From ac2081cdc4d99c57f219c1a6171526e0fa0a6fff Mon Sep 17 00:00:00 2001 From: Will Deacon Date: Thu, 2 Jul 2020 21:16:20 +0100 Subject: arm64: ptrace: Consistently use pseudo-singlestep exceptions Although the arm64 single-step state machine can be fast-forwarded in cases where we wish to generate a SIGTRAP without actually executing an instruction, this has two major limitations outside of simply skipping an instruction due to emulation. 1. Stepping out of a ptrace signal stop into a signal handler where SIGTRAP is blocked. Fast-forwarding the stepping state machine in this case will result in a forced SIGTRAP, with the handler reset to SIG_DFL. 2. The hardware implicitly fast-forwards the state machine when executing an SVC instruction for issuing a system call. This can interact badly with subsequent ptrace stops signalled during the execution of the system call (e.g. SYSCALL_EXIT or seccomp traps), as they may corrupt the stepping state by updating the PSTATE for the tracee. Resolve both of these issues by injecting a pseudo-singlestep exception on entry to a signal handler and also on return to userspace following a system call. Cc: Cc: Mark Rutland Tested-by: Luis Machado Reported-by: Keno Fischer Signed-off-by: Will Deacon --- arch/arm64/include/asm/thread_info.h | 1 + arch/arm64/kernel/ptrace.c | 25 +++++++++++++++++++------ arch/arm64/kernel/signal.c | 11 ++--------- arch/arm64/kernel/syscall.c | 2 +- 4 files changed, 23 insertions(+), 16 deletions(-) (limited to 'arch') diff --git a/arch/arm64/include/asm/thread_info.h b/arch/arm64/include/asm/thread_info.h index 6ea8b6a26ae9..5e784e16ee89 100644 --- a/arch/arm64/include/asm/thread_info.h +++ b/arch/arm64/include/asm/thread_info.h @@ -93,6 +93,7 @@ void arch_release_task_struct(struct task_struct *tsk); #define _TIF_SYSCALL_EMU (1 << TIF_SYSCALL_EMU) #define _TIF_UPROBE (1 << TIF_UPROBE) #define _TIF_FSCHECK (1 << TIF_FSCHECK) +#define _TIF_SINGLESTEP (1 << TIF_SINGLESTEP) #define _TIF_32BIT (1 << TIF_32BIT) #define _TIF_SVE (1 << TIF_SVE) diff --git a/arch/arm64/kernel/ptrace.c b/arch/arm64/kernel/ptrace.c index 68b7f34a08f5..057d4aa1af4d 100644 --- a/arch/arm64/kernel/ptrace.c +++ b/arch/arm64/kernel/ptrace.c @@ -1818,12 +1818,23 @@ static void tracehook_report_syscall(struct pt_regs *regs, saved_reg = regs->regs[regno]; regs->regs[regno] = dir; - if (dir == PTRACE_SYSCALL_EXIT) + if (dir == PTRACE_SYSCALL_ENTER) { + if (tracehook_report_syscall_entry(regs)) + forget_syscall(regs); + regs->regs[regno] = saved_reg; + } else if (!test_thread_flag(TIF_SINGLESTEP)) { tracehook_report_syscall_exit(regs, 0); - else if (tracehook_report_syscall_entry(regs)) - forget_syscall(regs); + regs->regs[regno] = saved_reg; + } else { + regs->regs[regno] = saved_reg; - regs->regs[regno] = saved_reg; + /* + * Signal a pseudo-step exception since we are stepping but + * tracer modifications to the registers may have rewound the + * state machine. + */ + tracehook_report_syscall_exit(regs, 1); + } } int syscall_trace_enter(struct pt_regs *regs) @@ -1851,12 +1862,14 @@ int syscall_trace_enter(struct pt_regs *regs) void syscall_trace_exit(struct pt_regs *regs) { + unsigned long flags = READ_ONCE(current_thread_info()->flags); + audit_syscall_exit(regs); - if (test_thread_flag(TIF_SYSCALL_TRACEPOINT)) + if (flags & _TIF_SYSCALL_TRACEPOINT) trace_sys_exit(regs, regs_return_value(regs)); - if (test_thread_flag(TIF_SYSCALL_TRACE)) + if (flags & (_TIF_SYSCALL_TRACE | _TIF_SINGLESTEP)) tracehook_report_syscall(regs, PTRACE_SYSCALL_EXIT); rseq_syscall(regs); diff --git a/arch/arm64/kernel/signal.c b/arch/arm64/kernel/signal.c index 