[PATCH 4.4 04/27] x86/efi: Hoist page table switching code into efi_call_virt()

[Greg Kroah-Hartman]

4.4-stable review patch.  If anyone has any objections, please let me know.

------------------

From: Matt Fleming <matt@xxxxxxxxxxxxxxxxxxx>

commit c9f2a9a65e4855b74d92cdad688f6ee4a1a323ff upstream.

This change is a prerequisite for pending patches that switch to
a dedicated EFI page table, instead of using 'trampoline_pgd'
which shares PGD entries with 'swapper_pg_dir'. The pending
patches make it impossible to dereference the runtime service
function pointer without first switching %cr3.

It's true that we now have duplicated switching code in
efi_call_virt() and efi_call_phys_{prolog,epilog}() but we are
sacrificing code duplication for a little more clarity and the
ease of writing the page table switching code in C instead of
asm.

Signed-off-by: Matt Fleming <matt@xxxxxxxxxxxxxxxxxxx>
Reviewed-by: Borislav Petkov <bp@xxxxxxx>
Acked-by: Borislav Petkov <bp@xxxxxxx>
Cc: Andrew Morton <akpm@xxxxxxxxxxxxxxxxxxxx>
Cc: Andy Lutomirski <luto@xxxxxxxxxxxxxx>
Cc: Andy Lutomirski <luto@xxxxxxxxxx>
Cc: Ard Biesheuvel <ard.biesheuvel@xxxxxxxxxx>
Cc: Borislav Petkov <bp@xxxxxxxxx>
Cc: Brian Gerst <brgerst@xxxxxxxxx>
Cc: Dave Jones <davej@xxxxxxxxxxxxxxxxx>
Cc: Denys Vlasenko <dvlasenk@xxxxxxxxxx>
Cc: H. Peter Anvin <hpa@xxxxxxxxx>
Cc: Linus Torvalds <torvalds@xxxxxxxxxxxxxxxxxxxx>
Cc: Peter Zijlstra <peterz@xxxxxxxxxxxxx>
Cc: Sai Praneeth Prakhya <sai.praneeth.prakhya@xxxxxxxxx>
Cc: Stephen Smalley <sds@xxxxxxxxxxxxx>
Cc: Thomas Gleixner <tglx@xxxxxxxxxxxxx>
Cc: Toshi Kani <toshi.kani@xxxxxx>
Cc: linux-efi@xxxxxxxxxxxxxxx
Link: http://lkml.kernel.org/r/1448658575-17029-5-git-send-email-matt@xxxxxxxxxxxxxxxxxxx
Signed-off-by: Ingo Molnar <mingo@xxxxxxxxxx>
Cc: "Ghannam, Yazen" <Yazen.Ghannam@xxxxxxx>
Signed-off-by: Greg Kroah-Hartman <gregkh@xxxxxxxxxxxxxxxxxxx>

---
 arch/x86/include/asm/efi.h          |   25 ++++++++++++++++++++
 arch/x86/platform/efi/efi_64.c      |   24 +++++++++-----------
 arch/x86/platform/efi/efi_stub_64.S |   43 ------------------------------------
 3 files changed, 36 insertions(+), 56 deletions(-)

--- a/arch/x86/include/asm/efi.h
+++ b/arch/x86/include/asm/efi.h
@@ -3,6 +3,7 @@
 
 #include <asm/fpu/api.h>
 #include <asm/pgtable.h>
+#include <asm/tlb.h>
 
 /*
  * We map the EFI regions needed for runtime services non-contiguously,
@@ -64,6 +65,17 @@ extern u64 asmlinkage efi_call(void *fp,
 
 #define efi_call_phys(f, args...)		efi_call((f), args)
 
+/*
+ * Scratch space used for switching the pagetable in the EFI stub
+ */
+struct efi_scratch {
+	u64	r15;
+	u64	prev_cr3;
+	pgd_t	*efi_pgt;
+	bool	use_pgd;
+	u64	phys_stack;
+} __packed;
+
 #define efi_call_virt(f, ...)						\
 ({									\
 	efi_status_t __s;						\
@@ -71,7 +83,20 @@ extern u64 asmlinkage efi_call(void *fp,
 	efi_sync_low_kernel_mappings();					\
 	preempt_disable();						\
 	__kernel_fpu_begin();						\
+									\
+	if (efi_scratch.use_pgd) {					\
+		efi_scratch.prev_cr3 = read_cr3();			\
+		write_cr3((unsigned long)efi_scratch.efi_pgt);		\
+		__flush_tlb_all();					\
+	}								\
+									\
 	__s = efi_call((void *)efi.systab->runtime->f, __VA_ARGS__);	\
+									\
+	if (efi_scratch.use_pgd) {					\
+		write_cr3(efi_scratch.prev_cr3);			\
+		__flush_tlb_all();					\
+	}								\
+									\
 	__kernel_fpu_end();						\
 	preempt_enable();						\
 	__s;								\
--- a/arch/x86/platform/efi/efi_64.c
+++ b/arch/x86/platform/efi/efi_64.c
@@ -47,16 +47,7 @@
  */
 static u64 efi_va = EFI_VA_START;
 
