[PATCH] [v3] x86, syscalls: use SYSCALL_DEFINE() macros for sys_modify_ldt()

[PATCH] [v3] x86, syscalls: use SYSCALL_DEFINE() macros for sys_modify_ldt()

[Dave Hansen]

Changes from v2:
 * Fixed UML compile error from not including syscall header

Changes from v1:
 * Added cast to (unsigned int)
 * Added comments

--

From: Dave Hansen <dave.hansen@linux.intel.com>

We do not have tracepoints for sys_modify_ldt() because we define
it directly instead of using the normal SYSCALL_DEFINEx() macros.

However, there is a reason sys_modify_ldt() does not use the macros:
it has an 'int' return type instead of 'unsigned long'.  This is
a bug, but it's a bug cemented in the ABI.

What does this mean?  If we return -EINVAL from a function that
returns 'int', we have 0x00000000ffffffea in %rax.  But, if we
return -EINVAL from a function returning 'unsigned long', we end
up with 0xffffffffffffffea in %rax, which is wrong.

To work around this and maintain the 'int' behavior while using
the SYSCALL_DEFINEx() macros, so we add a cast to 'unsigned int'
in both implementations of sys_modify_ldt().

Signed-off-by: Dave Hansen <dave.hansen@linux.intel.com>
Reviewed-by: Andy Lutomirski <luto@kernel.org>
Reviewed-by: Brian Gerst <brgerst@gmail.com>
Cc: x86@kernel.org
---

 b/arch/x86/include/asm/syscalls.h |    2 +-
 b/arch/x86/kernel/ldt.c           |   16 +++++++++++++---
 b/arch/x86/um/ldt.c               |    7 +++++--
 3 files changed, 19 insertions(+), 6 deletions(-)

diff -puN arch/x86/include/asm/syscalls.h~x86-syscall-macros-modify_ldt arch/x86/include/asm/syscalls.h
--- a/arch/x86/include/asm/syscalls.h~x86-syscall-macros-modify_ldt	2017-10-18 09:21:54.210460494 -0700
+++ b/arch/x86/include/asm/syscalls.h	2017-10-18 09:21:54.217460834 -0700
@@ -21,7 +21,7 @@ asmlinkage long sys_ioperm(unsigned long
 asmlinkage long sys_iopl(unsigned int);
 
 /* kernel/ldt.c */
-asmlinkage int sys_modify_ldt(int, void __user *, unsigned long);
+asmlinkage long sys_modify_ldt(int, void __user *, unsigned long);
 
 /* kernel/signal.c */
 asmlinkage long sys_rt_sigreturn(void);
diff -puN arch/x86/kernel/ldt.c~x86-syscall-macros-modify_ldt arch/x86/kernel/ldt.c
--- a/arch/x86/kernel/ldt.c~x86-syscall-macros-modify_ldt	2017-10-18 09:21:54.212460591 -0700
+++ b/arch/x86/kernel/ldt.c	2017-10-18 09:21:54.218460882 -0700
@@ -12,6 +12,7 @@
 #include <linux/string.h>
 #include <linux/mm.h>
 #include <linux/smp.h>
+#include <linux/syscalls.h>
 #include <linux/slab.h>
 #include <linux/vmalloc.h>
 #include <linux/uaccess.h>
@@ -294,8 +295,8 @@ out:
 	return error;
 }
 
-asmlinkage int sys_modify_ldt(int func, void __user *ptr,
-			      unsigned long bytecount)
+SYSCALL_DEFINE3(modify_ldt, int , func , void __user * , ptr ,
+		unsigned long , bytecount)
 {
 	int ret = -ENOSYS;
 
@@ -313,5 +314,14 @@ asmlinkage int sys_modify_ldt(int func,
 		ret = write_ldt(ptr, bytecount, 0);
 		break;
 	}
-	return ret;
+	/*
+	 * The SYSCALL_DEFINE() macros give us an 'unsigned long'
+	 * return type, but tht ABI for sys_modify_ldt() expects
+	 * 'int'.  This cast gives us an int-sized value in %rax
+	 * for the return code.  The 'unsigned' is necessary so
+	 * the compiler does not try to sign-extend the negative
+	 * return codes into the high half of the register when
+	 * taking the value from int->long.
+	 */
+	return (unsigned int)ret;
 }
diff -puN arch/x86/um/ldt.c~x86-syscall-macros-modify_ldt arch/x86/um/ldt.c
--- a/arch/x86/um/ldt.c~x86-syscall-macros-modify_ldt	2017-10-18 09:21:54.214460688 -0700
+++ b/arch/x86/um/ldt.c	2017-10-18 09:25:55.128131160 -0700
@@ -6,6 +6,7 @@
 #include <linux/mm.h>
 #include <linux/sched.h>
 #include <linux/slab.h>
+#include <linux/syscalls.h>
 #include <linux/uaccess.h>
 #include <asm/unistd.h>
 #include <os.h>
@@ -369,7 +370,9 @@ void free_ldt(struct mm_context *mm)
 	mm->arch.ldt.entry_count = 0;
 }
 
-int sys_modify_ldt(int func, void __user *ptr, unsigned long bytecount)
+SYSCALL_DEFINE3(modify_ldt, int , func , void __user * , ptr ,
+		unsigned long , bytecount)
 {
-	return do_modify_ldt_skas(func, ptr, bytecount);
+	/* See non-um modify_ldt() for why we do this cast */
+	return (unsigned int)do_modify_ldt_skas(func, ptr, bytecount);
 }
_

[tip:x86/asm] x86/entry: Use SYSCALL_DEFINE() macros for sys_modify_ldt()

[tip-bot for Dave Hansen]

Commit-ID:  da20ab35180780e4a6eadc804544f1fa967f3567
Gitweb:     https://git.kernel.org/tip/da20ab35180780e4a6eadc804544f1fa967f3567
Author:     Dave Hansen <dave.hansen@linux.intel.com>
AuthorDate: Wed, 18 Oct 2017 10:21:07 -0700
Committer:  Ingo Molnar <mingo@kernel.org>
CommitDate: Fri, 20 Oct 2017 10:37:33 +0200

x86/entry: Use SYSCALL_DEFINE() macros for sys_modify_ldt()

We do not have tracepoints for sys_modify_ldt() because we define
it directly instead of using the normal SYSCALL_DEFINEx() macros.

