4 files changed, 41 insertions, 23 deletions

diff --git a/arch/x86/kernel/alternative.c b/arch/x86/kernel/alternative.c
index 4adbe65afe23..2400ad62f330 100644
--- a/arch/x86/kernel/alternative.c
+++ b/arch/x86/kernel/alternative.c
@@ -807,6 +807,15 @@ static inline temp_mm_state_t use_temporary_mm(struct mm_struct *mm)
 	temp_mm_state_t temp_state;
 
 	lockdep_assert_irqs_disabled();
+
+	/*
+	 * Make sure not to be in TLB lazy mode, as otherwise we'll end up
+	 * with a stale address space WITHOUT being in lazy mode after
+	 * restoring the previous mm.
+	 */
+	if (this_cpu_read(cpu_tlbstate.is_lazy))
+		leave_mm(smp_processor_id());
+
 	temp_state.mm = this_cpu_read(cpu_tlbstate.loaded_mm);
 	switch_mm_irqs_off(NULL, mm, current);
 
diff --git a/arch/x86/kernel/kexec-bzimage64.c b/arch/x86/kernel/kexec-bzimage64.c
index 57c2ecf43134..ce831f9448e7 100644
--- a/arch/x86/kernel/kexec-bzimage64.c
+++ b/arch/x86/kernel/kexec-bzimage64.c
@@ -200,8 +200,7 @@ setup_boot_parameters(struct kimage *image, struct boot_params *params,
 	params->hdr.hardware_subarch = boot_params.hdr.hardware_subarch;
 
 	/* Copying screen_info will do? */
-	memcpy(&params->screen_info, &boot_params.screen_info,
-				sizeof(struct screen_info));
+	memcpy(&params->screen_info, &screen_info, sizeof(struct screen_info));
 
 	/* Fill in memsize later */
 	params->screen_info.ext_mem_k = 0;
diff --git a/arch/x86/kernel/traps.c b/arch/x86/kernel/traps.c
index 3c70fb34028b..e19df6cde35d 100644
--- a/arch/x86/kernel/traps.c
+++ b/arch/x86/kernel/traps.c
@@ -793,19 +793,6 @@ static __always_inline unsigned long debug_read_clear_dr6(void)
 	set_debugreg(DR6_RESERVED, 6);
 	dr6 ^= DR6_RESERVED; /* Flip to positive polarity */
 
-	/*
-	 * Clear the virtual DR6 value, ptrace routines will set bits here for
-	 * things we want signals for.
-	 */
-	current->thread.virtual_dr6 = 0;
-
-	/*
-	 * The SDM says "The processor clears the BTF flag when it
-	 * generates a debug exception."  Clear TIF_BLOCKSTEP to keep
-	 * TIF_BLOCKSTEP in sync with the hardware BTF flag.
-	 */
-	clear_thread_flag(TIF_BLOCKSTEP);
-
 	return dr6;
 }
 
@@ -873,6 +860,20 @@ static __always_inline void exc_debug_kernel(struct pt_regs *regs,
 	 */
 	WARN_ON_ONCE(user_mode(regs));
 
+	if (test_thread_flag(TIF_BLOCKSTEP)) {
+		/*
+		 * The SDM says "The processor clears the BTF flag when it
+		 * generates a debug exception." but PTRACE_BLOCKSTEP requested
+		 * it for userspace, but we just took a kernel #DB, so re-set
+		 * BTF.
+		 */
+		unsigned long debugctl;
+
+		rdmsrl(MSR_IA32_DEBUGCTLMSR, debugctl);
+		debugctl |= DEBUGCTLMSR_BTF;
+		wrmsrl(MSR_IA32_DEBUGCTLMSR, debugctl);
+	}
+
 	/*
 	 * Catch SYSENTER with TF set and clear DR_STEP. If this hit a
 	 * watchpoint at the same time then that will still be handled.
@@ -936,6 +937,22 @@ static __always_inline void exc_debug_user(struct pt_regs *regs,
 	instrumentation_begin();
 
 	/*
+	 * Start the virtual/ptrace DR6 value with just the DR_STEP mask
+	 * of the real DR6. ptrace_triggered() will set the DR_TRAPn bits.
+	 *
+	 * Userspace expects DR_STEP to be visible in ptrace_get_debugreg(6)
+	 * even if it is not the result of PTRACE_SINGLESTEP.
+	 */
+	current->thread.virtual_dr6 = (dr6 & DR_STEP);
+
+	/*
+	 * The SDM says "The processor clears the BTF flag when it
+	 * generates a debug exception."  Clear TIF_BLOCKSTEP to keep
+	 * TIF_BLOCKSTEP in sync with the hardware BTF flag.
+	 */
+	clear_thread_flag(TIF_BLOCKSTEP);
+
+	/*
 	 * If dr6 has no reason to give us about the origin of this trap,
 	 * then it's very likely the result of an icebp/int01 trap.
 	 * User wants a sigtrap for that.
diff --git a/arch/x86/kernel/unwind_orc.c b/arch/x86/kernel/unwind_orc.c
index 6a339ce328e0..73f800100066 100644
--- a/arch/x86/kernel/unwind_orc.c
+++ b/arch/x86/kernel/unwind_orc.c
@@ -321,19 +321,12 @@ EXPORT_SYMBOL_GPL(unwind_get_return_address);
 
 unsigned long *unwind_get_return_address_ptr(struct unwind_state *state)
 {
-	struct task_struct *task = state->task;
-
 	if (unwind_done(state))
 		return NULL;
 
 	if (state->regs)
 		return &state->regs->ip;
 
-	if (task != current && state->sp == task->thread.sp) {
-		struct inactive_task_frame *frame = (void *)task->thread.sp;
-		return &frame->ret_addr;
-	}
-
 	if (state->sp)
 		return (unsigned long *)state->sp - 1;
 
@@ -663,7 +656,7 @@ void __unwind_start(struct unwind_state *state, struct task_struct *task,
 	} else {
 		struct inactive_task_frame *frame = (void *)task->thread.sp;
 
-		state->sp = task->thread.sp;
+		state->sp = task->thread.sp + sizeof(*frame);
 		state->bp = READ_ONCE_NOCHECK(frame->bp);
 		state->ip = READ_ONCE_NOCHECK(frame->ret_addr);
 		state->signal = (void *)state->ip == ret_from_fork;