801d56cdf701..3b4f31f35e45 100644 --- a/arch/arm64/kernel/signal.c +++ b/arch/arm64/kernel/signal.c @@ -800,7 +800,6 @@ static void setup_restart_syscall(struct pt_regs *regs) */ static void handle_signal(struct ksignal *ksig, struct pt_regs *regs) { - struct task_struct *tsk = current; sigset_t *oldset = sigmask_to_save(); int usig = ksig->sig; int ret; @@ -824,14 +823,8 @@ static void handle_signal(struct ksignal *ksig, struct pt_regs *regs) */ ret |= !valid_user_regs(®s->user_regs, current); - /* - * Fast forward the stepping logic so we step into the signal - * handler. - */ - if (!ret) - user_fastforward_single_step(tsk); - - signal_setup_done(ret, ksig, 0); + /* Step into the signal handler if we are stepping */ + signal_setup_done(ret, ksig, test_thread_flag(TIF_SINGLESTEP)); } /* diff --git a/arch/arm64/kernel/syscall.c b/arch/arm64/kernel/syscall.c index 5f5b868292f5..7c14466a12af 100644 --- a/arch/arm64/kernel/syscall.c +++ b/arch/arm64/kernel/syscall.c @@ -139,7 +139,7 @@ static void el0_svc_common(struct pt_regs *regs, int scno, int sc_nr, if (!has_syscall_work(flags) && !IS_ENABLED(CONFIG_DEBUG_RSEQ)) { local_daif_mask(); flags = current_thread_info()->flags; - if (!has_syscall_work(flags)) { + if (!has_syscall_work(flags) && !(flags & _TIF_SINGLESTEP)) { /* * We're off to userspace, where interrupts are * always enabled after we restore the flags from -- cgit v1.2.3 From 3a5a4366cecc25daa300b9a9174f7fdd352b9068 Mon Sep 17 00:00:00 2001 From: Will Deacon Date: Thu, 13 Feb 2020 12:06:26 +0000 Subject: arm64: ptrace: Override SPSR.SS when single-stepping is enabled Luis reports that, when reverse debugging with GDB, single-step does not function as expected on arm64: | I've noticed, under very specific conditions, that a PTRACE_SINGLESTEP | request by GDB won't execute the underlying instruction. As a consequence, | the PC doesn't move, but we return a SIGTRAP just like we would for a | regular successful PTRACE_SINGLESTEP request. The underlying problem is that when the CPU register state is restored as part of a reverse step, the SPSR.SS bit is cleared and so the hardware single-step state can transition to the "active-pending" state, causing an unexpected step exception to be taken immediately if a step operation is attempted. In hindsight, we probably shouldn't have exposed SPSR.SS in the pstate accessible by the GPR regset, but it's a bit late for that now. Instead, simply prevent userspace from configuring the bit to a value which is inconsistent with the TIF_SINGLESTEP state for the task being traced. Cc: Cc: Mark Rutland Cc: Keno Fischer Link: https://lore.kernel.org/r/1eed6d69-d53d-9657-1fc9-c089be07f98c@linaro.org Reported-by: Luis Machado Tested-by: Luis Machado Signed-off-by: Will Deacon --- arch/arm64/include/asm/debug-monitors.h | 2 ++ arch/arm64/kernel/debug-monitors.c | 20 ++++++++++++++++---- arch/arm64/kernel/ptrace.c | 4 ++-- 3 files changed, 20 insertions(+), 6 deletions(-) (limited to 'arch') diff --git a/arch/arm64/include/asm/debug-monitors.h b/arch/arm64/include/asm/debug-monitors.h index e5ceea213e39..0b298f48f5bf 100644 --- a/arch/arm64/include/asm/debug-monitors.h +++ b/arch/arm64/include/asm/debug-monitors.h @@ -109,6 +109,8 @@ void disable_debug_monitors(enum dbg_active_el el); void user_rewind_single_step(struct task_struct *task); void user_fastforward_single_step(struct task_struct *task); +void user_regs_reset_single_step(struct user_pt_regs *regs, + struct task_struct *task); void kernel_enable_single_step(struct pt_regs *regs); void kernel_disable_single_step(void); diff --git a/arch/arm64/kernel/debug-monitors.c b/arch/arm64/kernel/debug-monitors.c