[AARCH64] Add support for new control bits CTR_EL0.DIC and CTR_EL0.IDC

The DCache clean & ICache invalidation requirements for instructions
to be data coherence are discoverable through new fields in CTR_EL0.
Let's support the two bits if they are enabled, the CPU core will
not execute the unnecessary DCache clean or Icache Invalidation
instructions.

2019-09-25  Shaokun Zhang  <zhangshaokun@hisilicon.com>

	* config/aarch64/sync-cache.c (__aarch64_sync_cache_range): Add support for
	CTR_EL0.IDC and CTR_EL0.DIC.

From-SVN: r276122

diff --git a/libgcc/ChangeLog b/libgcc/ChangeLog
index 74deb0f185a758faa335951c41d611f62607a7d7..261ea7b9d912f9dfb525bce000299421705d1525 100644 (file)
--- a/libgcc/ChangeLog
+++ b/libgcc/ChangeLog
@@ -1,3 +1,8 @@
+2019-09-25  Shaokun Zhang  <zhangshaokun@hisilicon.com>
+
+       * config/aarch64/sync-cache.c (__aarch64_sync_cache_range): Add support for
+       CTR_EL0.IDC and CTR_EL0.DIC.
+
 2019-09-20  Christophe Lyon  <christophe.lyon@st.com>
 
        Revert:

diff --git a/libgcc/config/aarch64/sync-cache.c b/libgcc/config/aarch64/sync-cache.c
index 791f5e42ff444042ad8f2980bcd902969f1785a0..ea3da4be02b37bc60aaf6d22319ff84fa8e84fc5 100644 (file)
--- a/libgcc/config/aarch64/sync-cache.c
+++ b/libgcc/config/aarch64/sync-cache.c
@@ -23,6 +23,9 @@ a copy of the GCC Runtime Library Exception along with this program;
 see the files COPYING3 and COPYING.RUNTIME respectively.  If not, see
 <http://www.gnu.org/licenses/>.  */
 
+#define CTR_IDC_SHIFT           28
+#define CTR_DIC_SHIFT           29
+
 void __aarch64_sync_cache_range (const void *, const void *);
 
 void
@@ -41,32 +44,44 @@ __aarch64_sync_cache_range (const void *base, const void *end)
   icache_lsize = 4 << (cache_info & 0xF);
   dcache_lsize = 4 << ((cache_info >> 16) & 0xF);
 
-  /* Loop over the address range, clearing one cache line at once.
-     Data cache must be flushed to unification first to make sure the
-     instruction cache fetches the updated data.  'end' is exclusive,
-     as per the GNU definition of __clear_cache.  */
+  /* If CTR_EL0.IDC is enabled, Data cache clean to the Point of Unification is
+     not required for instruction to data coherence.  */
+
+  if (((cache_info >> CTR_IDC_SHIFT) & 0x1) == 0x0) {
+    /* Loop over the address range, clearing one cache line at once.
+       Data cache must be flushed to unification first to make sure the
+       instruction cache fetches the updated data.  'end' is exclusive,
+       as per the GNU definition of __clear_cache.  */
 
-  /* Make the start address of the loop cache aligned.  */
-  address = (const char*) ((__UINTPTR_TYPE__) base
-                          & ~ (__UINTPTR_TYPE__) (dcache_lsize - 1));
+    /* Make the start address of the loop cache aligned.  */
+    address = (const char*) ((__UINTPTR_TYPE__) base
+                            & ~ (__UINTPTR_TYPE__) (dcache_lsize - 1));
 
-  for (; address < (const char *) end; address += dcache_lsize)
-    asm volatile ("dc\tcvau, %0"
-                 :
-                 : "r" (address)
-                 : "memory");
+    for (; address < (const char *) end; address += dcache_lsize)
+      asm volatile ("dc\tcvau, %0"
+                   :
+                   : "r" (address)
+                   : "memory");
+  }
 
   asm volatile ("dsb\tish" : : : "memory");
 
-  /* Make the start address of the loop cache aligned.  */
-  address = (const char*) ((__UINTPTR_TYPE__) base
-                          & ~ (__UINTPTR_TYPE__) (icache_lsize - 1));
+  /* If CTR_EL0.DIC is enabled, Instruction cache cleaning to the Point of
+     Unification is not required for instruction to data coherence.  */
+
+  if (((cache_info >> CTR_DIC_SHIFT) & 0x1) == 0x0) {
+    /* Make the start address of the loop cache aligned.  */
+    address = (const char*) ((__UINTPTR_TYPE__) base
+                            & ~ (__UINTPTR_TYPE__) (icache_lsize - 1));
+
+    for (; address < (const char *) end; address += icache_lsize)
+      asm volatile ("ic\tivau, %0"
+                   :
+                   : "r" (address)
+                   : "memory");
 
-  for (; address < (const char *) end; address += icache_lsize)
-    asm volatile ("ic\tivau, %0"
-                 :
-                 : "r" (address)
-                 : "memory");
+    asm volatile ("dsb\tish" : : : "memory");
+  }
 
-  asm volatile ("dsb\tish; isb" : : : "memory");
+  asm volatile("isb" : : : "memory");
 }