ARM: 9294/2: vfp: Fix broken softirq handling with instrumentation enabled

Commit 62b95a7 ("ARM: 9282/1: vfp: Manipulate task VFP state with
softirqs disabled") replaced the en/disable preemption calls inside the
VFP state handling code with en/disabling of soft IRQs, which is
necessary to allow kernel use of the VFP/SIMD unit when handling a soft
IRQ.

Unfortunately, when lockdep is enabled (or other instrumentation that
enables TRACE_IRQFLAGS), the disable path implemented in asm fails to
perform the lockdep and RCU related bookkeeping, resulting in spurious
warnings and other badness.

Set let's rework the VFP entry code a little bit so we can make the
local_bh_disable() call from C, with all the instrumentations that
happen to have been configured. Calling local_bh_enable() can be done
from asm, as it is a simple wrapper around __local_bh_enable_ip(), which
is always a callable function.

Link: https://lore.kernel.org/all/ZBBYCSZUJOWBg1s8@localhost.localdomain/

Fixes: 62b95a7 ("ARM: 9282/1: vfp: Manipulate task VFP state with softirqs disabled")
Signed-off-by: Ard Biesheuvel <ardb@kernel.org>
Reviewed-by: Linus Walleij <linus.walleij@linaro.org>
Tested-by: Guenter Roeck <linux@roeck-us.net>
Signed-off-by: Russell King (Oracle) <rmk+kernel@armlinux.org.uk>

Author: ardbiesheuvel

arch/arm/include/asm/assembler.h

@@ -244,19 +244,6 @@ THUMB(	fpreg	.req	r7	)
 	.endm
 #endif
 
-	.macro	local_bh_disable, ti, tmp
-	ldr	\tmp, [\ti, #TI_PREEMPT]
-	add	\tmp, \tmp, #SOFTIRQ_DISABLE_OFFSET
-	str	\tmp, [\ti, #TI_PREEMPT]
-	.endm
-
-	.macro	local_bh_enable_ti, ti, tmp
-	get_thread_info \ti
-	ldr	\tmp, [\ti, #TI_PREEMPT]
-	sub	\tmp, \tmp, #SOFTIRQ_DISABLE_OFFSET
-	str	\tmp, [\ti, #TI_PREEMPT]
-	.endm
-
 #define USERL(l, x...)				\
 9999:	x;					\
 	.pushsection __ex_table,"a";		\

arch/arm/vfp/entry.S

@@ -24,14 +24,5 @@
 ENTRY(do_vfp)
 	mov	r1, r10
 	mov	r3, r9
- 	ldr	r4, .LCvfp
-	ldr	pc, [r4]		@ call VFP entry point
+	b	vfp_entry
 ENDPROC(do_vfp)
-
-ENTRY(vfp_null_entry)
-	ret	lr
-ENDPROC(vfp_null_entry)
-
-	.align	2
-.LCvfp:
-	.word	vfp_vector

arch/arm/vfp/vfphw.S

@@ -75,8 +75,6 @@
 @  lr  = unrecognised instruction return address
 @  IRQs enabled.
 ENTRY(vfp_support_entry)
-	local_bh_disable r1, r4
-
 	ldr	r11, [r1, #TI_CPU]	@ CPU number
 	add	r10, r1, #TI_VFPSTATE	@ r10 = workspace
 
@@ -179,9 +177,12 @@ vfp_hw_state_valid:
 					@ else it's one 32-bit instruction, so
 					@ always subtract 4 from the following
 					@ instruction address.
-	local_bh_enable_ti r10, r4
-	ret	r3			@ we think we have handled things
 
+	mov	lr, r3			@ we think we have handled things
+local_bh_enable_and_ret:
+	adr	r0, .
+	mov	r1, #SOFTIRQ_DISABLE_OFFSET
+	b	__local_bh_enable_ip	@ tail call
 
 look_for_VFP_exceptions:
 	@ Check for synchronous or asynchronous exception
@@ -204,8 +205,7 @@ skip:
 	@ not recognised by VFP
 
 	DBGSTR	"not VFP"
-	local_bh_enable_ti r10, r4
-	ret	lr
+	b	local_bh_enable_and_ret
 
 process_exception:
 	DBGSTR	"bounce"

arch/arm/vfp/vfpmodule.c

@@ -32,10 +32,9 @@
 /*
  * Our undef handlers (in entry.S)
  */
-asmlinkage void vfp_support_entry(void);
-asmlinkage void vfp_null_entry(void);
+asmlinkage void vfp_support_entry(u32, void *, u32, u32);
 
-asmlinkage void (*vfp_vector)(void) = vfp_null_entry;
+static bool have_vfp __ro_after_init;
 
 /*
  * Dual-use variable.
@@ -645,6 +644,25 @@ static int vfp_starting_cpu(unsigned int unused)
 	return 0;
 }
 
+/*
+ * Entered with:
+ *
+ *  r0  = instruction opcode (32-bit ARM or two 16-bit Thumb)
+ *  r1  = thread_info pointer
+ *  r2  = PC value to resume execution after successful emulation
+ *  r3  = normal "successful" return address
+ *  lr  = unrecognised instruction return address
+ */
+asmlinkage void vfp_entry(u32 trigger, struct thread_info *ti, u32 resume_pc,
+			  u32 resume_return_address)
+{
+	if (unlikely(!have_vfp))
+		return;
+
+	local_bh_disable();
+	vfp_support_entry(trigger, ti, resume_pc, resume_return_address);
+}
+
 #ifdef CONFIG_KERNEL_MODE_NEON
 
 static int vfp_kmode_exception(struct pt_regs *regs, unsigned int instr)
@@ -798,7 +816,6 @@ static int __init vfp_init(void)
 	vfpsid = fmrx(FPSID);
 	barrier();
 	unregister_undef_hook(&vfp_detect_hook);
-	vfp_vector = vfp_null_entry;
 
 	pr_info("VFP support v0.3: ");
 	if (VFP_arch) {
@@ -883,7 +900,7 @@ static int __init vfp_init(void)
 				  "arm/vfp:starting", vfp_starting_cpu,
 				  vfp_dying_cpu);
 
-	vfp_vector = vfp_support_entry;
+	have_vfp = true;
 
 	thread_register_notifier(&vfp_notifier_block);
 	vfp_pm_init();