Skip to contentSkip to conversation

x86/espfix changes for v3.16

GIT PULL H. Peter Anvin 1 participant 1 message Jun 4, 2014

Subsystems (3)
lore
Share & tools
lore
#0 lore raw

Hi Linus,

This is the espfix64 code, which fixes the IRET information leak as well as the associated functionality problem. With this code applied, 16-bit stack segments finally work as intended even on a 64-bit kernel.

Consequently, this patchset also removes the runtime option that we added as an interrim measure.

To help the people working on Linux kernels for very small systems, this patchset also makes these compile-time configurable features.

The following changes since commit 172de656b98efd81399aec83837dccaa276622c4:

Merge branch 'x86-urgent-for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip (2014-05-20 14:21:11 +0900)

are available in the git repository at:

git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip.git x86/espfix

for you to fetch changes up to e6ab9a20e73e790d47e6aa231fcf66f27b6ce3d4:

Merge commit '7ed6fb9b5a5510e4ef78ab27419184741169978a' into x86/espfix (2014-05-21 15:23:19 -0700)

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

H. Peter Anvin (8):
x86-64, espfix: Don't leak bits 31:16 of %esp returning to 16-bit stack x86-32, espfix: Remove filter for espfix32 due to race
x86, espfix: Move espfix definitions into a separate header file x86, espfix: Fix broken header guard
x86, espfix: Make espfix64 a Kconfig option, fix UML
x86, espfix: Make it possible to disable 16-bit support
Revert "x86-64, modify_ldt: Make support for 16-bit segments a runtime option" Merge commit '7ed6fb9b5a5510e4ef78ab27419184741169978a' into x86/espfix

 Documentation/x86/x86_64/mm.txt         |   2 +
 arch/x86/Kconfig                        |  25 +++-
 arch/x86/include/asm/espfix.h           |  16 +++
 arch/x86/include/asm/pgtable_64_types.h |   2 +
 arch/x86/include/asm/setup.h            |   2 +
 arch/x86/kernel/Makefile                |   1 +
 arch/x86/kernel/entry_32.S              |  17 ++-
 arch/x86/kernel/entry_64.S              |  81 ++++++++++++-
 arch/x86/kernel/espfix_64.c             | 209 ++++++++++++++++++++++++++++++++
 arch/x86/kernel/ldt.c                   |  10 +-
 arch/x86/kernel/smpboot.c               |   7 ++
 arch/x86/mm/dump_pagetables.c           |  44 +++++--
 arch/x86/vdso/vdso32-setup.c            |   8 --
 init/main.c                             |   4 +
 14 files changed, 387 insertions(+), 41 deletions(-)
 create mode 100644 arch/x86/include/asm/espfix.h
 create mode 100644 arch/x86/kernel/espfix_64.c
Documentation/x86/x86_64/mm.txt +2 -0
index c584a51..afe68dd 100644
@@ -12,6 +12,8 @@ ffffc90000000000 - ffffe8ffffffffff (=45 bits) vmalloc/ioremap space
 ffffe90000000000 - ffffe9ffffffffff (=40 bits) hole
 ffffea0000000000 - ffffeaffffffffff (=40 bits) virtual memory map (1TB)
 ... unused hole ...
+ffffff0000000000 - ffffff7fffffffff (=39 bits) %esp fixup stacks
+... unused hole ...
 ffffffff80000000 - ffffffffa0000000 (=512 MB)  kernel text mapping, from phys 0
 ffffffffa0000000 - ffffffffff5fffff (=1525 MB) module mapping space
 ffffffffff600000 - ffffffffffdfffff (=8 MB) vsyscalls
arch/x86/Kconfig +21 -4
index 25d2c6f..956c770 100644
@@ -909,10 +909,27 @@ config VM86
 	default y
 	depends on X86_32
 	---help---
-	  This option is required by programs like DOSEMU to run 16-bit legacy
-	  code on X86 processors. It also may be needed by software like
-	  XFree86 to initialize some video cards via BIOS. Disabling this
-	  option saves about 6k.
+	  This option is required by programs like DOSEMU to run
+	  16-bit real mode legacy code on x86 processors. It also may
+	  be needed by software like XFree86 to initialize some video
+	  cards via BIOS. Disabling this option saves about 6K.
+
+config X86_16BIT
+	bool "Enable support for 16-bit segments" if EXPERT
+	default y
+	---help---
+	  This option is required by programs like Wine to run 16-bit
+	  protected mode legacy code on x86 processors.  Disabling
+	  this option saves about 300 bytes on i386, or around 6K text
+	  plus 16K runtime memory on x86-64,
+
+config X86_ESPFIX32
+	def_bool y
+	depends on X86_16BIT && X86_32
+
+config X86_ESPFIX64
+	def_bool y
+	depends on X86_16BIT && X86_64
 
