[RFC 21/30] x86/vdso/compat: Wire up SYSENTER and SYSCSALL for compat userspace

From: Andy Lutomirski
Date: Tue Sep 01 2015 - 18:42:26 EST

What, you didn't realize that SYSENTER and SYSCALL were actually the
same thing? :)

Unlike the old code, this actually passes the ptrace_syscall_32 test
on AMD systems.

Signed-off-by: Andy Lutomirski <luto@xxxxxxxxxx>
---
arch/x86/entry/entry_64_compat.S | 90 +++++++++++++++++++-------------
arch/x86/entry/vdso/vdso32/system_call.S | 8 +++
2 files changed, 62 insertions(+), 36 deletions(-)

diff --git a/arch/x86/entry/entry_64_compat.S b/arch/x86/entry/entry_64_compat.S
index f384bb79b4fb..1c8ac2e64a1e 100644
--- a/arch/x86/entry/entry_64_compat.S
+++ b/arch/x86/entry/entry_64_compat.S
@@ -52,15 +52,18 @@ ENTRY(entry_SYSENTER_compat)
SWAPGS_UNSAFE_STACK
movq PER_CPU_VAR(cpu_current_top_of_stack), %rsp

- /* Zero-extending 32-bit regs, do not remove */
- movl %ebp, %ebp
+ /*
+ * User tracing code (ptrace or signal handlers) might assume that
+ * the saved RAX contains a 32-bit number when we're invoking a 32-bit
+ * syscall. Just in case the high bits are nonzero, zero-extend
+ * the syscall number. (This could almost certainly be deleted
+ * with no ill effects.)
+ */
movl %eax, %eax

- movl ASM_THREAD_INFO(TI_sysenter_return, %rsp, 0), %r10d
-
/* Construct struct pt_regs on stack */
pushq $__USER32_DS /* pt_regs->ss */
- pushq %rbp /* pt_regs->sp */
+ pushq %rcx /* pt_regs->sp */

/*
* Push flags. This is nasty. First, interrupts are currently
@@ -70,17 +73,28 @@ ENTRY(entry_SYSENTER_compat)
*/
pushfq /* pt_regs->flags (except IF = 0) */
orl $X86_EFLAGS_IF, (%rsp) /* Fix saved flags */
+ ASM_CLAC /* Clear AC after saving FLAGS */

pushq $__USER32_CS /* pt_regs->cs */
- pushq %r10 /* pt_regs->ip = thread_info->sysenter_return */
+ xorq %r8,%r8
+ pushq %r8 /* pt_regs->ip = 0 (placeholder) */
pushq %rax /* pt_regs->orig_ax */
pushq %rdi /* pt_regs->di */
pushq %rsi /* pt_regs->si */
pushq %rdx /* pt_regs->dx */
- pushq %rcx /* pt_regs->cx */
+ pushq %rcx /* pt_regs->cx (will be overwritten) */
pushq $-ENOSYS /* pt_regs->ax */
+ pushq %r8 /* pt_regs->r8 = 0 */
+ pushq %r8 /* pt_regs->r9 = 0 */
+ pushq %r8 /* pt_regs->r10 = 0 */
+ pushq %r8 /* pt_regs->r11 = 0 */
+ pushq %rbx /* pt_regs->rbx */
+ pushq %rbp /* pt_regs->rbp */
+ pushq %r8 /* pt_regs->r12 = 0 */
+ pushq %r8 /* pt_regs->r13 = 0 */
+ pushq %r8 /* pt_regs->r14 = 0 */
+ pushq %r8 /* pt_regs->r15 = 0 */
cld
- sub $(10*8), %rsp /* pt_regs->r8-11, bp, bx, r12-15 not saved */

/*
* Sysenter doesn't filter flags, so we need to clear NT
@@ -93,16 +107,15 @@ ENTRY(entry_SYSENTER_compat)
jnz sysenter_fix_flags
sysenter_flags_fixed:

- /* Temporary: SYSENTER is disabled. */
-#ifdef CONFIG_CONTEXT_TRACKING
- call enter_from_user_mode
-#endif
- ENABLE_INTERRUPTS(CLBR_NONE)
- movl $11, %edi
- call do_exit
+ /*
+ * User mode is traced as though IRQs are on, and SYSENTER
+ * turned them off.
+ */
+ TRACE_IRQS_OFF

