ARC: cacheflush optim - PTAG can be loop invariant if V-P is const

Line op needs vaddr (indexing) and paddr (tag match). For page sized
flushes (V-P const), each line op will need a different index, but the
tag bits wil remain constant, hence paddr can be setup once outside the
loop.

This improves select LMBench numbers for Aliasing dcache where we have
more "preventive" cache flushing.

Processor, Processes - times in microseconds - smaller is better
------------------------------------------------------------------------------
Host                 OS  Mhz null null      open slct sig  sig  fork exec sh
                             call  I/O stat clos TCP  inst hndl proc proc proc
--------- ------------- ---- ---- ---- ---- ---- ---- ---- ---- ---- ---- ----
3.11-rc7- Linux 3.11.0-   80 4.66 8.88 69.7 112. 268. 8.60 28.0 3489 13.K 27.K	# Non alias ARC700
3.11-rc7- Linux 3.11.0-   80 4.64 8.51 68.6 98.5 271. 8.58 28.1 4160 15.K 32.K	# Aliasing
3.11-rc7- Linux 3.11.0-   80 4.64 8.51 69.8 99.4 270. 8.73 27.5 3880 15.K 31.K	# PTAG loop Inv

Signed-off-by: Vineet Gupta <vgupta@synopsys.com>

diff --git a/arch/arc/mm/cache_arc700.c b/arch/arc/mm/cache_arc700.c
index a152f32..6b58c1d 100644 (file)
--- a/arch/arc/mm/cache_arc700.c
+++ b/arch/arc/mm/cache_arc700.c
@@ -250,6 +250,7 @@ static inline void __cache_line_loop(unsigned long paddr, unsigned long vaddr,
 {
        unsigned int aux_cmd, aux_tag;
        int num_lines;
+       const int full_page_op = __builtin_constant_p(sz) && sz == PAGE_SIZE;
 
        if (cacheop == OP_INV_IC) {
                aux_cmd = ARC_REG_IC_IVIL;
@@ -267,7 +268,7 @@ static inline void __cache_line_loop(unsigned long paddr, unsigned long vaddr,
         *  -@paddr will be cache-line aligned already (being page aligned)
         *  -@sz will be integral multiple of line size (being page sized).
         */
-       if (!(__builtin_constant_p(sz) && sz == PAGE_SIZE)) {
+       if (!full_page_op) {
                sz += paddr & ~CACHE_LINE_MASK;
                paddr &= CACHE_LINE_MASK;
                vaddr &= CACHE_LINE_MASK;
@@ -278,19 +279,26 @@ static inline void __cache_line_loop(unsigned long paddr, unsigned long vaddr,
 #if (CONFIG_ARC_MMU_VER <= 2)
        /* MMUv2 and before: paddr contains stuffed vaddrs bits */
        paddr |= (vaddr >> PAGE_SHIFT) & 0x1F;
+#else
+       /* if V-P const for loop, PTAG can be written once outside loop */
+       if (full_page_op)
+               write_aux_reg(ARC_REG_DC_PTAG, paddr);
 #endif
 
        while (num_lines-- > 0) {
 #if (CONFIG_ARC_MMU_VER > 2)
                /* MMUv3, cache ops require paddr seperately */
-               write_aux_reg(ARC_REG_DC_PTAG, paddr);
+               if (!full_page_op) {
+                       write_aux_reg(aux_tag, paddr);
+                       paddr += L1_CACHE_BYTES;
+               }
 
                write_aux_reg(aux_cmd, vaddr);
                vaddr += L1_CACHE_BYTES;
 #else
                write_aux_reg(aux, paddr);
-#endif
                paddr += L1_CACHE_BYTES;
+#endif
        }
 }