From 6342adcaa683c2b705c24ed201dc11b35854c88d Mon Sep 17 00:00:00 2001 From: Gabriel Krisman Bertazi Date: Wed, 3 Feb 2021 13:00:48 -0500 Subject: [PATCH 1/2] entry: Ensure trap after single-step on system call return Commit 299155244770 ("entry: Drop usage of TIF flags in the generic syscall code") introduced a bug on architectures using the generic syscall entry code, in which processes stopped by PTRACE_SYSCALL do not trap on syscall return after receiving a TIF_SINGLESTEP. The reason is that the meaning of TIF_SINGLESTEP flag is overloaded to cause the trap after a system call is executed, but since the above commit, the syscall call handler only checks for the SYSCALL_WORK flags on the exit work. Split the meaning of TIF_SINGLESTEP such that it only means single-step mode, and create a new type of SYSCALL_WORK to request a trap immediately after a syscall in single-step mode. In the current implementation, the SYSCALL_WORK flag shadows the TIF_SINGLESTEP flag for simplicity. Update x86 to flip this bit when a tracer enables single stepping. Fixes: 299155244770 ("entry: Drop usage of TIF flags in the generic syscall code") Suggested-by: Linus Torvalds Signed-off-by: Gabriel Krisman Bertazi Signed-off-by: Thomas Gleixner Tested-by: Kyle Huey Link: https://lore.kernel.org/r/87h7mtc9pr.fsf_-_@collabora.com --- arch/x86/include/asm/entry-common.h | 2 -- arch/x86/kernel/step.c | 10 ++++++++-- include/linux/entry-common.h | 1 + include/linux/thread_info.h | 2 ++ kernel/entry/common.c | 12 ++---------- 5 files changed, 13 insertions(+), 14 deletions(-) diff --git a/arch/x86/include/asm/entry-common.h b/arch/x86/include/asm/entry-common.h index 6fe54b2813c1..2b87b191b3b8 100644 --- a/arch/x86/include/asm/entry-common.h +++ b/arch/x86/include/asm/entry-common.h @@ -43,8 +43,6 @@ static __always_inline void arch_check_user_regs(struct pt_regs *regs) } #define arch_check_user_regs arch_check_user_regs -#define ARCH_SYSCALL_EXIT_WORK (_TIF_SINGLESTEP) - static inline void arch_exit_to_user_mode_prepare(struct pt_regs *regs, unsigned long ti_work) { diff --git a/arch/x86/kernel/step.c b/arch/x86/kernel/step.c index 60d2c3798ba2..0f3c307b37b3 100644 --- a/arch/x86/kernel/step.c +++ b/arch/x86/kernel/step.c @@ -127,12 +127,17 @@ static int enable_single_step(struct task_struct *child) regs->flags |= X86_EFLAGS_TF; /* - * Always set TIF_SINGLESTEP - this guarantees that - * we single-step system calls etc.. This will also + * Always set TIF_SINGLESTEP. This will also * cause us to set TF when returning to user mode. */ set_tsk_thread_flag(child, TIF_SINGLESTEP); + /* + * Ensure that a trap is triggered once stepping out of a system + * call prior to executing any user instruction. + */ + set_task_syscall_work(child, SYSCALL_EXIT_TRAP); + oflags = regs->flags; /* Set TF on the kernel stack.. */ @@ -230,6 +235,7 @@ void user_disable_single_step(struct task_struct *child) /* Always clear TIF_SINGLESTEP... */ clear_tsk_thread_flag(child, TIF_SINGLESTEP); + clear_task_syscall_work(child, SYSCALL_EXIT_TRAP); /* But touch TF only if it was set by us.. */ if (test_and_clear_tsk_thread_flag(child, TIF_FORCED_TF)) diff --git a/include/linux/entry-common.h b/include/linux/entry-common.h index ca86a00abe86..a104b298019a 100644 --- a/include/linux/entry-common.h +++ b/include/linux/entry-common.h @@ -46,6 +46,7 @@ SYSCALL_WORK_SYSCALL_TRACE | \ SYSCALL_WORK_SYSCALL_AUDIT | \ SYSCALL_WORK_SYSCALL_USER_DISPATCH | \ + SYSCALL_WORK_SYSCALL_EXIT_TRAP | \ ARCH_SYSCALL_WORK_EXIT) /* diff --git a/include/linux/thread_info.h b/include/linux/thread_info.h index c8a974cead73..9b2158c69275 100644 --- a/include/linux/thread_info.h +++ b/include/linux/thread_info.h @@ -43,6 +43,7 @@ enum syscall_work_bit { SYSCALL_WORK_BIT_SYSCALL_EMU, SYSCALL_WORK_BIT_SYSCALL_AUDIT, SYSCALL_WORK_BIT_SYSCALL_USER_DISPATCH, + SYSCALL_WORK_BIT_SYSCALL_EXIT_TRAP, }; #define SYSCALL_WORK_SECCOMP BIT(SYSCALL_WORK_BIT_SECCOMP) @@ -51,6 +52,7 @@ enum syscall_work_bit { #define SYSCALL_WORK_SYSCALL_EMU BIT(SYSCALL_WORK_BIT_SYSCALL_EMU) #define SYSCALL_WORK_SYSCALL_AUDIT BIT(SYSCALL_WORK_BIT_SYSCALL_AUDIT) #define SYSCALL_WORK_SYSCALL_USER_DISPATCH BIT(SYSCALL_WORK_BIT_SYSCALL_USER_DISPATCH) +#define SYSCALL_WORK_SYSCALL_EXIT_TRAP BIT(SYSCALL_WORK_BIT_SYSCALL_EXIT_TRAP) #endif #include diff --git a/kernel/entry/common.c b/kernel/entry/common.c index 6dd82be60df8..f9d491b17b78 100644 --- a/kernel/entry/common.c +++ b/kernel/entry/common.c @@ -209,15 +209,9 @@ static void exit_to_user_mode_prepare(struct pt_regs *regs) lockdep_sys_exit(); } -#ifndef _TIF_SINGLESTEP -static inline bool report_single_step(unsigned long work) -{ - return false; -} -#else /* * If SYSCALL_EMU is set, then the only reason to report is when - * TIF_SINGLESTEP is set (i.e. PTRACE_SYSEMU_SINGLESTEP). This syscall + * SINGLESTEP is set (i.e. PTRACE_SYSEMU_SINGLESTEP). This syscall * instruction has been already reported in syscall_enter_from_user_mode(). */ static inline bool report_single_step(unsigned long work) @@ -225,10 +219,8 @@ static inline bool report_single_step(unsigned long work) if (work & SYSCALL_WORK_SYSCALL_EMU) return false; - return !!(current_thread_info()->flags & _TIF_SINGLESTEP); + return work & SYSCALL_WORK_SYSCALL_EXIT_TRAP; } -#endif - static void syscall_exit_work(struct pt_regs *regs, unsigned long work) { From 36a6c843fd0d8e02506681577e96dabd203dd8e8 Mon Sep 17 00:00:00 2001 From: Gabriel Krisman Bertazi Date: Fri, 5 Feb 2021 13:43:21 -0500 Subject: [PATCH 2/2] entry: Use different define for selector variable in SUD Michael Kerrisk suggested that, from an API perspective, it is a bad idea to share the PR_SYS_DISPATCH_ defines between the prctl operation and the selector variable. Therefore, define two new constants to be used by SUD's selector variable and update the corresponding documentation and test cases. While this changes the API syscall user dispatch has never been part of a Linux release, it will show up for the first time in 5.11. Suggested-by: Michael Kerrisk (man-pages) Signed-off-by: Gabriel Krisman Bertazi Signed-off-by: Thomas Gleixner Link: https://lore.kernel.org/r/20210205184321.2062251-1-krisman@collabora.com --- .../admin-guide/syscall-user-dispatch.rst | 4 ++-- include/uapi/linux/prctl.h | 3 +++ kernel/entry/syscall_user_dispatch.c | 4 ++-- .../syscall_user_dispatch/sud_benchmark.c | 8 +++++--- .../selftests/syscall_user_dispatch/sud_test.c | 14 ++++++++------ 5 files changed, 20 insertions(+), 13 deletions(-) diff --git a/Documentation/admin-guide/syscall-user-dispatch.rst b/Documentation/admin-guide/syscall-user-dispatch.rst index a380d6515774..60314953c728 100644 --- a/Documentation/admin-guide/syscall-user-dispatch.rst +++ b/Documentation/admin-guide/syscall-user-dispatch.rst @@ -70,8 +70,8 @@ trampoline code on the vDSO, that trampoline is never intercepted. [selector] is a pointer to a char-sized region in the process memory region, that provides a quick way to enable disable syscall redirection thread-wide, without the need to invoke the kernel directly. selector -can be set to PR_SYS_DISPATCH_ON or PR_SYS_DISPATCH_OFF. Any other -value should terminate the program with a SIGSYS. +can be set to SYSCALL_DISPATCH_FILTER_ALLOW or SYSCALL_DISPATCH_FILTER_BLOCK. +Any other value should terminate the program with a SIGSYS. Security Notes -------------- diff --git a/include/uapi/linux/prctl.h b/include/uapi/linux/prctl.h index 90deb41c8a34..667f1aed091c 100644 --- a/include/uapi/linux/prctl.h +++ b/include/uapi/linux/prctl.h @@ -251,5 +251,8 @@ struct prctl_mm_map { #define PR_SET_SYSCALL_USER_DISPATCH 59 # define PR_SYS_DISPATCH_OFF 0 # define PR_SYS_DISPATCH_ON 1 +/* The control values for the user space selector when dispatch is enabled */ +# define SYSCALL_DISPATCH_FILTER_ALLOW 0 +# define SYSCALL_DISPATCH_FILTER_BLOCK 1 #endif /* _LINUX_PRCTL_H */ diff --git a/kernel/entry/syscall_user_dispatch.c b/kernel/entry/syscall_user_dispatch.c index b0338a5625d9..c240302f56e2 100644 --- a/kernel/entry/syscall_user_dispatch.c +++ b/kernel/entry/syscall_user_dispatch.c @@ -50,10 +50,10 @@ bool syscall_user_dispatch(struct pt_regs *regs) if (unlikely(__get_user(state, sd->selector))) do_exit(SIGSEGV); - if (likely(state == PR_SYS_DISPATCH_OFF)) + if (likely(state == SYSCALL_DISPATCH_FILTER_ALLOW)) return false; - if (state != PR_SYS_DISPATCH_ON) + if (state != SYSCALL_DISPATCH_FILTER_BLOCK) do_exit(SIGSYS); } diff --git a/tools/testing/selftests/syscall_user_dispatch/sud_benchmark.c b/tools/testing/selftests/syscall_user_dispatch/sud_benchmark.c index 6689f1183dbf..073a03702ff5 100644 --- a/tools/testing/selftests/syscall_user_dispatch/sud_benchmark.c +++ b/tools/testing/selftests/syscall_user_dispatch/sud_benchmark.c @@ -22,6 +22,8 @@ # define PR_SET_SYSCALL_USER_DISPATCH 59 # define PR_SYS_DISPATCH_OFF 0 # define PR_SYS_DISPATCH_ON 1 +# define SYSCALL_DISPATCH_FILTER_ALLOW 0 +# define SYSCALL_DISPATCH_FILTER_BLOCK 1 #endif #ifdef __NR_syscalls @@ -55,8 +57,8 @@ unsigned long trapped_call_count = 0; unsigned long native_call_count = 0; char selector; -#define SYSCALL_BLOCK (selector = PR_SYS_DISPATCH_ON) -#define SYSCALL_UNBLOCK (selector = PR_SYS_DISPATCH_OFF) +#define SYSCALL_BLOCK (selector = SYSCALL_DISPATCH_FILTER_BLOCK) +#define SYSCALL_UNBLOCK (selector = SYSCALL_DISPATCH_FILTER_ALLOW) #define CALIBRATION_STEP 100000 #define CALIBRATE_TO_SECS 5 @@ -170,7 +172,7 @@ int main(void) syscall(MAGIC_SYSCALL_1); #ifdef TEST_BLOCKED_RETURN - if (selector == PR_SYS_DISPATCH_OFF) { + if (selector == SYSCALL_DISPATCH_FILTER_ALLOW) { fprintf(stderr, "Failed to return with selector blocked.\n"); exit(-1); } diff --git a/tools/testing/selftests/syscall_user_dispatch/sud_test.c b/tools/testing/selftests/syscall_user_dispatch/sud_test.c index 6498b050ef89..b5d592d4099e 100644 --- a/tools/testing/selftests/syscall_user_dispatch/sud_test.c +++ b/tools/testing/selftests/syscall_user_dispatch/sud_test.c @@ -18,6 +18,8 @@ # define PR_SET_SYSCALL_USER_DISPATCH 59 # define PR_SYS_DISPATCH_OFF 0 # define PR_SYS_DISPATCH_ON 1 +# define SYSCALL_DISPATCH_FILTER_ALLOW 0 +# define SYSCALL_DISPATCH_FILTER_BLOCK 1 #endif #ifndef SYS_USER_DISPATCH @@ -30,8 +32,8 @@ # define MAGIC_SYSCALL_1 (0xff00) /* Bad Linux syscall number */ #endif -#define SYSCALL_DISPATCH_ON(x) ((x) = 1) -#define SYSCALL_DISPATCH_OFF(x) ((x) = 0) +#define SYSCALL_DISPATCH_ON(x) ((x) = SYSCALL_DISPATCH_FILTER_BLOCK) +#define SYSCALL_DISPATCH_OFF(x) ((x) = SYSCALL_DISPATCH_FILTER_ALLOW) /* Test Summary: * @@ -56,7 +58,7 @@ TEST_SIGNAL(dispatch_trigger_sigsys, SIGSYS) { - char sel = 0; + char sel = SYSCALL_DISPATCH_FILTER_ALLOW; struct sysinfo info; int ret; @@ -79,7 +81,7 @@ TEST_SIGNAL(dispatch_trigger_sigsys, SIGSYS) TEST(bad_prctl_param) { - char sel = 0; + char sel = SYSCALL_DISPATCH_FILTER_ALLOW; int op; /* Invalid op */ @@ -220,7 +222,7 @@ TEST_SIGNAL(bad_selector, SIGSYS) sigset_t mask; struct sysinfo info; - glob_sel = 0; + glob_sel = SYSCALL_DISPATCH_FILTER_ALLOW; nr_syscalls_emulated = 0; si_code = 0; si_errno = 0; @@ -288,7 +290,7 @@ TEST(direct_dispatch_range) { int ret = 0; struct sysinfo info; - char sel = 0; + char sel = SYSCALL_DISPATCH_FILTER_ALLOW; /* * Instead of calculating libc addresses; allow the entire