[tip:x86/asm] x86/entry/compat: Implement opportunistic SYSRETL for compat syscalls

[tip-bot for Andy Lutomirski]

Commit-ID:  7841b408717d4c3b1b334c8f1fef7f18c98cd2bd
Gitweb:     http://git.kernel.org/tip/7841b408717d4c3b1b334c8f1fef7f18c98cd2bd
Author:     Andy Lutomirski <luto@xxxxxxxxxx>
AuthorDate: Mon, 5 Oct 2015 17:48:12 -0700
Committer:  Ingo Molnar <mingo@xxxxxxxxxx>
CommitDate: Fri, 9 Oct 2015 09:41:10 +0200

x86/entry/compat: Implement opportunistic SYSRETL for compat syscalls

If CS, SS and IP are as expected and FLAGS is compatible with
SYSRETL, then return from fast compat syscalls (both SYSCALL and
SYSENTER) using SYSRETL.

Unlike native 64-bit opportunistic SYSRET, this is not invisible
to user code: RCX and R8-R15 end up in a different state than
shown saved in pt_regs.  To compensate, we only do this when
returning to the vDSO fast syscall return path.  This won't
interfere with syscall restart, as we won't use SYSRETL when
returning to the INT80 restart instruction.

Signed-off-by: Andy Lutomirski <luto@xxxxxxxxxx>
Cc: Andy Lutomirski <luto@xxxxxxxxxxxxxx>
Cc: Borislav Petkov <bp@xxxxxxxxx>
Cc: Brian Gerst <brgerst@xxxxxxxxx>
Cc: Denys Vlasenko <dvlasenk@xxxxxxxxxx>
Cc: H. Peter Anvin <hpa@xxxxxxxxx>
Cc: Linus Torvalds <torvalds@xxxxxxxxxxxxxxxxxxxx>
Cc: Peter Zijlstra <peterz@xxxxxxxxxxxxx>
Cc: Thomas Gleixner <tglx@xxxxxxxxxxxxx>
Cc: linux-kernel@xxxxxxxxxxxxxxx
Link: http://lkml.kernel.org/r/aa15e49db33773eb10b73d73466b6d5466d7856a.1444091585.git.luto@xxxxxxxxxx
Signed-off-by: Ingo Molnar <mingo@xxxxxxxxxx>
---
 arch/x86/entry/common.c          | 23 +++++++++++++++++++---
 arch/x86/entry/entry_64_compat.S | 42 ++++++++++++++++++++++++++++++++++++++--
 2 files changed, 60 insertions(+), 5 deletions(-)

diff --git a/arch/x86/entry/common.c b/arch/x86/entry/common.c
index 1b2606e..88dc5ba 100644
--- a/arch/x86/entry/common.c
+++ b/arch/x86/entry/common.c
@@ -363,7 +363,8 @@ __visible void do_int80_syscall_32(struct pt_regs *regs)
 	syscall_return_slowpath(regs);
 }
 
-__visible void do_fast_syscall_32(struct pt_regs *regs)
+/* Returns 0 to return using IRET or 1 to return using SYSRETL. */
+__visible long do_fast_syscall_32(struct pt_regs *regs)
 {
 	/*
 	 * Called using the internal vDSO SYSENTER/SYSCALL32 calling
@@ -395,12 +396,28 @@ __visible void do_fast_syscall_32(struct pt_regs *regs)
 		enter_from_user_mode();
 #endif
 		prepare_exit_to_usermode(regs);
-		return;
+		return 0;	/* Keep it simple: use IRET. */
 	}
 	local_irq_disable();
 
 	/* Now this is just like a normal syscall. */
 	do_int80_syscall_32(regs);
-	return;
+
+#ifdef CONFIG_X86_64
+	/*
+	 * Opportunistic SYSRETL: if possible, try to return using SYSRETL.
+	 * SYSRETL is available on all 64-bit CPUs, so we don't need to
+	 * bother with SYSEXIT.
+	 *
+	 * Unlike 64-bit opportunistic SYSRET, we can't check that CX == IP,
+	 * because the ECX fixup above will ensure that this is essentially
+	 * never the case.
+	 */
+	return regs->cs == __USER32_CS && regs->ss == __USER_DS &&
+		regs->ip == landing_pad &&
+		(regs->flags & (X86_EFLAGS_RF | X86_EFLAGS_TF)) == 0;
+#else
+	return 0;
+#endif
 }
 #endif
diff --git a/arch/x86/entry/entry_64_compat.S b/arch/x86/entry/entry_64_compat.S
index 8f109de5..cf9641c 100644
--- a/arch/x86/entry/entry_64_compat.S
+++ b/arch/x86/entry/entry_64_compat.S
@@ -115,7 +115,9 @@ sysenter_flags_fixed:
 
 	movq	%rsp, %rdi
 	call	do_fast_syscall_32
-	jmp	.Lsyscall_32_done
+	testl	%eax, %eax
+	jz	.Lsyscall_32_done
+	jmp	sysret32_from_system_call
 
 sysenter_fix_flags:
 	pushq	$X86_EFLAGS_FIXED
@@ -192,7 +194,43 @@ ENTRY(entry_SYSCALL_compat)
 
 	movq	%rsp, %rdi
 	call	do_fast_syscall_32
-	jmp	.Lsyscall_32_done
+	testl	%eax, %eax
+	jz	.Lsyscall_32_done
+
+	/* Opportunistic SYSRET */
+sysret32_from_system_call:
+	TRACE_IRQS_ON			/* User mode traces as IRQs on. */
+	movq	RBX(%rsp), %rbx		/* pt_regs->rbx */
+	movq	RBP(%rsp), %rbp		/* pt_regs->rbp */
+	movq	EFLAGS(%rsp), %r11	/* pt_regs->flags (in r11) */
+	movq	RIP(%rsp), %rcx		/* pt_regs->ip (in rcx) */
+	addq	$RAX, %rsp		/* Skip r8-r15 */
+	popq	%rax			/* pt_regs->rax */
+	popq	%rdx			/* Skip pt_regs->cx */
+	popq	%rdx			/* pt_regs->dx */
+	popq	%rsi			/* pt_regs->si */
+	popq	%rdi			/* pt_regs->di */
+
+        /*
+         * USERGS_SYSRET32 does:
+         *  GSBASE = user's GS base
+         *  EIP = ECX
+         *  RFLAGS = R11
+         *  CS = __USER32_CS
+         *  SS = __USER_DS
+         *
+	 * ECX will not match pt_regs->cx, but we're returning to a vDSO
+	 * trampoline that will fix up RCX, so this is okay.
+	 *
+	 * R12-R15 are callee-saved, so they contain whatever was in them
+	 * when the system call started, which is already known to user
+	 * code.  We zero R8-R10 to avoid info leaks.
+         */
+	xorq	%r8, %r8
+	xorq	%r9, %r9
+	xorq	%r10, %r10
+	movq	RSP-ORIG_RAX(%rsp), %rsp
+        USERGS_SYSRET32
 END(entry_SYSCALL_compat)
 
 /*
--
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/