diff mbox series

[01/23] all: syscall wrappers: add documentation

Message ID 1464048292-30136-2-git-send-email-ynorov@caviumnetworks.com
State New
Headers show
Series [01/23] all: syscall wrappers: add documentation | expand

Commit Message

Yury Norov May 24, 2016, 12:04 a.m. UTC 
Signed-off-by: Yury Norov <ynorov@caviumnetworks.com>

---
 Documentation/adding-syscalls.txt | 32 ++++++++++++++++++++++++++++++++
 1 file changed, 32 insertions(+)

-- 
2.5.0
diff mbox series

Patch

diff --git a/Documentation/adding-syscalls.txt b/Documentation/adding-syscalls.txt
index cc2d4ac..d02a6bd 100644
--- a/Documentation/adding-syscalls.txt
+++ b/Documentation/adding-syscalls.txt
@@ -341,6 +341,38 @@  To summarize, you need:
  - instance of __SC_COMP not __SYSCALL in include/uapi/asm-generic/unistd.h
 
 
+Compatibility System Calls Wrappers
+--------------------------------
+
+Some architectures prevent 32-bit userspace from access to top halves of 64-bit
+registers, but some not. It's not a problem if specific argument is the same
+size in kernel and userspace. It also is not a problem if system call is already
+handled by compatible routine. Otherwise we'd take care of it. Usually, glibc
+and compiler handles register's top halve, but from kernel side, we cannot rely
+on it, as malicious code may cause incorrect behaviour and/or security
+vulnerabilities.
+
+For now, only s390 and arm64/ilp32 are affected.
+
+To clear that top halves, automatic wrappers are introduced. They clear all
+required registers before passing control to regular syscall handler.
+
+If your architecture allows userspace code to access top halves of register,
+you need to:
+ - enable COMPAT_WRAPPER in configuration file;
+ - declare: "#define __SC_WRAP(nr, sym) [nr] = compat_##sym,", just before
+   compatible syscall table declaration, if you use generic unistd; or
+ - declare compat wrappers manually, if you use non-generic syscall table.
+   The list of unsafe syscalls is in kernel/compat_wrapper.
+
+If you write new syscall, make sure, its arguments are the same size in both
+64- and 32-bits modes. If no, and if there's no explicit compat version for
+syscall handler, you need to:
+ - declare compat version prototype in 'include/linux/compat.h';
+ - in 'include/uapi/asm-generic/unistd.h' declare syscall with macro '__SC_WRAP'
+   instead of '__SYSCALL';
+ - add corresponding line to 'kernel/compat_wrapper.c' to let it generate wrapper.
+
 Compatibility System Calls (x86)
 --------------------------------