ARCv2: guard SLC DMA ops with spinlock

SLC maintenance ops need to be serialized by software as there is no
inherent buffering / quequing of aux commands. It can silently ignore a
new aux operation if previous one is still ongoing (SLC_CTRL_BUSY)

So gaurd the SLC op using a spin lock

The spin lock doesn't seem to be contended even in heavy workloads such
as iperf. On FPGA @ 75 MHz.

 [1] Before this change:
 ============================================================
  # iperf -c 10.42.0.1
 ------------------------------------------------------------
 Client connecting to 10.42.0.1, TCP port 5001
 TCP window size: 43.8 KByte (default)
 ------------------------------------------------------------
 [  3] local 10.42.0.110 port 38935 connected with 10.42.0.1 port 5001
 [ ID] Interval       Transfer     Bandwidth
 [  3]  0.0-10.0 sec  48.4 MBytes  40.6 Mbits/sec
 ============================================================

 [2] After this change:
 ============================================================
 # iperf -c 10.42.0.1
 ------------------------------------------------------------
 Client connecting to 10.42.0.1, TCP port 5001
 TCP window size: 43.8 KByte (default)
 ------------------------------------------------------------
 [  3] local 10.42.0.243 port 60248 connected with 10.42.0.1 port 5001
 [ ID] Interval       Transfer     Bandwidth
 [  3]  0.0-10.0 sec  47.5 MBytes  39.8 Mbits/sec
 # iperf -c 10.42.0.1
 ------------------------------------------------------------
 Client connecting to 10.42.0.1, TCP port 5001
 TCP window size: 43.8 KByte (default)
 ------------------------------------------------------------
 [  3] local 10.42.0.243 port 60249 connected with 10.42.0.1 port 5001
 [ ID] Interval       Transfer     Bandwidth
 [  3]  0.0-10.0 sec  54.9 MBytes  46.0 Mbits/sec
 ============================================================

Signed-off-by: Alexey Brodkin <abrodkin@synopsys.com>
Cc: arc-linux-dev@synopsys.com
Signed-off-by: Vineet Gupta <vgupta@synopsys.com>

arch/arc/mm/cache.c

@@ -468,10 +468,18 @@ static void __ic_line_inv_vaddr(unsigned long paddr, unsigned long vaddr,
 noinline void slc_op(unsigned long paddr, unsigned long sz, const int op)
 {
 #ifdef CONFIG_ISA_ARCV2
+	/*
+	 * SLC is shared between all cores and concurrent aux operations from
+	 * multiple cores need to be serialized using a spinlock
+	 * A concurrent operation can be silently ignored and/or the old/new
+	 * operation can remain incomplete forever (lockup in SLC_CTRL_BUSY loop
+	 * below)
+	 */
+	static DEFINE_SPINLOCK(lock);
 	unsigned long flags;
 	unsigned int ctrl;
 
-	local_irq_save(flags);
+	spin_lock_irqsave(&lock, flags);
 
 	/*
 	 * The Region Flush operation is specified by CTRL.RGN_OP[11..9]
@@ -504,7 +512,7 @@ noinline void slc_op(unsigned long paddr, unsigned long sz, const int op)
 
 	while (read_aux_reg(ARC_REG_SLC_CTRL) & SLC_CTRL_BUSY);
 
-	local_irq_restore(flags);
+	spin_unlock_irqrestore(&lock, flags);
 #endif
 }