index 5df49366e9ab..91146c0a3691 100644 --- a/arch/arm64/kernel/debug-monitors.c +++ b/arch/arm64/kernel/debug-monitors.c @@ -141,17 +141,20 @@ postcore_initcall(debug_monitors_init); /* * Single step API and exception handling. */ -static void set_regs_spsr_ss(struct pt_regs *regs) +static void set_user_regs_spsr_ss(struct user_pt_regs *regs) { regs->pstate |= DBG_SPSR_SS; } -NOKPROBE_SYMBOL(set_regs_spsr_ss); +NOKPROBE_SYMBOL(set_user_regs_spsr_ss); -static void clear_regs_spsr_ss(struct pt_regs *regs) +static void clear_user_regs_spsr_ss(struct user_pt_regs *regs) { regs->pstate &= ~DBG_SPSR_SS; } -NOKPROBE_SYMBOL(clear_regs_spsr_ss); +NOKPROBE_SYMBOL(clear_user_regs_spsr_ss); + +#define set_regs_spsr_ss(r) set_user_regs_spsr_ss(&(r)->user_regs) +#define clear_regs_spsr_ss(r) clear_user_regs_spsr_ss(&(r)->user_regs) static DEFINE_SPINLOCK(debug_hook_lock); static LIST_HEAD(user_step_hook); @@ -402,6 +405,15 @@ void user_fastforward_single_step(struct task_struct *task) clear_regs_spsr_ss(task_pt_regs(task)); } +void user_regs_reset_single_step(struct user_pt_regs *regs, + struct task_struct *task) +{ + if (test_tsk_thread_flag(task, TIF_SINGLESTEP)) + set_user_regs_spsr_ss(regs); + else + clear_user_regs_spsr_ss(regs); +} + /* Kernel API */ void kernel_enable_single_step(struct pt_regs *regs) { diff --git a/arch/arm64/kernel/ptrace.c b/arch/arm64/kernel/ptrace.c index 057d4aa1af4d..22f9053b55b6 100644 --- a/arch/arm64/kernel/ptrace.c +++ b/arch/arm64/kernel/ptrace.c @@ -1947,8 +1947,8 @@ static int valid_native_regs(struct user_pt_regs *regs) */ int valid_user_regs(struct user_pt_regs *regs, struct task_struct *task) { - if (!test_tsk_thread_flag(task, TIF_SINGLESTEP)) - regs->pstate &= ~DBG_SPSR_SS; + /* https://lore.kernel.org/lkml/20191118131525.GA4180@willie-the-truck */ + user_regs_reset_single_step(regs, task); if (is_compat_thread(task_thread_info(task))) return valid_compat_regs(regs); -- cgit v1.2.3 From 15956689a0e60aa0c795174f3c310b60d8794235 Mon Sep 17 00:00:00 2001 From: Will Deacon Date: Fri, 3 Jul 2020 12:08:42 +0100 Subject: arm64: compat: Ensure upper 32 bits of x0 are zero on syscall return Although we zero the upper bits of x0 on entry to the kernel from an AArch32 task, we do not clear them on the exception return path and can therefore expose 64-bit sign extended syscall return values to userspace via interfaces such as the 'perf_regs' ABI, which deal exclusively with 64-bit registers. Explicitly clear the upper 32 bits of x0 on return from a compat system call. Cc: Cc: Mark Rutland Cc: Keno Fischer Cc: Luis Machado Signed-off-by: Will Deacon --- arch/arm64/include/asm/syscall.h | 12 +++++++++++- arch/arm64/kernel/syscall.c | 3 +++ 2 files changed, 14 insertions(+), 1 deletion(-) (limited to 'arch') diff --git a/arch/arm64/include/asm/syscall.h b/arch/arm64/include/asm/syscall.h index 65299a2dcf9c..cfc0672013f6 100644 --- a/arch/arm64/include/asm/syscall.h +++ b/arch/arm64/include/asm/syscall.h @@ -34,6 +34,10 @@ static inline long syscall_get_error(struct task_struct *task, struct pt_regs *regs) { unsigned long error = regs->regs[0]; + + if (is_compat_thread(task_thread_info(task))) + error = sign_extend64(error, 31); + return IS_ERR_VALUE(error) ? error : 0; } @@ -47,7 +51,13 @@ static inline void syscall_set_return_value(struct task_struct *task, struct pt_regs *regs, int error, long val) { - regs->regs[0] = (long) error ? error : val; + if (error) + val = error; + + if (is_compat_thread(task_thread_info(task))) + val = lower_32_bits(val); + + regs->regs[0] = val; } #define SYSCALL_MAX_ARGS 6 diff --git a/arch/arm64/kernel/syscall.c