From 4facb95b7adaf77e2da73aafb9ba60996fe42a12 Mon Sep 17 00:00:00 2001 From: Thomas Gleixner Date: Wed, 2 Sep 2020 01:50:54 +0200 Subject: x86/entry: Unbreak 32bit fast syscall Andy reported that the syscall treacing for 32bit fast syscall fails: # ./tools/testing/selftests/x86/ptrace_syscall_32 ... [RUN] SYSEMU [FAIL] Initial args are wrong (nr=224, args=10 11 12 13 14 4289172732) ... [RUN] SYSCALL [FAIL] Initial args are wrong (nr=29, args=0 0 0 0 0 4289172732) The eason is that the conversion to generic entry code moved the retrieval of the sixth argument (EBP) after the point where the syscall entry work runs, i.e. ptrace, seccomp, audit... Unbreak it by providing a split up version of syscall_enter_from_user_mode(). - syscall_enter_from_user_mode_prepare() establishes state and enables interrupts - syscall_enter_from_user_mode_work() runs the entry work Replace the call to syscall_enter_from_user_mode() in the 32bit fast syscall C-entry with the split functions and stick the EBP retrieval between them. Fixes: 27d6b4d14f5c ("x86/entry: Use generic syscall entry function") Reported-by: Andy Lutomirski Signed-off-by: Thomas Gleixner Link: https://lore.kernel.org/r/87k0xdjbtt.fsf@nanos.tec.linutronix.de --- kernel/entry/common.c | 35 +++++++++++++++++++++++++++++------ 1 file changed, 29 insertions(+), 6 deletions(-) (limited to 'kernel/entry/common.c') diff --git a/kernel/entry/common.c b/kernel/entry/common.c index fcae019158ca..18683598edbc 100644 --- a/kernel/entry/common.c +++ b/kernel/entry/common.c @@ -69,22 +69,45 @@ static long syscall_trace_enter(struct pt_regs *regs, long syscall, return ret ? : syscall_get_nr(current, regs); } -noinstr long syscall_enter_from_user_mode(struct pt_regs *regs, long syscall) +static __always_inline long +__syscall_enter_from_user_work(struct pt_regs *regs, long syscall) { unsigned long ti_work; - enter_from_user_mode(regs); - instrumentation_begin(); - - local_irq_enable(); ti_work = READ_ONCE(current_thread_info()->flags); if (ti_work & SYSCALL_ENTER_WORK) syscall = syscall_trace_enter(regs, syscall, ti_work); - instrumentation_end(); return syscall; } +long syscall_enter_from_user_mode_work(struct pt_regs *regs, long syscall) +{ + return __syscall_enter_from_user_work(regs, syscall); +} + +noinstr long syscall_enter_from_user_mode(struct pt_regs *regs, long syscall) +{ + long ret; + + enter_from_user_mode(regs); + + instrumentation_begin(); + local_irq_enable(); + ret = __syscall_enter_from_user_work(regs, syscall); + instrumentation_end(); + + return ret; +} + +noinstr void syscall_enter_from_user_mode_prepare(struct pt_regs *regs) +{ + enter_from_user_mode(regs); + instrumentation_begin(); + local_irq_enable(); + instrumentation_end(); +} + /** * exit_to_user_mode - Fixup state when exiting to user mode * -- cgit v1.2.3-70-g09d2 From b6ec413461034d49f9e586845825adb35ba308f6 Mon Sep 17 00:00:00 2001 From: Kees Cook Date: Fri, 11 Sep 2020 17:58:26 -0700 Subject: core/entry: Report syscall correctly for trace and audit On v5.8 when doing seccomp syscall rewrites (e.g. getpid into getppid as seen in the seccomp selftests), trace (and audit) correctly see the rewritten syscall on entry and exit: seccomp_bpf-1307 [000] .... 22974.874393: sys_enter: NR 110 (... seccomp_bpf-1307 [000] .N.. 22974.874401: sys_exit: NR 110 = 1304 With mainline we see a mismatched enter and exit (the original syscall is incorrectly visible on entry): seccomp_bpf-1030 [000] .... 21.806766: sys_enter: NR 39 (... seccomp_bpf-1030 [000] .... 21.806767: sys_exit: NR 110 = 1027 When ptrace or seccomp change the syscall, this needs to be visible to trace and audit at that time as well. Update the syscall earlier so they see the correct value. Fixes: d88d59b64ca3 ("core/entry: Respect syscall number rewrites") Reported-by: Michael Ellerman Signed-off-by: Kees Cook Signed-off-by: Thomas Gleixner Link: https://lore.kernel.org/r/20200912005826.586171-1-keescook@chromium.org --- kernel/entry/common.c | 6 ++++-- 1 file changed, 4 insertions(+), 2 deletions(-) (limited to 'kernel/entry/common.c') diff --git a/kernel/entry/common.c b/kernel/entry/common.c index 18683598edbc..6fdb6105e6d6 100644 --- a/kernel/entry/common.c +++ b/kernel/entry/common.c @@ -60,13 +60,15 @@ static long syscall_trace_enter(struct pt_regs *regs, long syscall, return ret; } + /* Either of the above might have changed the syscall number */ + syscall = syscall_get_nr(current, regs); + if (unlikely(ti_work & _TIF_SYSCALL_TRACEPOINT)) trace_sys_enter(regs, syscall); syscall_enter_audit(regs, syscall); - /* The above might have changed the syscall number */ - return ret ? : syscall_get_nr(current, regs); + return ret ? : syscall; } static __always_inline long -- cgit v1.2.3-70-g09d2