-/*
- * Scratch space used for switching the pagetable in the EFI stub
- */
-struct efi_scratch {
-	u64 r15;
-	u64 prev_cr3;
-	pgd_t *efi_pgt;
-	bool use_pgd;
-	u64 phys_stack;
-} __packed;
+struct efi_scratch efi_scratch;
 
 static void __init early_code_mapping_set_exec(int executable)
 {
@@ -83,8 +74,11 @@ pgd_t * __init efi_call_phys_prolog(void
 	int pgd;
 	int n_pgds;
 
-	if (!efi_enabled(EFI_OLD_MEMMAP))
-		return NULL;
+	if (!efi_enabled(EFI_OLD_MEMMAP)) {
+		save_pgd = (pgd_t *)read_cr3();
+		write_cr3((unsigned long)efi_scratch.efi_pgt);
+		goto out;
+	}
 
 	early_code_mapping_set_exec(1);
 
@@ -96,6 +90,7 @@ pgd_t * __init efi_call_phys_prolog(void
 		vaddress = (unsigned long)__va(pgd * PGDIR_SIZE);
 		set_pgd(pgd_offset_k(pgd * PGDIR_SIZE), *pgd_offset_k(vaddress));
 	}
+out:
 	__flush_tlb_all();
 
 	return save_pgd;
@@ -109,8 +104,11 @@ void __init efi_call_phys_epilog(pgd_t *
 	int pgd_idx;
 	int nr_pgds;
 
-	if (!save_pgd)
+	if (!efi_enabled(EFI_OLD_MEMMAP)) {
+		write_cr3((unsigned long)save_pgd);
+		__flush_tlb_all();
 		return;
+	}
 
 	nr_pgds = DIV_ROUND_UP((max_pfn << PAGE_SHIFT) , PGDIR_SIZE);
 
--- a/arch/x86/platform/efi/efi_stub_64.S
+++ b/arch/x86/platform/efi/efi_stub_64.S
@@ -38,41 +38,6 @@
 	mov %rsi, %cr0;			\
 	mov (%rsp), %rsp
 
-	/* stolen from gcc */
-	.macro FLUSH_TLB_ALL
-	movq %r15, efi_scratch(%rip)
-	movq %r14, efi_scratch+8(%rip)
-	movq %cr4, %r15
-	movq %r15, %r14
-	andb $0x7f, %r14b
-	movq %r14, %cr4
-	movq %r15, %cr4
-	movq efi_scratch+8(%rip), %r14
-	movq efi_scratch(%rip), %r15
-	.endm
-
-	.macro SWITCH_PGT
-	cmpb $0, efi_scratch+24(%rip)
-	je 1f
-	movq %r15, efi_scratch(%rip)		# r15
-	# save previous CR3
-	movq %cr3, %r15
-	movq %r15, efi_scratch+8(%rip)		# prev_cr3
-	movq efi_scratch+16(%rip), %r15		# EFI pgt
-	movq %r15, %cr3
-	1:
-	.endm
-
-	.macro RESTORE_PGT
-	cmpb $0, efi_scratch+24(%rip)
-	je 2f
-	movq efi_scratch+8(%rip), %r15
-	movq %r15, %cr3
-	movq efi_scratch(%rip), %r15
-	FLUSH_TLB_ALL
-	2:
-	.endm
-
 ENTRY(efi_call)
 	SAVE_XMM
 	mov (%rsp), %rax
@@ -83,16 +48,8 @@ ENTRY(efi_call)
 	mov %r8, %r9
 	mov %rcx, %r8
 	mov %rsi, %rcx
-	SWITCH_PGT
 	call *%rdi
-	RESTORE_PGT
 	addq $48, %rsp
 	RESTORE_XMM
 	ret
 ENDPROC(efi_call)
-
-	.data
-ENTRY(efi_scratch)
-	.fill 3,8,0
-	.byte 0
-	.quad 0