commit 710246df58041106b7de645f4b45770f8a59a269
author Andy Lutomirski <luto@kernel.org> Mon Oct 05 17:48:10 2015 -0700
committer Ingo Molnar <mingo@kernel.org> Fri Oct 09 09:41:09 2015 +0200
tree 2a6809135079d9ff4854620f966c16a8dee69aef
parent ee08c6bd315e70756ad2c47ee6ea708a4a882b55

x86/entry: Add C code for fast system call entries

This handles both SYSENTER and SYSCALL.  The asm glue will take
care of the differences.

Signed-off-by: Andy Lutomirski <luto@kernel.org>
Cc: Andy Lutomirski <luto@amacapital.net>
Cc: Borislav Petkov <bp@alien8.de>
Cc: Brian Gerst <brgerst@gmail.com>
Cc: Denys Vlasenko <dvlasenk@redhat.com>
Cc: H. Peter Anvin <hpa@zytor.com>
Cc: Linus Torvalds <torvalds@linux-foundation.org>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: Thomas Gleixner <tglx@linutronix.de>
Cc: linux-kernel@vger.kernel.org
Link: http://lkml.kernel.org/r/6041a58a9b8ef6d2522ab4350deb1a1945eb563f.1444091585.git.luto@kernel.org
Signed-off-by: Ingo Molnar <mingo@kernel.org>

arch/x86/entry/common.c

diff --git a/arch/x86/entry/common.c b/arch/x86/entry/common.c
index 41d1750..1b2606e 100644
--- a/arch/x86/entry/common.c
+++ b/arch/x86/entry/common.c
@@ -24,6 +24,8 @@
 
 #include <asm/desc.h>
 #include <asm/traps.h>
+#include <asm/vdso.h>
+#include <asm/uaccess.h>
 
 #define CREATE_TRACE_POINTS
 #include <trace/events/syscalls.h>
@@ -360,4 +362,45 @@
 
 	syscall_return_slowpath(regs);
 }
+
+__visible void do_fast_syscall_32(struct pt_regs *regs)
+{
+	/*
+	 * Called using the internal vDSO SYSENTER/SYSCALL32 calling
+	 * convention.  Adjust regs so it looks like we entered using int80.
+	 */
+
+	unsigned long landing_pad = (unsigned long)current->mm->context.vdso +
+		vdso_image_32.sym_int80_landing_pad;
+
+	/*
+	 * SYSENTER loses EIP, and even SYSCALL32 needs us to skip forward
+	 * so that 'regs->ip -= 2' lands back on an int $0x80 instruction.
+	 * Fix it up.
+	 */
+	regs->ip = landing_pad;
+
+	/*
+	 * Fetch ECX from where the vDSO stashed it.
+	 *
+	 * WARNING: We are in CONTEXT_USER and RCU isn't paying attention!
+	 */
+	local_irq_enable();
+	if (get_user(*(u32 *)&regs->cx,
+		     (u32 __user __force *)(unsigned long)(u32)regs->sp)) {
+		/* User code screwed up. */
+		local_irq_disable();
+		regs->ax = -EFAULT;
+#ifdef CONFIG_CONTEXT_TRACKING
+		enter_from_user_mode();
+#endif
+		prepare_exit_to_usermode(regs);
+		return;
+	}
+	local_irq_disable();
+
+	/* Now this is just like a normal syscall. */
+	do_int80_syscall_32(regs);
+	return;
+}
 #endif