x86/boot/32: Defer resyncing initial_page_table until per-cpu is set up

The x86 smpboot trampoline expects initial_page_table to have the
GDT mapped.  If the GDT ends up in a virtually mapped per-cpu page,
then it won't be in the page tables at all until perc-pu areas are
set up.  The result will be a triple fault the first time that the
CPU attempts to access the GDT after LGDT loads the perc-pu GDT.

This appears to be an old bug, but somehow the GDT fixmap rework
is triggering it.  This seems to have something to do with the
memory layout.

Signed-off-by: Andy Lutomirski <luto@kernel.org>
Cc: Ard Biesheuvel <ard.biesheuvel@linaro.org>
Cc: Boris Ostrovsky <boris.ostrovsky@oracle.com>
Cc: Borislav Petkov <bp@alien8.de>
Cc: Brian Gerst <brgerst@gmail.com>
Cc: Denys Vlasenko <dvlasenk@redhat.com>
Cc: H. Peter Anvin <hpa@zytor.com>
Cc: Josh Poimboeuf <jpoimboe@redhat.com>
Cc: Juergen Gross <jgross@suse.com>
Cc: Linus Torvalds <torvalds@linux-foundation.org>
Cc: Matt Fleming <matt@codeblueprint.co.uk>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: Thomas Garnier <thgarnie@google.com>
Cc: Thomas Gleixner <tglx@linutronix.de>
Cc: linux-efi@vger.kernel.org
Link: http://lkml.kernel.org/r/a553264a5972c6a86f9b5caac237470a0c74a720.1490218061.git.luto@kernel.org
Signed-off-by: Ingo Molnar <mingo@kernel.org>

diff --git a/arch/x86/kernel/setup.c b/arch/x86/kernel/setup.c
index 4bf0c8926a1c061bb22c1973962a0d668bfa3d98..56b1177155db0c9bce4ec444464d677341ba83fc 100644 (file)
--- a/arch/x86/kernel/setup.c
+++ b/arch/x86/kernel/setup.c
@@ -1226,21 +1226,6 @@ void __init setup_arch(char **cmdline_p)
 
        kasan_init();
 
-#ifdef CONFIG_X86_32
-       /* sync back kernel address range */
-       clone_pgd_range(initial_page_table + KERNEL_PGD_BOUNDARY,
-                       swapper_pg_dir     + KERNEL_PGD_BOUNDARY,
-                       KERNEL_PGD_PTRS);
-
-       /*
-        * sync back low identity map too.  It is used for example
-        * in the 32-bit EFI stub.
-        */
-       clone_pgd_range(initial_page_table,
-                       swapper_pg_dir     + KERNEL_PGD_BOUNDARY,
-                       min(KERNEL_PGD_PTRS, KERNEL_PGD_BOUNDARY));
-#endif
-
        tboot_probe();
 
        map_vsyscall();

diff --git a/arch/x86/kernel/setup_percpu.c b/arch/x86/kernel/setup_percpu.c
index 11338b0b3ad272fe5d879d985602b6082ab210ef..bb1e8cc0bc84816b8976dec088d3c18b038f8c01 100644 (file)
--- a/arch/x86/kernel/setup_percpu.c
+++ b/arch/x86/kernel/setup_percpu.c
@@ -288,4 +288,25 @@ void __init setup_per_cpu_areas(void)
 
        /* Setup cpu initialized, callin, callout masks */
        setup_cpu_local_masks();
+
+#ifdef CONFIG_X86_32
+       /*
+        * Sync back kernel address range.  We want to make sure that
+        * all kernel mappings, including percpu mappings, are available
+        * in the smpboot asm.  We can't reliably pick up percpu
+        * mappings using vmalloc_fault(), because exception dispatch
+        * needs percpu data.
+        */
+       clone_pgd_range(initial_page_table + KERNEL_PGD_BOUNDARY,
+                       swapper_pg_dir     + KERNEL_PGD_BOUNDARY,
+                       KERNEL_PGD_PTRS);
+
+       /*
+        * sync back low identity map too.  It is used for example
+        * in the 32-bit EFI stub.
+        */
+       clone_pgd_range(initial_page_table,
+                       swapper_pg_dir     + KERNEL_PGD_BOUNDARY,
+                       min(KERNEL_PGD_PTRS, KERNEL_PGD_BOUNDARY));
+#endif
 }