- /* Unreachable. */
- ud2
+ movq %rsp, %rdi
+ call do_fast_syscall_32
+ jmp .Lsyscall_32_done

sysenter_fix_flags:
pushq $X86_EFLAGS_FIXED
@@ -135,26 +148,14 @@ ENDPROC(entry_SYSENTER_compat)
* edi arg5
* esp user stack
* 0(%esp) arg6
- *
- * This is purely a fast path. For anything complicated we use the int 0x80
- * path below. We set up a complete hardware stack frame to share code
- * with the int 0x80 path.
*/
ENTRY(entry_SYSCALL_compat)
- /*
- * Interrupts are off on entry.
- * We do not frame this tiny irq-off block with TRACE_IRQS_OFF/ON,
- * it is too small to ever cause noticeable irq latency.
- */
+ /* Interrupts are off on entry. */
SWAPGS_UNSAFE_STACK

- /* Temporary: SYSCALL32 is disabled. */
- movl $-ENOSYS, %eax
- USERGS_SYSRET32
-
+ /* Stash user ESP and switch to the kernel stack. */
movl %esp, %r8d
movq PER_CPU_VAR(cpu_current_top_of_stack), %rsp
- ENABLE_INTERRUPTS(CLBR_NONE)

/* Zero-extending 32-bit regs, do not remove */
movl %eax, %eax
@@ -169,13 +170,29 @@ ENTRY(entry_SYSCALL_compat)
pushq %rdi /* pt_regs->di */
pushq %rsi /* pt_regs->si */
pushq %rdx /* pt_regs->dx */
- pushq %rbp /* pt_regs->cx */
- movl %ebp, %ecx
+ pushq %rcx /* pt_regs->cx (will be overwritten) */
pushq $-ENOSYS /* pt_regs->ax */
- sub $(10*8), %rsp /* pt_regs->r8-11, bp, bx, r12-15 not saved */
+ xorq %r8,%r8
+ pushq %r8 /* pt_regs->r8 = 0 */
+ pushq %r8 /* pt_regs->r9 = 0 */
+ pushq %r8 /* pt_regs->r10 = 0 */
+ pushq %r8 /* pt_regs->r11 = 0 */
+ pushq %rbx /* pt_regs->rbx */
+ pushq %rbp /* pt_regs->rbp */
+ pushq %r8 /* pt_regs->r12 = 0 */
+ pushq %r8 /* pt_regs->r13 = 0 */
+ pushq %r8 /* pt_regs->r14 = 0 */
+ pushq %r8 /* pt_regs->r15 = 0 */
+
+ /*
+ * User mode is traced as though IRQs are on, and SYSENTER
+ * turned them off.
+ */
+ TRACE_IRQS_OFF

- /* Unreachable. */
- ud2
+ movq %rsp, %rdi
+ call do_fast_syscall_32
+ jmp .Lsyscall_32_done
END(entry_SYSCALL_compat)

/*
@@ -243,6 +260,7 @@ ENTRY(entry_INT80_compat)

movq %rsp, %rdi
call do_int80_syscall_32
+.Lsyscall_32_done:

/* Go back to user mode. */
TRACE_IRQS_ON
diff --git a/arch/x86/entry/vdso/vdso32/system_call.S b/arch/x86/entry/vdso/vdso32/system_call.S
index d591fe93e93a..00157cae71e0 100644
--- a/arch/x86/entry/vdso/vdso32/system_call.S
+++ b/arch/x86/entry/vdso/vdso32/system_call.S
@@ -3,6 +3,8 @@
*/

#include <asm/dwarf2.h>
+#include <asm/cpufeature.h>
+#include <asm/alternative-asm.h>

/*
* First get the common code for the sigreturn entry points.
@@ -28,6 +30,12 @@ __kernel_vsyscall:
CFI_REL_OFFSET ecx, 0
movl %esp, %ecx

+#ifdef CONFIG_X86_64
+ /* If SYSENTER (Intel) or SYSCALL32 (AMD) is available, use it. */
+ ALTERNATIVE_2 "", "sysenter", X86_FEATURE_SYSENTER32, \
+ "syscall", X86_FEATURE_SYSCALL32
+#endif
+
/* Enter using int $0x80 */
movl (%esp), %ecx
int $0x80
--
2.4.3

--
To unsubscribe from this list: send the line "unsubscribe linux-kernel" in
the body of a message to majordomo@xxxxxxxxxxxxxxx
More majordomo info at http://vger.kernel.org/majordomo-info.html
Please read the FAQ at http://www.tux.org/lkml/