MIPS: Fix ejtag handler on SMP

On SMP systems, the shared ejtag debug buffer may be overwritten by
other cores, because every cores can generate ejtag exception at
same time.

Unfortunately, in that context, it's difficult to relax more registers
to access per cpu buffers. so use ll/sc to serialize the access.

[paul.burton@mips.com:
  This could in theory be backported at least as far back as the
  beginning of the git era, however in general it's exceedingly rare
  that anyone would hit this without further changes, so it doesn't seem
  worthwhile marking for backport.]
Signed-off-by: Heiher <r@hev.cc>
Patchwork: https://patchwork.linux-mips.org/patch/19507/Signed-off-by: Paul Burton <paul.burton@mips.com>
Cc: jhogan@kernel.org
Cc: ralf@linux-mips.org

arch/mips/kernel/genex.S

@@ -354,16 +354,56 @@ NESTED(ejtag_debug_handler, PT_SIZE, sp)
 	sll	k0, k0, 30	# Check for SDBBP.
 	bgez	k0, ejtag_return
 
+#ifdef CONFIG_SMP
+1:	PTR_LA	k0, ejtag_debug_buffer_spinlock
+	ll	k0, 0(k0)
+	bnez	k0, 1b
+	PTR_LA	k0, ejtag_debug_buffer_spinlock
+	sc	k0, 0(k0)
+	beqz	k0, 1b
+# ifdef CONFIG_WEAK_REORDERING_BEYOND_LLSC
+	sync
+# endif
+
+	PTR_LA	k0, ejtag_debug_buffer
+	LONG_S	k1, 0(k0)
+
+	ASM_CPUID_MFC0 k1, ASM_SMP_CPUID_REG
+	PTR_SRL	k1, SMP_CPUID_PTRSHIFT
+	PTR_SLL	k1, LONGLOG
+	PTR_LA	k0, ejtag_debug_buffer_per_cpu
+	PTR_ADDU k0, k1
+
+	PTR_LA	k1, ejtag_debug_buffer
+	LONG_L	k1, 0(k1)
+	LONG_S	k1, 0(k0)
+
+	PTR_LA	k0, ejtag_debug_buffer_spinlock
+	sw	zero, 0(k0)
+#else
 	PTR_LA	k0, ejtag_debug_buffer
 	LONG_S	k1, 0(k0)
+#endif
+
 	SAVE_ALL
 	move	a0, sp
 	jal	ejtag_exception_handler
 	RESTORE_ALL
+
+#ifdef CONFIG_SMP
+	ASM_CPUID_MFC0 k1, ASM_SMP_CPUID_REG
+	PTR_SRL	k1, SMP_CPUID_PTRSHIFT
+	PTR_SLL	k1, LONGLOG
+	PTR_LA	k0, ejtag_debug_buffer_per_cpu
+	PTR_ADDU k0, k1
+	LONG_L	k1, 0(k0)
+#else
 	PTR_LA	k0, ejtag_debug_buffer
 	LONG_L	k1, 0(k0)
+#endif
 
 ejtag_return:
+	back_to_back_c0_hazard
 	MFC0	k0, CP0_DESAVE
 	.set	mips32
 	deret
@@ -377,6 +417,12 @@ ejtag_return:
 	.data
 EXPORT(ejtag_debug_buffer)
 	.fill	LONGSIZE
+#ifdef CONFIG_SMP
+EXPORT(ejtag_debug_buffer_spinlock)
+	.fill	LONGSIZE
+EXPORT(ejtag_debug_buffer_per_cpu)
+	.fill	LONGSIZE * NR_CPUS
+#endif
 	.previous
 
 	__INIT