 config TOSHIBA
 	tristate "Toshiba Laptop support"
arch/x86/include/asm/espfix.h new file +16 -0
new file mode 100644
index 0000000..99efebb
@@ -0,0 +1,16 @@
+#ifndef _ASM_X86_ESPFIX_H
+#define _ASM_X86_ESPFIX_H
+
+#ifdef CONFIG_X86_64
+
+#include <asm/percpu.h>
+
+DECLARE_PER_CPU_READ_MOSTLY(unsigned long, espfix_stack);
+DECLARE_PER_CPU_READ_MOSTLY(unsigned long, espfix_waddr);
+
+extern void init_espfix_bsp(void);
+extern void init_espfix_ap(void);
+
+#endif /* CONFIG_X86_64 */
+
+#endif /* _ASM_X86_ESPFIX_H */
arch/x86/include/asm/pgtable_64_types.h +2 -0
index c883bf7..7166e25 100644
@@ -61,6 +61,8 @@ typedef struct { pteval_t pte; } pte_t;
 #define MODULES_VADDR    (__START_KERNEL_map + KERNEL_IMAGE_SIZE)
 #define MODULES_END      _AC(0xffffffffff000000, UL)
 #define MODULES_LEN   (MODULES_END - MODULES_VADDR)
+#define ESPFIX_PGD_ENTRY _AC(-2, UL)
+#define ESPFIX_BASE_ADDR (ESPFIX_PGD_ENTRY << PGDIR_SHIFT)
 
 #define EARLY_DYNAMIC_PAGE_TABLES	64
 
arch/x86/include/asm/setup.h +2 -0
index 9264f04..ff4e7b2 100644
@@ -59,6 +59,8 @@ static inline void x86_ce4100_early_setup(void) { }
 
 #ifndef _SETUP
 
+#include <asm/espfix.h>
+
 /*
  * This is set up by the setup-routine at boot-time
  */
arch/x86/kernel/Makefile +1 -0
index f4d9600..491ef3e 100644
@@ -29,6 +29,7 @@ obj-$(CONFIG_X86_64)	+= sys_x86_64.o x8664_ksyms_64.o
 obj-y			+= syscall_$(BITS).o vsyscall_gtod.o
 obj-$(CONFIG_X86_64)	+= vsyscall_64.o
 obj-$(CONFIG_X86_64)	+= vsyscall_emu_64.o
+obj-$(CONFIG_X86_ESPFIX64)	+= espfix_64.o
 obj-$(CONFIG_SYSFS)	+= ksysfs.o
 obj-y			+= bootflag.o e820.o
 obj-y			+= pci-dma.o quirks.o topology.o kdebugfs.o
arch/x86/kernel/entry_32.S +12 -5
index a2a4f46..98313ff 100644
@@ -527,6 +527,7 @@ syscall_exit:
 restore_all:
 	TRACE_IRQS_IRET
 restore_all_notrace:
+#ifdef CONFIG_X86_ESPFIX32
 	movl PT_EFLAGS(%esp), %eax	# mix EFLAGS, SS and CS
 	# Warning: PT_OLDSS(%esp) contains the wrong/random values if we
 	# are returning to the kernel.
@@ -537,6 +538,7 @@ restore_all_notrace:
 	cmpl $((SEGMENT_LDT << 8) | USER_RPL), %eax
 	CFI_REMEMBER_STATE
 	je ldt_ss			# returning to user-space with LDT SS
+#endif
 restore_nocheck:
 	RESTORE_REGS 4			# skip orig_eax/error_code
 irq_return:
@@ -549,13 +551,9 @@ ENTRY(iret_exc)
 .previous
 	_ASM_EXTABLE(irq_return,iret_exc)
 
+#ifdef CONFIG_X86_ESPFIX32
 	CFI_RESTORE_STATE
 ldt_ss:
-	larl PT_OLDSS(%esp), %eax
-	jnz restore_nocheck
-	testl $0x00400000, %eax		# returning to 32bit stack?
-	jnz restore_nocheck		# allright, normal return
-
 #ifdef CONFIG_PARAVIRT
 	/*
 	 * The kernel can't run on a non-flat stack if paravirt mode
@@ -597,6 +595,7 @@ ldt_ss:
 	lss (%esp), %esp		/* switch to espfix segment */
 	CFI_ADJUST_CFA_OFFSET -8
 	jmp restore_nocheck
+#endif
 	CFI_ENDPROC
 ENDPROC(system_call)
 
@@ -704,6 +703,7 @@ END(syscall_badsys)
  * the high word of the segment base from the GDT and swiches to the
  * normal stack and adjusts ESP with the matching offset.
  */
+#ifdef CONFIG_X86_ESPFIX32
 	/* fixup the stack */
 	mov GDT_ESPFIX_SS + 4, %al /* bits 16..23 */
 	mov GDT_ESPFIX_SS + 7, %ah /* bits 24..31 */
@@ -713,8 +713,10 @@ END(syscall_badsys)
 	pushl_cfi %eax
 	lss (%esp), %esp		/* switch to the normal stack segment */
 	CFI_ADJUST_CFA_OFFSET -8
+#endif
 .endm
 .macro UNWIND_ESPFIX_STACK
+#ifdef CONFIG_X86_ESPFIX32
 	movl %ss, %eax
 	/* see if on espfix stack */
 	cmpw $__ESPFIX_SS, %ax
@@ -725,6 +727,7 @@ END(syscall_badsys)
 	/* switch to normal stack */
 	FIXUP_ESPFIX_STACK
 27:
+#endif
 .endm
 
