Ensure that a syscall does not return to user-mode with a kernel address limit. If that happens, a process can corrupt kernel-mode memory and elevate privileges [1]. The CONFIG_ADDR_LIMIT_CHECK option disables the generic check so each architecture can create optimized versions. [1] https://bugs.chromium.org/p/project-zero/issues/detail?id=990 Signed-off-by: Thomas Garnier <thgarnie@xxxxxxxxxx> Tested-by: Kees Cook <keescook@xxxxxxxxxxxx> --- Based on next-20170426 --- arch/s390/Kconfig | 1 + include/linux/syscalls.h | 27 ++++++++++++++++++++++++++- init/Kconfig | 6 ++++++ kernel/sys.c | 13 +++++++++++++ 4 files changed, 46 insertions(+), 1 deletion(-) diff --git a/arch/s390/Kconfig b/arch/s390/Kconfig index d25435d94b6e..164de1d24e92 100644 --- a/arch/s390/Kconfig +++ b/arch/s390/Kconfig @@ -103,6 +103,7 @@ config S390 select ARCH_INLINE_WRITE_UNLOCK_BH select ARCH_INLINE_WRITE_UNLOCK_IRQ select ARCH_INLINE_WRITE_UNLOCK_IRQRESTORE + select ADDR_LIMIT_CHECK select ARCH_SAVE_PAGE_KEYS if HIBERNATION select ARCH_SUPPORTS_ATOMIC_RMW select ARCH_SUPPORTS_DEFERRED_STRUCT_PAGE_INIT diff --git a/include/linux/syscalls.h b/include/linux/syscalls.h index 980c3c9b06f8..ebde64f1622c 100644 --- a/include/linux/syscalls.h +++ b/include/linux/syscalls.h @@ -191,6 +191,28 @@ extern struct trace_event_functions exit_syscall_print_funcs; SYSCALL_METADATA(sname, x, __VA_ARGS__) \ __SYSCALL_DEFINEx(x, sname, __VA_ARGS__) + +/* + * Called before coming back to user-mode. Returning to user-mode with an + * address limit different than USER_DS can allow to overwrite kernel memory. + */ +static inline void addr_limit_check_syscall(void) +{ + BUG_ON(!segment_eq(get_fs(), USER_DS)); +} + +#ifndef CONFIG_ADDR_LIMIT_CHECK +#define __CHECK_USERMODE_SYSCALL() \ + bool user_caller = segment_eq(get_fs(), USER_DS) +#define __VERIFY_ADDR_LIMIT() \ + if (user_caller) addr_limit_check_syscall() +#else +#define __CHECK_USERMODE_SYSCALL() +#define __VERIFY_ADDR_LIMIT() +asmlinkage void addr_limit_check_failed(void) __noreturn; +#endif + + #define __PROTECT(...) asmlinkage_protect(__VA_ARGS__) #define __SYSCALL_DEFINEx(x, name, ...) \ asmlinkage long sys##name(__MAP(x,__SC_DECL,__VA_ARGS__)) \ @@ -199,7 +221,10 @@ extern struct trace_event_functions exit_syscall_print_funcs; asmlinkage long SyS##name(__MAP(x,__SC_LONG,__VA_ARGS__)); \ asmlinkage long SyS##name(__MAP(x,__SC_LONG,__VA_ARGS__)) \ { \ - long ret = SYSC##name(__MAP(x,__SC_CAST,__VA_ARGS__)); \ + long ret; \ + __CHECK_USERMODE_SYSCALL(); \ + ret = SYSC##name(__MAP(x,__SC_CAST,__VA_ARGS__)); \ + __VERIFY_ADDR_LIMIT(); \ __MAP(x,__SC_TEST,__VA_ARGS__); \ __PROTECT(x, ret,__MAP(x,__SC_ARGS,__VA_ARGS__)); \ return ret; \ diff --git a/init/Kconfig b/init/Kconfig index 42a346b0df43..599d9fe30703 100644 --- a/init/Kconfig +++ b/init/Kconfig @@ -1961,6 +1961,12 @@ config PROFILING config TRACEPOINTS bool +config ADDR_LIMIT_CHECK + bool + help + Disable the generic address limit check. Allow each architecture to + optimize how and when the verification is done. + source "arch/Kconfig" endmenu # General setup diff --git a/kernel/sys.c b/kernel/sys.c index 8a94b4eabcaa..a1cbcd715d62 100644 --- a/kernel/sys.c +++ b/kernel/sys.c @@ -2458,3 +2458,16 @@ COMPAT_SYSCALL_DEFINE1(sysinfo, struct compat_sysinfo __user *, info) return 0; } #endif /* CONFIG_COMPAT */ + +#ifdef CONFIG_ADDR_LIMIT_CHECK +/* + * Used when an architecture specific implementation detects an invalid address + * limit. This function does not return. + */ +asmlinkage void addr_limit_check_failed(void) +{ + /* Try to fail on the generic address limit check */ + addr_limit_check_syscall(); + panic("Invalid address limit before returning to user-mode"); +} +#endif -- 2.13.0.rc0.306.g87b477812d-goog -- To unsubscribe from this list: send the line "unsubscribe linux-api" in the body of a message to majordomo@xxxxxxxxxxxxxxx More majordomo info at http://vger.kernel.org/majordomo-info.html
