[PATCH] D69247: [AArch64][Builtins] Avoid unnecssary cache cleaning

[Bryan Chan via Phabricator via llvm-commits]

bryanpkc created this revision.
bryanpkc added a reviewer: howard.hinnant.
Herald added subscribers: llvm-commits, Sanitizers, delcypher, kristof.beyls.
Herald added projects: LLVM, Sanitizers.

Use new control bits CTR_EL0.DIC and CTR_EL0.IDC to discover the d-cache
cleaning and i-cache invalidation requirements for instruction-to-data
coherence. This matches the behavior in the latest libgcc.

Author: Shaokun Zhang <zhangshaokun at hisilicon.com>


Repository:
  rCRT Compiler Runtime

https://reviews.llvm.org/D69247

Files:
  lib/builtins/clear_cache.c


Index: lib/builtins/clear_cache.c
===================================================================
--- lib/builtins/clear_cache.c
+++ lib/builtins/clear_cache.c
@@ -93,24 +93,33 @@
 #elif defined(__aarch64__) && !defined(__APPLE__)
   uint64_t xstart = (uint64_t)(uintptr_t)start;
   uint64_t xend = (uint64_t)(uintptr_t)end;
-  uint64_t addr;
 
-  // Get Cache Type Info
+  // Get Cache Type Info.
   uint64_t ctr_el0;
   __asm __volatile("mrs %0, ctr_el0" : "=r"(ctr_el0));
 
-  // dc & ic instructions must use 64bit registers so we don't use
+  // The DC and IC instructions must use 64-bit registers so we don't use
   // uintptr_t in case this runs in an IPL32 environment.
-  const size_t dcache_line_size = 4 << ((ctr_el0 >> 16) & 15);
-  for (addr = xstart & ~(dcache_line_size - 1); addr < xend;
-       addr += dcache_line_size)
-    __asm __volatile("dc cvau, %0" ::"r"(addr));
+  uint64_t addr;
+
+  // If CTR_EL0.IDC is set, data cache cleaning to the point of unification
+  // is not required for instruction to data coherence.
+  if (((ctr_el0 >> 28) & 0x1) == 0x0) {
+    const size_t dcache_line_size = 4 << ((ctr_el0 >> 16) & 15);
+    for (addr = xstart & ~(dcache_line_size - 1); addr < xend;
+         addr += dcache_line_size)
+      __asm __volatile("dc cvau, %0" ::"r"(addr));
+  }
   __asm __volatile("dsb ish");
 
-  const size_t icache_line_size = 4 << ((ctr_el0 >> 0) & 15);
-  for (addr = xstart & ~(icache_line_size - 1); addr < xend;
-       addr += icache_line_size)
-    __asm __volatile("ic ivau, %0" ::"r"(addr));
+  // If CTR_EL0.DIC is set, instruction cache invalidation to the point of
+  // unification is not required for instruction to data coherence.
+  if (((ctr_el0 >> 29) & 0x1) == 0x0) {
+    const size_t icache_line_size = 4 << ((ctr_el0 >> 0) & 15);
+    for (addr = xstart & ~(icache_line_size - 1); addr < xend;
+         addr += icache_line_size)
+      __asm __volatile("ic ivau, %0" ::"r"(addr));
+  }
   __asm __volatile("isb sy");
 #elif defined(__powerpc64__)
   const size_t line_size = 32;


-------------- next part --------------
A non-text attachment was scrubbed...
Name: D69247.225848.patch
Type: text/x-patch
Size: 2055 bytes
Desc: not available
URL: <http://lists.llvm.org/pipermail/llvm-commits/attachments/20191021/6e13a70f/attachment.bin>