b/arch/arm64/kernel/syscall.c index 7c14466a12af..98a26d4e7b0c 100644 --- a/arch/arm64/kernel/syscall.c +++ b/arch/arm64/kernel/syscall.c @@ -50,6 +50,9 @@ static void invoke_syscall(struct pt_regs *regs, unsigned int scno, ret = do_ni_syscall(regs, scno); } + if (is_compat_task()) + ret = lower_32_bits(ret); + regs->regs[0] = ret; } -- cgit v1.2.3 From 59ee987ea47caff8c1e7ba4b89932c6900a35d0c Mon Sep 17 00:00:00 2001 From: Will Deacon Date: Thu, 2 Jul 2020 21:14:20 +0100 Subject: arm64: ptrace: Add a comment describing our syscall entry/exit trap ABI Our tracehook logic for syscall entry/exit raises a SIGTRAP back to the tracer following a ptrace request such as PTRACE_SYSCALL. As part of this procedure, we clobber the reported value of one of the tracee's general purpose registers (x7 for native tasks, r12 for compat) to indicate whether the stop occurred on syscall entry or exit. This is a slightly unfortunate ABI, as it prevents the tracer from accessing the real register value and is at odds with other similar stops such as seccomp traps. Since we're stuck with this ABI, expand the comment in our tracehook logic to acknowledge the issue and describe the behaviour in more detail. Cc: Mark Rutland Cc: Luis Machado Reported-by: Keno Fischer Signed-off-by: Will Deacon --- arch/arm64/kernel/ptrace.c | 16 ++++++++++++++-- 1 file changed, 14 insertions(+), 2 deletions(-) (limited to 'arch') diff --git a/arch/arm64/kernel/ptrace.c b/arch/arm64/kernel/ptrace.c index 22f9053b55b6..89fbee3991a2 100644 --- a/arch/arm64/kernel/ptrace.c +++ b/arch/arm64/kernel/ptrace.c @@ -1811,8 +1811,20 @@ static void tracehook_report_syscall(struct pt_regs *regs, unsigned long saved_reg; /* - * A scratch register (ip(r12) on AArch32, x7 on AArch64) is - * used to denote syscall entry/exit: + * We have some ABI weirdness here in the way that we handle syscall + * exit stops because we indicate whether or not the stop has been + * signalled from syscall entry or syscall exit by clobbering a general + * purpose register (ip/r12 for AArch32, x7 for AArch64) in the tracee + * and restoring its old value after the stop. This means that: + * + * - Any writes by the tracer to this register during the stop are + * ignored/discarded. + * + * - The actual value of the register is not available during the stop, + * so the tracer cannot save it and restore it later. + * + * - Syscall stops behave differently to seccomp and pseudo-step traps + * (the latter do not nobble any registers). */ regno = (is_compat_task() ? 12 : 7); saved_reg = regs->regs[regno]; -- cgit v1.2.3 From 139dbe5d8ed383cbd1ada56c78dbbbd35bf6a9d3 Mon Sep 17 00:00:00 2001 From: Will Deacon Date: Fri, 3 Jul 2020 09:41:24 +0100 Subject: arm64: syscall: Expand the comment about ptrace and syscall(-1) If a task executes syscall(-1), we intercept this early and force x0 to be -ENOSYS so that we don't need to distinguish this scenario from one where the scno is -1 because a tracer wants to skip the system call using ptrace. With the return value set, the return path is the same as the skip case. Although there is a one-line comment noting this in el0_svc_common(), it misses out most of the detail. Expand the comment to describe a bit more about what is going on. Cc: Mark Rutland Cc: Keno Fischer Cc: Luis Machado Signed-off-by: Will Deacon --- arch/arm64/kernel/syscall.c | 16 +++++++++++++++- 1 file changed, 15 insertions(+), 1 deletion(-) (limited to 'arch') diff --git a/arch/arm64/kernel/syscall.c b/arch/arm64/kernel/syscall.c index 98a26d4e7b0c..5f0c04863d2c 100644 --- a/arch/arm64/kernel/syscall.c +++ b/arch/arm64/kernel/syscall.c @@ -124,7 +124,21 @@ static void el0_svc_common(struct pt_regs *regs, int scno, int sc_nr, user_exit(); if (has_syscall_work(flags)) { - /* set default errno for user-issued syscall(-1) */ + /* + * The de-facto standard way to skip a system call using ptrace + * is to set the system call to -1 (NO_SYSCALL) and set x0 to a + * suitable error code for consumption by userspace. However, + * this cannot be distinguished from a user-issued syscall(-1) + * and so we must set x0 to -ENOSYS here in case the tracer doesn't + * issue the skip and we fall into trace_exit with x0 preserved. + * + * This is slightly odd because it also means that if a tracer + * sets the system call number to -1 but does not initialise x0, + * then x0 will be preserved for all system calls apart from a + * user-issued syscall(-1). However, requesting a skip and not + * setting the return value is unlikely to do anything sensible + * anyway. + */ if (scno == NO_SYSCALL) regs->regs[0] = -ENOSYS; scno = syscall_trace_enter(regs); -- cgit v1.2.3 From d83ee6e3e75db6f518ef2b0858f163849f2ddeb7 Mon Sep 17 00:00:00 2001 From: Will Deacon Date: Fri, 10 Jul 2020 13:20:57 +0100 Subject: arm64: ptrace: Use NO_SYSCALL instead of -1 in syscall_trace_enter() Setting a system call number of -1 is special, as it indicates that the current system call should be skipped. Use NO_SYSCALL instead of -1 when checking for this scenario, which is different from the -1 returned due to a seccomp failure. Cc: Mark Rutland Cc: Keno Fischer Cc: Luis Machado Signed-off-by: Will Deacon --- arch/arm64/kernel/ptrace.c | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) (limited to 'arch') diff --git a/arch/arm64/kernel/ptrace.c b/arch/arm64/kernel/ptrace.c index 89fbee3991a2..1e02e98e68dd 100644 --- a/arch/arm64/kernel/ptrace.c +++ b/arch/arm64/kernel/ptrace.c @@ -1856,12 +1856,12 @@ int syscall_trace_enter(struct pt_regs *regs) if (flags & (_TIF_SYSCALL_EMU | _TIF_SYSCALL_TRACE)) { tracehook_report_syscall(regs, PTRACE_SYSCALL_ENTER); if (!in_syscall(regs) || (flags & _TIF_SYSCALL_EMU)) - return -1; + return NO_SYSCALL; } /* Do the secure computing after ptrace; failures should be fast. */ if (secure_computing() == -1) - return -1; + return NO_SYSCALL; if (test_thread_flag(TIF_SYSCALL_TRACEPOINT)) trace_sys_enter(regs, regs->syscallno); -- cgit v1.2.3 From 5afc78551bf5d53279036e0bf63314e35631d79f Mon Sep 17 00:00:00 2001 From: Will Deacon Date: Thu, 13 Feb 2020 12:12:26 +0000 Subject: arm64: Use test_tsk_thread_flag() for checking TIF_SINGLESTEP Rather than open-code test_tsk_thread_flag() at each callsite, simply replace the couple of offenders with calls to test_tsk_thread_flag() directly. Signed-off-by: Will Deacon --- arch/arm64/kernel/debug-monitors.c | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) (limited to 'arch') diff --git a/arch/arm64/kernel/debug-monitors.c b/arch/arm64/kernel/debug-monitors.c index 91146c0a3691..7310a4f7f993 100644 --- a/arch/arm64/kernel/debug-monitors.c +++ b/arch/arm64/kernel/debug-monitors.c @@ -394,14 +394,14 @@ void user_rewind_single_step(struct task_struct *task) * If single step is active for this thread, then set SPSR.SS * to 1 to avoid returning to the active-pending state. */ - if (test_ti_thread_flag(task_thread_info(task), TIF_SINGLESTEP)) + if (test_tsk_thread_flag(task, TIF_SINGLESTEP)) set_regs_spsr_ss(task_pt_regs(task)); } NOKPROBE_SYMBOL(user_rewind_single_step); void user_fastforward_single_step(struct task_struct *task) { - if (test_ti_thread_flag(task_thread_info(task), TIF_SINGLESTEP)) + if (test_tsk_thread_flag(task, TIF_SINGLESTEP)) clear_regs_spsr_ss(task_pt_regs(task)); } -- cgit v1.2.3