1 files changed, 53 insertions, 21 deletions

diff --git a/arch/arm/vfp/vfpmodule.c b/arch/arm/vfp/vfpmodule.c
index b68efe643a12..d44867fc0c5e 100644
--- a/arch/arm/vfp/vfpmodule.c
+++ b/arch/arm/vfp/vfpmodule.c
@@ -56,6 +56,34 @@ extern unsigned int VFP_arch_feroceon __alias(VFP_arch);
 union vfp_state *vfp_current_hw_state[NR_CPUS];
 
 /*
+ * Claim ownership of the VFP unit.
+ *
+ * The caller may change VFP registers until vfp_state_release() is called.
+ *
+ * local_bh_disable() is used to disable preemption and to disable VFP
+ * processing in softirq context. On PREEMPT_RT kernels local_bh_disable() is
+ * not sufficient because it only serializes soft interrupt related sections
+ * via a local lock, but stays preemptible. Disabling preemption is the right
+ * choice here as bottom half processing is always in thread context on RT
+ * kernels so it implicitly prevents bottom half processing as well.
+ */
+static void vfp_state_hold(void)
+{
+	if (!IS_ENABLED(CONFIG_PREEMPT_RT))
+		local_bh_disable();
+	else
+		preempt_disable();
+}
+
+static void vfp_state_release(void)
+{
+	if (!IS_ENABLED(CONFIG_PREEMPT_RT))
+		local_bh_enable();
+	else
+		preempt_enable();
+}
+
+/*
  * Is 'thread's most up to date state stored in this CPUs hardware?
  * Must be called from non-preemptible context.
  */
@@ -240,7 +268,7 @@ static void vfp_panic(char *reason, u32 inst)
 /*
  * Process bitmask of exception conditions.
  */
-static void vfp_raise_exceptions(u32 exceptions, u32 inst, u32 fpscr, struct pt_regs *regs)
+static int vfp_raise_exceptions(u32 exceptions, u32 inst, u32 fpscr)
 {
 	int si_code = 0;
 
@@ -248,8 +276,7 @@ static void vfp_raise_exceptions(u32 exceptions, u32 inst, u32 fpscr, struct pt_
 
 	if (exceptions == VFP_EXCEPTION_ERROR) {
 		vfp_panic("unhandled bounce", inst);
-		vfp_raise_sigfpe(FPE_FLTINV, regs);
-		return;
+		return FPE_FLTINV;
 	}
 
 	/*
@@ -277,8 +304,7 @@ static void vfp_raise_exceptions(u32 exceptions, u32 inst, u32 fpscr, struct pt_
 	RAISE(FPSCR_OFC, FPSCR_OFE, FPE_FLTOVF);
 	RAISE(FPSCR_IOC, FPSCR_IOE, FPE_FLTINV);
 
-	if (si_code)
-		vfp_raise_sigfpe(si_code, regs);
+	return si_code;
 }
 
 /*
@@ -324,6 +350,8 @@ static u32 vfp_emulate_instruction(u32 inst, u32 fpscr, struct pt_regs *regs)
 static void VFP_bounce(u32 trigger, u32 fpexc, struct pt_regs *regs)
 {
 	u32 fpscr, orig_fpscr, fpsid, exceptions;
+	int si_code2 = 0;
+	int si_code = 0;
 
 	pr_debug("VFP: bounce: trigger %08x fpexc %08x\n", trigger, fpexc);
 
@@ -369,8 +397,8 @@ static void VFP_bounce(u32 trigger, u32 fpexc, struct pt_regs *regs)
 		 * unallocated VFP instruction but with FPSCR.IXE set and not
 		 * on VFP subarch 1.
 		 */
-		 vfp_raise_exceptions(VFP_EXCEPTION_ERROR, trigger, fpscr, regs);
-		return;
+		si_code = vfp_raise_exceptions(VFP_EXCEPTION_ERROR, trigger, fpscr);
+		goto exit;
 	}
 
 	/*
@@ -394,14 +422,14 @@ static void VFP_bounce(u32 trigger, u32 fpexc, struct pt_regs *regs)
 	 */
 	exceptions = vfp_emulate_instruction(trigger, fpscr, regs);
 	if (exceptions)
-		vfp_raise_exceptions(exceptions, trigger, orig_fpscr, regs);
+		si_code2 = vfp_raise_exceptions(exceptions, trigger, orig_fpscr);
 