However, there is a reason sys_modify_ldt() does not use the macros:
it has an 'int' return type instead of 'unsigned long'.  This is
a bug, but it's a bug cemented in the ABI.

What does this mean?  If we return -EINVAL from a function that
returns 'int', we have 0x00000000ffffffea in %rax.  But, if we
return -EINVAL from a function returning 'unsigned long', we end
up with 0xffffffffffffffea in %rax, which is wrong.

To work around this and maintain the 'int' behavior while using
the SYSCALL_DEFINEx() macros, so we add a cast to 'unsigned int'
in both implementations of sys_modify_ldt().

Signed-off-by: Dave Hansen <dave.hansen@linux.intel.com>
Reviewed-by: Andy Lutomirski <luto@kernel.org>
Reviewed-by: Brian Gerst <brgerst@gmail.com>
Cc: Linus Torvalds <torvalds@linux-foundation.org>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: Thomas Gleixner <tglx@linutronix.de>
Link: http://lkml.kernel.org/r/20171018172107.1A79C532@viggo.jf.intel.com
Signed-off-by: Ingo Molnar <mingo@kernel.org>
---
 arch/x86/include/asm/syscalls.h |  2 +-
 arch/x86/kernel/ldt.c           | 16 +++++++++++++---
 arch/x86/um/ldt.c               |  7 +++++--
 3 files changed, 19 insertions(+), 6 deletions(-)

diff --git a/arch/x86/include/asm/syscalls.h b/arch/x86/include/asm/syscalls.h
index 91dfcaf..bad25bb 100644
--- a/arch/x86/include/asm/syscalls.h
+++ b/arch/x86/include/asm/syscalls.h
@@ -21,7 +21,7 @@ asmlinkage long sys_ioperm(unsigned long, unsigned long, int);
 asmlinkage long sys_iopl(unsigned int);
 
 /* kernel/ldt.c */
-asmlinkage int sys_modify_ldt(int, void __user *, unsigned long);
+asmlinkage long sys_modify_ldt(int, void __user *, unsigned long);
 
 /* kernel/signal.c */
 asmlinkage long sys_rt_sigreturn(void);
diff --git a/arch/x86/kernel/ldt.c b/arch/x86/kernel/ldt.c
index f0e64db..0402d44 100644
--- a/arch/x86/kernel/ldt.c
+++ b/arch/x86/kernel/ldt.c
@@ -12,6 +12,7 @@
 #include <linux/string.h>
 #include <linux/mm.h>
 #include <linux/smp.h>
+#include <linux/syscalls.h>
 #include <linux/slab.h>
 #include <linux/vmalloc.h>
 #include <linux/uaccess.h>
@@ -294,8 +295,8 @@ out:
 	return error;
 }
 
-asmlinkage int sys_modify_ldt(int func, void __user *ptr,
-			      unsigned long bytecount)
+SYSCALL_DEFINE3(modify_ldt, int , func , void __user * , ptr ,
+		unsigned long , bytecount)
 {
 	int ret = -ENOSYS;
 
@@ -313,5 +314,14 @@ asmlinkage int sys_modify_ldt(int func, void __user *ptr,
 		ret = write_ldt(ptr, bytecount, 0);
 		break;
 	}
-	return ret;
+	/*
+	 * The SYSCALL_DEFINE() macros give us an 'unsigned long'
+	 * return type, but tht ABI for sys_modify_ldt() expects
+	 * 'int'.  This cast gives us an int-sized value in %rax
+	 * for the return code.  The 'unsigned' is necessary so
+	 * the compiler does not try to sign-extend the negative
+	 * return codes into the high half of the register when
+	 * taking the value from int->long.
+	 */
+	return (unsigned int)ret;
 }
diff --git a/arch/x86/um/ldt.c b/arch/x86/um/ldt.c
index 836a1eb..3ee234b6 100644
--- a/arch/x86/um/ldt.c
+++ b/arch/x86/um/ldt.c
@@ -6,6 +6,7 @@
 #include <linux/mm.h>
 #include <linux/sched.h>
 #include <linux/slab.h>
+#include <linux/syscalls.h>
 #include <linux/uaccess.h>
 #include <asm/unistd.h>
 #include <os.h>
@@ -369,7 +370,9 @@ void free_ldt(struct mm_context *mm)
 	mm->arch.ldt.entry_count = 0;
 }
 
-int sys_modify_ldt(int func, void __user *ptr, unsigned long bytecount)
+SYSCALL_DEFINE3(modify_ldt, int , func , void __user * , ptr ,
+		unsigned long , bytecount)
 {
-	return do_modify_ldt_skas(func, ptr, bytecount);
+	/* See non-um modify_ldt() for why we do this cast */
+	return (unsigned int)do_modify_ldt_skas(func, ptr, bytecount);
 }