Merge tag 'arm64-fixes' of git://git.kernel.org/pub/scm/linux/kernel/git/arm64/linux into master

Pull arm64 fixes from Will Deacon:
 "A batch of arm64 fixes.

  Although the diffstat is a bit larger than we'd usually have at this
  stage, a decent amount of it is the addition of comments describing
  our syscall tracing behaviour, and also a sweep across all the modular
  arm64 PMU drivers to make them rebust against unloading and unbinding.

  There are a couple of minor things kicking around at the moment (CPU
  errata and module PLTs for very large modules), but I'm not expecting
  any significant changes now for us in 5.8.

   - Fix kernel text addresses for relocatable images booting using EFI
     and with KASLR disabled so that they match the vmlinux ELF binary.

   - Fix unloading and unbinding of PMU driver modules.

   - Fix generic mmiowb() when writeX() is called from preemptible
     context (reported by the riscv folks).

   - Fix ptrace hardware single-step interactions with signal handlers,
     system calls and reverse debugging.

   - Fix reporting of 64-bit x0 register for 32-bit tasks via
     'perf_regs'.

   - Add comments describing syscall entry/exit tracing ABI"

* tag 'arm64-fixes' of git://git.kernel.org/pub/scm/linux/kernel/git/arm64/linux:
  drivers/perf: Prevent forced unbinding of PMU drivers
  asm-generic/mmiowb: Allow mmiowb_set_pending() when preemptible()
  arm64: Use test_tsk_thread_flag() for checking TIF_SINGLESTEP
  arm64: ptrace: Use NO_SYSCALL instead of -1 in syscall_trace_enter()
  arm64: syscall: Expand the comment about ptrace and syscall(-1)
  arm64: ptrace: Add a comment describing our syscall entry/exit trap ABI
  arm64: compat: Ensure upper 32 bits of x0 are zero on syscall return
  arm64: ptrace: Override SPSR.SS when single-stepping is enabled
  arm64: ptrace: Consistently use pseudo-singlestep exceptions
  drivers/perf: Fix kernel panic when rmmod PMU modules during perf sampling
  efi/libstub/arm64: Retain 2MB kernel Image alignment if !KASLR

1 files changed, 37 insertions, 12 deletions

diff --git a/arch/arm64/kernel/ptrace.c b/arch/arm64/kernel/ptrace.c
index 68b7f34a08f5..1e02e98e68dd 100644
--- a/arch/arm64/kernel/ptrace.c
+++ b/arch/arm64/kernel/ptrace.c
@@ -1811,19 +1811,42 @@ 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];
 	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)
@@ -1833,12 +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);
@@ -1851,12 +1874,14 @@ 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);
@@ -1934,8 +1959,8 @@ 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);