 	/*
 	 * If there isn't a second FP instruction, exit now. Note that
 	 * the FPEXC.FP2V bit is valid only if FPEXC.EX is 1.
 	 */
 	if ((fpexc & (FPEXC_EX | FPEXC_FP2V)) != (FPEXC_EX | FPEXC_FP2V))
-		return;
+		goto exit;
 
 	/*
 	 * The barrier() here prevents fpinst2 being read
@@ -413,7 +441,13 @@ static void VFP_bounce(u32 trigger, u32 fpexc, struct pt_regs *regs)
  emulate:
 	exceptions = vfp_emulate_instruction(trigger, orig_fpscr, regs);
 	if (exceptions)
-		vfp_raise_exceptions(exceptions, trigger, orig_fpscr, regs);
+		si_code = vfp_raise_exceptions(exceptions, trigger, orig_fpscr);
+exit:
+	vfp_state_release();
+	if (si_code2)
+		vfp_raise_sigfpe(si_code2, regs);
+	if (si_code)
+		vfp_raise_sigfpe(si_code, regs);
 }
 
 static void vfp_enable(void *unused)
@@ -512,11 +546,9 @@ static inline void vfp_pm_init(void) { }
  */
 void vfp_sync_hwstate(struct thread_info *thread)
 {
-	unsigned int cpu = get_cpu();
+	vfp_state_hold();
 
-	local_bh_disable();
-
-	if (vfp_state_in_hw(cpu, thread)) {
+	if (vfp_state_in_hw(raw_smp_processor_id(), thread)) {
 		u32 fpexc = fmrx(FPEXC);
 
 		/*
@@ -527,8 +559,7 @@ void vfp_sync_hwstate(struct thread_info *thread)
 		fmxr(FPEXC, fpexc);
 	}
 
-	local_bh_enable();
-	put_cpu();
+	vfp_state_release();
 }
 
 /* Ensure that the thread reloads the hardware VFP state on the next use. */
@@ -683,7 +714,7 @@ static int vfp_support_entry(struct pt_regs *regs, u32 trigger)
 	if (!user_mode(regs))
 		return vfp_kmode_exception(regs, trigger);
 
-	local_bh_disable();
+	vfp_state_hold();
 	fpexc = fmrx(FPEXC);
 
 	/*
@@ -748,6 +779,7 @@ static int vfp_support_entry(struct pt_regs *regs, u32 trigger)
 		 * replay the instruction that trapped.
 		 */
 		fmxr(FPEXC, fpexc);
+		vfp_state_release();
 	} else {
 		/* Check for synchronous or asynchronous exceptions */
 		if (!(fpexc & (FPEXC_EX | FPEXC_DEX))) {
@@ -762,17 +794,17 @@ static int vfp_support_entry(struct pt_regs *regs, u32 trigger)
 			if (!(fpscr & FPSCR_IXE)) {
 				if (!(fpscr & FPSCR_LENGTH_MASK)) {
 					pr_debug("not VFP\n");
-					local_bh_enable();
+					vfp_state_release();
 					return -ENOEXEC;
 				}
 				fpexc |= FPEXC_DEX;
 			}
 		}
 bounce:		regs->ARM_pc += 4;
+		/* VFP_bounce() will invoke vfp_state_release() */
 		VFP_bounce(trigger, fpexc, regs);
 	}
 
-	local_bh_enable();
 	return 0;
 }
 
@@ -837,7 +869,7 @@ void kernel_neon_begin(void)
 	unsigned int cpu;
 	u32 fpexc;
 
-	local_bh_disable();
+	vfp_state_hold();
 
 	/*
 	 * Kernel mode NEON is only allowed outside of hardirq context with
@@ -868,7 +900,7 @@ void kernel_neon_end(void)
 {
 	/* Disable the NEON/VFP unit. */
 	fmxr(FPEXC, fmrx(FPEXC) & ~FPEXC_EN);
-	local_bh_enable();
+	vfp_state_release();
 }
 EXPORT_SYMBOL(kernel_neon_end);