[RFC 11/30] x86/vdso/32: Save extra registers in the INT80 vsyscall path

[Andy Lutomirski]

The goal is to integrate the SYSENTER and SYSCALL32 entry paths with
the INT80 path.  SYSENTER clobbers ESP and EIP.  SYSCALL32 clobbers
ECX (and, invisibly, R11).  SYSRETL (long mode to compat mode)
clobbers ECX and, invisibly, R11.  SYSEXIT (which we only need for
native 32-bit) clobbers ECX and EDX.

This means that we'll need to provide ESP to the kernel in a
register (I chose ECX, since it's only needed for SYSENTER) and we
need to provide the args that normally live in ECX and EDX in
memory.

The epilogue needs to restore ECX and EDX, since user code relies on
regs being preserved.

We don't need to do anything special about EIP, since the kernel
already knows where we are.  The kernel will eventually need to
know where int $0x80 lands, so add a vdso_image entry for it.

The only user-visible effect of this code is that ptrace-induced
changes to ECX and EDX during fast syscalls will be lost.  This is
already the case for the SYSENTER path.

Signed-off-by: Andy Lutomirski <luto@xxxxxxxxxx>
---
 arch/x86/entry/vdso/vdso2c.c             |  1 +
 arch/x86/entry/vdso/vdso32/system_call.S | 25 ++++++++++++++++++++++++-
 arch/x86/include/asm/vdso.h              |  1 +
 3 files changed, 26 insertions(+), 1 deletion(-)

diff --git a/arch/x86/entry/vdso/vdso2c.c b/arch/x86/entry/vdso/vdso2c.c
index 2637eb1e3949..785d9922b106 100644
--- a/arch/x86/entry/vdso/vdso2c.c
+++ b/arch/x86/entry/vdso/vdso2c.c
@@ -101,6 +101,7 @@ struct vdso_sym required_syms[] = {
 	{"__kernel_vsyscall", true},
 	{"__kernel_sigreturn", true},
 	{"__kernel_rt_sigreturn", true},
+	{"int80_landing_pad", true},
 };
 
 __attribute__((format(printf, 1, 2))) __attribute__((noreturn))
diff --git a/arch/x86/entry/vdso/vdso32/system_call.S b/arch/x86/entry/vdso/vdso32/system_call.S
index b52cbfbe119e..d591fe93e93a 100644
--- a/arch/x86/entry/vdso/vdso32/system_call.S
+++ b/arch/x86/entry/vdso/vdso32/system_call.S
@@ -16,7 +16,30 @@
 	ALIGN
 __kernel_vsyscall:
 	CFI_STARTPROC
-	int $0x80
+	/*
+	 * Reshuffle regs so that all of any of the entry instructions
+	 * will preserve enough state.
+	 */
+	pushl	%edx
+	CFI_ADJUST_CFA_OFFSET	4
+	CFI_REL_OFFSET		edx, 0
+	pushl	%ecx
+	CFI_ADJUST_CFA_OFFSET	4
+	CFI_REL_OFFSET		ecx, 0
+	movl	%esp, %ecx
+
+	/* Enter using int $0x80 */
+	movl	(%esp), %ecx
+	int	$0x80
+GLOBAL(int80_landing_pad)
+
+	/* Restore ECX and EDX in case they were clobbered. */
+	popl	%ecx
+	CFI_RESTORE		ecx
+	CFI_ADJUST_CFA_OFFSET	-4
+	popl	%edx
+	CFI_RESTORE		edx
+	CFI_ADJUST_CFA_OFFSET	-4
 	ret
 	CFI_ENDPROC
 
diff --git a/arch/x86/include/asm/vdso.h b/arch/x86/include/asm/vdso.h
index 5bcb1de8296e..756de9190aec 100644
--- a/arch/x86/include/asm/vdso.h
+++ b/arch/x86/include/asm/vdso.h
@@ -26,6 +26,7 @@ struct vdso_image {
 	long sym___kernel_sigreturn;
 	long sym___kernel_rt_sigreturn;
 	long sym___kernel_vsyscall;
+	long sym_int80_landing_pad;
 };
 
 #ifdef CONFIG_X86_64
-- 
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/