 /*
@@ -1355,11 +1358,13 @@ END(debug)
 ENTRY(nmi)
 	RING0_INT_FRAME
 	ASM_CLAC
+#ifdef CONFIG_X86_ESPFIX32
 	pushl_cfi %eax
 	movl %ss, %eax
 	cmpw $__ESPFIX_SS, %ax
 	popl_cfi %eax
 	je nmi_espfix_stack
+#endif
 	cmpl $ia32_sysenter_target,(%esp)
 	je nmi_stack_fixup
 	pushl_cfi %eax
@@ -1399,6 +1404,7 @@ nmi_debug_stack_check:
 	FIX_STACK 24, nmi_stack_correct, 1
 	jmp nmi_stack_correct
 
+#ifdef CONFIG_X86_ESPFIX32
 nmi_espfix_stack:
 	/* We have a RING0_INT_FRAME here.
 	 *
@@ -1420,6 +1426,7 @@ nmi_espfix_stack:
 	lss 12+4(%esp), %esp		# back to espfix stack
 	CFI_ADJUST_CFA_OFFSET -24
 	jmp irq_return
+#endif
 	CFI_ENDPROC
 END(nmi)
 
arch/x86/kernel/entry_64.S +77 -4

120 lines not on this page · raw message

arch/x86/kernel/espfix_64.c new file +209 -0

209 lines not on this page · raw message

arch/x86/kernel/ldt.c +1 -9
index dcbbaa1..c37886d 100644
@@ -20,8 +20,6 @@
 #include <asm/mmu_context.h>
 #include <asm/syscalls.h>
 
-int sysctl_ldt16 = 0;
-
 #ifdef CONFIG_SMP
 static void flush_ldt(void *current_mm)
 {
@@ -231,16 +229,10 @@ static int write_ldt(void __user *ptr, unsigned long bytecount, int oldmode)
 		}
 	}
 
-	/*
-	 * On x86-64 we do not support 16-bit segments due to
-	 * IRET leaking the high bits of the kernel stack address.
-	 */
-#ifdef CONFIG_X86_64
-	if (!ldt_info.seg_32bit && !sysctl_ldt16) {
+	if (!IS_ENABLED(CONFIG_X86_16BIT) && !ldt_info.seg_32bit) {
 		error = -EINVAL;
 		goto out_unlock;
 	}
-#endif
 
 	fill_ldt(&ldt, &ldt_info);
 	if (oldmode)
arch/x86/kernel/smpboot.c +7 -0
index 3482693..5d93ac1 100644
@@ -244,6 +244,13 @@ static void notrace start_secondary(void *unused)
 	check_tsc_sync_target();
 
 	/*
+	 * Enable the espfix hack for this CPU
+	 */
+#ifdef CONFIG_X86_ESPFIX64
+	init_espfix_ap();
+#endif
+
+	/*
 	 * We need to hold vector_lock so there the set of online cpus
 	 * does not change while we are assigning vectors to cpus.  Holding
 	 * this lock ensures we don't half assign or remove an irq from a cpu.
arch/x86/mm/dump_pagetables.c +33 -11

94 lines not on this page · raw message

arch/x86/vdso/vdso32-setup.c +0 -8
index e1f220e..0034898 100644
@@ -39,7 +39,6 @@
 #ifdef CONFIG_X86_64
 #define vdso_enabled			sysctl_vsyscall32
 #define arch_setup_additional_pages	syscall32_setup_pages
-extern int sysctl_ldt16;
 #endif
 
 /*
@@ -250,13 +249,6 @@ static struct ctl_table abi_table2[] = {
 		.mode		= 0644,
 		.proc_handler	= proc_dointvec
 	},
-	{
-		.procname	= "ldt16",
-		.data		= &sysctl_ldt16,
-		.maxlen		= sizeof(int),
-		.mode		= 0644,
-		.proc_handler	= proc_dointvec
-	},
 	{}
 };
 
init/main.c +4 -0
index 48655ce..eb0ea86 100644
@@ -617,6 +617,10 @@ asmlinkage __visible void __init start_kernel(void)
 	if (efi_enabled(EFI_RUNTIME_SERVICES))
 		efi_enter_virtual_mode();
 #endif
+#ifdef CONFIG_X86_ESPFIX64
+	/* Should be run before the first non-init thread is created */
+	init_espfix_bsp();
+#endif
 	thread_info_cache_init();
 	cred_init();
 	fork_init(totalram_pages);