write(__stack_chk_guard, canary);
 #endif
 }
 
@@ -95,48 +80,16 @@ static inline void cpu_init_stack_canary(int cpu, struct task_struct *idle)
 #ifdef CONFIG_X86_64
 	per_cpu(fixed_percpu_data.stack_canary, cpu) = idle->stack_canary;
 #else
-	per_cpu(stack_canary.canary, cpu) = idle->stack_canary;
-#endif
-}
-
-static inline void setup_stack_canary_segment(int cpu)
-{
-#ifdef CONFIG_X86_32
-	unsigned long canary = (unsigned long)&per_cpu(stack_canary, cpu);
-	struct desc_struct *gdt_table = get_cpu_gdt_rw(cpu);
-	struct desc_struct desc;
-
-	desc = gdt_table[GDT_ENTRY_STACK_CANARY];
-	set_desc_base(&desc, canary);
-	write_gdt_entry(gdt_table, GDT_ENTRY_STACK_CANARY, &desc, DESCTYPE_S);
-#endif
-}
-
-static inline void load_stack_canary_segment(void)
-{
-#ifdef CONFIG_X86_32
-	asm("mov %0, %%gs" : : "r" (__KERNEL_STACK_CANARY) : "memory");
+	per_cpu(__stack_chk_guard, cpu) = idle->stack_canary;
 #endif
 }
 
 #else	/* STACKPROTECTOR */
 
-#define GDT_STACK_CANARY_INIT
-
 /* dummy boot_init_stack_canary() is defined in linux/stackprotector.h */
 
-static inline void setup_stack_canary_segment(int cpu)
-{ }
-
 static inline void cpu_init_stack_canary(int cpu, struct task_struct *idle)
 { }
 
-static inline void load_stack_canary_segment(void)
-{
-#ifdef CONFIG_X86_32
-	asm volatile ("mov %0, %%gs" : : "r" (0));
-#endif
-}
-
 #endif	/* STACKPROTECTOR */
 #endif	/* _ASM_STACKPROTECTOR_H */